{ "id": "acna2019", "name": "ApacheCon NA 2019", "url": "https://www.apachecon.com/schedule", "homeUrl": "https://www.apachecon.com", "metaData": { "id": "acna2019", "audiences": [ ], "eventTypes": [ { "id": "1", "order": 1, "names": { "en": "Evening Event" }, "icon": "eventType_1.png" }, { "id": "2", "order": 2, "names": { "en": "talk" }, "icon": "eventType_2.png" }, { "id": "3", "order": 4, "names": { "en": "keynote" }, "icon": "eventType_4.png" }, { "id": "4", "order": 7, "names": { "en": "panel" }, "icon": "eventType_7.png" }, { "id": "5", "order": 11, "names": { "en": "Food & Beverages" }, "icon": "eventType_11.png" } ], "languages": [ { "id": "1", "code": "en", "order": 2, "names": { "en": "English" }, "icon": "language_en.png" } ], "defaultLanguage": { "id": "1", "code": "en", "order": 1, "names": { "en": "English" }, "icon": "language_en.png" }, "tracks": [ { "id": "1015", "order": 16, "names": { "en": "Streaming" }, "icon": "track_1015.png" }, { "id": "1017", "order": 18, "names": { "en": "Content Delivery" }, "icon": "track_1017.png" }, { "id": "1005", "order": 6, "names": { "en": "Apache Tomcat" }, "icon": "track_1005.png" }, { "id": "1011", "order": 12, "names": { "en": "Integration" }, "icon": "track_1011.png" }, { "id": "1010", "order": 11, "names": { "en": "Graph processing" }, "icon": "track_1010.png" }, { "id": "1019", "order": 20, "names": { "en": "OFBiz" }, "icon": "track_1019.png" }, { "id": "1001", "order": 2, "names": { "en": "Apache Cassandra" }, "icon": "track_1001.png" }, { "id": "1003", "order": 4, "names": { "en": "Apache Drill" }, "icon": "track_1003.png" }, { "id": "1007", "order": 8, "names": { "en": "Big Data" }, "icon": "track_1007.png" }, { "id": "1009", "order": 10, "names": { "en": "Geospatial software" }, "icon": "track_1009.png" }, { "id": "1013", "order": 14, "names": { "en": "Machine Learning" }, "icon": "track_1013.png" }, { "id": "1018", "order": 19, "names": { "en": "Mobile" }, "icon": "track_1018.png" }, { "id": "1004", "order": 5, "names": { "en": "Apache Karaf" }, "icon": "track_1004.png" }, { "id": "1012", "order": 13, "names": { "en": "Internet of Things" }, "icon": "track_1012.png" }, { "id": "1016", "order": 17, "names": { "en": "General" }, "icon": "track_1016.png" }, { "id": "1014", "order": 15, "names": { "en": "Observability" }, "icon": "track_1014.png" }, { "id": "1008", "order": 9, "names": { "en": "Community" }, "icon": "track_1008.png" }, { "id": "1002", "order": 3, "names": { "en": "Cloudstack Collaboration Conference" }, "icon": "track_1002.png" }, { "id": "1020", "order": 21, "names": { "en": "Beam Summit" }, "icon": "track_1020.png" } ], "locations": [ { "id": "1012", "order": 1012, "names": { "en": "Valley of Fire 1, 2" }, "icon": "location_1012.png", "capacity": 80 }, { "id": "1008", "order": 1008, "names": { "en": "El Dorado" }, "icon": "location_1008.png", "capacity": 400 }, { "id": "1014", "order": 1014, "names": { "en": "Red Rock III-V" }, "icon": "location_1014.png", "capacity": 220 }, { "id": "1004", "order": 1004, "names": { "en": "Reno II" }, "icon": "location_1004.png", "capacity": 100 }, { "id": "1003", "order": 1003, "names": { "en": "Reno I" }, "icon": "location_1003.png", "capacity": 100 }, { "id": "1010", "order": 1010, "names": { "en": "Savoy" }, "icon": "location_1010.png", "capacity": 260 }, { "id": "1007", "order": 1007, "names": { "en": "Virginia City 2" }, "icon": "location_1007.png", "capacity": 100 }, { "id": "1005", "order": 1005, "names": { "en": "Laughlin 1" }, "icon": "location_1005.png", "capacity": 100 }, { "id": "1006", "order": 1006, "names": { "en": "Laughlin 2" }, "icon": "location_1006.png", "capacity": 100 }, { "id": "1002", "order": 1002, "names": { "en": "Laughlin 3" }, "icon": "location_1002.png", "capacity": 80 }, { "id": "1009", "order": 1009, "names": { "en": "Mesquite" }, "icon": "location_1009.png", "capacity": 100 }, { "id": "1013", "order": 1013, "names": { "en": "Red Rock VI-VIII" }, "icon": "location_1013.png", "capacity": 200 }, { "id": "1000", "order": 1000, "names": { "en": "Vista" }, "icon": "location_1000.png", "capacity": 900 }, { "id": "1066", "order": 1066, "names": { "en": "Lake Mead 1, 2" }, "icon": "location_1066.png", "capacity": 80 } ], "defaultIcon": "Unknown.png" }, "events": [ { "id": "1", "start": "2019-09-09T08:00:00", "end": "2019-09-09T09:00:00", "title": "Coffee/Breakfast", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ "food" ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "11", "locationId": "1", "speakerIds": [ ], "languageId": "1" }, { "id": "2", "start": "2019-09-09T11:00:00", "end": "2019-09-09T11:30:00", "title": "Coffee", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ "food" ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "11", "locationId": "1", "speakerIds": [ ], "languageId": "1" }, { "id": "3", "start": "2019-09-09T12:30:00", "end": "2019-09-09T14:00:00", "title": "Lunch", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ "food" ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "11", "locationId": "1", "speakerIds": [ ], "languageId": "1" }, { "id": "5", "start": "2019-09-09T16:00:00", "end": "2019-09-09T16:30:00", "title": "Coffee", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ "food" ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "11", "locationId": "1", "speakerIds": [ ], "languageId": "1" }, { "id": "6", "start": "2019-09-09T19:00:00", "end": "2019-09-09T22:00:00", "title": "BOFs - Birds of a Feather sessions - all rooms.", "abstractText": "Birds of a Feather sesions are self-organizing sessions on any topic. See https://www.apachecon.com/acna19/bof.html for the full schedule. Contact Rich - rbowen@apache.org - to schedule yours.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1", "speakerIds": [ ], "languageId": "1" }, { "id": "27", "start": "2019-09-09T09:00:00", "end": "2019-09-09T09:50:00", "title": "Hackathon", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1002", "speakerIds": [ ], "languageId": "1" }, { "id": "28", "start": "2019-09-09T10:00:00", "end": "2019-09-09T10:50:00", "title": "Hackathon", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1002", "speakerIds": [ ], "languageId": "1" }, { "id": "29", "start": "2019-09-09T11:30:00", "end": "2019-09-09T12:20:00", "title": "Hackathon", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1002", "speakerIds": [ ], "languageId": "1" }, { "id": "30", "start": "2019-09-09T14:00:00", "end": "2019-09-09T14:50:00", "title": "Hackathon", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1002", "speakerIds": [ ], "languageId": "1" }, { "id": "31", "start": "2019-09-09T15:00:00", "end": "2019-09-09T15:50:00", "title": "Hackathon", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1002", "speakerIds": [ ], "languageId": "1" }, { "id": "32", "start": "2019-09-09T16:30:00", "end": "2019-09-09T17:20:00", "title": "Hackathon", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1002", "speakerIds": [ ], "languageId": "1" }, { "id": "33", "start": "2019-09-09T17:30:00", "end": "2019-09-09T18:20:00", "title": "Hackathon", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1002", "speakerIds": [ ], "languageId": "1" }, { "id": "34", "start": "2019-09-09T09:00:00", "end": "2019-09-09T09:50:00", "title": "BAR CAMP", "abstractText": "Details at https://cwiki.apache.org/confluence/display/APACHECON/BarCampApacheLasVegas", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1066", "speakerIds": [ ], "languageId": "1" }, { "id": "35", "start": "2019-09-09T10:00:00", "end": "2019-09-09T10:50:00", "title": "BAR CAMP", "abstractText": "Details at https://cwiki.apache.org/confluence/display/APACHECON/BarCampApacheLasVegas", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1066", "speakerIds": [ ], "languageId": "1" }, { "id": "36", "start": "2019-09-09T11:30:00", "end": "2019-09-09T12:20:00", "title": "BAR CAMP", "abstractText": "Details at https://cwiki.apache.org/confluence/display/APACHECON/BarCampApacheLasVegas", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1066", "speakerIds": [ ], "languageId": "1" }, { "id": "37", "start": "2019-09-09T14:00:00", "end": "2019-09-09T14:50:00", "title": "BAR CAMP", "abstractText": "Details at https://cwiki.apache.org/confluence/display/APACHECON/BarCampApacheLasVegas", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1066", "speakerIds": [ ], "languageId": "1" }, { "id": "38", "start": "2019-09-09T15:00:00", "end": "2019-09-09T15:50:00", "title": "BAR CAMP", "abstractText": "Details at https://cwiki.apache.org/confluence/display/APACHECON/BarCampApacheLasVegas", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1066", "speakerIds": [ ], "languageId": "1" }, { "id": "39", "start": "2019-09-09T16:30:00", "end": "2019-09-09T17:20:00", "title": "BAR CAMP", "abstractText": "Details at https://cwiki.apache.org/confluence/display/APACHECON/BarCampApacheLasVegas", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1066", "speakerIds": [ ], "languageId": "1" }, { "id": "40", "start": "2019-09-09T17:30:00", "end": "2019-09-09T18:20:00", "title": "BAR CAMP", "abstractText": "Details at https://cwiki.apache.org/confluence/display/APACHECON/BarCampApacheLasVegas", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1066", "speakerIds": [ ], "languageId": "1" }, { "id": "63", "start": "2019-09-10T08:00:00", "end": "2019-09-10T09:00:00", "title": "Coffee/Breakfast", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ "food" ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "11", "locationId": "1", "speakerIds": [ ], "languageId": "1" }, { "id": "64", "start": "2019-09-10T09:00:00", "end": "2019-09-10T09:30:00", "title": "Keynote: Founders Panel", "abstractText": "During the Founders Panel you will find out why a set of globally dispersed individuals came together to form a Foundation. What motivates them to this day to collaborate with others? What has and hasn’t changed in the last two decades? Let these pioneers inspire you!", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "11", "locationId": "1000", "speakerIds": [ "2045", "2046", "1054", "2052", "2062", "2066", "1086" ], "languageId": "1" }, { "id": "65", "start": "2019-09-10T09:30:00", "end": "2019-09-10T10:00:00", "title": "Keynote: Algorithm Soup", "abstractText": "Can we better understand the new era of floating software by looking back 3 billion years? As Moore’s Law fades, computational progress is driven less by hardware and more by rapidly advancing software entities that are fluid, dispersed, nothing like the smart machines envisioned in old sci fi. Some envision a molecular Internet of Services without clear boundaries. But a case can be made for replicating life. For developing “cell walls,” separate identities and AI entities that can be held accountable.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "11", "locationId": "1000", "speakerIds": [ "2001" ], "languageId": "1" }, { "id": "66", "start": "2019-09-10T10:00:00", "end": "2019-09-10T10:15:00", "title": "Keynote: It isn't about the license, it's about the collaboration", "abstractText": "There's been a disturbance in the force lately with a number of projects abandoning open source licenses for licenses that carry commercial covenants or constraints, or worse, abandoning open source licensing altogether in favor of source available licensing. This will not end well if the industry doesn't recognize that open source isn't about the license. The value isn't in the source code. It's about fostering a diverse collaborative community of sustainable support and continuous improvement and innovation. In his talk, Christopher, an IBM Fellow and IBM's CTO of Open Technology, will share his perspectives on the value of open governance for open source projects.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ "food" ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "11", "locationId": "1000", "speakerIds": [ "2034" ], "languageId": "1" }, { "id": "67", "start": "2019-09-10T10:15:00", "end": "2019-09-10T10:30:00", "title": "Keynote: Our three pillar commitment to Apache Cassandra and Tinkerpop", "abstractText": "At DataStax, we embrace Code, Content and Community as our three pillars of support for Apache projects and to balance our commercial and open source constituencies. This will be an overview of our current and future contributions to help build a stronger Apache Cassandra and Tinkerpop.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "11", "locationId": "1000", "speakerIds": [ "2041" ], "languageId": "1" }, { "id": "68", "start": "2019-09-10T10:30:00", "end": "2019-09-10T11:00:00", "title": "State of the Feather", "abstractText": "Join us for the official presentation on the people, projects, and progress of The Apache Software Foundation (ASF), delivered by an ASF officer at every ApacheCon --2019 features ASF President Sam Ruby in Las Vegas and ASF Executive Vice President David Nalley in Berlin. Highlights include key activities and achievements by Apache projects and their communities, as well as ASF Operations, and a look back over the past year’s activities.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ "food" ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "11", "locationId": "1000", "speakerIds": [ "2000" ], "languageId": "1" }, { "id": "69", "start": "2019-09-10T11:00:00", "end": "2019-09-10T11:30:00", "title": "Coffee", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ "food" ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "11", "locationId": "1", "speakerIds": [ ], "languageId": "1" }, { "id": "70", "start": "2019-09-10T12:30:00", "end": "2019-09-10T14:00:00", "title": "Lunch", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ "food" ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "11", "locationId": "1", "speakerIds": [ ], "languageId": "1" }, { "id": "71", "start": "2019-09-10T16:00:00", "end": "2019-09-10T16:30:00", "title": "Coffee", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ "food" ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "11", "locationId": "1", "speakerIds": [ ], "languageId": "1" }, { "id": "72", "start": "2019-09-10T19:00:00", "end": "2019-09-10T20:30:00", "title": "Welcome Reception", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1000", "speakerIds": [ ], "languageId": "1" }, { "id": "73", "start": "2019-09-10T20:30:00", "end": "2019-09-10T22:00:00", "title": "BOFs - Birds of a Feather sessions - all rooms.", "abstractText": "Birds of a Feather sesions are self-organizing sessions on any topic. See https://www.apachecon.com/acna19/bof.html for the full schedule. Contact Rich - rbowen@apache.org - to schedule yours.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1", "speakerIds": [ ], "languageId": "1" }, { "id": "98", "start": "2019-09-10T11:15:00", "end": "2019-09-10T12:05:00", "title": "Hackathon", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1002", "speakerIds": [ ], "languageId": "1" }, { "id": "99", "start": "2019-09-10T12:15:00", "end": "2019-09-10T13:05:00", "title": "Hackathon", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1002", "speakerIds": [ ], "languageId": "1" }, { "id": "100", "start": "2019-09-10T14:30:00", "end": "2019-09-10T15:20:00", "title": "Hackathon", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1002", "speakerIds": [ ], "languageId": "1" }, { "id": "101", "start": "2019-09-10T15:30:00", "end": "2019-09-10T16:20:00", "title": "Hackathon", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1002", "speakerIds": [ ], "languageId": "1" }, { "id": "102", "start": "2019-09-10T17:00:00", "end": "2019-09-10T17:50:00", "title": "Hackathon", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1002", "speakerIds": [ ], "languageId": "1" }, { "id": "103", "start": "2019-09-10T18:00:00", "end": "2019-09-10T18:50:00", "title": "Hackathon", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1002", "speakerIds": [ ], "languageId": "1" }, { "id": "207", "start": "2019-09-11T11:00:00", "end": "2019-09-11T11:50:00", "title": "Hackathon: Yes, 1 Billion Kids Can Code", "abstractText": "Keynote speaker, Samaira Mehta, will be holding a one-hour Hackathon to help kids of all ages learn how to code. Created by Samaira and her 5-year-old brother, Aadit, “Yes, 1 Billion Kids Can Code” gives kids living below the poverty line the educational tools and coding programs to allow them to join the leaders of tomorrow. Open to attendees from first grade and up. *Space is limited to 20 attendees.\nAdvanced sign-up required! Please book your spot at https://www.eventbrite.com/e/yes-1-billion-kids-can-code-registration-66834093573", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1002", "speakerIds": [ "2002" ], "languageId": "1" }, { "id": "208", "start": "2019-09-11T12:00:00", "end": "2019-09-11T12:50:00", "title": "Hackathon", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1002", "speakerIds": [ ], "languageId": "1" }, { "id": "209", "start": "2019-09-11T14:15:00", "end": "2019-09-11T15:05:00", "title": "Hackathon", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1002", "speakerIds": [ ], "languageId": "1" }, { "id": "210", "start": "2019-09-11T15:15:00", "end": "2019-09-11T16:05:00", "title": "Hackathon", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1002", "speakerIds": [ ], "languageId": "1" }, { "id": "211", "start": "2019-09-11T16:45:00", "end": "2019-09-11T17:35:00", "title": "Hackathon", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1002", "speakerIds": [ ], "languageId": "1" }, { "id": "212", "start": "2019-09-11T17:45:00", "end": "2019-09-11T18:35:00", "title": "Hackathon", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1002", "speakerIds": [ ], "languageId": "1" }, { "id": "200", "start": "2019-09-12T09:00:00", "end": "2019-09-12T09:50:00", "title": "Hackathon", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1002", "speakerIds": [ ], "languageId": "1" }, { "id": "201", "start": "2019-09-12T10:00:00", "end": "2019-09-12T10:50:00", "title": "Hackathon", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1002", "speakerIds": [ ], "languageId": "1" }, { "id": "202", "start": "2019-09-12T13:00:00", "end": "2019-09-12T13:50:00", "title": "Hackathon", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1002", "speakerIds": [ ], "languageId": "1" }, { "id": "203", "start": "2019-09-12T14:00:00", "end": "2019-09-12T14:50:00", "title": "Hackathon", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1002", "speakerIds": [ ], "languageId": "1" }, { "id": "204", "start": "2019-09-12T15:30:00", "end": "2019-09-12T16:20:00", "title": "Hackathon", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1002", "speakerIds": [ ], "languageId": "1" }, { "id": "205", "start": "2019-09-12T16:30:00", "end": "2019-09-12T17:20:00", "title": "Hackathon", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1002", "speakerIds": [ ], "languageId": "1" }, { "id": "206", "start": "2019-09-12T17:30:00", "end": "2019-09-12T18:20:00", "title": "Hackathon", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1002", "speakerIds": [ ], "languageId": "1" }, { "id": "220", "start": "2019-09-11T11:00:00", "end": "2019-09-11T11:50:00", "title": "Cloudstack Hackathon", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1002", "audienceId": "", "typeId": "", "locationId": "1005", "speakerIds": [ ], "languageId": "1" }, { "id": "221", "start": "2019-09-11T12:00:00", "end": "2019-09-11T12:50:00", "title": "Cloudstack Hackathon", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1002", "audienceId": "", "typeId": "", "locationId": "1005", "speakerIds": [ ], "languageId": "1" }, { "id": "222", "start": "2019-09-11T14:15:00", "end": "2019-09-11T15:05:00", "title": "Cloudstack Hackathon", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1002", "audienceId": "", "typeId": "", "locationId": "1005", "speakerIds": [ ], "languageId": "1" }, { "id": "223", "start": "2019-09-11T15:15:00", "end": "2019-09-11T16:05:00", "title": "Cloudstack Hackathon", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1002", "audienceId": "", "typeId": "", "locationId": "1005", "speakerIds": [ ], "languageId": "1" }, { "id": "224", "start": "2019-09-11T16:45:00", "end": "2019-09-11T17:35:00", "title": "Cloudstack Hackathon", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1002", "audienceId": "", "typeId": "", "locationId": "1005", "speakerIds": [ ], "languageId": "1" }, { "id": "225", "start": "2019-09-11T17:45:00", "end": "2019-09-11T18:35:00", "title": "Cloudstack Hackathon", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1002", "audienceId": "", "typeId": "", "locationId": "1005", "speakerIds": [ ], "languageId": "1" }, { "id": "1000", "start": "2019-09-09T15:00:00", "end": "2019-09-09T15:50:00", "title": "Geospatial Indexing and Search at Scale with Apache Lucene", "abstractText": "Come have a look under the covers at new data structures that enable geospatial and multi-dimensional indexing and search at massive scale in Apache Lucene. This talk will cover the indexing structures considered and ultimately implemented in the Apache Lucene Open Source Project along with the 25 - 30X boost in performance and centimeter spatial accuracy achieved in the latest release. Join us and see what's next for scalable Geospatial Search in Apache Lucene.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1009", "audienceId": "", "typeId": "2", "locationId": "1013", "speakerIds": [ "1000" ], "languageId": "1" }, { "id": "1001", "start": "2019-09-10T12:15:00", "end": "2019-09-10T13:05:00", "title": "Let's Encrypt Apache Tomcat", "abstractText": "The Let's Encrypt initiative has changed the landscape for online security. The capital cost of cryptographic security for every web site worldwide has been lowered from potentially thousands of dollars per year to zero. One of the trade-offs for the availability of these free certificates is that they are short-lived, making automated deployment of certificates an essential piece of any deployment plan. Let's Encrypt supports Apache httpd out of the box for single-command renewal and deployment on a single host, while with Tomcat it's more complicated. We'll be discussing how Let's Encrypt handles domain-validated authentication, initial requests, and renewals, and how to automate the deployment process in your Tomcat-based environment with minimal downtime. ", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1005", "audienceId": "", "typeId": "2", "locationId": "1007", "speakerIds": [ "1001" ], "languageId": "1" }, { "id": "1002", "start": "2019-09-10T11:15:00", "end": "2019-09-10T12:05:00", "title": "Using Apache Traffic Control to cache any web object at scale", "abstractText": "This talk will focus on how any organization can deploy a Content Delivery Network (CDN) to cache web object at scale using Apache Traffic Control (ATC) and Apache Traffic Server (ATS). Topics covered will be a brief introduction to the projects, a high-level overview of traffic routing on a CDN, followed by a deep dive into how to efficiently cache objects on an ATC CDN using ATS. Based on years of experience operating ATC CDNs, several different scenarios with corresponding object types (video, web content, etc) will be presented. Learn how the ATC configuration relates to ATS, how different storage mediums can be employed to cache different objects types, how to select the correct redundancy strategies, and how a caching hierarchy can be employed to increase cache efficiency.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1017", "audienceId": "", "typeId": "2", "locationId": "1003", "speakerIds": [ "1002" ], "languageId": "1" }, { "id": "1003", "start": "2019-09-10T17:00:00", "end": "2019-09-10T17:50:00", "title": "Locking Down Apache Tomcat: Practical Security for Real-world Applications", "abstractText": "Out of the box, Apache Tomcat is quite secure. Then you need to configure it to suit your environment, connect your data sources, and deploy your applications. Those processes can potentially reduce the security of the entire system. A thorough review of your host, network, application and configuration is necessary to identify those areas where your security needs improvement. We’ll discuss each of these areas in some detail and how some simple tweaks and tools can make you and your users safer.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1005", "audienceId": "", "typeId": "2", "locationId": "1007", "speakerIds": [ "1001" ], "languageId": "1" }, { "id": "1004", "start": "2019-09-11T12:00:00", "end": "2019-09-11T12:50:00", "title": "Packaging Tomcat for Linux Distributions", "abstractText": "What is the difference between the ASF Tomcat distribution and the various flavors of tomcat packages on Linux? Most users don’t know! In this discussion Coty will explain how the tomcat packages distributed by a couple flavors of Linux (Red Hat and Debian/Ubuntu) are structured and why the container is provided that way. Coty also hopes to get feedback from the audience and to discuss how these Linux distributions can better provide tomcat to users.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1005", "audienceId": "", "typeId": "2", "locationId": "1007", "speakerIds": [ "1003" ], "languageId": "1" }, { "id": "1005", "start": "2019-09-10T18:00:00", "end": "2019-09-10T18:50:00", "title": "Improving Apache Traffic Control CDN Operations: Cache-Side Config Generation and Layered Profiles", "abstractText": "We will overview several ongoing activities on the Apache Traffic Control project directed toward improving the operations and management of production ATC CDNs.\n Presently, ATC generates configuration for the Apache Traffic Server caching proxy on the monolithic Traffic Ops service. There is an ongoing project to move config generation to the caches. This has many advantages for production CDNs: breaking up the monolith, making deployments smaller and safer, enabling canary deployments of code changes, making Traffic Control more cache-agnostic, and more.\n We’ll discuss the challenges involved, the techniques we used, and what we learned from the process. We’ll also talk about what this means for Traffic Control CDN operators, how your workflow might change, and what it means for the future of configuration and deployment on Traffic Control.\n We’ll also present Layered Profiles: a new feature proposal to improve Traffic Control operations. Layered Profiles will allow operators to apply multiple Profiles to each Server and Delivery Service in ATC, reducing the cognitive overhead and risk of Profiles and Parameters, and eliminating the combinatorial explosion of Profiles for each Server category and type.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1017", "audienceId": "", "typeId": "2", "locationId": "1003", "speakerIds": [ "1004" ], "languageId": "1" }, { "id": "1006", "start": "2019-09-12T09:00:00", "end": "2019-09-12T09:50:00", "title": "How Netflix debugs and fixes Apache Cassandra when it breaks", "abstractText": "Netflix relies on Apache Cassandra as a critical source of truth database, and while Cassandra is a remarkably resilient database, it does, ever so occasionally, break. This talk explores how complex Cassandra deployments fail in production, but more importantly, the techniques, tools, and approaches our distributed systems engineers use to debug and mitigate these failures. We will first cover software-based failure modes that come either from our software or the software that Cassandra builds upon. For example, retry storms or unbounded queues can effectively overwhelm the database. Cassandra and Linux give you many tools to detect these, and there are numerous strategies you can use to avoid them. Along the way we will also visit common JVM failure modes and how to assess and remediate these. Next, we will cover hardware-based failure modes that come from a typical cloud environment. We will cover the broad classes of drive and network failures that we cope with every day, as well as the metrics and tests we use to detect them. With these understandings, we will learn how to automatically heal these failures and safely meet our latency SLOs. Finally, we will cover systemic failure modes, including complex interactions of multiple components and systems. This will involve a number of concrete failures we observed that involved multiple bugs, system failures, or data modeling issues in combination. At the end of the talk, we hope that the audience leaves understanding how large distributed databases can fail, but also how to use DevOps skills and tools to debug, mitigate, and automate away these failure modes going forward.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1001", "audienceId": "", "typeId": "2", "locationId": "1010", "speakerIds": [ "1005" ], "languageId": "1" }, { "id": "1007", "start": "2019-09-10T17:00:00", "end": "2019-09-10T17:50:00", "title": "Kubernetes on BareMetal with Apache CloudStack", "abstractText": "nCloudStack currently supports Kubernetes deployment using Hypervisors, which enables PaaS on top of IaaS. However, PaaS applications having data-heavy loads are the most likely to be negatively impacted, especially when the service is oversubscribed. This is where BareMetal cloud offers a significant advantage over Hypervisors, especially for latency-sensitive workloads. This talk and demo will provide turnkey solution for integrating Kubernetes on CloudStack using BareMetal servers.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1002", "audienceId": "", "typeId": "2", "locationId": "1005", "speakerIds": [ "1006", "1007" ], "languageId": "1" }, { "id": "1008", "start": "2019-09-11T12:00:00", "end": "2019-09-11T12:50:00", "title": "Supporting Cassandra In-House – Our Story !!", "abstractText": "In this presentation, senior Cassandra Architects at Ericsson will share their vast experience in supporting around 100 Cassandra deployments in production. They will share the key challenges and best practices with respect to Cassandra operations, maintenance and support. There is plenty to learn when the team talks about many problems which they faced in production and how they fixed each one of them successfully by providing interesting solutions. Audience: All Cassandra users especially Cassandra operators and administrators.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1001", "audienceId": "", "typeId": "2", "locationId": "1009", "speakerIds": [ "1008", "1009" ], "languageId": "1" }, { "id": "1009", "start": "2019-09-10T14:30:00", "end": "2019-09-10T15:20:00", "title": "Customizing virtual machines with cloud init", "abstractText": "This presentation will cover the basic design around how CloudStack implements support for cloud-init datasources, configuring the cloud-init service within a VM template to talk to one of the CloudStack supported datasources, and give a basic introduction to using cloud-init to customize virtual machines upon deployment.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1002", "audienceId": "", "typeId": "2", "locationId": "1005", "speakerIds": [ "1010" ], "languageId": "1" }, { "id": "1010", "start": "2019-09-10T11:15:00", "end": "2019-09-10T12:05:00", "title": "How Netflix manages petabyte scale Apache Cassandra in the cloud", "abstractText": "At Netflix, we manage petabytes of data in Apache Cassandra which must be reliably accessible to users in mere milliseconds. To achieve this, we have built sophisticated control planes that turn our persistence layer based on Apache Cassandra into a truly self-driving system. We will start with the user interface that Netflix developers use to interact with their Cassandra databases and dive deep into the automation that powers it all. From cluster creation, through scaling up, to cluster death, complex automation drives large fleets of virtual machines hosted on the AWS cloud. First, we will cover the basics of how Netflix deploys Apache Cassandra. In particular, this begins with how we mold Apache Cassandra to the Netflix philosophy of immutable infrastructure, including managing software and hardware upgrades in the face of ever-failing hardware. Then we will explore the concrete techniques needed for such a massive deployment, specifically pull-based control planes and auto-healing strategies. Next, we will cover how Netflix has automated complex but critical Apache Cassandra maintenance tasks such as continuous snapshot backups and always-on anti-entropy repair for keeping our datasets safe and consistent. Both of these systems have gone through multiple architectural evolutions, and we have learned many lessons along the way. Lastly, we will share some of the ways this has gone wrong, and what you can do to avoid them. We will cover a few case studies of major Cassandra outages at Netflix, their root cause, and what we learned from those incidents. At the end of this talk, we hope that participants leave with concrete understanding of the challenges in running massive scale Apache Cassandra as well as solid advice and techniques for building their own self-driving data persistence layer.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1001", "audienceId": "", "typeId": "2", "locationId": "1000", "speakerIds": [ "1005", "1011" ], "languageId": "1" }, { "id": "1011", "start": "2019-09-12T17:30:00", "end": "2019-09-12T18:20:00", "title": "Next Generation Cassandra Compaction, Going beyond LCS", "abstractText": "Cassandra users with general purpose workloads typically must choose the lesser of two evils between the default “write optimized” Size Tiered Compaction Strategy (STCS) and the “read optimized” Leveled Compaction Strategy (LCS). It is typical these days to hear “use LCS unless it explodes, in which case use STCS…unless that explodes, in which case you are out of luck”. I believe that by taking what we as a community learned from the development and real world deployment of LCS, we can create a next generation compaction strategy which offers all of the benefits of LCS with few of the drawbacks. I will begin this talk with an overview of the existing general purpose options, and explore their deficiencies. In particular, we will explore how STCS naïvely groups SSTables of similar size together regardless of read amplification, expends system resources compacting data that does not benefit from compaction, and creates large files that are difficult to process both by Cassandra and downstream systems. The LCS compaction algorithm was developed to mitigate many of these issues. However, LCS suffers from issues of its own: implementation bugs caused by the complexity of the algorithm, significant write amplification introduced in the L0 to L1 transition, and a lack of efficient full compaction. LCS is a worthwhile compaction strategy, but these flaws prevent it from being applied universally to general purpose workloads. Once we have a firm understanding of the issues facing current implementations, I will present a number of potential incremental improvements to the existing choices. I’ll also synthesize these ideas into a blueprint for a new, general purpose, compaction strategy. A key design consideration is to offer users a single compaction interface with easy to understand tunables that adapt to all use cases historically covered by either STCS or LCS. Once I have laid out the proposal, I will open the topic for feedback from other developers in the room and I hope that at the end we will have built consensus around the key challenges of Cassandra compaction, as well as come to a decision on the best path forward.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1001", "audienceId": "", "typeId": "2", "locationId": "1010", "speakerIds": [ "1005" ], "languageId": "1" }, { "id": "1012", "start": "2019-09-10T12:15:00", "end": "2019-09-10T13:05:00", "title": "Managing Hundreds of Petabytes of data in the Cloud", "abstractText": "Twitter's on premise HDFS clusters are scaled out to handle hundreds of petabyte data serving thousands of developers every day. Managing such large scale data introduces several challenges. Organization, discovery, data life cycle, replication, schema management and many more questions needs to be answered at scale. Our data infrastructure is built on different open source and in house projects working together to solve this problem. While we extend our data to cloud, we had to solve similar challenges on cloud environment at Twitter scale. In this talk we lay out our framework, talk about challenges we faced on cloud and solutions we are working towards to support thousands of users dealing with hundreds of petabytes of data on cloud. ", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1007", "audienceId": "", "typeId": "2", "locationId": "1009", "speakerIds": [ "1012", "2044" ], "languageId": "1" }, { "id": "1014", "start": "2019-09-12T10:00:00", "end": "2019-09-12T10:50:00", "title": "How to Raise an Erudite Chatbot", "abstractText": "Availability of content and training sets is a major bottleneck for a chatbot development today. Relying on Apache OpenNLP and its sub-project OpenNLP.chatbot, we introduce a number of tools and components to design a chatbot and its training set to be knowledgeable and intelligent. n In this talk we will analyze the reasons it is so hard to find a chatbot demo today for a nontrivial task or to observe an intelligent behavior of a chatbot. It is easy to see how a success in AI can boost the chatbot development on one hand, but it is hard to detect intelligence in those chatbots that are available to the public, on the other hand. n We will present an advanced search engine for chatbots with the focus on linguistic features and discourse-level analysis for dialogue management. We will introduce a tool that builds a dialogue from an arbitrary document to form a training dataset for deep learning chatbots. We will demo a chatbot supporting virtual dialogue, where a user joins a virtual community built on the fly, whose members answer questions in this user's current area of interest. An extended content for this talk is available in the book recently published by the speaker “Developing Enterprise Chatbots”.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1013", "audienceId": "", "typeId": "2", "locationId": "1007", "speakerIds": [ "1014", "2033" ], "languageId": "1" }, { "id": "1015", "start": "2019-09-09T15:00:00", "end": "2019-09-09T15:50:00", "title": "Using Apache Pulsar to Provide Real-Time IoT Analytics on the Edge", "abstractText": "he business value of data decreases rapidly after it is created, particularly in use cases such as fraud prevention, cybersecurity, and real-time system monitoring. The high-volume, high-velocity datasets used to feed these use cases often contain valuable, but perishable, insights that must be acted upon immediately. In order to maximize the value of their data enterprises must fundamentally change their approach to processing real-time data to focusing reducing their decision latency on the perishable insights that exist within their real-time data streams. Thereby enabling the organization to act upon them while the window of opportunity is open. Generating timely insights in a high-volume, high-velocity data environment is challenging for a multitude of reasons. As the volume of data increases, so does the amount of time required to transmit it back to the datacenter and process it. Secondly, as the velocity of the data increases, the faster the data and the insights derived from it lose value. In this talk, we will present a solution based on Apache Pulsar Functions that significantly reduces decision latency by using probabilistic algorithms to perform analytic calculations on the edge.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1012", "audienceId": "", "typeId": "2", "locationId": "1014", "speakerIds": [ "1015" ], "languageId": "1" }, { "id": "1016", "start": "2019-09-09T17:30:00", "end": "2019-09-09T18:20:00", "title": "There's life in the (old) dog yet: Apache Edgent reinvents itself and Edge Analytics", "abstractText": "Apache Edgent (formerly Quarks) is a Project in the Apache Incubator since early 2016. The main focus of the project is to simplify edge processing pipelines. Through the last year it went a bit silent around the project and although the topic is hotter than ever the project lost its drive and went into hibernation. With the rise of other projects in the (industrial) IoT ecosystem like Apache PLC4X and Apache IoTDB there are a lot of new use cases and applications for edge processing, especially in the field of industrial IoT thus, a group of contributors from other IoT related projects has gathered to bring the project back to life and on track.nIn this talk, an introduction into Apache Edgent is given. Its past, its current state and plans on how the project could evolve in the near future.nProjects like Apache PLC4X (incubating) allow us to gather massive amounts of data from machines and plants and close the gap between the `Shopfloor`and the Big Data ecosystem. But, there are a few important differences between `classical` stream processing and the processing of industrial data streams. As the `classical` Big Data world is all about (vertical) scaling and parallelism this is not necessarily true for industrial data. Furthermore, many industrial sides are connected with low bandwidths which makes it even more difficult to send all the data to the cloud. Apache Edgent tries to address these issues by providing a platform for Edge processing.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1012", "audienceId": "", "typeId": "2", "locationId": "1014", "speakerIds": [ "1016" ], "languageId": "1" }, { "id": "1017", "start": "2019-09-10T18:00:00", "end": "2019-09-10T18:50:00", "title": "Anomaly Prediction in Apache CloudStack", "abstractText": "There is a chance of system, storage and network failures in the CloudStack environment at any point of time, which is unknown to the end users and administrators. The administrators are highly depend on the alert and monitoring system to raise an alarm on failures, upon the action is being taken. This can down the operations and will impact the end user services. The prediction of such failures ahead in CloudStack environment would be required instead of depending on the monitoring systems. Anomaly Prediction requires a model using the existing knowledge base and history of the CloudStack environment. This model would help in predicting the failures/abnormalities ahead of time. The necessary action is taken on these to minimize the down time or no down time, and making the CloudStack environment robust. The actions taken are learnt by the system and would automatically apply on the respective failures, make it a self-healing system.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1002", "audienceId": "", "typeId": "2", "locationId": "1006", "speakerIds": [ "1007", "1017" ], "languageId": "1" }, { "id": "1020", "start": "2019-09-09T10:00:00", "end": "2019-09-09T10:50:00", "title": "Automating Apache Traffic Control Server Deployments with IPv6", "abstractText": "Apache Traffic Control has some built-in tools for assisting in the installation and deployment of new servers; however, it is still a somewhat manual and repetitive process. I will be demonstrating how the Traffic Control API, used in conjunction with IPv6 autoconf can be used to streamline the deployment process, allowing servers to configure themselves post-install. Will highlight the use of the ‘tc-netconfig’ application, which was developed to facilitate this process.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1017", "audienceId": "", "typeId": "2", "locationId": "1003", "speakerIds": [ "1019" ], "languageId": "1" }, { "id": "1021", "start": "2019-09-11T14:15:00", "end": "2019-09-11T15:05:00", "title": "The Rise of Open Source Software (and Apache projects) in China", "abstractText": "This talk will cover the evolution, the current status and the outlook of the China open source landscape and ecosystem. This talk will also share the summary and analysis of varies open source software survey reports for China, the largest software developers market in the world. The Apache Software Foundation's projects and their communities play a critical role in leading and developing the OSS ecosystems in China where some leading IT enterprises and individuals, such as Huawei, Alibaba, Baidu, Tencent, Kyligence, SkyWalking, etc., are leading the way in contributing to many ASF projects, open-sourcing their projects, donating to and incubating their projects at ASF, graduating as top-level project of ASF, developing their respective ASF project communities in China, last but not least, advocating the Apache Way when and wherever possible. This reach-out and engage-in journey, starting 2014, to build and cross the culture, language and diversity bridge does not come easy. A story of sweat and tears to share and interact with the audience.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1008", "audienceId": "", "typeId": "2", "locationId": "1013", "speakerIds": [ "1020" ], "languageId": "1" }, { "id": "1022", "start": "2019-09-11T11:00:00", "end": "2019-09-11T11:50:00", "title": "Managing Trillions of Rows with Aplomb (well, actually with Drill)", "abstractText": "'Ingesting lots of data isn’t very hard any more. Ingesting it on a critical schedule, within strict time bounds while minimizing the risk of bogus data showing up is much harder. In practice, grownup data ingestion and access requires the following capabilities * Incoming data can be fully ingested into our working dataset but hidden from users until all quality checks are completedn * Individual batches of data can be released atomicallyn * Any indexing updates should also appear appear atomicallyn * Expiring data should disappear atomically either according to ingest batch or precise time bounds Apache Drill provides several capabilities that make it much easier to meet these goals. You can handle large volumes of data while allowing in-situ quality controls and while controlling the visibility of unverified data. I will describe a worked example that shows how Drill helps make this happen. (with aplomb)n'", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1003", "audienceId": "", "typeId": "2", "locationId": "1014", "speakerIds": [ "1021" ], "languageId": "1" }, { "id": "1023", "start": "2019-09-11T11:00:00", "end": "2019-09-11T11:50:00", "title": "The State of Diversity in Open Source & the ASF", "abstractText": "I'd like to cover the landscape of D&I in tech, then in open source, and then in the ASF. I'd like to discuss the dimensions used to evaluate our current status and I'd like to discuss the efforts we're working on to changer things. I will like to give this talk in the general track to a) celebrate the 20th Anniversary by reflecting back in our wins on diversity and inclusion and b) make it part of the foundation's big picture", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1008", "audienceId": "", "typeId": "2", "locationId": "1013", "speakerIds": [ "1022" ], "languageId": "1" }, { "id": "1024", "start": "2019-09-11T15:15:00", "end": "2019-09-11T16:05:00", "title": "Lessons from the Apache Beam Journey", "abstractText": "Apache Beam is a big data processing framework that can run on multiple big data engines, including Apache Spark, Apache Flink, Apache Samza, Apache Apex, and a number of non-Apache OSS engines and proprietary engines. After situating Beam in the OSS ecosystem, I will share lessons from Apache Beam's journey, including topics such as: - how do you onboard newcomers to the Apache Way?n - how is open source different / the same as internal corporate work?n - what are techniques for mitigating corporate politics in OSS governance?n - what does a healthy project look like in the stats?n - building community via pull requestn - how do OSS contributing teams look different?n - technical decisions have community impactn - how does ASF merit sustain projects for the long term?n - what seems to motivate volunteers?n - honoring non-code contributions", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1008", "audienceId": "", "typeId": "2", "locationId": "1013", "speakerIds": [ "1023" ], "languageId": "1" }, { "id": "1025", "start": "2019-09-11T14:15:00", "end": "2019-09-11T15:05:00", "title": "Declarative Benchmarking of Cassandra and Its Data Models", "abstractText": "You have made changes to Cassandra code base. How do you benchmark these changes for scalability and correctness, including different data models (schema), easily? You have created a Cassandra schema for your service. How do you ensure this is scalable? How can you emulate application specific CQL queries, with specified distribution, to validate scale of your schema and associated data scalability without having to code your whole application? I am the author of the NDBench CQL Plugin tool, which was built at Netflix to address these needs and more, Declaratively. One of the Cassandra committers has called this tool 'Game Changing'. This plugin is currently (June 2019) being prepped to be open sourced ahead of this talk. This talk presents: 1. An example of how we used declarative benchmarking to achieve 1 Million requests per second for a user specified data model and query distribution backing a critical service at Netflix. 2. For users: n a. How to certify scalability of new or existing data models on new version of Cassandra, for confident upgrades?n b. How to certify scalability of new complex data models? 3. For committers: n a. Define various profiles to emulate real world use cases to build confidence in changes and certifying new releases. n b. Compare scalability of the same data model across different Cassandra version. 4. The philosophy of the tool, it’s internal architecture, and future enhancements.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1001", "audienceId": "", "typeId": "2", "locationId": "1009", "speakerIds": [ "1024" ], "languageId": "1" }, { "id": "1026", "start": "2019-09-11T16:45:00", "end": "2019-09-11T17:35:00", "title": "Instaclustr's Open Source Tools For Cassandra - LDAP/Kerberos, Prometheus Exporter, Debug Tooling and K8s Operator", "abstractText": "This session walks devs through Instaclustr's Cassandra tools and how they add key functionality and ease-of-use to their deployments.n- An LDAP authenticator plug-in for CassandranThe open source LDAP authenticator plug-in works closely with the existing CassandraAuthorizer implementation. The plug-in enables developers to quickly reap the benefits of secure LDAP authentication without the need to write their own solutions, and to transition to using the authenticator with zero downtime. - A Kerberos authenticator plug-in for CassandranThe open source Kerberos authenticator plug-in enables Cassandra users to leverage Kerberos’ industry-leading secure authentication and true single sign-on capabilities. The open source project also includes a Kerberos authenticator plugin for the Cassandra Java driver. - Cassandra Prometheus ExporternThe cassandra-exporter is a high-performance metrics collection agent that allows for easy integration with the Prometheus monitoring solution. It has been designed to collect detailed metrics on production-sized clusters with complex schemata with minimal performance impact while at the same time following Prometheus's best practices for exporting metrics. - Additional utilities and debugging toolsnIncluding a utility to assist with backup and restore to various cloud providers, and tools to provide debug-level information about SSTables. - A Cassandra operator for running and operating Cassandra within KubernetesnThe open source Cassandra operator functions as a Cassandra-as-a-Service on Kubernetes, fully handling deployment and operations duties so that developers don’t have to. It also offers a consistent environment and set of operations founded on best practices, which is reproducible across production clusters and development, staging, and QA environments. The audience for this presentation will learn the specifics of how to implement – and get the most out of – these open source solutions.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1001", "audienceId": "", "typeId": "2", "locationId": "1009", "speakerIds": [ "1025" ], "languageId": "1" }, { "id": "1027", "start": "2019-09-11T11:00:00", "end": "2019-09-11T11:50:00", "title": "Two years in the making: What’s new with Apache Cassandra 4.0?", "abstractText": "At almost two years in the making Apache Cassandra 4.0 is almost here. With a focus on performance and stability, it is full of interesting features. This talk takes you through a tour of the new features and performance improvements. From Zero Copy Faster Streaming support to Virtual Tables and Audit Logging, learn how Apache Cassandra 4.0 has departed from previous major releases to be focused on the features required by the most demanding users. Attendees will not only gain an understanding of new features in Apache Cassandra, but understand what drove their creation and therefore have a better idea of how to best use these features in their own systems.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1001", "audienceId": "", "typeId": "2", "locationId": "1010", "speakerIds": [ "1026" ], "languageId": "1" }, { "id": "1028", "start": "2019-09-11T17:45:00", "end": "2019-09-11T18:35:00", "title": "Happiness is a hybrid cloud with Apache Cassandra™", "abstractText": "The world's data and the speed with which we expect to access it continues to grow rapidly. Apache Cassandra was built for hybrid cloud implementations and that makes it easy for companies to fully exploit their cloud strategies without having to re-architect their applications or change their systems for data management. Sounds too good to be true? A lot of big companies have been doing it for years and you can too! In this presentation, we will cover best practices and strategies for deploying your app to Cassandra on any cloud that you want. We will discuss: * Uses cases that require the power of Cassandra for hybrid cloud * Data model considerations for your active anywhere applicatio * Deployment strategies on any cloud. We do not care which cloud :)", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1001", "audienceId": "", "typeId": "2", "locationId": "1010", "speakerIds": [ "1027" ], "languageId": "1" }, { "id": "1030", "start": "2019-09-10T14:30:00", "end": "2019-09-10T15:20:00", "title": "How eBay builds Data Quality Platform with Apache Griffin", "abstractText": "High Quality data plays an important role for incubating awesome big data applications. In real projects, governing data, observing their quality health, and taking remedy actions are tedious and time-consuming. Apache Griffin is an open source Data Quality solution for Big Data, which supports both batch and streaming mode. It offers a unified process to measure your data quality from different perspectives, helping you build trusted data assets, therefore boost your confidence for your business. In this session, we will talk about how eBay leverage Apache Griffin and build a big data quality platform to support all kinds of business critical data applications. First, we will introduce the key concepts and architecture design of Griffin and share the experience of open-source it under the Apache way. Then, we will dive into our internal data quality platform and its use cases.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1014", "audienceId": "", "typeId": "2", "locationId": "1004", "speakerIds": [ "1029", "1030" ], "languageId": "1" }, { "id": "1031", "start": "2019-09-10T15:30:00", "end": "2019-09-10T16:20:00", "title": "Improving the Observability of Cassandra, Kafka and Kubernetes applications with Prometheus and OpenTracing", "abstractText": "As distributed applications grow more complex, dynamic, and massively scalable, “observability” becomes more critical. Observability is the practice of using metrics, monitoring and distributed tracing to understand how a system works. In this presentation we’ll explore two complementary Open Source technologies: Prometheus for monitoring application metrics; and OpenTracing and Jaeger for distributed tracing. We’ll discover how they improve the observability of a massively scalable Anomaly Detection system - an application which is built around Apache Cassandra and Apache Kafka for the data layers, and dynamically deployed and scaled on Kubernetes, a container orchestration technology. We will give an overview of Prometheus and OpenTracing/Jaeger, explain how the application is instrumented, and describe how Prometheus and OpenTracing are deployed and configured in a production environment running Kubernetes, to dynamically monitor the application at scale. We conclude by exploring the benefits of monitoring and tracing technologies for understanding, debugging and tuning complex dynamic distributed systems built on Kafka, Cassandra and Kubernetes. ", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1014", "audienceId": "", "typeId": "2", "locationId": "1004", "speakerIds": [ "1031" ], "languageId": "1" }, { "id": "1032", "start": "2019-09-10T14:30:00", "end": "2019-09-10T15:20:00", "title": "Panel discussion on recognizing non-code contributions", "abstractText": "A discussion panel with 2 or 3 projects who have been successful at growing their communities outside the English speaking countries and how they did it.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1008", "audienceId": "", "typeId": "2", "locationId": "1000", "speakerIds": [ "1022", "1323", "1114" ], "languageId": "1" }, { "id": "1033", "start": "2019-09-12T13:00:00", "end": "2019-09-12T13:50:00", "title": "Apache Groovy Update and Roadmap", "abstractText": "This talk looks at the latest features in Groovy from 2.5 and 3.0. This includes new AST transforms, new macro features, the new Parrot parser and a myriad of other new miscellaneous features. The talk outlines a broad roadmap of how the new features are planned to be rolled out and the system requirements for each version.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1016", "audienceId": "", "typeId": "2", "locationId": "1000", "speakerIds": [ "1032" ], "languageId": "1" }, { "id": "1034", "start": "2019-09-11T16:45:00", "end": "2019-09-11T17:35:00", "title": "Efficient data integrations with the Medley platform", "abstractText": "In this talk, we will introduce the Medley data integration platform used at Uber. Medley is based on the Apache Camel framework, and centered around integrating internal systems efficiently and with great precision on multiple network environments. We will focus on the concept of reusability of integrations, where integrations can be securely shared by implementing integrations as web services. Also, implementing business entity change detection with publish/subscribe to changes to allow event based integrations based on data state changes. Finally, we will describe the challenges dealing with many types of integration use cases, development processes, monitoring, and troubleshooting.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1011", "audienceId": "", "typeId": "2", "locationId": "1006", "speakerIds": [ "1033" ], "languageId": "1" }, { "id": "1035", "start": "2019-09-10T11:15:00", "end": "2019-09-10T12:05:00", "title": "State of the cat, new and upcoming", "abstractText": "This presentation will detail the current state of the Apache Tomcat project and its community. After going through information on recent releases, community metrics and security advisories, this will cover important new and upcoming features. This includes HTTP/X support, clustering, TLS, cloud enablement, and much more.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1005", "audienceId": "", "typeId": "2", "locationId": "1007", "speakerIds": [ "1034" ], "languageId": "1" }, { "id": "1036", "start": "2019-09-10T18:00:00", "end": "2019-09-10T18:50:00", "title": "Introducing Secure Boot in Apache CloudStack", "abstractText": "nExisting CloudStack supports legacy boot loader BIOS by default for Guest VM’s booting on Hypervisor(XEN, VMware, KVM etc). In Virtualization, hypervisor emulates the hardware for the Guest VM. BIOS {Basic Input-Output system} is a low-level software. The BIOS loads when a VM starts up, and the BIOS is responsible for waking up your VM’s hardware(emulated) components, ensures they are functioning properly, and then runs the boot loader that boots Windows or whatever other operating system have installed. The existing BIOS has serious limitations. It can only boot from drives of two 1 TB or less. 3 TB drives are now common, and a computer with a BIOS can’t boot from them. That limitation is due to the way the BIOS’s Master Boot Record system works. BIOS can be used in devices that do not require large storage or security. UEFI { Unified Extensible Firmware Interface} can work alongside BIOS. It can sit on top of BIOS and work independently. Benefits of UEFI boot mode over Legacy BIOS boot mode include: Support for hard drive partitions larger than 2 TBn Support for more than four partitions on a driven Fast bootingn Efficient power and system managementn Robust reliability and fault management", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1002", "audienceId": "", "typeId": "2", "locationId": "1005", "speakerIds": [ "1035", "1036" ], "languageId": "1" }, { "id": "1037", "start": "2019-09-09T17:30:00", "end": "2019-09-09T18:20:00", "title": "Network Visibility in Hybrid and Multi Clouds", "abstractText": "Network Visibility in Apache CloudStack", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1002", "audienceId": "", "typeId": "2", "locationId": "1005", "speakerIds": [ "1007", "1006" ], "languageId": "1" }, { "id": "1038", "start": "2019-09-10T18:00:00", "end": "2019-09-10T18:50:00", "title": "Podling's Shark Tank", "abstractText": "Is it a panel? Is it a talk? It is a Podling's Shark Tank! Back by popular demand with even sharkier judges! What is it, you ask? Well, this is just like Shark Tank TV show (think speed dating between entrepreneurs and investors) but instead of “Squirrel Boss” and “Man Candle” you'll be hearing pitches for Apache Incubator projects. Also instead of Mark Cuban and Kevin O'Leary you'll be pitching to the panel of ASF old timers (trying to convince them that your project is worthy of their esteemed attention and endorsement). There will be snark, there will be prizes, there will be reciting of Apache Way creed. But most of all there will be fun. We guaranteed it! And don't forget, if you want your favorite podling to be featured on the show, volunteer to do the pitch by simply signing up on this wiki page: https://wiki.apache.org/apachecon/ACNA19PodlingSharkTank ", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1008", "audienceId": "", "typeId": "2", "locationId": "1013", "speakerIds": [ "1037" ], "languageId": "1" }, { "id": "1039", "start": "2019-09-09T16:30:00", "end": "2019-09-09T17:20:00", "title": "Cloudstack API development 101", "abstractText": "This is a primer to getting started with adding functionality to CloudStack. In this presentation we will go over a custom Maven archetype that will fast track CloudStack development, whether the goal is to develop functionality to contribute to CloudStack project or to integrate CloudStack with site specific systems. It is geared toward Java developers who are new to the CloudStack code base.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1002", "audienceId": "", "typeId": "2", "locationId": "1006", "speakerIds": [ "1010" ], "languageId": "1" }, { "id": "1040", "start": "2019-09-09T14:00:00", "end": "2019-09-09T14:50:00", "title": "Open vSwitch with DPDK on CloudStack", "abstractText": "Support for Open vSwitch with DPDK has been introduced on CloudStack version 4.12. In this talk we will go through the motivations and advantages of using DPDK on KVM hosts, high level architecture of the feature, what is needed and how can it be used on production environments and future works.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1002", "audienceId": "", "typeId": "2", "locationId": "1006", "speakerIds": [ "1038" ], "languageId": "1" }, { "id": "1041", "start": "2019-09-12T13:00:00", "end": "2019-09-12T13:50:00", "title": "The Apache Way May Save Us All", "abstractText": "The commercial software industry is plagued by numerous significant problems: Cost and schedule overruns, poor software quality, unrealistic expectations, products that fail to meet customer needs, and more. These problems are historic, chronic, and pervasive; they’ve been with us for decades, and changes to methodology haven’t had much effect in remedying them. By contrast, the Apache Software Foundation has been around for 20 years and the Apache Way - the framework of values and governance for Apache Software Foundation projects - has been the guiding force for dozens of highly successful software projects that are used in countless environments everywhere, run much of the Internet, and are probably used by every technical person in one way or another every day. In fact it would be hard to find any other software organization, open or proprietary, with a better track record. What if the Apache Way were applied to all software projects? Could the Apache Way be the answer to solve these universal software engineering challenges, for everybody, once and for all?", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1008", "audienceId": "", "typeId": "2", "locationId": "1013", "speakerIds": [ "1039" ], "languageId": "1" }, { "id": "1042", "start": "2019-09-10T12:15:00", "end": "2019-09-10T13:05:00", "title": "Cassandra Traffic Management at Instagram", "abstractText": "Cassandra has been deployed for many years at Instagram and is still growing fast. Over the years, we’ve constantly improved the design of our infrastructure: we’ve introduced Cassandra proxy nodes to decouple the processing and storage workloads, we've developed Rocksandra, a new storage engine relying on RocksDB that reduced the GC pressure and improved the efficiency of our clusters. Lately, we've added an intermediate layer in our Cassandra infrastructure, where we could add many traffic optimizations to further improve our Cassandra clusters' efficiency and reliability. This talk will explain in detail this new component and the results we've observed.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1001", "audienceId": "", "typeId": "2", "locationId": "1010", "speakerIds": [ "1040" ], "languageId": "1" }, { "id": "1043", "start": "2019-09-12T15:30:00", "end": "2019-09-12T16:20:00", "title": "Apache Training, How it came to be and what it is about", "abstractText": "There are lots of companies offering training for, and around, the Apache ecosystem, as well as many other topics that all create their own training material. Keeping this material up to date, especially in the fast-moving open-source world is not an easy task and takes a lot of time and effort. And all the time someone not too far away is probably working on a very similar slide-deck to explain what ZooKeeper does... It is this fundamental issue that the Apache Training project was created to address - centralising training resources and making them easier to access and (re-)use. We believe that training material, while important, is only part of what constitutes good training. The larger part is an experienced trainer who actually understands how the key aspects can be applied in real life and also the consequences of not implementing things correctly.nGreat training tends to come from the experiences and stories that a trainer can share in addition to the actual material. Based on this underlying belief and the very real pain of updating training material the Apache Training project was born. In early 2019, it entered Apache Incubator and is already building a community and gaining various contributions. In this talk, we want to share with you some of the events and the thought process that went into the creation of this project, as well as our main goals and principles. The first part of this talk will focus on how we arrived at the decision that open-source training material is a good thing to have and a little bit of the early history of this project. In the second part, we will discuss what the project is actually about. We will demonstrate the version-control friendly system of designing slides in source control that is at the core of this project. On top of these source files, we aim to create a metadata repository which will enable everybody to efficiently search available content and easily create tailored decks from existing material. And last but very much not least, we will cover how you can contribute to and benefit from this project, as this is front and center an effort from the community for the community!", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1008", "audienceId": "", "typeId": "2", "locationId": "1013", "speakerIds": [ "1041", "1042" ], "languageId": "1" }, { "id": "1044", "start": "2019-09-12T14:00:00", "end": "2019-09-12T14:50:00", "title": "Apache Cordova In Action", "abstractText": "Apache Cordova is a platform for building Hybrid mobile apps using common Web technologies (HTML, CSS and JavaScript). Apache Cordova offers a set of APIs that allow the mobile app developers to utilize mobile native functions such as (Audio, Camera, Contacts …etc) using JavaScript. Ionic is one of the best mobile web application frameworks, which allows the web developers to develop neat mobile web applications. This session discusses why there is a need for Hybrid mobile development, the current challenges of mobile development, and how using Apache Cordova can help in overcoming many of these technical challenges. Finally, it demonstrates a real Cordova mobile app for showing the audience the best practices of designing, developing, and deploying hybrid Android and iOS mobile apps.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1018", "audienceId": "", "typeId": "2", "locationId": "1009", "speakerIds": [ "1043" ], "languageId": "1" }, { "id": "1045", "start": "2019-09-09T08:00:00", "end": "2019-09-09T08:50:00", "title": "Welcome to the Content Delivery Track", "abstractText": "This presentation will open the track and serve as a welcome to those attending. I will cover what’s new in the ATC (Apache Traffic Control) community, introduce our new committers and PMC members, talk about what we will cover during the conference and then talk a little about the CDN market as a whole.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1017", "audienceId": "", "typeId": "2", "locationId": "1003", "speakerIds": [ "1044" ], "languageId": "1" }, { "id": "1046", "start": "2019-09-09T17:30:00", "end": "2019-09-09T18:20:00", "title": "Workshop: Getting Apache Traffic Control Up And Running", "abstractText": "CDN-in-a-Box is a subproject within Apache Traffic Control (ATC) to build a test/experimental CDN in docker on an individual workstation. The process is still challenging, so I'd like to do a workshop to guide interested users through the process on their own laptops. The goal is to show them how the CDN works at a fairly low level and how to test that the various parts work as expected as well as troubleshooting if things go awry. This would hopefully drum up more interest in participation in the ATC project.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1017", "audienceId": "", "typeId": "2", "locationId": "1003", "speakerIds": [ "1045" ], "languageId": "1" }, { "id": "1047", "start": "2019-09-09T15:00:00", "end": "2019-09-09T15:50:00", "title": "Anycast ATC Integration at Comcast", "abstractText": "Anycast is an industry proven technology and is quickly becoming a requirement for off-the-shelf CDNs as well as CDN-as-a-Service. In this talk we will investigate how Comcast is integrating anycast functionality into Apache Traffic Control to improve resiliency, convergence and localization.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1017", "audienceId": "", "typeId": "2", "locationId": "1003", "speakerIds": [ "1046" ], "languageId": "1" }, { "id": "1048", "start": "2019-09-11T11:00:00", "end": "2019-09-11T11:50:00", "title": "Apache Tomcat, your webapp, and the Graal", "abstractText": "Graal's native image generation has been the focus of a lot of attention recently, despite being in the very early stages. This session will look at the Tomcat embedded packaging, how to handle your webapp, and will demo use of Graal and Tomcat in a container environment. The session will mostly be tutorial/demo oriented, after a brief overview of the concept and tools used.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1005", "audienceId": "", "typeId": "2", "locationId": "1007", "speakerIds": [ "1034" ], "languageId": "1" }, { "id": "1049", "start": "2019-09-11T11:00:00", "end": "2019-09-11T11:50:00", "title": "Apache Hadoop 3.x State of The Union and Upgrade Guidance", "abstractText": "'Apache Hadoop YARN is the modern Distributed Operating System for big data applications. It morphed the Hadoop compute layer to be a common resource-management platform that can host a wide variety of applications. Many organizations leverage YARN in building their applications on top of Hadoop without themselves repeatedly worrying about resource management, isolation, multi-tenancy issues etc. The Hadoop Distributed File System (HDFS) is the primary data storage system used by Hadoop applications. It employs a NameNode and DataNode architecture to implement a distributed file system that provides high-performance access to data across highly scalable Hadoop clusters. In this talk, we’ll start with the current status of Apache Hadoop 3.x – how it is used today in deployments large and small. We’ll then move on to the exciting present & future of Hadoop 3.x – features that are further strengthening Hadoop as the primary resource-management platform as well as the storage system for enterprise data-centers. We’ll discuss the current status as well as the future promise of features and initiatives for both YARN and HDFS of Hadoop 3.x: For YARN 3.x, we have powerful container placement, global scheduling, support for machine learning (Spark) and deep learning (TensorFlow) workloads through GPU & FPGA scheduling and isolation support, extreme scale with YARN federation, containerized apps on YARN, support for long-running services (alongside applications) natively without any changes, seamless application/services upgrades, powerful scheduling features like application priorities, intra-queue preemption across applications and operational enhancements including insights through Timeline Service V2, a new web UI, better queue management, etc.nAlso, HDFS 3.0 announced GA for erasure coding which doubles the storage efficiency of data and thus reduces the cost of storage for enterprise use cases. HDFS added support for multiple standby NameNodes for better availability. For better reliability of metadata and easier operations, Journal nodes have been enhanced to sync the edit log segments to protect against rolling failures.nDisk balancing within a DataNode was another important feature added to ensure disks are evenly utilized in a DataNode, which also ensures better aggregate throughput, and prevents from lopsided utilization if new disks are added or replaced in a DataNode. HDFS team is currently driving the Ozone initiative which lays the foundation of the next generation of storage architecture for HDFS where data blocks are organized in Storage Containers for higher scale and handling of small objects in HDFS. Ozone project also includes an object store implementation to support new use cases. At last, since more and more users are planning to upgrade from 2.x to 3.x to get all the benefits mentioned above, we will also briefly talk about upgrade guidance from Hadoop 2.x to 3.×.n'", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1007", "audienceId": "", "typeId": "2", "locationId": "1000", "speakerIds": [ "2023", "2022" ], "languageId": "1" }, { "id": "1051", "start": "2019-09-09T11:30:00", "end": "2019-09-09T12:20:00", "title": "Building a smart query mediation engine for Genome Research using Apache Drill", "abstractText": "The integration of both clinical and genomics data into a single platformnthat will allow the researchers to search, analyze and discover the hidde patterns in biomedical databases. Developing this integrated platform be-ncomes a complex and challenging task due to (i) heterogeneous data typesn(ii) huge volume of data (iii) number of attributes are di erent across thendata (iv) generated data are from heterogeneous platform and (v) corre-nlation between clinical and genomics data are di erent to each other andn(vi) scalability factors. To address these problems, Biomedical InformaticsnDivision within Sidra Research took the initiative to develop a personalized health-nintegrated informatics platform that will help the researchersnto get insights to questions previously un-answered.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1003", "audienceId": "", "typeId": "2", "locationId": "1000", "speakerIds": [ "1050" ], "languageId": "1" }, { "id": "1052", "start": "2019-09-11T12:00:00", "end": "2019-09-11T12:50:00", "title": "What’s Surprising about Apache Drill and Why That’s a Challenge", "abstractText": "'Apache Drill has some very surprising characteristics and, more importantly, it enables Drill users to do some surprising things. It’s no longer surprising to be able to do standard SQL in a highly distributed and large scale system - there is an entire class of modern tools that do this including Apache Hive, Presto or Spark SQL. But Drill has other capabilities that are surprising and make it stand apart from its class. For one thing, Drill provides an extraordinary degree of flexibility in several ways, including: Support for a wide variety of file formats including semi-structured and nested data (such as Parquet, JSON, Avro) and non-file data sources - not just data access but ability to fully use these data sources with high performance Schema discovery - a capability that opens up data exploration in unexpected ways for Drill users and allows progressive data modelling Easy extensibility with high performance - you don’t have to trade one for the other These are valuable if surprising capabilities. Why, then, is that a challenge? Because people don’t expect them, they also may not come looking for a tool that can do these things. The challenge comes in how to make potential users aware of the opportunities that Drill offers. This talk will explore some of Drill’s surprising capabilities, how it’s able to do these things and what impact that has for Drill users. In addition, we will open a discussion about how best to inform and engage a broader user community. This latter issue is not only important for Drill but for other Apache projects as well.'", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1003", "audienceId": "", "typeId": "2", "locationId": "1014", "speakerIds": [ "1051" ], "languageId": "1" }, { "id": "1053", "start": "2019-09-10T14:30:00", "end": "2019-09-10T15:20:00", "title": "Monitoring of CloudStack", "abstractText": "Our approach of monitoring the CloudStack management server, parts of CloudStacks ecosystem and its underlying components. We give an introduction of how to monitor virtual routers, customer systems and customer resources in CloudStack.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1002", "audienceId": "", "typeId": "2", "locationId": "1006", "speakerIds": [ "1052" ], "languageId": "1" }, { "id": "1054", "start": "2019-09-12T15:30:00", "end": "2019-09-12T16:20:00", "title": "Apache Cassandra Sidecar, let’s make C* attractive and easy to operate", "abstractText": "Cloud database offerings have expanded over the past decade, encompassing everything from virtualized machines in the cloud to entirely serverless databases. With this pace of innovation in the cloud ecosystem, Cassandra stands in a unique position to serve its users with unique advantages over any other system. This also puts Cassandra in an interesting position to compete with the ongoing innovations in the cloud. With the internal architecture and storage mechanism aside, citizen developers in the community are looking for several other operability aspects/ ecosystem around the services for the long term investments and benefits from such service. At this juncture, it is vital for the Cassandra dev community to build muscle around supporting such an ecosystem that the community is looking for, to be on par with rest of cloud services and other competing offers in the industry. Specifically, it is important for us to innovate and focus on improving these areas along with the rest of the product.\n - Ease of use \n- Simplified operability in the cloud, precisely simplified operability in the hybrid/multi-cloud\n- Pluggability with other infrastructure services such as metrics, discovery, and monitoring\n- Painless rollouts of version and protocol upgrades\n- Elegant developer experience in polyglot environments\n- Dev education of Cassandra best practices\n- Unified access across the complex systems\n As Cassandra stands today, operating the database requires either considerable labor, complex automation, or both. Some of this complexity is an unavoidable result of operating a distributed system, but much of it is operational complexity stemming from properties of C* itself. As a result of these complexities, C* operators spend too much time dealing with issues that the database should solve on its own, and are unable to reap the full benefit of Cassandra’s powerful distributed data model. As part of this talk, we will focus on how to address the aforementioned challenges to keep the Cassandra competitive within the cloud offerings and database services industry, with simplified operability and elegant developer and operator experience. We also hope to get Apache Cassandra 4.0 up and running in any cloud without a hassle with the help of the sidecar. We hope to leave a thought in the Cassandra dev community to start thinking about these areas in upcoming releases of Cassandra. ", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1001", "audienceId": "", "typeId": "2", "locationId": "1010", "speakerIds": [ "1011", "1026" ], "languageId": "1" }, { "id": "1055", "start": "2019-09-12T14:00:00", "end": "2019-09-12T14:50:00", "title": "Agile Integration - Cloud Native Application Development", "abstractText": "Cloud native application development is more than just container orchestration, when it comes to designing proper agile software architecture, there are many aspect that need to be taken into account. From simple microservices runtime, orchestration of core business, interacting with legacy, connecting with external SaaS application. To a more reactive system with events driven backbone, and also avoid data silos and how to deal with routing, versioning deployment strategy. Putting everything into a big picture, guide you through what next generation of cloud native architecture should be like and how everything works together.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1011", "audienceId": "", "typeId": "2", "locationId": "1006", "speakerIds": [ "1053" ], "languageId": "1" }, { "id": "1056", "start": "2019-09-10T11:15:00", "end": "2019-09-10T12:05:00", "title": "The Apache Way - Not only the What but the Why", "abstractText": "The Apache Way consists of the basic core tenets, embraced by all ASF projects, which define how Open Source projects should be managed, governed and maintained. But in addition to a simply list of what those tenets are, we will dig deeper and discover the history and rationale behind them all. The incredible success of the Apache Way can be used to immediate advantage in your open source project and actual forms the core philosophy behind InnerSource.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1008", "audienceId": "", "typeId": "2", "locationId": "1013", "speakerIds": [ "1054" ], "languageId": "1" }, { "id": "1057", "start": "2019-09-12T14:00:00", "end": "2019-09-12T14:50:00", "title": "Apache httpd 2.4 Overview", "abstractText": "All the Ins and Outs related to what's old, and NEW, in Apache httpd 2.4. If you haven't use httpd in awhile, this is a great way to find out all the new features and enhancements. And if you are a current user, you find out about how to tune httpd for peak performance", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1016", "audienceId": "", "typeId": "2", "locationId": "1000", "speakerIds": [ "1054" ], "languageId": "1" }, { "id": "1058", "start": "2019-09-10T11:15:00", "end": "2019-09-10T12:05:00", "title": "Apache SkyWalking -- Top level open source APM", "abstractText": "SkyWalking has just graduated as Top Level Project in this year. SkyWalking is an open source APM system, including monitoring, tracing, diagnosing capabilities for distributed systems in Cloud Native architecture. In the modern world, we have legacy and cloud-native distributed systems, even in hybrid. SkyWalking provides different observability methods, including language agents and service mesh angle, which adopt different scenarios. In this session, I will introduce what SkyWalking do, and how we do it, even without requiring any big data tech. A lightweight and powerful observability platform provides the core features of APM system.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1014", "audienceId": "", "typeId": "2", "locationId": "1004", "speakerIds": [ "1055" ], "languageId": "1" }, { "id": "1059", "start": "2019-09-12T09:00:00", "end": "2019-09-12T09:50:00", "title": "Apache Camel K: connect your Knative serverless applications with everything else", "abstractText": "When you start developing serverless applications in the real world, sooner rather than later you will need to talk to external (legacy) systems. In this talk you will discover how to leverage Apache Camel K to connect your Knative serverless applications with everything Camel can connect.nApache Camel K allows running Camel routes as serverless applications directly on top of any Kubernetes cluster, leveraging Knative serverless capabilities such as auto-scaling, scaling to zero, event-based communication in order to connect serverless functions and microservice with external systems.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1011", "audienceId": "", "typeId": "2", "locationId": "1006", "speakerIds": [ "1056", "1057" ], "languageId": "1" }, { "id": "1060", "start": "2019-09-11T11:00:00", "end": "2019-09-11T11:50:00", "title": "The Apache TinkerPop4 Virtual Machine", "abstractText": "The Apache TinkerPop team is working on the next major version of the project -- TinkerPop4. TinkerPop4 advances the technology developed in TinkerPop3 with a new virtual machine architecture that enables any query language to control any processing engine manipulating any data structure. A query language can support a compiler to TinkerPop4's Turing Complete bytecode specification. Compiled bytecode is then translated into an intermediate functional representation that an integrated processing engine will ultimately transform into a processor-specific execution plan. TinkerPop4's intermediate representation naturally supports pull-based, push-based, distributed, message passing, threaded, query routing, etc. semantics which are captured in various data processors such as Pipes, Rx, Akka, Flink, Apex, Spark, and more. Additionally, a subset of the instructions in TinkerPop's bytecode specification denote manipulations to data stored in graph databases, relational databases, document databases, in-memory, and other data structure systems. In this way, TinkerPop4 enables system-agnostic universal computing across the numerous Apache (and other) language, processor, and database projects. This presentation offers an in-depth, technical analysis of the TinkerPop4 virtual machine architecture.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1010", "audienceId": "", "typeId": "2", "locationId": "1006", "speakerIds": [ "1058" ], "languageId": "1" }, { "id": "1061", "start": "2019-09-09T16:30:00", "end": "2019-09-09T17:20:00", "title": "GeoSpatial and Temporal Forecasting in Uber Marketplace", "abstractText": "Uber’s Marketplace is the algorithmic brain and decision engine behind our ride-sharing services. Marketplace Forecasting builds and deploys ML algorithms to handle the immense coordination, hyperlocal decision making, and learning needed to tackle the enormous scale and movement of our transportation network. In order for our decision engines to be future-aware, we need to be able to “see into the future” as accurately as possible across both space and time. In Uber, we use H3 (a hexagonal hierarchical geospatial indexing system) to partition the data geospatially. To incorporate both geospatial and temporal features into the forecasting models in real time, we need efficient and scalable techniques for data processing. In this presentation, we provide an overview of geospatial and temporal forecasting problem in Uber Marketplace Forecasting. Then, we use real time forecasting as an example to show the need for efficient data smoothing and describe a hexagon convolution based approach for processing H3 data in production. We will demonstrate how we could incorporate hexagon convolution with Apache Flink to scale the data smooth for forecasting.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1009", "audienceId": "", "typeId": "2", "locationId": "1013", "speakerIds": [ "1059", "2036" ], "languageId": "1" }, { "id": "1062", "start": "2019-09-09T11:30:00", "end": "2019-09-09T12:20:00", "title": "Automating Apache Traffic Control Environment Deployments with Ansible", "abstractText": "Apache Traffic Control is a set of applications designed to complement Apache Traffic Server to comprise a Content Delivery Network. Currently the creation of a complete production-ready CDN environment is a complex process. I will be demonstrating automation leveraging Ansible and CDN environment designs to facilitate consistent and more rapid testing environment creation.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1017", "audienceId": "", "typeId": "2", "locationId": "1003", "speakerIds": [ "1060" ], "languageId": "1" }, { "id": "1063", "start": "2019-09-09T16:30:00", "end": "2019-09-09T17:20:00", "title": "Machine Learning and Data Analytics in the Content Delivery Context", "abstractText": "In line with the content delivery community's interest in data-driven operational insights and improving operational efficiency, this presentation and discussion will address the following topics: (1) What are Machine Learning, Deep Learning, and the different types of analytics (from descriptive through prescriptive)? (2) What are the potential benefits and risks of analytical solutions? (3) And finally - a walkthrough of some example use cases from modern content delivery networks and their corresponding analytical solutions.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1017", "audienceId": "", "typeId": "2", "locationId": "1003", "speakerIds": [ "1061" ], "languageId": "1" }, { "id": "1064", "start": "2019-09-10T12:15:00", "end": "2019-09-10T13:05:00", "title": "Traffic Server Remap Update", "abstractText": "Rewriting URLs, or 'remapping', is probably the single most used feature of the Traffic Servernproxy. With the transition to YAML from a proprietary line based format, it was decided to startnover with effectively a blank slate, to design a configuration with a functionality emphasizingnpower and flexibility over compatibility. This talk will elaborate on the decision path leading upnto this complete restructuring, the design of the configuration, and examples of its use. Thenunderlying implementation will be sketched out to show some of the interesting C++ techniques usednto make it possible.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1017", "audienceId": "", "typeId": "2", "locationId": "1003", "speakerIds": [ "1062" ], "languageId": "1" }, { "id": "1065", "start": "2019-09-12T13:00:00", "end": "2019-09-12T13:50:00", "title": "The ASF and OFBiz - How Community Makes It All Possible", "abstractText": "Going back well before the ASF was formed, community has played a vital role in the development of open source software. With the formation of the ASF, we see a great example of open source community being formalized and actively facilitated. Although it can seem counterintuitive, especially to the uninitiated, placing 'Community over code' helps ensure the ongoing relevance of open source as a movement, inviting individuals and organizations alike to invest in 'free' software. The community participation statistics across the ASF are impressive and highly convincing.nThe results of this community participation include personal growth, an ever evolving and strengthening Apache project, as well as a strong foundation for commercial business development.n- Brief historyn- ASF stats overviewn- What 'Community over code' means to various Apache community members At the individual project level, Apache OFBiz has benefitted from hundreds of thousands of volunteer hours (over 75,000 from one application development company alone) over the past 13 years, and relies on numerous other Apache projects. The presenter will share examples of one service provider's approach to making community contributions, including those of individuals as well as company-wide initiatives that have worked well over the years.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1019", "audienceId": "", "typeId": "2", "locationId": "1005", "speakerIds": [ "1063" ], "languageId": "1" }, { "id": "1066", "start": "2019-09-11T14:15:00", "end": "2019-09-11T15:05:00", "title": "Protect your Private Data in your Hadoop Clusters with ORC Column Encryption", "abstractText": "Fine-grained data protection at a column level in data lake environments has become a mandatory requirement to demonstrate compliance with multiple local and international regulations across many industries today. ORC is a self-describing type-aware columnar file format designed for Hadoop workloads that provides optimized streaming reads, but with integrated support for finding required rows quickly. In this talk, we will outline the progress made in Apache community for adding fine-grained column level encryption natively into ORC format that will also provide capabilities to mask or redact data on write while protecting sensitive column metadata such as statistics to avoid information leakage. The column encryption capabilities will be fully compatible with Hadoop Key Management Server (KMS) and use the KMS to manage master keys providing the additional flexibility to use and manage keys per column centrally. An end to end scenario that demonstrates how this capability can be leveraged will be also demonstrated.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1007", "audienceId": "", "typeId": "2", "locationId": "1000", "speakerIds": [ "1064" ], "languageId": "1" }, { "id": "1067", "start": "2019-09-12T16:30:00", "end": "2019-09-12T17:20:00", "title": "Running an Apache Project: 10 Traps and How to Avoid Them", "abstractText": "When you are starting on your open source adventure, there are lot ofnthings to learn that have very little to do with coding and insteadnrelate to interacting with people. Apache is, at its best, a group ofnpeople who are trying to share their experience and teach new projectsnand contributors how to successfully manage open source projects.nHowever, like the blind people each describing a part of an elephant,neach mentor brings their personal experience to the table, and thusncan give good, yet conflicting advice to new projects. However, thatnaggregate advice has helped many projects to become successful. Based on the author's experience, this talk will take you through 10ncommon traps in running Apache projects, why they happen, and how tonavoid or mitigate them.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1008", "audienceId": "", "typeId": "2", "locationId": "1013", "speakerIds": [ "1064" ], "languageId": "1" }, { "id": "1068", "start": "2019-09-11T11:00:00", "end": "2019-09-11T11:50:00", "title": "Using the TLP toolchain as a crystal ball for your cluster", "abstractText": "Cassandra cluster management is hard. Understanding how your Cassandra data model will hold up in production over a period of time can be tricky. If that is not tough enough, understanding how a change to a Cassandra setting will affect your cluster can be be difficult. Knowing how your data model or setting change will perform under a production data load can prevent performance degradation or worse nodes going down. In the last year, The Last Pickle has invested the time to develop the tooling necessary to create test clusters in AWS, as well as a scalable stress tool which can run pre-configured workloads. These tools are designed to take the guess work out of data modelling and configuration changes in Cassandra. In this talk we will introduce our toolchain, look at what each tool does, how they work, and where you would use them. In addition, we will show how the toolchain can be used to quickly test a data model or feature in Cassandra.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1001", "audienceId": "", "typeId": "2", "locationId": "1009", "speakerIds": [ "1065" ], "languageId": "1" }, { "id": "1069", "start": "2019-09-11T15:15:00", "end": "2019-09-11T16:05:00", "title": "(Apache) Drill-ing into Collections of HDF5 Files", "abstractText": "This talk is about building bridges between two ecosystems, Apache and HDF5.nHDF5 is a widely used storage container for complex data from embedded devicesnto supercomputers, and is developed and maintained as FOSS by The HDF Group.nWhile it is easy to imagine the potential benefits of making HDF5 containersnaccessible from the various Apache frameworks, there are several technicalnchallenges to overcome, and what makes a 'good' integration is by no meansnobvious. It requires the input and collaboration of experts from both sides. The core of this presentation will be an overview of a joint project between The HDF Group and Apache Drill contributor Charles Givre. We will show how tonuse Apache Drill to explore collections of HDF5 containers and discuss thenunderlying design decisions and a few technicalities. We will use thisnopportunity to give the Apache community an update on the support forncollections of HDF5 files on HDFS, in cloud storage (such as S3), our Sparkndata source and our new 'HDF5 in the cloud' platform, HDF KITA. The intended audience are 'bridge-builders' and curious members of the Apachencommunity, and anyone interested in 'HDF5 demystified.'", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1003", "audienceId": "", "typeId": "2", "locationId": "1014", "speakerIds": [ "1066" ], "languageId": "1" }, { "id": "1070", "start": "2019-09-11T17:45:00", "end": "2019-09-11T18:35:00", "title": "Consistent Cassandra schema changes in Elassandra", "abstractText": "As described in CASSANDRA-10699 (Make schema alterations strongly consistent), concurrent schema changes can still lead to schema disagreement in Cassandra 3.0. In order to properly support Elasticsearch dynamic mapping in Elassandra, we will see how multiple schema changes are validated on a working copy of the Cassandra schema, and applied in an atomic update to all nodes if a light weight transaction succeed, thus avoiding concurrent schema changes issue. I will also explain how we have taken advantage of Cassandra table extensions to store the Elasticsearch mapping directly into the CQL schema with several benefits.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1001", "audienceId": "", "typeId": "2", "locationId": "1009", "speakerIds": [ "1067" ], "languageId": "1" }, { "id": "1071", "start": "2019-09-10T15:30:00", "end": "2019-09-10T16:20:00", "title": "Diversity, a beginners introduction", "abstractText": "Diversity and inclusion are becoming hot topics within our open source communities and industry, but for those of us 'playing life on easy', the subject and impact can be harder to 'get'. Like many people who used to play life on easy, I've had some blind spots around diversity and inclusion. I only discovered these through working on projects, communities and support at the ASF, and by moving to a new country! Now it is my mission to help others see the light, learn for themselves, and through that build better open source communities. I'll be sharing what I learnt, giving resources, and specific takeaway actions.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1008", "audienceId": "", "typeId": "2", "locationId": "1013", "speakerIds": [ "1068" ], "languageId": "1" }, { "id": "1072", "start": "2019-09-09T17:30:00", "end": "2019-09-09T18:20:00", "title": "Evaluating Content/Text Extraction at Scale with Apache Tika", "abstractText": "Text extraction tools are essential for obtaining the textual content and metadata of computer files for use in a wide variety of applications, including search and natural language processing tools. Techniques and tools for evaluating text extraction tools are largely missing from academia and industry. This talk will focus on recent improvements to Apache Tika's tika-eval module to help integrators evaluate content extraction at scale. The tika-eval module was initially developed for a single batch mode on a single vm. In recent months, however, Apache Tika has refactored this module to allow for easier scaling within Apache Solr and other large scale processing frameworks. This talk will offer an overview of the techniques used to identify potential extraction problems -- including garbled text without ground truth; and the talk will show how the tika-eval module can be used at scale to identify potential problems with content extraction. ", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1007", "audienceId": "", "typeId": "2", "locationId": "1000", "speakerIds": [ "1069" ], "languageId": "1" }, { "id": "1073", "start": "2019-09-12T15:30:00", "end": "2019-09-12T16:20:00", "title": "Reverse Proxy Magic with Apache httpd 2.4", "abstractText": "One of the best not-so-well-known features of Apache httpd is its incredible capability as a Reverse Proxy server. Whether as a front end to application servers such as Tomcat and PMP-FPM, or as a caching server for static content, or as a robust load-balancer with dynamic configuration, or all, Apache httpd is not only feature rich but easily matches or surpasses the performance of other proxies.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1016", "audienceId": "", "typeId": "2", "locationId": "1000", "speakerIds": [ "1054" ], "languageId": "1" }, { "id": "1074", "start": "2019-09-11T14:15:00", "end": "2019-09-11T15:05:00", "title": "Cassandra at Instagram 2019", "abstractText": "At Instagram, our mission is to capture and share the world's moments. Our app is used by over 1 billion people monthly; this creates a lot of challenging data needs. We use Cassandra behind a lot of different product features. In this presentation, I will talk about how we use Cassandra to serve our critical use cases; the improvements we made in last several years to make sure Cassandra can meet our low latency, high scalability requirements; and future plans.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1001", "audienceId": "", "typeId": "2", "locationId": "1010", "speakerIds": [ "1070" ], "languageId": "1" }, { "id": "1075", "start": "2019-09-10T18:00:00", "end": "2019-09-10T18:50:00", "title": "Building and running cloud-native Cassandra", "abstractText": "This session will re-evaluate Cassandra’s relationship with runtime and build systems, pointing out ways that the existing systems fall down, and identifying avenues for improvement. Over the past few years, a number of platforms have emerged for running user code. Container runtimes like Docker, container orchestrators such as Kubernetes, and metrics collections agents like Prometheus and Spectator have all gained popularity and mind-share. Cassandra functionality such as metrics, bootstrapping, and monitoring integrates with the newer paradigms, but in an ad-hoc and improvised fashion. By taking a purposeful approach to integrating with these new methods of deployment, the Cassandra community can more fully benefit from their advertised strengths. The Cassandra build system based on Ant+Ivy dates to the early 2000’s, and reflects legacy complexity that could be avoided with modern build systems. Cassandra’s system package builds are not much better and often fail to integrate with industry standards such as systemd. Iterating on the existing systems is difficult, but this technical debt slows innovation in our build systems. In this talk, we propose solutions to make building, deploying and monitoring Cassandra easy and low overhead, while taking advantage of cloud advancements wherever possible.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1001", "audienceId": "", "typeId": "2", "locationId": "1010", "speakerIds": [ "1011", "1005" ], "languageId": "1" }, { "id": "1076", "start": "2019-09-10T11:15:00", "end": "2019-09-10T12:05:00", "title": "Apache Cassandra community health", "abstractText": "This talk will discuss the current health of the Apache Cassandra community looking at everything from community adoption, user adoption, health of contributors/committers, project velocity and a number of other measures of community health. In this talk Ben will also discuss broader market changes and challenges that impact the Apache Cassandra community drawn from our experience at Instaclustr, discussions with industry analysts and public data sources. This talk will be an update on the state of Apache Cassandra community presentation from NGCC 2017.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1001", "audienceId": "", "typeId": "2", "locationId": "1010", "speakerIds": [ "1071", "1072" ], "languageId": "1" }, { "id": "1077", "start": "2019-09-10T15:30:00", "end": "2019-09-10T16:20:00", "title": "Self-Service IoT Data Analytics with StreamPipes", "abstractText": "In many application domains such as manufacturing, the integration and continuous processing of real-time sensor data from the Internet of Things (IoT) is crucial to continuously monitor and detect upcoming situations. While continuous processing of events in scalable architectures is already well supported by the existing Big Data tool landscape, building such applications requires technical effort and programming skills, which is often not present in manufacturing companies. To solve this problem, we have developed StreamPipes (https://www.streampipes.org), which aims at simplifying IoT data analytics for domain experts. Originating from a research project, StreamPipes has been publicly released under the Apache License in early 2018. At its core, StreamPipes provides non-technical users with an easy and intuitive way to create stream processing pipelines through a graphical editor. Pipelines consist of reusable pipeline elements, each of them implemented as a microservice using a wrapper for a specific Big Data technology (e.g., Apache Flink, Kafka Streams or lightweight runtimes that can run directly at the edge). We motivate our talk by showing examples we gathered from a number of industry projects during the past years in Industrial IoT domains, present technical details of StreamPipes and show how the tool eases the accessibility of Big Data tools for non-technical users.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1012", "audienceId": "", "typeId": "2", "locationId": "1014", "speakerIds": [ "1073" ], "languageId": "1" }, { "id": "1078", "start": "2019-09-10T17:00:00", "end": "2019-09-10T17:50:00", "title": "Hello World! Introducing Apache IoTDB - a Database for the Internet of Things", "abstractText": "Time series data management system is becoming increasingly important with the rise of the Internet of Things, especially in the industrial area. Apache IoTDB (incubating), one of the youngest projects in the Apache Incubator, is born for that!nApache IoTDB is an integrated data management engine designed for time series data, based on a file format which is able to store time series data very efficiently. It provides users specific services for data collection, storage and analysis. Due to its lightweight structure, high performance and usable features together with its good integration with Apache Hadoop and Apache Spark, it can meet the requirements of massive dataset storage, high-speed data ingestion and complex data analysis for industrial IoT applications.nAs the project is very new to the ASF, the talk has four objectives. First, discuss the time series data management requirement in the IoT area; Second, introduce Apache IoTDB to the world; Third, to give an overview about the architecture of the project and the technologies used inside and Fourth, to give an idea about how IoTDB integrates with other Apache Projects and where it fits in the (IoT) data processing ecosystem. Some practical use cases are also introduced.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1012", "audienceId": "", "typeId": "2", "locationId": "1014", "speakerIds": [ "1074", "1016" ], "languageId": "1" }, { "id": "1079", "start": "2019-09-09T11:30:00", "end": "2019-09-09T12:20:00", "title": "Episode IV - A New Hope: Industry 4.0 done our way", "abstractText": "It is a period of technological change. Rebel Industry 4.0 open-source software solutions, striking from hidden bases, have won their first victories against the evil proprietary Industrial Empire. During the battle, Rebel spies managed to implement industrial protocols to the Empire’s ultimate weapons, the industrial Programmable Logic Controllers, almost unprotected pieces of hardware with enough power to destroy an entire planet. Pursued by the Empire’s sinister agents, a representative of the project races to Las Vegas aboard his intercontinental sub-orbital shuttle, custodian of his plans to revolutionize the way we are building Industry 4.0 applications, that can free all companies and restore freedom to the industry … Learn how the Apache PLC4X project has evolved and what we have planned for the future and especially how it can currently help close the gap between industrial hardware and modern software solutions to build the next generation of industrial IoT solutions, based entirely on open-source software.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1012", "audienceId": "", "typeId": "2", "locationId": "1014", "speakerIds": [ "1075" ], "languageId": "1" }, { "id": "1080", "start": "2019-09-11T14:15:00", "end": "2019-09-11T15:05:00", "title": "SPARQL at scale with Apache Rya", "abstractText": "The Resource Description Framework (RDF) is a standard model for storing graph data. While the standard was initially created for storing meta-data about the World Wide Web, its flexible format made it a popular choice for storing many different types of information. With the explosive increase in the size of available data, scalable solutions are needed to efficiently store and query very large RDF graphs within big data architectures. Apache Rya (incubating) is a scalable database management system designed for storing and searching very large RDF data. Rya is built on top of Apache Accumulo and also supports a MongoDB back end. nIn this talk, we introduce storage methods, primary and secondary indexing schemes, statistics based query optimization, as well as query evaluation techniques that allow Rya to scale to billions of triples across multiple nodes, while providing fast and easy access to the data through conventional query mechanisms such as SPARQL.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1010", "audienceId": "", "typeId": "2", "locationId": "1006", "speakerIds": [ "1076" ], "languageId": "1" }, { "id": "1081", "start": "2019-09-10T18:00:00", "end": "2019-09-10T18:50:00", "title": "Standardizing Industrial IoT with Apache PLC4X, Apache Daffodil, and DFDL", "abstractText": "Industrial IoT is made up of many different programmable logic controllers (PLCs) that communicate with often incompatible and proprietary data formats. Apache PLC4X standardizes access to these PLCs by creating a set of libraries across a variety of languages to read and write PLC data with a unified API. Unfortunately, developing and maintaining support for these different data formats, especially across multiple languages, can be burdensome. In this talk we discuss how we can describe PLC data using the open standard Data Format Description Language (DFDL), how Apache Daffodil uses these descriptions to transform data to a standard and easily consumable representation, and an approach to extend PLC4X to use Daffodil and DFDL descriptions to reduce the effort needed to support a variety of PLCs and languages.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1012", "audienceId": "", "typeId": "2", "locationId": "1014", "speakerIds": [ "1077" ], "languageId": "1" }, { "id": "1082", "start": "2019-09-12T15:30:00", "end": "2019-09-12T16:20:00", "title": "Everything about Apache Marvin Platform", "abstractText": "Apache Marvin is an open source project that focuses on empowering data science teams to deliver industrial-grade applications supported by a high-scale, low-latency, language agnostic, and standardized architecture platform created to simplify the process of exploration and modeling in Machine Learning projects. Marvin aims at abstracting the complexities in the creation process of scalable, highly available, interoperable and maintainable predictive software. In this presentation, the speaker is going to talk about the architecture behind the platform and show the cooler features of Apache Marvin.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1013", "audienceId": "", "typeId": "2", "locationId": "1008", "speakerIds": [ "1078" ], "languageId": "1" }, { "id": "1083", "start": "2019-09-10T18:00:00", "end": "2019-09-10T18:50:00", "title": "Tomcat from a cluster to a cloud.", "abstractText": "Using Tomcat in a cluster and in a cloud. nWe start by looking how to configure tomcat to get a cluster andnthen explore the problems and solutions to have distributed applications running in a cloud. Most cloud providers now have a Kubernetes API.nWe will look to what we have to add to Tomcat to have a decent cloud supportnfor monitoring, tracing and operating on the cloud.nWe will show how to use all the pieces.nA demo of a cluster will be prepared and run during the presentation andnthe corresponding application will be moved to a Kubernetes cloud.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1005", "audienceId": "", "typeId": "2", "locationId": "1007", "speakerIds": [ "1079" ], "languageId": "1" }, { "id": "1084", "start": "2019-09-11T17:45:00", "end": "2019-09-11T18:35:00", "title": "How to Grow Communities, Not Just Code", "abstractText": "Good code isn't enough for a successful open source project. First of all, only you know how to use what you've made. Maybe it's time for a little UI and UX help? At the very least some documentation! Next, how is anyone else going to find what you've created? And that's only the beginning. Ruth Suehle, manager of Red Hat's Open Source and Standards community leadership team, will take you through examples of the best and the worst, from projects large and small, to help you see what you need beyond your code to build a successful open source project and community.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1008", "audienceId": "", "typeId": "2", "locationId": "1013", "speakerIds": [ "1080" ], "languageId": "1" }, { "id": "1085", "start": "2019-09-10T14:30:00", "end": "2019-09-10T15:20:00", "title": "IoT Applications and Patterns using Apache Spark & Apache Bahir", "abstractText": "The Internet of Things (IoT) is all about connected devices that produce and exchange data, and building applications that produce insights from these high volumes of data are very challenging and require an understanding of multiple protocols, platforms, and other components. On this session, we will start by providing a quick introduction to IoT, some of the common analytic patterns used on IoT, and also touch on the MQTT protocol and how it is used by IoT solutions some of the quality of services tradeoffs to be considered when building an IoT application. We will also discuss some of the Apache Spark platform components, the ones utilized by IoT applications to process devices streaming data. We will also talk about Apache Bahir and some of its IoT connectors available for the Apache Spark platform. We will also go over the details on how to build, test and deploy an IoT application for Apache Spark using the MQTT data source for the new Apache Spark Structure Streaming functionality.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1012", "audienceId": "", "typeId": "2", "locationId": "1014", "speakerIds": [ "1081", "1082" ], "languageId": "1" }, { "id": "1086", "start": "2019-09-12T15:30:00", "end": "2019-09-12T16:20:00", "title": "Adding AI to customer segmentation using Apache Unomi and Apache PredictionIO", "abstractText": "Apache Unomi is a Customer Data Platform that is easy to extend as it uses the Apache Karaf runtime. In this session, you will discover how to integrate Unomi with Apache PredictionIO to be able to leverage artificial intelligence algorithms to recommend segments or products to users as they interact with websites. Of course, as all of this will be bleeding-edge stuff, expect plenty of last-minute drama, half-finished code and hopefully some fun demos.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1013", "audienceId": "", "typeId": "2", "locationId": "1007", "speakerIds": [ "1083" ], "languageId": "1" }, { "id": "1087", "start": "2019-09-10T15:30:00", "end": "2019-09-10T16:20:00", "title": "Proxies, TLS, and Injecting Security Into Cloud Communication", "abstractText": "With the expansion of moving legacy applications into public clouds, there have been an increased need for features in proxies to inject security into legacy application deployments. In this talk, we present extensions made to the Apache Traffic Server proxy over the past two years to enable the secure deployment of legacy applications in a wider variety of network configurations. Specifically, we discuss how Traffic Sever can be used for Layer 4 Routing. In this case, the router does not terminate the TLS connection, but rather use the Server Name Indicator (SNI) to determine were the TLS connection should actually be terminated. Traffic Server configuration additions were also made to allow for the finer-grained deployment of mutual TLS authentication both between the user agent and Traffic Server and between Traffic Server and the origin. A new TLS Bridge plugin allows for the injection of a proxy-to-proxy TLS tunnels to support older applications securely communicating between organizations (e.g. between public cloud and on premise cloud). While we have specifically been working with Traffic Server, our development and production deployment experiences for moving applications into new cross-cloud configurations apply to the problem space in general.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1017", "audienceId": "", "typeId": "2", "locationId": "1003", "speakerIds": [ "1084" ], "languageId": "1" }, { "id": "1088", "start": "2019-09-12T16:30:00", "end": "2019-09-12T17:20:00", "title": "CANCELED: Robust Elastic Scaling of Deep Learning on Kubernates", "abstractText": "With the increasing popularity of deep learning workloads in academia, government and industry, several organizations have developed cloud-based deep learning platforms whose goals are to enable organizations utilize expensive resources effectively, and to share said resources among multiple teams in a fair and effective manner. We present the elastic scaling in the context of such large scale deep learning platforms. The traditional deep learning workload is the parallel job where can not fully utilize the cluster gpu resources. We begin by analyzing deep learning training workloads, and how they differ from conventional workloads as far as elastic scaling is concerned. The scheduler driven scaling to optimize resource utilization, support priorities, maintenance, at the same time promising the accuracy and user can define the strategy for scale out. The presentation will describe the design and implementation of a DL workload aware scheduling supporting flexible scheduling-driven scaling on the top of kubernetes cluster. Compare with kub-batch, kub-flow, the new scheduler offer much better job through put.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1013", "audienceId": "", "typeId": "2", "locationId": "1008", "speakerIds": [ "1085" ], "languageId": "1" }, { "id": "1089", "start": "2019-09-12T10:00:00", "end": "2019-09-12T10:50:00", "title": "Apache Toree: A Jupyter Kernel for Scala / Apache Spark", "abstractText": "Many data scientists are already making heavy usage of the Jupyter ecosystem for analyzing data using interactive notebooks. Apache Toree (incubating) is a Jupyter kernel designed that enables data scientists and data engineers to easily connect and leverage Apache Spark and its powerful APIs from a standard Jupyter notebook to execute their analytics workloads. In this talk, we will go over what's new with the most recent Apache Toree release. We will cover available magics and visualizations extensions that can be integrated with Toree to enable better data exploration and data visualizations. We will also describe some high-level design of Toree and how users can extend the functionality of Apache Toree powerful plugin system. And all of these with multiple live demos that demonstrate how Toree can help with your analytics workloads in an Apache Spark environment.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1013", "audienceId": "", "typeId": "2", "locationId": "1008", "speakerIds": [ "1081" ], "languageId": "1" }, { "id": "1090", "start": "2019-09-10T14:30:00", "end": "2019-09-10T15:20:00", "title": "Behind the Scenes of the Apache Software Foundation", "abstractText": "This presentation will give you everything you always wanted to know about the Apache Software Foundation (ASF), but were afraid to ask. It will show you that there is more than just the Apache web server, and provide you with information on how the ASF works and its history. The difference between membership and committership, who decides what, how elections take place, the technical infrastructure, project management committees, and the philosophy behind the incubator. Come and see behind the scenes of the Apache Software Foundation and let's talk about 'The Apache Way' and 'Community over Code' which have been the cornerstones of the ASF for 20 years.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1008", "audienceId": "", "typeId": "2", "locationId": "1013", "speakerIds": [ "1086" ], "languageId": "1" }, { "id": "1091", "start": "2019-09-12T16:30:00", "end": "2019-09-12T17:20:00", "title": "A Beginner's Guide to HTTPS and TLS", "abstractText": "This talk will introduce you to the fundamentals of securing communications with HTTPS. We will start by explaining the basics of X.509 server and client certificates, certification authorities, and using the OpenSSL toolkit. The TLS/SSL protocol will be introduced and how it is used together with HTTP in order to provide for data encryption, integrity, and authentication. We will talk through some important configuration details, standard use cases, common pitfalls, known SSL vulnerabilities, and issues when using HTTPS. The Apache HTTP Server will be used to provide specific examples, but the general information of the talk will be applicable to most server software that supports HTTPS.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1016", "audienceId": "", "typeId": "2", "locationId": "1000", "speakerIds": [ "1086" ], "languageId": "1" }, { "id": "1092", "start": "2019-09-12T10:00:00", "end": "2019-09-12T10:50:00", "title": "How China Search Giant Baidu adopt apache way inside its company", "abstractText": "Baidu is one of the biggest Internet company, it was founded 20 years ago with 10,000 more engineers now.nit began to embraces open source recently years, including adopting InnerSource and contributing to open source community. InnerSource is the use of apache ways inside the company. n As the leader of this program, I will talk about how this happened, and what's the challenges we faced and overcome. we need to set policies, define processes and enable tools , but the most important part is to cultivate open source culture, educate engineers what is apache way and how to cooperate inside company just like in open source community. And now, many projects inside Baidu have been adopting InnerSource, and some projects have became mature and open sourced to external world, even contributed to open source foundation.nWith my affords, Baidu has contributed three projects into apache software foundation as incubator projects,nthere are echarts, Doris, brpc. But open source is a long journey, we need to insist and keep going.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1008", "audienceId": "", "typeId": "2", "locationId": "1013", "speakerIds": [ "1087" ], "languageId": "1" }, { "id": "1093", "start": "2019-09-10T15:30:00", "end": "2019-09-10T16:20:00", "title": "Cassandra: Partition Management", "abstractText": "(Cassandra NGCC) Apache Cassandra on-disk storage model is based on immutable SSTables that are, depending on the compaction strategy, optimized for some general use cases. The main issue with optimally reading on-disk data is that a single partition data most of the time needs to be fetched from multiple partitions. None of the existing compaction strategies are optimized to provide a single file read guarantees on cold data. Partition based compaction strategy addresses that issue with effectively compacting all data that belongs to a single partition into the same SSTable. In this presentation, we will talk about proposed implementation details for such compaction strategy and a couple of solutions addressing the issues like write amplification and higher disk io requirements compared to default size tiered compaction.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1001", "audienceId": "", "typeId": "2", "locationId": "1010", "speakerIds": [ "1088", "1089" ], "languageId": "1" }, { "id": "1094", "start": "2019-09-12T13:00:00", "end": "2019-09-12T13:50:00", "title": "Using Apache MXNet to Train and Deploy your Deep Learning model", "abstractText": "AI is evolving rapidly, and much of the recent advancement is driven by Deep Learning, a machine learning technique inspired by the inner-working of the human brain. In this session, we will discuss what deep learning is, and the new capabilities it enables. We will dive into a few computer vision and natural language models that are demonstrating super-human performance, and to integrate these models into your existing Java system leveraging Apache MXNet - an open source deep learning framework – and it's Java API. In our session, we will show a brief introduction to DL, specifically about applications using MXNet Gluon to do the training and Java to do inference with different DL models in Production systems. We would also demostrate how to run and deploy the DL models with MXNet Java API. By the end of the session, audience will learn how to leverage deep learning tasks using Apache MXNet, the various gotchas involved, and where/how to learn more.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1013", "audienceId": "", "typeId": "2", "locationId": "1008", "speakerIds": [ "1090" ], "languageId": "1" }, { "id": "1095", "start": "2019-09-12T16:30:00", "end": "2019-09-12T17:20:00", "title": "Cassandra 4.0: Our Most Stable Major Release", "abstractText": "In mid-2018 the Cassandra community committed to making Cassandra 4.0 the most stable major release of Cassandra in the project’s history. In September, the community shifted focus from feature work and development to ensuring the quality of the release. To this end, we have adopted several new approaches to testing and validation including the replaying of production traffic, code audits, and property-based testing. This talk will explore the methodologies we’ve adopted and the results of their application as well as costs of this level of commitment to testing and its benefits. ", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1001", "audienceId": "", "typeId": "2", "locationId": "1010", "speakerIds": [ "1091" ], "languageId": "1" }, { "id": "1096", "start": "2019-09-12T09:00:00", "end": "2019-09-12T09:50:00", "title": "How to Slide Your Release Pass the Incubator", "abstractText": "All podling releases need to be voted on by the incubator PMC before being released to the world. I'll go through what the incubator PMC looks for in every release and what you can do to make it pass that IPMC vote and get your project one step closer to graduation. More importantly I'll cover where you can get help if you need it. In this talk, I'll describe current incubator and ASF policy, recent changes that you may not be aware of, and go into detail the legal requirements of common open source licenses and the best way to assemble your NOTICE and LICENSE files. Where possible I describe the reasons behind why things are done a certain which may not always be obvious from our documentation. I'll show how I review a release and the simple tools I use. I'll go through a worked example or two, including a fictional project called Apache Wombat, and cover common mistakes I've seen in releases.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1008", "audienceId": "", "typeId": "2", "locationId": "1013", "speakerIds": [ "1092" ], "languageId": "1" }, { "id": "1097", "start": "2019-09-09T11:30:00", "end": "2019-09-09T12:20:00", "title": "Openstack from a CloudStack perspective", "abstractText": "An experienced CloudStack developer will show his journey to deploy an OpenStack cloud. We will compare the pros and cons of CloudStack and OpenStack from the following perspectives:n(i) Deployment: cost, time and risks of deploying a CloudStack vs OpenStack infrastructure;n(ii) Maintenance: the costs and time required on maintaining a Cloud orchestrated with CloudStack and another with OpenStack; and,n(ii) Development: how development on both orchestrators is done? What looks like the codebase of each project and which technologies are involved? What kind of professional/development team is required?", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1002", "audienceId": "", "typeId": "2", "locationId": "1006", "speakerIds": [ "1093" ], "languageId": "1" }, { "id": "3001", "start": "2019-09-09T15:00:00", "end": "2019-09-09T15:50:00", "title": "Cloudstack Locking Service", "abstractText": "As CloudStack cannot work with any mysql clustering solution, it is time to explore a new locking service, manager and pluggable interface which would allow CloudStack DB to be HA enabled with multi-master read/write. Talk will focus on, - Need for a locking service and challenges with existing CloudStack architecture - Different possible clustering solution that can be adopted - Showcasing a PoC for future implementation with minimal changes to existing architecture using percona xtradb or any other clustering solution - Additionally, explore the idea of getting rid of mshost table, and use locking service to find about other management servers.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1002", "audienceId": "", "typeId": "2", "locationId": "1005", "speakerIds": [ "2004" ], "languageId": "1" }, { "id": "3002", "start": "2019-09-10T17:00:00", "end": "2019-09-10T17:50:00", "title": "CloudStack Monitoring - In-Depth Checks For Production Deployments", "abstractText": "This talk is for CloudStack administrators who're responsible for maintaining a robust and fault-free production deployment. It covers monitoring fine grained parameters of a CloudStack installation and how to measure and check not just discrete values but also routinely performed actions against their expected outcome. It also dwells upon how the same discrete values make a difference from an access perspective. Whether you want to auto-resolve common problems, provide an SLA or just keep a tab on your deployment, this talk will definitely provide some insights.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1002", "audienceId": "", "typeId": "2", "locationId": "1006", "speakerIds": [ "2005" ], "languageId": "1" }, { "id": "1098", "start": "2019-09-09T14:00:00", "end": "2019-09-09T14:50:00", "title": "Troubleshooting the Virtual Router - Run and Get Diagnostics", "abstractText": "Demonstration of CloudStack’s latest features for troubleshooting the Virtual Router connectivity and configuration, called Run and Get Diagnostics. Run Diagnostics gives the admin ability to execute diagnostics commands native the VR OS directly from the CloudStack UI. Admin is able to determine connectivity capabilities of the VR without logging into the SystemVM at all. Get diagnostics feature allow the admin to gather information about the SystemVM as fast as clicking on a button in the ‘QuickView’ of the VM. Admin can also execute custom scripts on each SystemVM type from the CloudStack UI. This session will begin with complete presentation of the features followed by live demo and Q&A.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1002", "audienceId": "", "typeId": "2", "locationId": "1005", "speakerIds": [ "1094" ], "languageId": "1" }, { "id": "1099", "start": "2019-09-11T16:45:00", "end": "2019-09-11T17:35:00", "title": "Apache Kibble Crash Course", "abstractText": "This presentation aims at showcasing the Apache Kibble project, getting new users set up with their own Kibble instance and getting started with project and community metrics. During this talk, the audience will learn what Apache Kibble is, what it does, HOW it does it, and how you can easily get set up in a few minutes and start reviewing metrics from your own project. We will also show a demo instance with a select handful of Apache projects, and dive into both single community metrics as well as comparative measuring across foundations. This presentation is aimed at both audiences wishing to start using community metrics and KPIs on their own hardware, as well as people just along for a quick demo of the project. The presentation will end with a discussion about KPIs and areas where these metrics can improve.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1008", "audienceId": "", "typeId": "2", "locationId": "1013", "speakerIds": [ "1095" ], "languageId": "1" }, { "id": "1100", "start": "2019-09-09T15:00:00", "end": "2019-09-09T15:50:00", "title": "State of Storage in Cloudstack", "abstractText": "With the increased focus and legislation around data sovereignty requirements, storage solutions play an increasingly important role in cloud infrastructures. We will present an overview of the evolution of storage orchestration in Apache CloudStack, with a focus on managed storage. It will also shed light on some upcoming features and the future direction.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1002", "audienceId": "", "typeId": "2", "locationId": "1006", "speakerIds": [ "1096" ], "languageId": "1" }, { "id": "1101", "start": "2019-09-12T10:00:00", "end": "2019-09-12T10:50:00", "title": "Running C* on Kubernetes with CassKop, the C* operator for K8S developed by Orange", "abstractText": "This presentation will describe the initial experience building and using CassKop, an operator developed for running Cassandra on top of Kubernetes. CassKop works as a usual K8S controller (reconcile the real state with a desired state) and automates the Cassandra operations through JMX. All the operations are launched by calling standard K8S APIs (kubectl apply …) or by using a K8S plugin (kubectl casskop …). CassKop is developed in GO, based on CoreOS operator-sdk framework.nAmong the main features :n- deploying a rack aware cluster (or AZ aware cluster)n- scaling up & down (including cleanups)n- setting and modifying configuration parameters (C* and JVM parameters)n- adding / removing a datacenter in Cassandran- rebuilding nodesn- removing node or replacing node (in case of hardware failure)n- upgrading C* or Java versions (including upgradesstables)n- monitoring (using Prometheus/Grafana)n- ... By using local and persistent volumes, it is possible to handle failures or stop/start nodes for maintenance operations with no transfer of data between nodes. Moreover, cassandra-reaper is deployed in K8S and used for scheduling repair sessions (Thanks to Spotify and TheLastPickle teams)nThe Cassandra exporter for Prometheus and backup/restore developed by Instaclustr are also used (Thanks to Instaclustr team) During this session, we will delve into the architecture and implementation of this operator, and share our learnings.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1001", "audienceId": "", "typeId": "2", "locationId": "1010", "speakerIds": [ "1097", "1098" ], "languageId": "1" }, { "id": "1102", "start": "2019-09-11T12:00:00", "end": "2019-09-11T12:50:00", "title": "Modernizing the Nordstrom Supply Chain: Efficient Order Fulfillment using JanusGraph, Cassandra and Spark", "abstractText": "DESCRIPTION: Today's Nordstrom customers expect order fulfillment options shipping to the most convenient locations in the timeframes that best fit their schedules. This session offers an inside look at how Nordstrom's Supply Chain Technology team combined an extensive network of brick and mortar facilities with a custom software stack built atop JanusGraph to present fulfillment options tailored to each individual order. ABSTRACT: Over the last decade, the volume of online retail sales as a proportion of overall retail sales has nearly tripled, and there are no signs of this trend slowing down. In a $500 billion online retail market driven by ever more savvy online shoppers, expectations for order fulfillment have grown more demanding. Consumers expect a choice of fulfillment options that offer convenience, flexibility and value. Nordstrom's Supply Chain Technology team is charged with meeting those customer expectations through efficient distribution of millions of unique items from a cross-country network of brick and mortar facilities. For the engineers on our team, it made perfect sense to use JanusGraph to model a dynamic inventory picture managed by a diverse set of geographically distributed facilities. Despite our enthusiasm, not everyone was eager to adopt an unfamiliar open source graph system. In this presentation, Jeff Callahan will discuss why his team at Nordstrom embraced JanusGraph as the backbone of a new data pipeline built to meet the evolving expectations of customers today (and tomorrow, too). After taking a detailed look at the system architecture, we'll also discuss some of the internal organizational challenges we faced in adopting JanusGraph, and how we managed to navigate those challenges to ultimately deliver an even stronger solution. NOTE: While this presentation focuses on JanusGraph, there is considerable overlap with Big Data, Machine Learning and Cassandra", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1010", "audienceId": "", "typeId": "2", "locationId": "1006", "speakerIds": [ "1099" ], "languageId": "1" }, { "id": "1103", "start": "2019-09-12T13:00:00", "end": "2019-09-12T13:50:00", "title": "Conquering Network Distributed Applications Using the Ballerina Programming Language", "abstractText": "Ballerina is the next generation programming language, which redefined what means to be 'general purpose'. Historically, programming languages concentrated on single machine execution, in a controlled environment, and also for good reason, because any other external interactions were out of the scope of a programming language, at least in the bygone days that is. But now, the communication network is something that is always there, and software often doesn't work alone. But rather, they work more and more by communicating with each other to do something meaningful. So hiding this network from our code is no longer an option, and we try to use various frameworks and libraries get the functionality we need. Ballerina is a general purpose programming language, which has built its core concepts and functionalities to support creation of networked application. These features include the built-in support for services/resources, transactions, and resilient communication support, and also combines with a type system which further enhances these operations. In this session, we will go through Ballerina, in understanding the motivation behind this language, the features it introduces, and why it is a critical and a timely addition to the tools and technologies we would need now.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1011", "audienceId": "", "typeId": "2", "locationId": "1006", "speakerIds": [ "1100" ], "languageId": "1" }, { "id": "1104", "start": "2019-09-11T15:15:00", "end": "2019-09-11T16:05:00", "title": "Building S3 over Ozone : Making a Cloud Native File System", "abstractText": "The AWS S3 protocol is the defacto interface for modern object stores. Ozone supports S3 protocol as the first-class notion in Ozone. For all practical purposes, a user of S3 can start using Ozone without any change to code or tools. S3 protocol support offered by Ozone is strongly consistent, so users don’t need to run sidekick tools like S3Guard when running big data applications like Apache Spark, Apache YARN or Apache Hive. This talk is a deep dive into how Ozone supports S3, and how easy it is to use the cloud tools against Ozone. We will demo S3 over Ozone with different off-the-shelf tools like Goofys, Kubernetes CSI, AWS CLI and also demonstrate how to use applications like Apache Spark, Apache Hive and YARN. We will also discuss some of the challenges faced during building S3 compatible rest server. For example, how we did the mapping of S3 semantics to ozone semantics, how we solved the S3 security issues and mapped them to ozone world. With S3 support Ozone has become a generic object store: it can be used with thousands of s3 compatible tools while it will also provide Hadoop compatible file system access.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1007", "audienceId": "", "typeId": "2", "locationId": "1000", "speakerIds": [ "1101", "2023" ], "languageId": "1" }, { "id": "1105", "start": "2019-09-09T10:00:00", "end": "2019-09-09T10:50:00", "title": "Apache Mynewt - ASF's Embedded OS Project", "abstractText": "Apache Mynewt is an operating system for low powered embedded systems based on 32-bit microcontrollers. At the core, it is a small pre-emptive RTOS and an extensive set of modules for connectivity, file systems, power and performance management options and lots more. It is a highly flexible, responsive, general purpose OS for constrained devices, think of it as embedded Linux for devices that can’t run Linux. Features include a secure bootloader, image management, hardware abstraction, instrumentation for stats and logs. This makes it easy to go from prototype to production when using Apache Mynewt without having to reinvent the wheel.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1012", "audienceId": "", "typeId": "2", "locationId": "1014", "speakerIds": [ "1092" ], "languageId": "1" }, { "id": "1106", "start": "2019-09-12T10:00:00", "end": "2019-09-12T10:50:00", "title": "Apache NetBeans clever APIs for cross platform development", "abstractText": "Hybrid applications can be a great solution for cross platform development, but JavaScript is not everyones cup of coffee. With a small set of clever APIs and SPIs, NetBeans has created a lean cross platform framework, that allows you to code in Java, and run the application on any mobile or desktop platform, as hybrid, or fully native application. In this sessions I'd like to unveil this hidden gem (improperly named 'HTML/Java'), show some real life applications and discuss how this improves client side software development dramatically.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1016", "audienceId": "", "typeId": "2", "locationId": "1000", "speakerIds": [ "1102" ], "languageId": "1" }, { "id": "1107", "start": "2019-09-10T12:15:00", "end": "2019-09-10T13:05:00", "title": "Processing IoT Data from End to End with MQTT and Apache Kafka", "abstractText": "This session discusses end-to-end use cases such as connected cars, smart home or healthcare sensors where you integrate IoT devices with enterprise IT using open source technologies and standards. MQTT is a lightweight messaging protocol for Internet of Things (IoT). However, MQTT is not built for high scalability, longer storage or easy integration to legacy systems. Apache Kafka is a highly scalable distributed streaming platform, which ingests, stores, processes and forwards high volumes of data from thousands of IoT devices. The session discusses how to leverage the Apache Kafka open source ecosystem as streaming platform to process IoT data. See a live demo of how MQTT brokers like Mosquitto integrate with Kafka, and how you can even integrate MQTT clients to Kafka without MQTT Broker. Learn how to analyze the IoT data either natively on Kafka with Kafka Streams / KSQL or on an external big data cluster like Spark, Flink or Elastic leveraging Kafka Connect.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1012", "audienceId": "", "typeId": "2", "locationId": "1014", "speakerIds": [ "1103" ], "languageId": "1" }, { "id": "1108", "start": "2019-09-10T15:30:00", "end": "2019-09-10T16:20:00", "title": "Machine Learning applications for CloudStack", "abstractText": "While Machine learning and data mining has had profound impact on how we model applications and use data for better product consumption, there is scope for extending prediction algorithms to lower levels as well. Some useful applications of machine learning in ACS could be exploring better resource allocation that is aware of usage statistics, predicting faults, load balancing, etc. In this talk we will * take a broad overview of what Machine Learning/Data mining is and how it is being used in today's tech ecosystemn* explore ways in which we can make ACS more efficientn* discuss some recent advancements in how ML can benefit datacenters from research community", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1002", "audienceId": "", "typeId": "2", "locationId": "1006", "speakerIds": [ "1104" ], "languageId": "1" }, { "id": "1109", "start": "2019-09-09T11:30:00", "end": "2019-09-09T12:20:00", "title": "NoVNC console implementation in CloudStack", "abstractText": "NoVNC is an open-source browser based VNC client, implemented using HTML5 technologies (Web Sockets, Canvas) with encryption (wss://) support. Proposed NoVNC implementation provides better performance and is more responsive when compared to the current ajax-based console in Apache CloudStack. Our implementation is based on NoVNC and websockify. Websockify is a websocket proxy converting WebSocket request from browser to TCP request and then forward it to VNC server. We have already implemented a NoVNC console for CloudStack 4.13. This new console is smooth and very stable. It can be accessed by multiple sessions at the same time and easily integrated into other platforms. During this talk we will demonstrate how NoVNC console is implemented in CloudStack and how VNC password authentication is implemented in NoVNC and websockify. ", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1002", "audienceId": "", "typeId": "2", "locationId": "1005", "speakerIds": [ "1105" ], "languageId": "1" }, { "id": "1110", "start": "2019-09-11T16:45:00", "end": "2019-09-11T17:35:00", "title": "Mission Critical Cassandra in Financial Services, The When/What/How Experiences for ALL!", "abstractText": "Apache Cassandra is a database product that is most notably known for being highly scalable and fault tolerant. Since these characteristics are something that is desirable in almost every use case, it attracts attention from developers up through executives when faced with decisions on how to architect mission critical systems. If these traits are so desirable, and Apache Cassandra makes these capabilities available to end users, then shouldn’t we use Cassandra for all our data storage needs? What is the catch? When considering Apache Cassandra for one’s database needs, it is critical for users to understand when it is appropriate for use, and what are the trade-off’s one needs to consider. A person must consider the priorities of their non-functional requirements, the required investment in knowledge acquisition, the increased complexity of distributed systems, and the operational needs of maintaining such a database system among other concerns. If used incorrectly, the results could be disastrous, but when used appropriately Apache Cassandra can produce the expected rewarding results. In this presentation, [redacted name] will share his experiences operating one of the largest Apache Cassandra deployments in the financial services industry. As such, specific topics will be detailed that are relevant to both the largest and smallest of use cases.n* When is it appropriate to use Cassandra? What has been successful/unsuccessful?n* What have been the largest barriers to adoption?n* How to operate at any scalen* Risk and Control considerationsn* Knowledge acquisition and proliferation. Please join us for this candid discussion in hopes of easing the journey to successful adoption of Cassandra.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1001", "audienceId": "", "typeId": "2", "locationId": "1010", "speakerIds": [ "1106" ], "languageId": "1" }, { "id": "1111", "start": "2019-09-12T15:30:00", "end": "2019-09-12T16:20:00", "title": "Configuring Apache Camel for the Cloud", "abstractText": "Cloud … check. Container … check. Orchestration … check. Now that you’ve got the basics it’s time to starting thinking about how all occupants of your new cloud infrastructure are going to communicate. And no mater what cloud, container or orchestration tool you choose, Apache Camel has what you need to get your system configured and connected. This talk will cover Camel components for cloud friendly configuration, communication, packaging, and deployment. The approaches presented will take a “use what is already there” philosophy. So whatever you’re working with from Do It Yourself Virtual Machines with containers like Apache Karaf or a fully managed Kubernetes clusters with fat jars, integrating vertically or horizontally, Apache Camel has the pieces to make it all work. This talk will cover how to do it as as well as advantages and drawbacks of each approach.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1011", "audienceId": "", "typeId": "2", "locationId": "1006", "speakerIds": [ "1107" ], "languageId": "1" }, { "id": "1112", "start": "2019-09-09T09:00:00", "end": "2019-09-09T09:50:00", "title": "Welcome to Cloudstack Collaboration Conference", "abstractText": "The CloudStack Project VP welcomes delegates to the CloudStack Collaboration Conference. And gives opening remarks about the CloudStack community, with special guest joining on stage.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1002", "audienceId": "", "typeId": "2", "locationId": "1005", "speakerIds": [ "1108" ], "languageId": "1" }, { "id": "1113", "start": "2019-09-10T12:15:00", "end": "2019-09-10T13:05:00", "title": "Hatching the Clutch - A Guide to the Apache Incubator", "abstractText": "What is the Apache Incubator? What is required from projects in order to graduate? What resources are available and which are required? What does the Foundation provide? Why is the dev email list so important? What about your Mentors? We are all volunteers and strive to be your gateway into taking full advantage of what the Foundation has to offer. Let's review the state of the Clutch and see what is happening now.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1008", "audienceId": "", "typeId": "2", "locationId": "1013", "speakerIds": [ "1109" ], "languageId": "1" }, { "id": "1114", "start": "2019-09-10T14:30:00", "end": "2019-09-10T15:20:00", "title": "Taming the Herd - Tuning ATS for linear video", "abstractText": "At Comcast we have a unique challenge of serving both static and live linear content via our CDN. In general a thundering herd (multiple instantaneous simultaneous requests for the same content) is not a large concern for static files barring a few situations like serving automatic pushed update files. However when serving live content the nature of it means you are almost always generating a herd or on the verge of it due to timing. This talk covers some of the issues we have seen while growing our CDN to serve both live and static content and the solutions we have come to with regards to using Apache Traffic Server as our main caching software.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1017", "audienceId": "", "typeId": "2", "locationId": "1003", "speakerIds": [ "1110" ], "languageId": "1" }, { "id": "1115", "start": "2019-09-10T17:00:00", "end": "2019-09-10T17:50:00", "title": "Does Open Source Participation Get Easier Over Time?", "abstractText": "What’s it like to be a committed member of an active open source community? What are the awesome parts? What are the challenges? Is open source for you? In this talk, presenters with a wide range of experience at Apache will share their stories and advice on open source participation. From starting out to ongoing involvement, from participating in open source as part of your job, to finding time to participate outside of your job, from finding models and mentors in an online, asynchronous communication environment to being such a mentor, from the worst to the best moments and experiences in open source, join us to hear about more than 30 years of combined experience with Apache projects.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1008", "audienceId": "", "typeId": "2", "locationId": "1013", "speakerIds": [ "1076", "1111", "1051", "1112", "1113", "1092", "2024" ], "languageId": "1" }, { "id": "1116", "start": "2019-09-12T17:30:00", "end": "2019-09-12T18:20:00", "title": "Widening the Circle: The open source journey from user to contributor", "abstractText": "Open source draws its strength from the communities that use and build it. It's their diversity of perspective, skills, and accountability that makes individual projects stronger and builds a richer and solid ecosystem. But while open source is used by the entire world, that broad user community is not yet reflected in the contributor base. In fact, diversity in open source is significantly worse than in proprietary software. While we claim that contribution is open to all, clearly not everybody feels empowered or welcome to contribute to open source projects. And that's a problem. How can we fix this? How can we enable all developers everywhere to contribute to open source and take advantage of the opportunities it presents? In Q1 2019, Google's Open Source Strategy team commissioned a user research study to better understand why users do (or do not) contribute back to the project, and how documentation can help remove roadblocks to that project's adoption and usage - and encourage and enable community contributions. In this talk, we'll cover the methodology and participant profiles of the study, and describe the four essential user personas we identified - along with their critical user-to-contributor journeys. And we'll also distill the research to provide concrete recommendations and best practices for creating documentation that helps your community flourish and your project thrive.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1008", "audienceId": "", "typeId": "2", "locationId": "1013", "speakerIds": [ "1114", "1115" ], "languageId": "1" }, { "id": "1117", "start": "2019-09-09T10:00:00", "end": "2019-09-09T10:50:00", "title": "Geospatial Data Management in Apache Spark", "abstractText": "The volume of spatial data increases at a staggering rate. This talk comprehensively studies how existing works, such as GeoSpark, extend Apache Spark to uphold massive-scale spatial data. During this talk, we first provide a background introduction of the characteristics of spatial data and the history of distributed data management systems. A follow-up section presents the common approaches used by the practitioners to extend Spark and introduces the vital components in a generic spatial data management system. The third and fourth sections then discuss the ongoing efforts and experience in spatial-temporal data and spatial data analytics, respectively. The fifth part finally concludes this talk to help the audience better grasp the overall content and points out future research directions.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1009", "audienceId": "", "typeId": "2", "locationId": "1013", "speakerIds": [ "1116", "1117" ], "languageId": "1" }, { "id": "1118", "start": "2019-09-09T16:30:00", "end": "2019-09-09T17:20:00", "title": "The First Mile -- Edge and IoT Data Collection with Apache NiFi and MiNiFi", "abstractText": "Apache NiFi provided a revolutionary data flow management system with a broad range of integrations with existing data production, consumption, and analysis ecosystems, all covered with robust data delivery and provenance infrastructure. Now learn about the follow-on project which expands the reach of NiFi to the edge, Apache MiNiFi. MiNiFi is a lightweight application which can be deployed on hardware orders of magnitude smaller and less powerful than the existing standard data collection platforms. With both a JVM compatible and native agent, MiNiFi allows data collection in brand new environments — sensors with tiny footprints, distributed systems with intermittent or restricted bandwidth, and even disposable or ephemeral hardware. Not only can this data be prioritized and have some initial analysis performed at the edge, it can be encrypted and secured immediately. Local governance and regulatory policies can be applied across geopolitical boundaries to conform with legal requirements. And all of this configuration can be done from central command & control using an existing NiFi with the trusted and stable UI data flow managers already love. ", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1012", "audienceId": "", "typeId": "2", "locationId": "1014", "speakerIds": [ "1118" ], "languageId": "1" }, { "id": "1119", "start": "2019-09-12T17:30:00", "end": "2019-09-12T18:20:00", "title": "Recent advances in Natural Language Processing and Deep Learning", "abstractText": "In recent years, Machine Learning (ML) approaches to Natural Language Processing (NLP) drastically changed. From a feature-based modelling, where NLP tasks are tackled by using a set of manually engineered features, we moved to the so-called representation learning: text is naturally represented as a sequence of symbols (e.g., words, characters, etc.) and the role of learning how these symbols should be represented is entirely left to the ML method. Deep Learning dominates such paradigmatic shift.nIn this presentation we will review the Deep Learning approach to NLP and discuss different alternatives for representing text, including word embeddings[1] and character embeddings[2].nFinally, we will focus on the latest advances, including: ELMo[3], a model for generating deep contextualized word embeddings, and BERT[4], a very recent Neural Network Model that allows to achieve state-of-the-art results on several NLP tasks with very little task-specific fine-tuning.nThis presentation will mix scientific theory and actual code examples from Apache MXNet (incubating) demonstrating how to leverage these advanced techniques to solve NLP tasks. [1] Word2Vec - Efficient Estimation of Word Representations in Vector Space, Mikolov et al. 2013n[2] CNN character embedding layer - Character-Aware Neural Language Models, Kim et al. 2015n[3] ELMo - Deep contextualized word representations, Peters et al. 2018n[4] BERT - BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding, Devlin et al. 2018", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1013", "audienceId": "", "typeId": "2", "locationId": "1008", "speakerIds": [ "1119" ], "languageId": "1" }, { "id": "1120", "start": "2019-09-09T09:00:00", "end": "2019-09-09T09:50:00", "title": "How to Become an IoT Developer (and Have Fun!)", "abstractText": "I started off my life as a developer writing machine code and C and working on some low-level hardware projects. Then this thing called the internet come along and I moved into the web application space for a couple of decades. More recently I've moved back into commercial IoT development and not unexpectedly a lot has changed over that time. In this talk, I'll cover what it's like developing IoT projects. I'll go over the tools you need and the protocols you need to be familiar with. I'll look at how the C language has evolved to what it is today and how to write code that works well on memory constrained devices. I'll go over producing prototypes, rapid development, debugging and testing embedded applications and what and how much electronics you should learn. In short, everything you need to know in becoming an IoT developer and have fun doing it.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1012", "audienceId": "", "typeId": "2", "locationId": "1014", "speakerIds": [ "1092" ], "languageId": "1" }, { "id": "1121", "start": "2019-09-12T09:00:00", "end": "2019-09-12T09:50:00", "title": "TVM: An Automated End-to-End Optimizing Compiler for Deep Learning", "abstractText": "There is an increasing need to bring machine learning to a wide diversity of hardware devices from the datacenter to the edge. Current frameworks rely on vendor-specific operator libraries and optimize for a narrow range of server-class GPUs. Deploying workloads to new platforms such as mobile phones, embedded devices, and accelerators (e.g., FPGAs, ASICs) requires significant manual effort. In this talk, we will talk about Apache TVM -- an end to end optimizing deep compiler stack that brings deep learning models on diverse hardware back-ends that are competitive with state-of-the-art hand-tuned libraries for low-power CPU, mobile GPU, and server-class GPUs. ", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1013", "audienceId": "", "typeId": "2", "locationId": "1008", "speakerIds": [ "1120" ], "languageId": "1" }, { "id": "1122", "start": "2019-09-11T15:15:00", "end": "2019-09-11T16:05:00", "title": "Apache Tomcat / HTTPD Configuration Management", "abstractText": "Does your organization have tons of applications and containers? Has this fleet grown to be completely unmanageable? Do undocumented changes cause downtime and pain for your operations? Using modern configuration management tools and practices (Chef and CI/CD), Mastercard created a set of cookbooks that builds, deploys and manages model driven middleware infrastructure. Join us for a talk where we will discuss what is and why you should do configuration management, how we chose to model the middleware configurations, examples of how to test the heck out of the whole assembly and how this methodology brings everything a step closer to “gitops”. This talk will dive into the guts of the cookbook and the processes around how teams onboard to the flow.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1005", "audienceId": "", "typeId": "2", "locationId": "1007", "speakerIds": [ "1121" ], "languageId": "1" }, { "id": "1123", "start": "2019-09-12T09:00:00", "end": "2019-09-12T09:50:00", "title": "Apache NetBeans - Shameless Marketing Tool", "abstractText": "NetBeans has completed its transition to Apache and is now a top level Apache project with a strong and dedicated community and millions of users worldwide. NetBeans always had great support for Apache Maven & having an IDE of our own is a great chance to further promote Apache projects to a large audience. In this session I'll show you how to plugin your own language, tool, library, server, database or framework and make it easy for developers to get started with them. Use NetBeans as a marketing tool to shamelessly plug your own cool project. ", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1008", "audienceId": "", "typeId": "2", "locationId": "1000", "speakerIds": [ "1102" ], "languageId": "1" }, { "id": "1124", "start": "2019-09-12T10:00:00", "end": "2019-09-12T10:50:00", "title": "Apache Kafka vs. Integration Middleware (MQ, ETL, ESB) - Friends, Enemies or Frenemies?", "abstractText": "MQ, ETL and ESB middleware are often used as integration backbone between legacy applications, modern microservices and cloud services. This introduces several challenges and complexities like point-to-point integration or non-scalable architectures. This session discusses how to build a completely event-driven streaming platform leveraging Apache Kafka’s open source messaging, integration and streaming components to leverage distributed processing, fault-tolerance, rolling upgrades and the ability to reprocess events. nLearn the differences between an event-driven streaming platform leveraging Apache Kafka and middleware like MQ, ETL and ESBs – including best practices and anti-patterns, but also how these concepts and tools complement each other in an enterprise architecture.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1011", "audienceId": "", "typeId": "2", "locationId": "1006", "speakerIds": [ "1103" ], "languageId": "1" }, { "id": "1125", "start": "2019-09-12T09:00:00", "end": "2019-09-12T09:50:00", "title": "Continuous Machine and Deep Learning at Scale with Apache Ignite", "abstractText": "With most machine learning (ML) and deep learning (DL) frameworks, it can take hours to move data, and hours to train models. It's also hard to scale, with data sets increasingly being larger than the capacity of any single server. The size of the data also makes it hard to incrementally test and retrain models in near real-time to improve results. Learn how Apache Ignite and GridGain help to address these limitations with model training and execution, and help achieve near-real-time, continuous learning. It will be explained how ML/DL work with Apache Ignite, and how to get started. Topics include:n n— Overview of distributed ML/DL including design, implementation, usage patterns, pros and consn— Overview of Apache Ignite ML/DL, including prebuilt ML/DL, and how to add your own ML/DL algorithmsn— Model execution with Apache Ignite, including how to build models with Apache Spark and deploy them in Igniten— How Apache Ignite and TensorFlow can be used together to build distributed DL model training and execution ", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1013", "audienceId": "", "typeId": "2", "locationId": "1007", "speakerIds": [ "1122" ], "languageId": "1" }, { "id": "1126", "start": "2019-09-11T15:15:00", "end": "2019-09-11T16:05:00", "title": "Day to day with Cassandra: The weirdest and complex situations we found!", "abstractText": "Every Cassandra operator has been hit with a couple of weird/complex cases that don't fit the normal expected failure situation. It can be a problem in hardware, software, networking, operator mistake, or a mix of it all. In this talk we will go through a compilation of such cases that we faced. How do they appear, how did we debug them and how did we fix them. We expect this to be a walk through weird, fun cases and sharing knowledge on the situations and on the fixing of such problems", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1001", "audienceId": "", "typeId": "2", "locationId": "1009", "speakerIds": [ "1123" ], "languageId": "1" }, { "id": "1127", "start": "2019-09-10T11:15:00", "end": "2019-09-10T12:05:00", "title": "Lessons learned while migrating 3000 openvz containers to CloudStack", "abstractText": "When Leaseweb acquired a new company 3000 public cloud customers we had to come up with a strategy to move all these VMs to our CloudStack setup. During this talk we will share: how we migrated a large foreign openvz environment into our kvm cloudstack environment in an automated fashion minimizing customer impact. The lessons we learned along the way and how we would do it again in the future. ", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1002", "audienceId": "", "typeId": "2", "locationId": "1006", "speakerIds": [ "1124","1018" ], "languageId": "1" }, { "id": "1128", "start": "2019-09-10T14:30:00", "end": "2019-09-10T15:20:00", "title": "RocksDB Based Storage Engine Recent Improvements", "abstractText": "In last year's NGCC session 'Cassandra Pluggable Storage Engine', Instagram Cassandra team presented a new RocksDB based Cassandra storage engine which brings us huge performance win. Since then our team have been actively working on the new storage engine for adding missing features and further improving efficiency. In this session I will talk about our work on following sections and their impacts to our production system.n* Large disaggregated flash disk supportn* RocksDB based streaming improvementsn* Decoding improvementsn* Space amplification improvementsn* Some missing features added", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1001", "audienceId": "", "typeId": "2", "locationId": "1010", "speakerIds": [ "1125" ], "languageId": "1" }, { "id": "1129", "start": "2019-09-10T12:15:00", "end": "2019-09-10T13:05:00", "title": "Observability in distributed system", "abstractText": "Observability is quite important for the cloud native application. Itncould be a challenge if we build up the system observer from thenstrache. By leveraging the Skywalking's extension mechanism, we couldnsend out the data to the backend directly to improve thenObservability of the Cloud Native Service. In distributed applications, horizontal sharding and transactio coordination are most popular solutions. Observability for businessninvocation on sharding scenario are not enough; but observer allnsharded details of backend infrastructures indifferently are tooncomplicated. We need a whole picture of SQL and transactions execution status. ShardingSphere is a transport databases middleware for sharding and aggregation service solution; ServiceComb is a micro service and distributed transaction solution. In this talk we will share our integration with Skywalking, which can observe a modern, complicated, distributed system immediately.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1014", "audienceId": "", "typeId": "2", "locationId": "1004", "speakerIds": [ "1127" ], "languageId": "1" }, { "id": "1130", "start": "2019-09-12T16:30:00", "end": "2019-09-12T17:20:00", "title": "Serverless Integration with Apache Camel and Knative", "abstractText": "Abstract: When we say cloud native what is it that we really mean, and how does this really adapt to our enterprise as we transition away from our now arcane ESB and SOA patterns and further along our integration journey to what everyone is calling cloud native. In this talk we'll discuss the promises of cloud native architecture, why it makes sense to distribute our integration logic in this fashion using Apache Camel in a serverless way and why Apache Camel is uniquely suited for this, and how to leverage an underlying Knative event bus to add state back into our serverless integration deployments which use Apache Camel. This talk will examine both Apache Camel and why integration is so important in our new cloud native MicroService world, and add a host of cloud native capabilities using Knative to bring us to our next iteration of distributed integration - cloud native integration.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1011", "audienceId": "", "typeId": "2", "locationId": "1006", "speakerIds": [ "1126" ], "languageId": "1" }, { "id": "1131", "start": "2019-09-09T14:00:00", "end": "2019-09-09T14:50:00", "title": "Using PLC4X and LF Edge EVE to build a next generation Industry 4.0 IoT Platform", "abstractText": "Industrial IoT platforms are undergoing rapid shift away from vertically integrated systems built mostly out of embedded software towards an Edge Virtualization Platforms and commodity, cloud native software. While the cloud, big-data, fast-data, machine-learning has been a huge thing in the IT industry for the last years, the production industry was stuck in a proprietary world, dominated by some of the big players. Two open source projects now offer the building blocks for the new platform that can hope to break that proprietary chokehold. Linux Foundation's Project EVE (Edge Virtualization Engine) aims to develop an open and standardized edge container runtime platform capable of orchestrating cloud-native applications across the enterprise, on-premises edge and IoT deployments. It does so by leveraging hardware-assisted virtualization and provides software defined networking and I/O virtualization capabilities to the end user applications running on it. We use EVE as a runtime for the new Apache PLC4X project that in turn provides a unified API for communicating with industrial controllers via a wide variety of protocols. Besides providing the APIs and driver implementations, PLC4X also provides integration modules to other Apache frameworks such as Apache Edgent, Apache Camel and Apache Kafka that are also supported by the unified EVE IoT edge container runtime. This makes it really easy to integrate industrial controllers into our Open-Source world. Self-optimizing production processes, predictive maintenance, industrial control systems running in the companies cloud. This was all almost impossible until now. With Apache PLC4X and LF Edge EVE it will be easy.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1012", "audienceId": "", "typeId": "2", "locationId": "1014", "speakerIds": [ "1037", "1075" ], "languageId": "1" }, { "id": "1132", "start": "2019-09-11T12:00:00", "end": "2019-09-11T12:50:00", "title": "Schema-Managed Big Data Column Access Control and Use Cases", "abstractText": "Motivation: Access control via encryption improves security coverage compared with traditional enforcement in the access path because encryption can prevent invalid accesses from any angle. Finer-grained access control at the column-level is needed because in a typical big dataset, only a few columns are sensitive and need to be protected, and different columns could have different sensitivities and a different set of eligible readers. Design: With encryption features in columnar file format like Apache Parquet, column access control via encryption becomes possible. But to adopt these features into existing analytic frameworks that might use Apache Hive, Apache Spark, Apache Preto etc, is a challenge because significant changes are needed to those query engines to control the encryption. n nTo avoid massive changes in existing frameworks, the Apache Parquet community designed a schema controlled column encryption mechanism. The schema of data tables can be leveraged by a system architect in order to define the sensitivity of a column, that will be propagated through the stack and will eventually trigger the encryption on that column in the Apache Parquet writing layer. This solution is applicable in many analytic frameworks via transparent plug-in invocation that avoids massive changes in the frameworks, making Apache Parquet encryption easy to adopt. This mechanism is possible to be extended to support Apache ORC too. n nUse Cases: 1. HDFS ingesting pipelines with Spark and Hudi encrypt sensitive columns automatically with schema-controlled crypto settings. n nIn this use case, we will talk about how to use schema to control column encryption in Apache Parquet, and what is the flow that the pipeline can automatically encrypt the columns once schema sets the sensitivity. n n2. Column access control scalability and performance analysis for analytic frameworks with Apache Hive and Presto on Apache Parquet.n nLike Apache Spark, Apache Hive and Presto are two popular query engines. We will show our analysis on scalability and performance of column access control in an analytic framework. n nSummary: In this talk, we will present the motivation and design of schema-controlled column encryption at file format level, and how it can ease the adoption of encryption features to current popular query engines like Apache Hive, Apache Spark and Presto. Use cases will be presented to show how to use schema controlled column encryption in analytic pipeline and frameworks.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1007", "audienceId": "", "typeId": "2", "locationId": "1000", "speakerIds": [ "1128", "1129", "2060" ], "languageId": "1" }, { "id": "1133", "start": "2019-09-12T14:00:00", "end": "2019-09-12T14:50:00", "title": "From an idea to an Apache TLP", "abstractText": "About 3 years ago, I had an idea of using Open-Source software to create the next generation of industrial it solutions. At ApacheCon 2017 in Miami I introduced this idea to the public with my 'Building SCADA systems with Apache Software'. 2019 the Apache PLC4X project is an Apache TLP. In this talk I will not talk about technical details of the project itself, but all the steps we took on this journey from a community-building point of view. Starting way before writing the first line of code. After these last two years, I would claim that 'community-building' is by far the most challenging task when initiating a new project, but it's also seems to be one we tend to treat as second-class citizens - even in established projects. Hopefully I will be able to show you how rewarding community-building can be ... After all: Apache is all about community over code and it's that way for a reason", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1008", "audienceId": "", "typeId": "2", "locationId": "1013", "speakerIds": [ "1075" ], "languageId": "1" }, { "id": "1134", "start": "2019-09-10T12:15:00", "end": "2019-09-10T13:05:00", "title": "Ceph with CloudStack", "abstractText": "In this presentation, we are going to give a brief introduction to Ceph and cover some considerations around it's architecture, both in general and related to CloudStack. We are going to cover Ceph's integration into CloudStack, compare it's feature set versus other Primary Storage solutions for CloudStack and also share some general advises on it's setup.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1002", "audienceId": "", "typeId": "2", "locationId": "1006", "speakerIds": [ "1130" ], "languageId": "1" }, { "id": "1135", "start": "2019-09-11T14:15:00", "end": "2019-09-11T15:05:00", "title": "HTTP/2, HTTP/3 and SSL/TLS State of Art in Our Servers", "abstractText": "A new protocol is getting ready HTTP/3 we will look to where we are with it in our serves.nThe 'old' HTTP/2 protocol and the corresponding TLS/SSL are common to Traffic Server, HTTP Server and Tomcat.nThe presentation will shortly explain the new protocol and the ALPN extensions and look to the state of the those in our 3 servers and show the common parts and the specifics of each servers.nA demo configuration of each server will be run.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1005", "audienceId": "", "typeId": "2", "locationId": "1007", "speakerIds": [ "1079" ], "languageId": "1" }, { "id": "1136", "start": "2019-09-12T17:30:00", "end": "2019-09-12T18:20:00", "title": "Apache httpd and TLS/SSL certificates validation", "abstractText": "We will look to 2 different things here, validation of the server certificate andnvalidation of the client certificates. For the server certificate we will show Let's encrypt and mod_md and speak aboutnthe new ACMEv2 protocol and OCSP stapling. For the client certificates we look to OCSP and other validations. Demo and quick start example will provided during the talk.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1016", "audienceId": "", "typeId": "2", "locationId": "1000", "speakerIds": [ "1079" ], "languageId": "1" }, { "id": "1137", "start": "2019-09-10T12:15:00", "end": "2019-09-10T13:05:00", "title": "Backup and Recovery in CloudStack (it's Here!)", "abstractText": "This presentation will demonstrate the long awaited Backup & Recovery Framework feature. The presentation will feature a real-world demonstration as well explain the design philosophy and how the feature has been built to be agnostic of the backend Backup and Recovery software in use.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1002", "audienceId": "", "typeId": "2", "locationId": "1005", "speakerIds": [ "1108" ], "languageId": "1" }, { "id": "1138", "start": "2019-09-11T17:45:00", "end": "2019-09-11T18:35:00", "title": "Building Data Platform for your Next Meetup Event with Apache Foundation on Cloud", "abstractText": "One of the challenges at Meetup is how to build a scalable, reliable and efficient data platform to help our ML team builds models that recommend events fit your interests. With emerging sophisticated batch and streaming frameworks and cloud solutions, our data platform went through massive changes in the past two years. In this talk, I'll discuss the evolution of how Meetup data platform utilizes Apache-based data systems, including Sqoop, Hive, Flume, Spark, Flink, Beam, Airflow. I'll talk about architecture changes to our batch and stream pipeline solutions and what pros/cons to move data platform 100% to cloud. I'll also share some lessons we learned and best practices on building distributed systems for data platform, and how the data platform collaborates with machines learning and data science team. ", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1007", "audienceId": "", "typeId": "2", "locationId": "1000", "speakerIds": [ "1131" ], "languageId": "1" }, { "id": "1139", "start": "2019-09-10T17:00:00", "end": "2019-09-10T17:50:00", "title": "Transaction Management on Cassandra", "abstractText": "Scalar DB is an open source library released under Apache 2 which realizes ACID-compliant transactions on Cassandra, without requiring any modifications to Cassandra itself. It achieves strongly-consistent, linearly scalable, and highly available transactions. This talk will present the theory and practice behind Scalar DB, as well as providing some benchmark results and use cases.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1001", "audienceId": "", "typeId": "2", "locationId": "1010", "speakerIds": [ "1132", "1133", "1070" ], "languageId": "1" }, { "id": "1140", "start": "2019-09-12T09:00:00", "end": "2019-09-12T09:50:00", "title": "Apache OFBiz in the Cloud(s)", "abstractText": "Cloud computing greatly simplifies provisioning, scaling, reliability and maintenance: these aspects are particularly important for Enterprise applications like Apache OFBiz. This talk will provide effective tips, based on experience and lessons learned in the field, to enable OFBiz for the cloud. Topics covered include OFBiz specific solutions for:n- deployments in AWSn- images - AMI, Dockern- continuous deploymentsn- configurations for load balancersn- session management - sticky sessions, distributed sessions (with Redis)n- database options for the cloud - RDS (AWS), Google Cloud Spanner", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1019", "audienceId": "", "typeId": "2", "locationId": "1005", "speakerIds": [ "1134" ], "languageId": "1" }, { "id": "1141", "start": "2019-09-11T15:15:00", "end": "2019-09-11T16:05:00", "title": "State of integration with Apache Camel", "abstractText": "Apache Camel is the leading open source integration framework, which has been around for over a decade. In this talk we will look back in history, to understand how the integration landscape has evolved from EAI, SOA, and ESB architectures up to microservices, and now with modern serverless and cloud native platforms. Apache Camel has been along for the ride. And we will look to the future and see how the latest release v3 of Apache Camel, is aimed for running modern cloud native workloads with Camel K. In this talk you will:n- Learn from history software integration, and why you should rely on existing, proven fully featured integration frameworks instead of rolling out your own DIY solutionsn- See how software integration is (still) important in today’s modern architectures and what role does Camel have in the new cloud native worldn- What is new and noteworthy in Apache Camel version 3", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1011", "audienceId": "", "typeId": "2", "locationId": "1006", "speakerIds": [ "1135" ], "languageId": "1" }, { "id": "1142", "start": "2019-09-11T17:45:00", "end": "2019-09-11T18:35:00", "title": "Apache Camel K: a cloud-native integration platform", "abstractText": "In this session we are going to introduce the latest innovation from the Apache Camel community: Camel K, a lightweight integration platform, born on Kubernetes, with serverless superpowers.nCamel K enables developers that want to integrate systems to directly write Camel DSL code in the cloud, with a great developer experience and really fast turnaround times.nYou’ll see Camel K in action with a live coding demo that will explore the main features that it provides.nYou’ll also learn how Camel K works under the hood and will have a glimpse on the future roadmap.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1011", "audienceId": "", "typeId": "2", "locationId": "1006", "speakerIds": [ "1057", "1056" ], "languageId": "1" }, { "id": "1143", "start": "2019-09-09T10:00:00", "end": "2019-09-09T10:50:00", "title": "Modern UI for CloudStack", "abstractText": "The CloudStack UI code has tolerated massive technical debt over the years and the UI codebase has reached a breaking point. In this talk, we will do a comparison of modern UI development techniques, the pros and cons of current UI UX and codebase, ideas and experiments of a new UI for CloudStack. We need to discuss and propose a new UI that:n* Has CloudMonkey like api discovery and show/hide/block, buttons/sections based on what is allowedn* URL router to navigate to resources, and clicking back button does not close the UIn* Easy to maintain, implement and extend via plugins etc.n* Does not take months to develop and port existing implementation to the new onen* Configurable, theme-able, don't use our own UI framework, but consider something like Vue/React/Angular etc.n* Explore a components based idea, show an api-auto-discovery approach to auto-generate boiler plate for UI component based on an API's request and response paramsn* Make UI more communicative about underlying infra state in real time with modern graphical libraries", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1002", "audienceId": "", "typeId": "2", "locationId": "1005", "speakerIds": [ "1104", "1136" ], "languageId": "1" }, { "id": "1144", "start": "2019-09-10T15:30:00", "end": "2019-09-10T16:20:00", "title": "CloudStack identity federation: An overview", "abstractText": "Federated authentication in online services is increasingly being used, whether through public identity providers such as Facebook, Google and others, or in organizations' private identity providers. Identity federation is a technology that has come to simplify the life of the user, but that does not always simplify the life of application developers and operators. The purpose of this talk is to share a bit the challenges, benefits and problems of using federated authentication with multiple identity providers in Apache Cloudstack.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1002", "audienceId": "", "typeId": "2", "locationId": "1005", "speakerIds": [ "1093" ], "languageId": "1" }, { "id": "1145", "start": "2019-09-10T15:30:00", "end": "2019-09-10T16:20:00", "title": "Serving Clean URLs via Custom Internet Media Types on Tomcat", "abstractText": "Increasingly static site generators are being used to create a presence on the web, both for the speed and simplicity of the resulting static pages. A related trend is the use of 'clean' URLs with no resource name extensions, such as `/products/mousetrap` instead of `/products/mousetrap.html`. Clean URLs are more memorable, less fragile, do not leak implementation information, and are more search engine friendly. Because the default Tomcat implementation determines MIME type by filename extension, 'clean' filenames are traditionally produced by servlet mapping or URL rewriting, perhaps coupled with Apache HTTP Server in front of Tomcat using `mod_rewrite`. This presentation shows how Tomcat has been extended to dynamically determine MIME type at runtime based on metadata stored in a parallel file tree or as sidecar files, and to serve the pages with clean resource names directly from Tomcat with no need for URL rewriting. A tutorial on the static site generator Guise Mummy is also included, illustrating how to generate a static site with clean resource names, host the site immediately using embedded Tomcat, and/or deploy the site to AWS S3 using bucket object metadata with a single command.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1005", "audienceId": "", "typeId": "2", "locationId": "1007", "speakerIds": [ "1137" ], "languageId": "1" }, { "id": "1146", "start": "2019-09-12T17:30:00", "end": "2019-09-12T18:20:00", "title": "Building an open source analytics distribution on Kubernetes that meets the needs of a modern data scientist.", "abstractText": "Modern machine learning libraries such as Jupyter, Kubeflow, PyTorch on technologies that are managed outside of the linux foundation, often forcing users to pay for cloud or hosted offerings to manage integration and tool dependencys. This challenges the ability of the ASF to continue blazing a trail of open innovation in the data science and analytics frontiers which are transforming so many businesses today. New projects in the ASF: such as Airflow, PredictionIO, SystemML, and NiFi - combined with technologies such as Spark and HDFS can be used to build an end-to-end analytics solution that is flexible and modular enough to meet the needs of modern data scientists, at pedabyte scale. In this talk, we'll introduce a prototypical 'next generation' prototype which we propose as the future direction of ApacheBigtop, which runs entirely on Kubernetes, to minimize cost and maximize the portability of your modern hybrid analytics architecture.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1013", "audienceId": "", "typeId": "2", "locationId": "1007", "speakerIds": [ "1138", "2065" ], "languageId": "1" }, { "id": "1147", "start": "2019-09-11T16:45:00", "end": "2019-09-11T17:35:00", "title": "From Postgres to an In-Memory Grid with Apache Ignite", "abstractText": "This talk describes how a food tech company with 50k merchants was at a critical situation by delivering events to devices by using events polling on a Postgres database, and how it could solve this problem by moving the events repository to Apache Ignite using distributed, in-memory SQL. The change also allowed the company to be on the right track to support more than 500k simultaneous merchants.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1007", "audienceId": "", "typeId": "2", "locationId": "1000", "speakerIds": [ "1139" ], "languageId": "1" }, { "id": "1148", "start": "2019-09-11T16:45:00", "end": "2019-09-11T17:35:00", "title": "I Love Lucee", "abstractText": "Lucee is a free and open source application server that implements the CFML language, which was popularized by the commercial product ColdFusion. It allows for rapid application development, and is implemented as a JSP Servlet so it is deployed inside a Servlet Container like Apache Tomcat. The Lucee website: https://lucee.org/ GitHub Repo:nhttps://github.com/lucee/Lucee Support Forum: https://dev.lucee.org/", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1005", "audienceId": "", "typeId": "2", "locationId": "1007", "speakerIds": [ "1140" ], "languageId": "1" }, { "id": "1149", "start": "2019-09-12T17:30:00", "end": "2019-09-12T18:20:00", "title": "Data Movement & Integration at PayPal & LinkedIn using Apache Gobblin", "abstractText": "Data replication at PayPal drives various different business use-cases from fraud detection, user behavioral analysis, credit checks to lot of other offline business decisions. During this talk, we will present how Apache Gobblin empowers data movement and integrations at PayPal in partnership with LinkedIn to showcase all the recent features as well as the planned roadmap for the platform. Apache Gobblin is a distributed data integration framework that simplifies common aspects of big data integration such as data ingestion, replication, organization and lifecycle management for both streaming and batch data ecosystems. In the second half of this presentation, we will present recent additions to Gobblin including: 1. A new declarative approach for defining data pipelines using Gobblin-as-a-Service, and 2. Real world experiences running hybrid batch and streaming pipelines using Gobblin.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1011", "audienceId": "", "typeId": "2", "locationId": "1006", "speakerIds": [ "1141", "1142" ], "languageId": "1" }, { "id": "1150", "start": "2019-09-09T09:00:00", "end": "2019-09-09T09:50:00", "title": "Geospatial Data and Processing - Reusable Building Blocks", "abstractText": "Reuse of common elements for geospatial information and processing results in increased productivity, lower interoperability friction, and higher data quality. This presentation provides a survey of reusable geospatial building blocks. Common practices for coordinate reference systems (CRSs), spatial geometries and data arrays used for projects with geospatial content will be described based on open source projects and open standards. Emphasis is placed on the use of open standards including the recently updated OGC CRS Well Known Text (CRS WKT) and OGC APIs. The presentation will provide the latest update on OGC API development. OGC APIs are being defined for geospatial resources, e.g., maps, features, coverages. Developed using OpenAPI, the APIS can be implemented in a number of languages and patterns. The presentation will be describe the state of implementations and plans for standardization. The modular structure enables flexibility for developers to reuse OGC APIs in their APIs. This presentation will allow time for discussion of coordination across Apache projects with geospatial content. Geospatial tracks at previous ApacheCons concluded with an open discussion leading to the creation of geospatial@apache.org.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1009", "audienceId": "", "typeId": "2", "locationId": "1013", "speakerIds": [ "1143" ], "languageId": "1" }, { "id": "1151", "start": "2019-09-11T12:00:00", "end": "2019-09-11T12:50:00", "title": "Apache When You’re Not In Charge", "abstractText": "Apache has a 20 year history of building resilient and sustainable communities of software developers through the Apache Way. While some companies are adopting Inner sourcing, other companies still have a taboo surrounding open source culture. Many of us work at these open source agnostic companies and don’t have manager in our title. Are those of us in those companies doomed to a life of Dilbert? You don’t have to be! This talk is all about how to bring a little Apache culture to your Apache oblivious team. This talk will cover how a little Apache Way goes a long way solving common team problems with knowledge sharing, technical/personal disputes, mentorship, and shipping software. So even though you’re the only one on your team that “gets” Apache, everyone can share in the rewards of being a part of an effective team.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1008", "audienceId": "", "typeId": "2", "locationId": "1013", "speakerIds": [ "1107" ], "languageId": "1" }, { "id": "1152", "start": "2019-09-09T15:00:00", "end": "2019-09-09T15:50:00", "title": "Going Beyond StringUtils: A Broader Look at Apache Commons", "abstractText": "The Apache Commons Project is home to one of the more widely consumed Java utility functions, namely “StringUtils.isBlank(String str);”. But when you look beyond commons-lang, you’ll find a wide array of heavily utilized and extremely useful tools. For example, commons-cli is the command line parser used by the Apache Maven project; commons-fileupload is heavily used by both Apache Tomcat and Apache Struts; commons-text is heavily used by Apache Hadoop; and commons-dbcp is a database connection pool used across Tomcat as well as the Spring Framework. We’ll look at some common problems facing developers today and how the Apache Commons Project can address them, diving into specific examples as we go.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1016", "audienceId": "", "typeId": "2", "locationId": "1000", "speakerIds": [ "1144" ], "languageId": "1" }, { "id": "1153", "start": "2019-09-10T11:15:00", "end": "2019-09-10T12:05:00", "title": "Life beyond Kafka with Apache Pulsar", "abstractText": "In a world where everything is connected, trillions of devices are sending data in real-time to data centers. Apache Kafka as a streaming platform is the system by excellence for many years. However, there are many competitors who are making its life more difficult. In this talk, I will introduce to one of them, Apache Pulsar sponsored by Yahoo itself. Pulsar is the next generation messaging system that uses a different architecture to achieve durability, performance, scalability, efficiency, multi-tenancy and geographic replication. Besides, I will focus on why Apache Pulsar is a great streaming platform in IoT projects.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1012", "audienceId": "", "typeId": "2", "locationId": "1014", "speakerIds": [ "1145", "2037" ], "languageId": "1" }, { "id": "1154", "start": "2019-09-09T14:00:00", "end": "2019-09-09T14:50:00", "title": "Apache Commons State of the Union", "abstractText": "We will go over the state of the Apache Commons Project. Where things stand, and will take a look at the future road map for the project.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1016", "audienceId": "", "typeId": "2", "locationId": "1000", "speakerIds": [ "1144" ], "languageId": "1" }, { "id": "1156", "start": "2019-09-11T17:45:00", "end": "2019-09-11T18:35:00", "title": "Apache httpd reverse proxy and Tomcat:", "abstractText": "Although mostly known as a fast and reliable web server, Apache httpd also excels as a reverse proxy.nIn this session find out how to setup httpd as a reverse proxy, how to connect to Tomcat using HTTP and AJP.nWe will also look to the full feature list of Apache httpd proxying capability.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1005", "audienceId": "", "typeId": "2", "locationId": "1007", "speakerIds": [ "1079" ], "languageId": "1" }, { "id": "1157", "start": "2019-09-10T11:15:00", "end": "2019-09-10T12:05:00", "title": "The future of the CloudStack Virtual Router", "abstractText": "This talk surveys and explores the scopes and design for the next-generation network model consolidation in CloudStack and a new super-fast micro-vm based VR. The talk will discuss the scope and goals for the next-generation VR, consolidation of basic and advanced networks and zones, flexible networking topologies, UI based network designing, a standard systemvm patching mechanism and uniform VR programming interface with a lightweight secured agent, faster rules programming and zero-downtime upgrades. It will also explore new abilities to allow live/online patching, containerization of VR processes and pluggability of user-imported data/router appliances (bring your own X) such as pfsense, vyos etc for VPN, FTP, DNS, DHCP, etc.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1002", "audienceId": "", "typeId": "2", "locationId": "1005", "speakerIds": [ "1136" ], "languageId": "1" }, { "id": "1158", "start": "2019-09-12T16:30:00", "end": "2019-09-12T17:20:00", "title": "What's New and Coming to Apache Hivemall: Building More Flexible Machine Learning Solution for Apache Hive and Spark", "abstractText": "Apache Hivemall is a scalable machine learning library for Apache Hive, Spark, and Pig. Hivemall allows us to apply a wealth of machine learning techniques to massive data stored in distributed storage by just writing a series of SQL-like queries. It provides classification, regression, recommendation, anomaly detection, and topic modeling functionalities in a scalable manner, along with a variety of auxiliary functions for data preprocessing and feature engineering. This talk demonstrates the Hivemall library with a special emphasis on its new features merged after the first Apache Incubator release. Hivemall v0.5.2-incubating, the latest version as of April 2019, has introduced a state-of-the-art generalized factor model named Field-Aware Factorization Machines and many useful UDFs (e.g., data sketching) originated from the Brickhouse Hive UDF package. We also show the roadmap of this incubating project. Open issues and pull requests include Apache Spark 2.4 support, implementation of new algorithms such as word2vec and multi-nominal logistic regression, as well as integration with widely-used tools like XGBoost and LightGBM.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1013", "audienceId": "", "typeId": "2", "locationId": "1007", "speakerIds": [ "1147", "1148" ], "languageId": "1" }, { "id": "1159", "start": "2019-09-10T14:30:00", "end": "2019-09-10T15:20:00", "title": "Tips for Debugging Tomcat and Web Applications", "abstractText": "Tips for Debugging Tomcat and Web Applications: Modern administrators are responsible for deploying, monitoring, and maintaining a wide variety of applications, but what happens when they break? Efficiently troubleshooting issues is an often overlooked skill, and few administrators have the time to dedicate to mastering these techniques. Resolving these issues in a timely and efficient manner can save companies time, money, and decrease customer-facing downtime, etc. In this session Coty will cover some of the basics for troubleshooting/debugging Apache Tomcat and the web applications deployed inside the server. The audience will get a first hand look at diagnosing problems with thread dumps, process output, etc to quickly determine the cause of issues and receive suggestions on next steps to resolve them.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1005", "audienceId": "", "typeId": "2", "locationId": "1007", "speakerIds": [ "1003" ], "languageId": "1" }, { "id": "1160", "start": "2019-09-10T17:00:00", "end": "2019-09-10T17:50:00", "title": "Unleashing Apache Kafka and TensorFlow in Hybrid Cloud Architectures", "abstractText": "How can you leverage the flexibility and extreme scale in the public cloud combined with your Apache Kafka ecosystem to build scalable, mission-critical machine learning infrastructures, which span multiple public clouds or bridge your on-premise data centre to cloud? nThis talk will discuss and demo how you can leverage machine learning technologies such as TensorFlow with your Kafka deployments in public cloud to build a scalable, mission-critical machine learning infrastructure for data ingestion and processing, and model training, deployment and monitoring.nThe discussed architecture includes capabilities like scalable data preprocessing for training and predictions, combination of different Deep Learning frameworks, data replication between data centres, intelligent real time microservices running on Kubernetes, and local deployment of analytic models for offline predictions.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1013", "audienceId": "", "typeId": "2", "locationId": "1000", "speakerIds": [ "1103" ], "languageId": "1" }, { "id": "1161", "start": "2019-09-09T10:00:00", "end": "2019-09-09T10:50:00", "title": "Customized CloudStack in Leaseweb", "abstractText": "In this talk we will share how Leaseweb customized the CloudStack project to serve our business model and our customers, by doing some improvements and do some bug fixes. We always focused on upgrading our fork to the latest in the community while making sure all our improvements are ported to the latest version. In this talk we will tell you about some features and fixes we did like: - multiple NICs feature, - NoVNC, autoscaling, - SSL offloading in load balancer - and other changes made to serve some of our customers' needs. We also love to give the community as we take from it, so we open PRs to release our improvements to the community and based on the community reactions to this talk will start to open new PRs of these changes. ", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1002", "audienceId": "", "typeId": "2", "locationId": "1006", "speakerIds": [ "1150" ], "languageId": "1" }, { "id": "1162", "start": "2019-09-09T16:30:00", "end": "2019-09-09T17:20:00", "title": "Customer Cloud Portal", "abstractText": "A technical overview showing how we at itelligence as a cloud service provider use CloudStack and how we extent our infrastructure with additional service components to enhance our cloud service portfolio.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1002", "audienceId": "", "typeId": "2", "locationId": "1005", "speakerIds": [ "1151", "1152" ], "languageId": "1" }, { "id": "1163", "start": "2019-09-09T11:30:00", "end": "2019-09-09T12:20:00", "title": "Apache Science Data Analytics Platform (SDAP)", "abstractText": "An Analytics Center Framework (ACF) is an environment that enables the confluence of resources for scientific investigation. It harmonizes data, tools and computational resources which subsequently enable the research community to focus on the investigation. The Earth science community is an innovative community. We produce many tools and solutions to improve how we do science. In computer science, a framework is a reusable, semi-complete application that can be specialized to produce custom applications [Johnson:88]. After more than two years of actively developing an open source ACF, on October 2017, the NASA AIST OceanWorks project established collaboration with the Apache Software Foundation, called the Apache Science Data Analytics Platform (SDAP). It is a big data analytics platform designed for cloud-based data management, analytics, match-up, and data discovery services. It is a community-support, extensible open source GIS platform. The motivation is to empower the Earth and Space Science Informatics community to develop a common big data solution for the cloud and on-premise cluster. The big data analytics platform is being used to support NASA Sea Level research, GRACE and GRACE Follow-On mission sciences, and NASA Physical Oceanography, etc. This talk describes the Apache SDAP and lesson learned from developing and moving SDAP in production to support various NASA and JPL researches.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1015", "audienceId": "", "typeId": "2", "locationId": "1013", "speakerIds": [ "1153" ], "languageId": "1" }, { "id": "1164", "start": "2019-09-09T14:00:00", "end": "2019-09-09T14:50:00", "title": "GeoMesa on top of Accumulo, HBase, Cassandra, and big data file formats for massive geospatial data - a LocationTech Project", "abstractText": "LocationTech is the geospatial software working group of the Eclipse Foundation. The projects range from fundamental libraries that provide spatial operations to complex library suites which coordinate multiple Apache projects to build complete spatial processing solutions.nLocationTech GeoMesa builds on top of distributed Apache databases like Accumulo, HBase, Cassandra and Kafka to provide indexing, querying, and analysis for large spatio-temporal datasets. GeoMesa does this by integrating other LocationTech projects like JTS, Spatial4J, and SFCurve with these databases as well as Apache open source file formats such as Avro, Arrow, Orc, and Parquet.nIn this talk, we will give an overview of the geospatial capabilities that the foundational LocationTech libraries can bring to a project. With that background, we will discuss how GeoMesa integrates those capabilities into distributed databases and the file formats. We will wrap up with a quick look at the other big geo-data projects in LocationTech (GeoTrellis, GeoWave, and RasterFrames).", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1015", "audienceId": "", "typeId": "2", "locationId": "1013", "speakerIds": [ "1154", "1155" ], "languageId": "1" }, { "id": "1165", "start": "2019-09-09T17:30:00", "end": "2019-09-09T18:20:00", "title": "Realtime Geospatial Analytics with GPUs, RAPIDS, and Apache Arrow", "abstractText": "Prior to RAPIDS, geospatial analytics, especially networking analytics for routing, required large CPU clusters to process. Even with 100s of machines, it would take hours if not days to get answers. With RAPIDS, and Apache 2.0 open source project built on Apache Arrow, graph analytics, clustering, and many other geospatial workflows can be completed end to end in seconds. Learn how to load data (CSV, Parquet, or ORC) directly into GPU memory with cuIO, process it with Dask-cuDF, and analyze it with cuML and cuGraph in seconds, all on a single node. Finally, learn how RAPIDS is scaling to multiple GPU nodes to solve the largest of geospatial challenges.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1015", "audienceId": "", "typeId": "2", "locationId": "1013", "speakerIds": [ "1156" ], "languageId": "1" }, { "id": "1166", "start": "2019-09-10T11:15:00", "end": "2019-09-10T12:05:00", "title": "Apache Iceberg: a table format for distributed databases", "abstractText": "'This talk will introduce Apache Iceberg (Incubating), a new table format designed for distributed databases that can be used directly by any size application. It will cover Iceberg’s design and the features that distinguish it from other table formats, including: -Reliable schema evolutio -Hidden partitioningn-Atomic operationsn-Support for object stores like S3n-Support for direct client access This talk will also present how Iceberg performs at scale in Netflix’s environment.'", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1007", "audienceId": "", "typeId": "2", "locationId": "1008", "speakerIds": [ "1157" ], "languageId": "1" }, { "id": "1167", "start": "2019-09-10T12:15:00", "end": "2019-09-10T13:05:00", "title": "Optimizing Big Data Pipelines with Apache Nemo (Incubating)", "abstractText": "Optimizing scheduling and communication behaviors of big data pipelines for resource and data characteristics is crucial for achieving high performance. For example, optimizing for geographically-distributed resources, cheap transient resources, disk-based large data shuffle, and skewed data have recently received a lot of interest and attention. The new incubating Apache Nemo project aims to make it easy to express and enforce such optimizations by providing a policy interface that transforms an intermediate representation (IR) of data processing applications. Apache Nemo executes the optimized IR on distributed computers while enforcing the specified scheduling and communication behaviors, and at the same time maintaining the correct application semantics. Apache Nemo is closely integrated with existing Apache Big Data projects. Apache Nemo currently supports optimizing Apache Beam and Apache Spark applications, and uses Apache REEF to run on Apache Hadoop YARN and Apache Mesos. In this talk I will describe how to develop and compose new optimization policies on Apache Nemo, how the optimizations are actually enforced in the distributed execution, and the roadmap to further improve Apache Nemo.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1007", "audienceId": "", "typeId": "2", "locationId": "1008", "speakerIds": [ "1158" ], "languageId": "1" }, { "id": "1168", "start": "2019-09-10T14:30:00", "end": "2019-09-10T15:20:00", "title": "Apache Hudi (Incubating) : the past, present and future of efficient data lake architectures", "abstractText": "Apache Hudi is a newly incubating project at the ASF. Originally created at Uber, to power it’s vast big data lake, Hudi provides key features like atomic writes, snapshot isolation, incremental views, rollbacks, point-in-time restores, file size management & many more. To date, the big data community has been polarized amongst batch and streaming systems, when balancing data freshness and scale. Hudi also addresses a combined need for speed and scale, that does not naturally fit into existing batch and streaming data processing architectures, by way of ability to support continuous ingestion and asynchronous compaction of row & columnar data. In this talk, we will briefly discuss the history of the project - the motivating use-cases & the architectural underpinnings, that spurred the need for such a system. We will examine a blueprint for reliable and state-of-the-art data lake architecture and explain how Hudi’s current capabilities play a central role in it. We will also share hands-on recipes to leverage Hudi in your organization, for popular tasks like data ingestion or ETLs. We will dedicate the remainder of the talk to discussing the roadmap ahead, touching upon areas like external indexing, storage layout organization, as well as advanced topics like building realtime ML feature stores or composing safe multi-stream ETL joins.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1007", "audienceId": "", "typeId": "2", "locationId": "1008", "speakerIds": [ "1159", "1160" ], "languageId": "1" }, { "id": "1169", "start": "2019-09-10T15:30:00", "end": "2019-09-10T16:20:00", "title": "Apache Pinot (incubating): Building Realtime Analytics Applications at LinkedIn Scale", "abstractText": "LinkedIn is the most advantageous social networking tool available to job seekers and business professionals today, with 610+ million members creating millions of posts, videos, and articles that generate tens of millions of shares, comments and likes per day. LinkedIn has leveraged this activity data to build rich interactive user-facing analytics applications like “Who Viewed My Profile”, Talent Insights, Ad Analytics and Publisher Analytics, among others. These applications are all powered by Pinot, as are internal dashboards, anomaly detection and root cause analysis platform like ThirdEye. Apache Pinot (incubating) is a distributed columnar storage engine that can ingest ndata in realtime and serve analytical queries at low latency. In this talk, we will discuss how Pinot has become the de-facto solution for serving analytic queries in milliseconds, ad-hoc reporting, monitoring & Anomaly Detection on multidimensional data.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1007", "audienceId": "", "typeId": "2", "locationId": "1008", "speakerIds": [ "1161", "1162", "2061" ], "languageId": "1" }, { "id": "1170", "start": "2019-09-10T17:00:00", "end": "2019-09-10T17:50:00", "title": "Apache Doris (incubating) -- A simple and single tightly coupled olap system", "abstractText": "Apache Doris (incubating) is an MPP-based interactive SQL data warehousing for reporting and analysis. It is open-sourced by Baidu. Doris mainly integrates the technology of Google Mesa and Apache Impala. Unlike other popular SQL-on-Hadoop systems, Doris is designed to be a simple and single tightly coupled system, not depending on other systems. Doris not only provides high concurrent low latency point query performance, but also provides high throughput queries of ad-hoc analysis. Doris not only provides batch data loading, but also provides near real-time mini-batch data loading. Doris also provides high availability, reliability, fault tolerance, and scalability. The simplicity (of developing, deploying and using) and meeting many data serving requirements in single system are the main features of Doris.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1007", "audienceId": "", "typeId": "2", "locationId": "1008", "speakerIds": [ "1163" ], "languageId": "1" }, { "id": "1171", "start": "2019-09-10T18:00:00", "end": "2019-09-10T18:50:00", "title": "Inside Apache Druid: Built for High-Performance Real-Time Analytics", "abstractText": "Interactive applications are replacing traditional reporting interfaces as the preferred means for organizations to derive value from their datasets. An interactive user experience requires latency on the order of milliseconds. Cluster computing frameworks such as Apache Hadoop or Apache Spark are tremendously beneficial in processing and deriving insights from data. However, high query latency makes these frameworks sub-optimal for interactive applications. Alternatively, the use of relational databases and key/value stores as dedicated query layers can reduce latency, but these approaches suffer many drawbacks for analytic use cases. Apache Druid (incubating) is well suited to power analytic applications working with real-time data and requiring low latency. This talk will cover the current state of analytics world, drawbacks of current popular databases, and what Druid nbrings to the table. The talk will cover technical details behind Druid’s design, including how its query processing layer works and how each component contributes to achieving top performance for analytical queries. We will discuss Druid modern architecture that implements a memory-mappable storage format, indexes, compression, late tuple materialization, and a query engine that can operate directly on compressed data. At the time of ApacheCon, Druid will very likely have been granted status as a top-level ASF project. ", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1007", "audienceId": "", "typeId": "2", "locationId": "1008", "speakerIds": [ "1164" ], "languageId": "1" }, { "id": "1172", "start": "2019-09-12T14:00:00", "end": "2019-09-12T14:50:00", "title": "Apache Training - Contributing more than just code", "abstractText": "Does it seem strange to you that we collectively collaborate on code but training material is produced individually in private? Why would each company or person produce their own material when it can be sourced from a central location, under a business friendly license, and built on and modified? Or perhaps you just see better ways of producing content, then come along and listen to what the Apache Training project is doing. You'll find out how make nice presentations with simple markup that can be put under version control and exported to many formats.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1008", "audienceId": "", "typeId": "2", "locationId": "1007", "speakerIds": [ "1092" ], "languageId": "1" }, { "id": "1173", "start": "2019-09-10T11:15:00", "end": "2019-09-10T12:05:00", "title": "YuniKorn: A Universal Resource Scheduler for both YARN and Kubernetes", "abstractText": "'We will talk about our open source work - YuniKorn scheduler project (Y for YARN, K for K8s, uni- for Unified) brings long-wanted features such as hierarchical queues, fairness between users/jobs/queues, preemption to Kubernetes; and it brings service scheduling enhancements to YARN. Any improvements to this scheduler can benefit both Kubernetes and YARN community. Abstract: YARN schedulers are optimized for high-throughput, multi-tenant batch workloads. It can scale up to 50k nodes per cluster, and schedule 20k containers per second; On the other side, Kubernetes schedulers are optimized for long-running services, but many features like hierarchical queues, fairness resource sharing, and preemption etc, are either missing or not mature enough at this point of time. However, underneath they are responsible for one same job: the decision maker for resource allocations. We see the need to run services on YARN as well as run jobs on Kubernetes. This motivates us to create a universal scheduler which can work for both YARN and Kubernetes, and configure in the same way. This YuniKorn scheduler (Y for YARN, K for K8s, uni- for Unified) brings long-wanted features such as hierarchical queues, fairness between users/jobs/queues, preemption to Kubernetes; and it brings service scheduling enhancements to YARN. Most importantly, it provides the opportunity to let YARN and Kubernetes share the same user experience on scheduling big data workloads. And any improvements to this scheduler can benefit both Kubernetes and YARN community. In this talk, we’re going to talk about our efforts of design and implement the YuniKorn scheduler. We have integrated it with both YARN and Kubernetes. We will show demos and best practices.n'", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1007", "audienceId": "", "typeId": "2", "locationId": "1009", "speakerIds": [ "1047" ], "languageId": "1" }, { "id": "1175", "start": "2019-09-10T15:30:00", "end": "2019-09-10T16:20:00", "title": "Wire Encryption In HDFS: Protect Your Data From Others, Not Yourself", "abstractText": "Wire data encryption is a key component of the Hadoop Distributed File System (HDFS). HDFS can enforce different levels of data protection, allowing users to specify one based on their own needs. However, such enforcement comes in as an all-or-nothing feature. Namely, wire encryption is enforced either for all accesses or none. Since encryption bears a considerable performance cost, the all-or-nothing condition forces users to choose between 'faster but unencrypted' or 'encrypted but slower' for all clients. In our use case at LinkedIn, we would like to selectively expose fast unencrypted access to fully managed internal clients, which can be trusted, while only expose encrypted access to clients outside of the trusted circle with higher security risks. That way we minimize performance overhead for trusted internal clients while still securing data from potential outside threats. We re-evaluate the RPC encryption mechanism in HDFS. Our design extends HDFS NameNode to run on multiple ports. Depending on the configuration, connecting to different NameNode ports would end up with different levels of encryption protection. This protection then gets enforced for both NameNode RPC and the subsequent data transfers to/from DataNode. System administrators then need to set up a simple firewall rule to allow access to the unencrypted port only for internal clients and expose the encrypted port to the outside clients. This approach comes with minimum operational and performance overhead. The feature has been introduced to Apache Hadoop under HDFS-13541.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1007", "audienceId": "", "typeId": "2", "locationId": "1009", "speakerIds": [ "1168", "2051" ], "languageId": "1" }, { "id": "1176", "start": "2019-09-10T17:00:00", "end": "2019-09-10T17:50:00", "title": "Ozone: Evolving HDFS Scalability to new heights & built-in GDPR Compliance", "abstractText": "Apache Hadoop Ozone is a robust, distributed key-value object store for Hadoop with layered architecture and strong consistency. It separates the namespace management from block and node management layer, which allows users to independently scale on both axes. Ozone is interoperable with Hadoop ecosystem as it provides OzoneFS (Hadoop compatible file system API), data locality and plug-n-play deployment with HDFS as it can be installed in an existing Hadoop cluster and can share storage disks with HDFS. Ozone solves the scalability challenges with HDFS by being size agnostic. Consequently, it allows users to store trillions of files in Ozone and access them as if they are on HDFS. Ozone plugs into existing Hadoop deployments seamlessly, and programs like Yarn, MapReduce, Spark, Hive and work without any modifications. In the era of increasing need for data privacy and regulations, Ozone also aims to provide built-in support for GDPR compliance with strong focus on Right to be Forgotten i.e., Data Erasure. At the end of this presentation the audience will be able to understand: 1. Overview of current challenges with HDFS scalability 2. How Ozone’s Architecture solves these challenges 3. Overview of GDPR 4. Built-in support for GDPR in Ozone", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1007", "audienceId": "", "typeId": "2", "locationId": "1009", "speakerIds": [ "1169" ], "languageId": "1" }, { "id": "1177", "start": "2019-09-10T18:00:00", "end": "2019-09-10T18:50:00", "title": "Hadoop Storage in the Cloud Native Era", "abstractText": "Hadoop was born much earlier than the Cloud Native era. But the question is still the same: what can it offer in the time of Kubernetes, containerization and hybrid clouds? Apache Hadoop Ozone is a new subproject of Hadoop. It is based a generic low-level binary layer, the Hadoop Distributed Data Storage (HDDS) and a S3 compatible Object Store implementation on top of it. The separation of the data storage layer has multiple benefits: it can help to solve the “small files problem” and increase the scalability of the Hadoop storage clusters but it also helps us to provide access to the same data via multiple interfaces. The same data can be accessed via a Hadoop compatible file system API, with an S3 compatible file system API or as a raw, mountable block device. Storage is still a hot topic with Kubernetes and in Cloud Native environments. Container Storage Interface specification is a vendor neutral standard to provide storage plugin for multiple container orchestration system. With implementing the vendor-independent Container Storage Interface, Ozone can provide block level access on top of the Hadoop Distributed Data Storage layer and it can be first class citizen of the containerized word. In this talk we will demonstrate how the Apache Hadoop Ozone storage could be used from containers, how can the same storage space can be used as Object Store, Hadoop compatible file system or native block device. We will explain the basic storage type of Kubernetes clusters and show how Apache Hadoop Ozone can help to solve the storage problem in an industry standard way.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1007", "audienceId": "", "typeId": "2", "locationId": "1009", "speakerIds": [ "1170" ], "languageId": "1" }, { "id": "1178", "start": "2019-09-11T11:00:00", "end": "2019-09-11T11:50:00", "title": "Building BigData Query Optimization with Apache Calcite – Best Practices from Alibaba MaxCompute", "abstractText": "MaxCompute is a large scale, distributed big data platform of Alibaba, which provides Exabyte storage capacity and massive computing power through tens of thousands of commodity machines. The system supports SQL-like declarative language for advanced query and analysis on web-scale data set. Millions of jobs with hundreds of petabytes of data are processed every day, powering mission critical business within Alibaba, including e-Commerce, mobile payment, logistics, etc. 

Query optimizer plays a key part in determining the optimal execution plan. We first provide a general introduction about the overall architecture of MaxCompute, then we introduce how MaxCompute leverages Apache Calcite to build an efficient and robust query optimizer. We will also discuss the physical operators that MaxCompute creates in order to adapt to Apache Calcite, and the improvements that have been done to Calcite, such as IN list optimization, outer join null skew optimization, and logical relational node preprocessing. We further introduce our data partitioning techniques, including hash and range partitioning, to support advanced query parallelism. We will also talk about HBO (Historical Based Optimization) for regular ETL tasks.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1007", "audienceId": "", "typeId": "2", "locationId": "1008", "speakerIds": [ "1171" ], "languageId": "1" }, { "id": "1179", "start": "2019-09-11T12:00:00", "end": "2019-09-11T12:50:00", "title": "Lessons Learned from Leveraging Real-Time Power Consumption Data with Apache Kudu", "abstractText": "IoT is widely spreading in various industries, and various sensor devices generate large amounts of data in real-time. Such big data is used for visualization, machine learning, and other data analysis. Kudu is one of the data stores for such use cases which require fast inserts and efficient scans. Apache HBase is also often used to handle time series data such as sensor data. We also evaluated HBase for smart meter data a few years ago. HBase is suitable for storing sensor data because it has excellent insert performance, but it is not suitable for big data analysis because scan performance is not so good. On the other hand, Kudu is suitable for both fast insert and big data scan. We evaluated the performance of Kudu for leveraging the power consumption data collected in every second from sensor devices. With this performance test, we confirmed that 4-node Kudu cluster can storing and referring data in real-time generated by 1 million sensor devices. In order to handle a large amount of data in real-time, it is important to increase the memory allocation, to reduce the tablet size, and to define the order of the primary key to reduce the load of compaction. This presentation will introduce the differences between Kudu and other data stores (HBase, HDFS), the use cases suitable for Kudu, and the tuning know-how obtained through performance test.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1007", "audienceId": "", "typeId": "2", "locationId": "1008", "speakerIds": [ "1172" ], "languageId": "1" }, { "id": "1180", "start": "2019-09-11T14:15:00", "end": "2019-09-11T15:05:00", "title": "Using Relational Cache to Boost Apache Spark SQL", "abstractText": "Apache Spark has become a popular engine for data analysis in industry, providing a handful SQL interface and processing data from various data sources. While many of our customers are using Apache Spark as an interactive query platform to meet their business requirement, one of the most common complaints we heard is that spark is not quite 'interactive' while data goes big. In traditional database systems, we can utilize materialized views to accelerate query processing, through pre-computation and query plan rewriting. We adopt a similar method to Spark, allow user to create flexible caches from a query or cube definition, and rewrite user queries at runtime to utilize pre-computed results. The cached data can persist to external data sources that Spark supports, or stay in memory, and updates automatically when new data ingested. nIn this talk, we'd like to take a deep dive into our design, and show real-world performance gain from our customers. This feature will be contributed to community.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1007", "audienceId": "", "typeId": "2", "locationId": "1008", "speakerIds": [ "1173" ], "languageId": "1" }, { "id": "1181", "start": "2019-09-11T15:15:00", "end": "2019-09-11T16:05:00", "title": "DataSketches - The Required Toolkit for the Analysis of Big Data", "abstractText": "In​ the analysis of b​ig data there are often problem queries that don’t scale because they require huge compute resources to generate exact results, or don’t parallelize well. Examples include c​ount-distinct, ​quantiles, most frequent items, joins, matrix computations, and graph analysis. Algorithms that can produce accuracy guaranteed approximate answers for these problem queries are a required toolkit for modern analysis systems that need to process massive amounts of data​ quickly. For interactive queries there may not be other viable alternatives, and in the case of real­-time streams, these specialized algorithms, called stochastic, s​treaming, sublinear algorithms,​ or 's​ketches',​ are the only known solution. This technology has helped Yahoo successfully reduce data processing times from days to hours or minutes on a number of its internal platforms and has enabled subsecond queries on real-time platforms that would have been infeasible without sketches. This article provides a short introduction to sketching and to DataSketches, an open source library of a core set of these algorithms designed for large production analysis systems.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1007", "audienceId": "", "typeId": "2", "locationId": "1008", "speakerIds": [ "1174" ], "languageId": "1" }, { "id": "1182", "start": "2019-09-11T16:45:00", "end": "2019-09-11T17:35:00", "title": "Samza 1.0: How we scaled stream processing at LinkedIn", "abstractText": "'At LinkedIn, we generate a staggering 2 trillion events to Kafka each day. nThe ingested events are processed by our streaming platform powered by Apache Samza. nWe currently have over 3000 applications in production that leverage Samza at LinkedIn. nThe use-cases include the LinkedIn feed, anomaly detection, combating fraud, profile notifications, realtime analytics and many more. In this talk, we will describe our journey in building and scaling a distributed stream nprocessing system over these years. Drawing from our experience running 24x7 applicationsnat LinkedIn, we motivate the key-challenges common across them, how we naddressed them and the lessons learnt along the way. Specific challenges include - massive scale, accuracy of results, multi-language support, ndeveloper productivity, high-performance data-access and fast recovery. Lastly, we will nalso share strategic areas for our future work in stream processing.'", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1007", "audienceId": "", "typeId": "2", "locationId": "1008", "speakerIds": [ "1175" ], "languageId": "1" }, { "id": "1183", "start": "2019-09-11T17:45:00", "end": "2019-09-11T18:35:00", "title": "Apache ECharts (incubating): Web-based Interactive Big Data Visualization", "abstractText": "Data visualization is a challenging job to do in the Web-based environment due to the limited rendering efficiency of Web browsers. Rendering big data and providing user interaction in real time is even more challenging. nIn this speech, we are going to introduce how we made this possible with ECharts, a popular Web-based data visualization tool. Generally speaking, the solution lies in the following four aspects:n1. Simplifying shapes and rendering faster but with a similar result.n2. Optimizing code to improve rendering efficiency.n3. Applying stream rendering to give viewers a partial response as soon as possible.n4. Split data into several files and render in a pipeline to speed up rendering.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1007", "audienceId": "", "typeId": "2", "locationId": "1008", "speakerIds": [ "1176" ], "languageId": "1" }, { "id": "1184", "start": "2019-09-11T12:00:00", "end": "2019-09-11T12:50:00", "title": "Game Changing Operational Visibility tools in Apache Cassandra 4.0", "abstractText": "In this talk, we will review the new and upcomming tools for Apache Cassandra operations. This talk will go over some of the new and soon to be tools for operational visibility. Specific areas covered will include:n- Different operational tasks will be exposed with an HTTP interface with the sidecarn- Virtual tables provides visibility to the state of a node with cqlshn- New commands added to nodetool and JMX See how these improvements and additions will give operation teams faster diagnostics to assist in discovering problematic clients and data models.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1001", "audienceId": "", "typeId": "2", "locationId": "1010", "speakerIds": [ "1177" ], "languageId": "1" }, { "id": "1185", "start": "2019-09-11T16:45:00", "end": "2019-09-11T17:35:00", "title": "Combining schema-on-read and schema-provisioning in Apache Drill", "abstractText": "The data generated from IoT devices, machine logs and similar sources is often semi-structured or unstructured. This poses a challenge for traditional schema-on-write systems that require a fixed schema up-front for querying. Modern analytic applications often have ad hoc usage patterns and require tremendous flexibility over how this data can be consumed. Further, they demand that the data be made available for querying soon after it has landed in their data platform – which may be a distributed file system or NoSQL database or something similar. In this talk I will first describe how Apache Drill’s innovative schema-on-read capability built into a distributed SQL query engine meets the demands of such applications. The raw data in various formats can be queried directly from either the distributed file system or other data sources such as NoSQL DBs without having to define a schema up-front. The Drill query planner (in conjunction with Apache Calcite) supports the ‘ANY’ type for columns which allows type validations. During execution, readers produce ‘RecordBatches’ where all rows in one RecordBatch have the same schema but across batches the schema may change. This provides the core foundation for the schema-on-read capability. Downstream SQL operators in the query pipeline perform run-time Java code generation by generating schema specific code. This code is compiled and executed on the JVM and based on this the operator produces output batches. In cases where Drill is not able to infer the schema correctly or when there are ambiguities, Drill has introduced schema provisioning to complement the schema-on-read. I will describe the functionality to define columns types and nullability, specify columns format and default values and control which columns are projected and their projection order. The schema can be specified declaratively as part of the query or in a separate file. Our expectation is that these complementary strategies will meet the demands of the modern analytic applications that require schema flexibility in addition to performance and scalability. ", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1003", "audienceId": "", "typeId": "2", "locationId": "1014", "speakerIds": [ "1178" ], "languageId": "1" }, { "id": "1186", "start": "2019-09-12T10:00:00", "end": "2019-09-12T10:50:00", "title": "OFBiz in the fashion Industry, an omnichannel approach", "abstractText": "The fashion industry works to meet the demand for apparel and dictates thentrends for what should be worn.nThis presentation will describe why Apache OFBiz is a great platform fornbuilding an ERP for the fashion industry and how it can be enhanced tonsupport its specific requirements. The various implementation steps of anconcrete project will be reviewed:n- Development of a custom eCommerce/B2B Responsive and Seo compliantnapplication using the Color-Size matrix feature.n- Integration of third-party applications such as retail, legacy Erp,nsocial network, WMS, Business Intelligence, mailing system.n- 'Soft migration'. Progressive replacement of the external proprietarynsystem with OfBiz. The result is an OfBiz-centric, holonic Erp system.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1019", "audienceId": "", "typeId": "2", "locationId": "1005", "speakerIds": [ "1179" ], "languageId": "1" }, { "id": "1187", "start": "2019-09-12T13:00:00", "end": "2019-09-12T13:50:00", "title": "Kafka, Cassandra and Kubernetes at Scale - Real-time Anomaly detection on 19 billion events a day", "abstractText": "Apache Kafka, Apache Cassandra and Kubernetes are open source big data technologies enabling applications and business operations to scale massively and rapidly. While Kafka and Cassandra underpins the data layer of the stack providing capability to stream, disseminate, store and retrieve data at very low latency, Kubernetes is a container orchestration technology that helps in automated application deployment and scaling of application clusters. In this presentation, we will reveal how we architected a massive scale deployment of a streaming data pipeline with Kafka and Cassandra to cater to an example Anomaly detection application running on a Kubernetes cluster and generating and processing massive amount of events. Anomaly detection is a method used to detect unusual events in an event stream. It is widely used in a range of applications such as financial fraud detection, security, threat detection, website user analytics, sensors, IoT, system health monitoring, etc. When such applications operate at massive scale generating millions or billions of events, they impose significant computational, performance and scalability challenges to anomaly detection algorithms and data layer technologies. We will demonstrate the scalability, performance and cost effectiveness of Apache Kafka, Cassandra and Kubernetes, with results from our experiments allowing the Anomaly detection application to scale to 19 Billion anomaly checks per day.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1001", "audienceId": "", "typeId": "2", "locationId": "1010", "speakerIds": [ "1031" ], "languageId": "1" }, { "id": "1188", "start": "2019-09-12T14:00:00", "end": "2019-09-12T14:50:00", "title": "Reduce your Storage Costs with Transient Replication and Cheap Quorums", "abstractText": "nIn eventually consistent systems, when a node failures or network partition occurs, we’re presented with a trade-off: to execute a request and sacrifice consistency or reject execution and sacrifice availability. In such system, quorums, overlapping node subsets guaranteeing at least one node to hold the most recent value, can be a good middle-ground. We can tolerate failures and loss of connectivity for some nodes while still serving latest results. Quorum-based replication schemes incur high storage costs: we have to store redundant values on several nodes to guarantee enough copies are going to be available in case of failure. It turns out that we do not have to store data on each replica. We can reduce storage and compute resources by storing the data only a subset of nodes, and only use the other nodes (Transient Replicas), for redundancy in failure scenarios. In this talk, we discuss Witness Replicas, a replication scheme used in Spanner and Megastore, and Apache Cassandra implementation of this concept, called Transient Replication and Cheap Quorums. (edited) ", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1001", "audienceId": "", "typeId": "2", "locationId": "1010", "speakerIds": [ "1180" ], "languageId": "1" }, { "id": "1189", "start": "2019-09-12T17:30:00", "end": "2019-09-12T18:20:00", "title": "Building Zhaopin's enterprise event bus based on Apache Pulsar", "abstractText": "Zhaopin.com is a Chinese online recruitment services provider. As a bilingual job board, Zhaopin.com has one of the largest selections of real-time job vacancies in China. All recruitment advertisements are provided by prominent Chinese and foreign companies and enterprises throughout China. Zhaopin.com provides professional HR services to over 2.2 million clients and its average daily page views are over 68 million.nApache Pulsar was developed to address several shortcomings of existing messaging systems including a lot of enterprise features, message durability, and lower message latency. Zhaopin.com had built its enterprise event bus By using RabbitMQ for years. As the company grows, the amount of its data is getting larger and larger, and the usage scenarios of message systems are also become varied. The original RabbitMQ based architecture was hard to afford. Ultimately, it chose Apache Pulsar to replace RabbitMQ based architecture in 2018. Since Apache Pulsar was deployed at August 2018, The data amount in Pulsar is increased from 30 million messages per day to 6 billion+ messages. By learning from a lot of practical experiences, they summarised the best practices to using Pulsar as an enterprise event bus. Penghui and Jia detail how Apache Pulsar meet the requirements from Zhaopin.com. How Apache Pulsar is used in Zhaoping.com, and What is the best practices to using Pulsar as an enterprise event bus. Along the way, they will highlight the advantages of Apache Pulsar over the old system, and how high durability, high throughput and low latency of Apache Pulsar make it ideally suited for enterprise event bus.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1007", "audienceId": "", "typeId": "2", "locationId": "1014", "speakerIds": [ "1181", "1182" ], "languageId": "1" }, { "id": "1190", "start": "2019-09-12T10:00:00", "end": "2019-09-12T10:50:00", "title": "Streamlining Streaming System Management with Apache Heron", "abstractText": "Apache Heron (Incubating) is a real-time, distributed, fault-tolerant stream processing engine. In 2018 it was donated to the Apache Foundation and is used for processing data sets in a way that allows systems to react to data as it is created. The big data era is here and it has become more critical than ever that organizations are able to make decisions based on the data they own in an efficient and accurate way. However, making this data available when and where it is needed can be problematic for organizations, product managers, and development teams across the globe. This is where data streaming steps in. The streaming system approach comes with both advantages and disadvantages. Heron assists with managing the pain points of streaming by relieving the developer from needing to manually intervene in many cases. Heron provides a way to build better distributed systems by implementing a process based architecture built in modern programming languages. We will walk through how Heron can assist organizations to build these systems with specific focus on use cases, system architecture, and system observability.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1007", "audienceId": "", "typeId": "2", "locationId": "1014", "speakerIds": [ "1183" ], "languageId": "1" }, { "id": "1191", "start": "2019-09-12T13:00:00", "end": "2019-09-12T13:50:00", "title": "One SQL to Rule Them All – a Syntactically Idiomatic Approach to Management of Streams and Tables", "abstractText": "Apache Calcite is a data management framework that includes a SQL parser and query optimizer. It is used by many projects that implement SQL processing capabilities, including Apache Beam and Apache Flink. Over the last years, members of these three communities had many discussions about the semantics and syntax of 'Streaming SQL'. End of last year, we decided to formalize and summarize our views and ideas in paper that we submitted to the Industrial Track of the SIGMOD 2019 conference. The paper got accepted (http://sigmod2019.org/sigmod_industry_list). It presents a three-part proposal for integrating robust streaming into SQL, namely: n(1) time-varying relations as a foundation for classical tables as well as streaming data,n(2) event time semantics, n(3) a limited set of optional keyword extensions to control the materialization of time-varying query results. The paper shows how with these minimal additions it is possible to utilize the complete suite of standard SQL semantics to perform robust stream processing and motivates and illustrate these concepts using examples and describe lessons learned from implementations in Apache Calcite, Apache Flink, and Apache Beam. In this talk, we present our 'Syntactically Idiomatic Approach to Manage Streams and Tables'.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1007", "audienceId": "", "typeId": "2", "locationId": "1014", "speakerIds": [ "1023", "1184" ], "languageId": "1" }, { "id": "1192", "start": "2019-09-12T14:00:00", "end": "2019-09-12T14:50:00", "title": "Interactive querying of streams using Apache Pulsar", "abstractText": "As applications become more reliant on real-time data, streaming/messaging platforms have become more and more popular and crucial to any data pipeline. Currently, many streaming/messaging platforms are only used to access the most recent events from streams of data, however, there is tremendous value that can be unlocked if the full history of streams can be queried in an interactive fashion. Pulsar SQL is a query layer built on top of Apache Pulsar (a next-gen messaging platform), that enables users to dynamically query all streams, old and new, stored inside of Pulsar. Thus, users can unlock insights from querying both new and historical streams of data in a single system. Pulsar SQL leverages Presto and Apache Pulsar’s unique architecture to execute queries in a highly scalable fashion regardless of the number of partitions of topics that make up the streams. In this talk, we will examine the use cases and advantages of being able to interactively query events within an streaming messagingnplatform and how Pulsar enables users to do that in the most user-friendly and efficient manner.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1007", "audienceId": "", "typeId": "2", "locationId": "1014", "speakerIds": [ "1185" ], "languageId": "1" }, { "id": "1193", "start": "2019-09-12T15:30:00", "end": "2019-09-12T16:20:00", "title": "Serverless Event Streaming with Pulsar Function: Use Cases and Best Practices", "abstractText": "As data continues to evolve, there are more and more requirements for calculating data. From servers to VMS to containers to serverless, the computing framework is constantly evolving with the needs of users. How to provide users with a fast, easy-to-deploy computing framework has become a question for everyone to think about. In this talk, we will introduce how Pulsar provides a powerful computing power based on the serverless computing architecture. Apache Pulsar is a new generation of cloud messaging system and real-time processing platform. The message system is closely related to the real-time computing platform, but it is often loosely deployed and managed separately. Pulsar Functions, as the computing component of Pulsar, is a fusion and innovation of the message and computing platform in the serverless direction. Pulsar Functions provides support for multiple languages such as Go, Python, and Java; and runtimes such as Thread, Process, and Kubernetes. This provides great flexibility for user-written, run, and deploy features. Let users only use logic that cares about real calculations, without complicated configuration or management; it is easier to build a message-triggered flow platform.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1007", "audienceId": "", "typeId": "2", "locationId": "1014", "speakerIds": [ "1186" ], "languageId": "1" }, { "id": "1194", "start": "2019-09-12T16:30:00", "end": "2019-09-12T17:20:00", "title": "Event Sourcing with Spring Boot and Apache Kafka", "abstractText": "In our global economy, businesses must be nimble and often have to adapt quickly. As a result, many businesses structure their teams in an Agile way to keep up with this demand. With Domain Driven Design, it’s possible to quickly modify applications to accommodate changing business needs and easily integrate with disparate third-party systems. But what if you were able to use historical data and analytics to enhance your applications capabilities? You may not always have all the necessary information in your CRUD database. With Event Sourcing, you are able to store new application events as well as existing events resulting in more robust applications. This makes it possible to change your application in ways you have never imagined before! This talk will show you how you can design your Event Sourcing based application with Spring Boot and Apache Kafka.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1007", "audienceId": "", "typeId": "2", "locationId": "1014", "speakerIds": [ "1187" ], "languageId": "1" }, { "id": "1195", "start": "2019-09-12T09:00:00", "end": "2019-09-12T09:50:00", "title": "Spoilt for Choice – Kafka Streams vs. KSQL for Stream Processing on top of Apache Kafka", "abstractText": "Apache Kafka is a de facto standard streaming data processing platform. It is widely deployed as event streaming platform. Part of Kafka is its stream processing API “Kafka Streams”. In addition, the Kafka ecosystem now offers KSQL, a declarative, SQL-like stream processing language that lets you define powerful stream-processing applications easily. What once took some moderately sophisticated Java code can now be done at the command line with a familiar and eminently approachable syntax.nThis session discusses and demos the pros and cons of Kafka Streams and KSQL to understand when to use which stream processing alternative for continuous stream processing natively on Apache Kafka infrastructures. The end of the session compares the trade-offs of Kafka Streams and KSQL to separate stream processing frameworks such as Apache Flink or Spark Streaming.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1007", "audienceId": "", "typeId": "2", "locationId": "1014", "speakerIds": [ "1103" ], "languageId": "1" }, { "id": "1196", "start": "2019-09-12T14:00:00", "end": "2019-09-12T14:50:00", "title": "Hadoop Submarine Ecosystem: Bringing Machine Learning and Big Data world (YARN and Kubernetes) together ", "abstractText": "'Data Scientists focuses on developing ML models with applications such as TensorFlow / MXNet / Caffe / XGBoost and do not deep dive into the complexities of computing and storage to run ML/DL jobs. Today’s most of ETL processed data are stored in HDFS and cloud, and leveraging this data to design strong ML models is a big challenge for a data scientist. In Big Data ecosystem, most of the ETL and batch jobs are running on Spark and Hive which process/ingest data to the same data stores. Data scientists find this challenging in order to effectively utilize these big data workloads to develop an effective ML model. Hadoop Submarine (https://hadoop.apache.org/submarine/) helps to bring these two worlds together and provides seamless integration across. Ecosystem around Hadoop Submarine helps to design and run ML workloads from a notebook. Integrations with notebook such as Zeppelin and workflow scheduler like Azkaban, helps user to consume data from spark or hive and effectively run ML jobs with ease on any compute cluster. In this deep dive session, we will demo the simplicity of Submarine by running distributed deep learning/machine learning applications on YARN and Kubernetes as simple as running it locally. We will also showcase the community effort in developing Submarine’s ecosystem which eases integrations with Zeppelin and Azkaban. Submarine project could easily launch in the same cluster to run DL/ML jobs without any additional upgrades or complexities of having different machines.n'", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1013", "audienceId": "", "typeId": "2", "locationId": "1008", "speakerIds": [ "1047", "2053" ], "languageId": "1" }, { "id": "1197", "start": "2019-09-09T09:00:00", "end": "2019-09-09T09:50:00", "title": "From (Single) ISP-CDN - To Multi-ISP CDN", "abstractText": "'Traffic-control was built as an ISP CDN, serving content within a single ISP. Using traffic-control for creating a multi-ISP CDN, puts up challenges in various aspects: starting from the deployment of the different TC components outside of the ISPs, towards the isolation between different ISPs, as well as self-service, dealing simultaneously with different structures of ISP networks, the changing popularity of content in different ISP etc. In this session we would like to described few of the above challenges, as well as the derived traffic-control components requirements, flexibility and modularity.'", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1017", "audienceId": "", "typeId": "2", "locationId": "1003", "speakerIds": [ "1188" ], "languageId": "1" }, { "id": "1198", "start": "2019-09-09T14:00:00", "end": "2019-09-09T14:50:00", "title": "Let's Encrypt Apache Traffic Control", "abstractText": "Let's Encrypt is a free, automated certificate authority (CA) which is open for use to anyone who owns a domain name. Using Traffic Router as the DNS, we have integrated with Let's Encrypt when utilizing HTTPS on the delivery service domains. Many open source projects provide libraries to ease implementation of Let's Encrypt, and for this project we used go-acme/lego (MIT licensed) to integrate with the Traffic Ops Golang API. Integration with Let's Encrypt provides many advantages including saving money by using a completely free CA, saving time with automation including certificate renewal, and improving reliability by eliminating manual intervention for certificate generation and deployment.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1017", "audienceId": "", "typeId": "2", "locationId": "1003", "speakerIds": [ "1189" ], "languageId": "1" }, { "id": "1199", "start": "2019-09-10T17:00:00", "end": "2019-09-10T17:50:00", "title": "Processing CDN Logging Events at Scale", "abstractText": "'Content Delivery Networks generate staggering amounts of event data at a rate that is exponentially increasing in line with the explosion of IP video. Managing this deluge with the usual suspects of Big Data platforms presents a formidable challenge, particularly in light of the often-competing goals of detailed troubleshooting investigation versus big picture analytics and machine learning. This presentation will explore capturing and processing events from the largest production deployment of Apache Traffic Server and Apache Traffic Control. We will examine some of the drawbacks of standard approaches, including Splunk, the Elastic stack, Hadoop, and time series and OLAP datastores. This will be followed by a deep dive into Comcast’s rapidly evolving MAPLE platform. MAPLE leverages the open source Clickhouse “warp speed” database, along with Apache staples Kafka and Zookeeper, to collect and transform more than two million CDN events per second. This firehose of data is available within seconds at both an individual event and aggregate level for alerting, troubleshooting, analytics, and machine learning.n'", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1017", "audienceId": "", "typeId": "2", "locationId": "1003", "speakerIds": [ "1190" ], "languageId": "1" }, { "id": "1200", "start": "2019-09-09T10:00:00", "end": "2019-09-09T10:50:00", "title": "A Mile in My Shoes: How Empathy & Compassion Can Transform Your Work & Your Life", "abstractText": "In many places, we're told to 'leave our emotions out of it,' in our work, and in our other technical endeavors, including in open source communities. But that is an irrational, dangerously naïve point of view, one that often leads us to not concern ourselves with the feelings of others, thereby allowing biases (intended or not) to come into play. This harms our communities, by excluding valuable contributors, and their skills and ideas. Empathy and compassion are powerful tools. Taking the time to understand the though processes of another person, and the variety of struggles that we all have, lets you serve them, collaborate with them, and lead them more effectively than you've ever done before. In this talk, you'll learn the science behind these powerful emotions, and how using them can help you build stronger, more inclusive communities. Empathy and compassion have the power to enrich your life, and that of the people you interact with ever day. Come learn how you can use these vital skills to work more effectively and transform your world into a more caring, open, and peaceful place to be. ", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1008", "audienceId": "", "typeId": "2", "locationId": "1000", "speakerIds": [ "1191" ], "languageId": "1" }, { "id": "1202", "start": "2019-09-12T10:00:00", "end": "2019-09-12T10:50:00", "title": "Enterprise Hybrid Mobile App Development", "abstractText": "This session shows how to develop and run native mobile apps without needing to know much about the native platforms, such as Android and iOS, by leveraging a hybrid development framework such as Apache Cordova, which is capable of transforming an ordinary web app into a mobile app. The presentation discusses a real-life enterprise-level Android and iOS mobile app developed under pressure for a wireless service provider. It covers some of the technical details of the app as well as how to perform device-level debugging of the Android app, using adb. You’ll get practical tips on what to watch out for and compare the hybrid approach to React and Kotlin/Native", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1018", "audienceId": "", "typeId": "2", "locationId": "1009", "speakerIds": [ "1192" ], "languageId": "1" }, { "id": "1203", "start": "2019-09-12T13:00:00", "end": "2019-09-12T13:50:00", "title": "Advanced Apache Cordova Development", "abstractText": "Apache Cordova is a platform for building mobile apps using common Web technologies (HTML, CSS and JavaScript). Apache Cordova offers a set of APIs that allow the mobile app developers to utilize mobile native functions such as (Audio, Camera, Contacts …etc) using JavaScript. This session discusses and demonstrates the advanced aspects of Apache Cordova. Advanced aspects include extending Apache Cordova framework by creating custom plugins in order to access more device hardware features. Advanced aspects also include empowering Apache Cordova apps with Push notifications and Cloud services. Finally, this session demonstrates the power of automated JavaScript unit testing for producing quality Apache Cordova apps.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1018", "audienceId": "", "typeId": "2", "locationId": "1009", "speakerIds": [ "1043" ], "languageId": "1" }, { "id": "1205", "start": "2019-09-12T15:30:00", "end": "2019-09-12T16:20:00", "title": "The Power of Plugins - Developing plugins for Apache Cordova", "abstractText": "Plugins are the powerhouse inside Apache Cordova applications, this isnwhere all native functionality is exposed, and your mobile app trulynbecomes hybrid. We will explore the full scope of plugins in ApachenCordova, not just how they work, but how they are created, installed,ndiscovered and distributed. We will deep dive into concrete examples tondemonstrate the power of plugins.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1015", "audienceId": "", "typeId": "2", "locationId": "1009", "speakerIds": [ "1194" ], "languageId": "1" }, { "id": "1206", "start": "2019-09-12T16:30:00", "end": "2019-09-12T17:20:00", "title": "OpenWhisk and Kubernetes based Mobile Backend as a Service", "abstractText": "So you've been hearing a lot of buzz about Serverless tech in conjunction with Containers and Mobile, but what exactly is the OpenWhisk in reference to Kubernetes? Come find out at this session. Serverless has become the new style of coding, and it might be perfect to offload your mobile apps, and container based systems without incurring unnecessary costs.nGet an intro into serverless/function-as-a-service/cloud native technologies in the Mobile-Backend-as-a-Service (MBaaS) context and learn why startups and enterprises are so excited about using it. We will be demoing Serverless and containers in Swift and iOS, and in Java for Android, and covering the following:n- Who are the players in the serverless ecosystemn- What are some use cases for serverless and container based solutions - with MBaaS as one of themn- Best practices for the serverless with the container system architecture for MBaaSn- If going serverless is really faster, better, cheaper for developers and organizationsn- Live coding examples using Swift and Java ", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1018", "audienceId": "", "typeId": "2", "locationId": "1009", "speakerIds": [ "1195" ], "languageId": "1" }, { "id": "1207", "start": "2019-09-12T17:30:00", "end": "2019-09-12T18:20:00", "title": "Tips and Tricks - Getting the most out of Apache Cordova", "abstractText": "Mobile development is hard, no matter what tools you use. With thenmultitude of devices out there how can you maximize the chance to delightnyour users? Jesse has been actively contributing to hybrid mobilendevelopment projects and writing hybrid mobile apps for 10 years and willnshare his bag of tricks. Learn best practices so you can optimize yournworkflow, and develop the best possible mobile applications.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1018", "audienceId": "", "typeId": "2", "locationId": "1009", "speakerIds": [ "1194" ], "languageId": "1" }, { "id": "1208", "start": "2019-09-12T14:00:00", "end": "2019-09-12T14:50:00", "title": "Apache Karaf on cloud, the kloud initiative", "abstractText": "Apache Karaf has been seen for a while as an applications server. If it's actually the case for the standard distribution, it's very easy to create a Karaf powered standard/immutable distribution embedding your applications. In combination with other Karaf subprojects (Decanter, Cave, ...), it provides a perfect applications runtime for the cloud.nThis talk will show how to start and focus on business code and then generate different distribution packages, up to a docker image ready to run on cloud.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1004", "audienceId": "", "typeId": "2", "locationId": "1005", "speakerIds": [ "1196" ], "languageId": "1" }, { "id": "1209", "start": "2019-09-12T15:30:00", "end": "2019-09-12T16:20:00", "title": "Serverless: Multi-tenant Rule Engine Service Powered by Apache Karaf", "abstractText": "The Netflix media pipeline processes thousands of new shows and movies every day so that you can watch them on any device anywhere. We use a forward chaining rule engine to coordinate all of this work in multiple workflows. Hosting these workflows in a reliable, scalable and cost effective manner is a huge challenge at our scale. In this talk, we will introduce the design of Netflix’s next generation rule engine framework. The goal is to boost modularity, increase developer productivity and decrease operational overhead. The new system is a platform as a service that lets workflow developers focus on workflow data model, execution conditions, and remote function invocations without worrying about how to deploy, scale, and monitor it. The system uses the OSGI framework to build separation among workflows and leverages Apache Karaf as the runtime container. Other interesting topics such as workflow bundle management and a novel rule domain specific language will be covered in this talk. Keywords:nRule engine, OSGI, Apache Karaf, Serverless", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1004", "audienceId": "", "typeId": "2", "locationId": "1005", "speakerIds": [ "1197", "1198", "1199" ], "languageId": "1" }, { "id": "1210", "start": "2019-09-12T16:30:00", "end": "2019-09-12T17:20:00", "title": "Customer segmentation and personalization in websites/PWAs using Apache Unomi", "abstractText": "In this session, you will learn all that’s new with Apache Unomi, the open source Customer Data platform (that graduated this year) based on the Apache Karaf runtime, and all that’s happened since the last ApacheCon. You will discover how to easily integrate it with an existing website or SPA/PWA using its built-in web tracker, how to build customer segments and how to use the API to personalize the experience for your users. You’ll also learn how you can extend it to do almost anything, using either the built-in rules engine or your own plugins. You will also discover the new Docker compatibility and the upcoming GraphQL API. Finally, you’ll learn what’s next and how you can help the project.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1004", "audienceId": "", "typeId": "2", "locationId": "1005", "speakerIds": [ "1083" ], "languageId": "1" }, { "id": "1211", "start": "2019-09-10T18:00:00", "end": "2019-09-10T18:50:00", "title": "Testing Contributions at Scale", "abstractText": "Time may be one of the most valuable resources in a project. Automating code reviews to allow for other tasks is a crucial goal for many communities. This talk will cover one way many Apache projects have significantly increased code quality and contribution feedback while simultaneously doing more with less.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1016", "audienceId": "", "typeId": "2", "locationId": "1000", "speakerIds": [ "1200" ], "languageId": "1" }, { "id": "1212", "start": "2019-09-10T12:15:00", "end": "2019-09-10T13:05:00", "title": "Peeking Behind the Curtain: The Anatomy of a Real Major Incident", "abstractText": "Failures are inevitable. But when they occur, our goal should be to resolve them as quickly and efficiently as possible. PagerDuty has developed an open-source Incident Response framework based on the Incident Command System (ICS). That product-independent process has helped many organizations set up Incident Response processes that resolve technical issues as quickly and effectively as possible. There's a lot of documentation you can follow, but how do incidents actually play out in real-time when they happen? In this talk, you get to peek behind the curtain to see what happens inside the walls of the company that's known for waking you up to tell you there's a technical incident you need to deal with. We will walk through a cascading failure that happened when unexpected errors were found happening in one of our Kafka clusters. I share all the gritty details of this actual incident, as they occurred, and use that as a way to demonstrate the structure of how we apply ICS to resolving technical problems. Attendees of this talk will walk away with an understanding of how to effectively manage complex technical incidents across multiple teams, the additional roles that are necessary to support technical responders, how to structure a blameless post-mortem, and how to start developing a similar process in their own organizations. This talk delves into technical concepts due to the nature of the problem, but it is mostly focused on the mechanics of managing any technical incident.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1016", "audienceId": "", "typeId": "2", "locationId": "1000", "speakerIds": [ "1201" ], "languageId": "1" }, { "id": "1213", "start": "2019-09-09T09:00:00", "end": "2019-09-09T09:50:00", "title": "New Features of Apache RocketMQ", "abstractText": "In the past year, Apache RocketMQ has released a series of new features including transactional messages, ACLs, message track, multiple replicas storage, and multi-language clients. These features are all from contributors from many companies. nThis talk is not only about bringing technical analysis related to these new features, but also will share how to collaborate on the development of important features in the community, which is very important for Apache.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1016", "audienceId": "", "typeId": "2", "locationId": "1000", "speakerIds": [ "1202", "1203" ], "languageId": "1" }, { "id": "1214", "start": "2019-09-09T16:30:00", "end": "2019-09-09T17:20:00", "title": "Java + Serverless - Finally a match made in Heaven?", "abstractText": "Why isn’t Java a more popular language for serverless developers? How does Apache Openwhisk work with Java? Despite there being 10 million Java developers, Java is being used for only 6% of serverless workloads according to a recent survey. Historical problems with long cold-starts, heavy-weight frameworks and lack of tooling have made Java an unpopular choice for serverless development…. until now! In this session, I will take you on a journey to explain what has changed with Java to finally make it an amazing language for building serverless applications, using the open source Apache Openwhisk platform! In this session, we cover these topics including… Previous issues Java developers faced using serverless platformsnWhy JVMs struggled with serverless execution environments.nWhat makes Serverless Java now possible:nJVM advancesnLow-overhead, serverless ready frameworksnAOT (ahead of time) compilation and no-VM binariesnThis session will end with an earth-shaking demo: a full Java application that includes ORM, Dependency Injection, Annotations, etc, that starts in less than 50ms!", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1016", "audienceId": "", "typeId": "2", "locationId": "1000", "speakerIds": [ "1204" ], "languageId": "1" }, { "id": "1300", "start": "2019-09-11T09:00:00", "end": "2019-09-11T09:30:00", "title": "Keynote: Yes, You Could Help Build the Next Disruptor!!", "abstractText": "Samaira's captivating and interactive talk will focus on the power within each of us that would help to nurture the next disruptor. She opens the talk with how all of us have grown so accustomed to technology, like our phones, for our day to day life. But reminds us that technology is not the future, people are the future. Each of us has superpowers that can bring and develop change agents and disruptors. She will talk about her journey that made her CEO at the age of 7. Her journey is full of success and failure stories, all of which are basic ingredients of learning and bringing out best inside us. Come and be inspired by Samaira Mehta, the 11-year-old Entrepreneur.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "11", "locationId": "1000", "speakerIds": [ "2002" ], "languageId": "1" }, { "id": "1301", "start": "2019-09-11T09:30:00", "end": "2019-09-11T10:00:00", "title": "My personal journey to Open Source", "abstractText": "Abstract: I’ve been involved in what is now called Open Source since the 70s, long before the term was coined. My attitudes toward open source, and the Apache approach to it, have been formed by a series of experiences. This talk will be a combination of stories and philosophy.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "11", "locationId": "1000", "speakerIds": [ "2003" ], "languageId": "1" }, { "id": "1302", "start": "2019-09-11T15:15:00", "end": "2019-09-11T16:05:00", "title": "Mythbusting with Apache Cassandra", "abstractText": "As a mature operational database with a 10+ year history as an Apache project, Cassandra has a long history with many twists and turns. In this talk, we’ll look at common misgivings and misunderstandings that we encounter in conversations with developers and get to the bottom of the story:\n\n- Cassandra is a “columnar” (or “column-oriented”) database.\n- Porting my relational data model to Cassandra will work well.\n- Cassandra is a niche database that is only good for narrow set of use cases.\n- My application can’t tolerate eventual consistency.\n- Cassandra counters are unreliable.\n- Never use materialized views or secondary indexes in production", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1001", "audienceId": "", "typeId": "11", "locationId": "1010", "speakerIds": [ "2006" ], "languageId": "1" }, { "id": "1304", "start": "2019-09-11T11:00:00", "end": "2019-09-11T11:50:00", "title": "Portable Spark Runner: Running Beam Pipelines Written in Python and Go with Spark", "abstractText": "Apache Spark is the most popular open source analytics engine for large-scale data processing. Spark is not only a mature system, but thanks to its support of multiple resource managers like Hadoop, Mesos, and Kubernetes it has become a popular choice for both batch and streaming workloads in the industry. Apache Beam has included a Spark runner since its inception to allow users to execute Beam pipelines on Spark, but until recently the Spark runner could only execute pipelines written in Java. In this talk we will introduce the portability framework and how we adapted it into the existing Spark runner translation to make the Spark runner portable. We will show you how to execute Beam pipelines written in Python and Golang in Spark with Beam and invite you to use the new Spark Portable Runner. We will mention the use case of Tensorflow Extended, the end-to-end platform for data validation and transformation and ML model analysis. Finally we will discuss ongoing work and some future plans for the portable runner.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1020", "audienceId": "", "typeId": "11", "locationId": "1003", "speakerIds": [ "2007", "2008" ], "languageId": "1" }, { "id": "1305", "start": "2019-09-11T12:00:00", "end": "2019-09-11T12:50:00", "title": "Friendlier Communities Through Infrastructure: Apache Beam’s Journey", "abstractText": "In this talk we will discuss the infrastructure Apache Beam has built to create a positive contributor experience. Over the last few years we have developed tooling, refactored code, instrumented Jenkins builds, collected metrics, created a metrics dashboard, and involved the community in order to ensure happy contributors. We will discuss the importance of engineering productivity and tooling in developing strong communities, where we have succeeded, and where we still have work to do. ", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1020", "audienceId": "", "typeId": "11", "locationId": "1003", "speakerIds": [ "2009", "2010" ], "languageId": "1" }, { "id": "1306", "start": "2019-09-12T14:00:00", "end": "2019-09-12T14:50:00", "title": "Using the Timer and State API to solve times series use case in Apache Beam", "abstractText": "Time series processing requires ordered processing of data points, often across windows boundaries. Tricky stuff for distributed processing systems, in this chat we look at how to solve for these problems using a combination of Global Windows, State and the Timer API' with Apache Beam.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1020", "audienceId": "", "typeId": "11", "locationId": "1003", "speakerIds": [ "2055", "1023" ], "languageId": "1" }, { "id": "1307", "start": "2019-09-11T15:15:00", "end": "2019-09-11T16:05:00", "title": "The journey of building a Beam runner based on Spark structured streaming framework", "abstractText": "Apache Beam provides a unified programming model to execute batch and streaming pipelines on all the popular big data engines. The translation layer from Beam to the chosen big data engine is called a runner. The current runner for Apache Spark is based on the RDD/DStream framework. However, there is an ongoing work to move it to Spark next generation framework a.k.a structured streaming. This talk will present why structured streaming is a good fit for Apache Beam, why it is worth the effort, and will give some feedback on how Apache Beam has solved the challenge, what the tough points and the sweet points were.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1020", "audienceId": "", "typeId": "11", "locationId": "1003", "speakerIds": [ "2011" ], "languageId": "1" }, { "id": "1308", "start": "2019-09-11T16:45:00", "end": "2019-09-11T17:35:00", "title": "Developing new IO connectors in Apache Beam", "abstractText": "One of the key components in any data processing system is IO connectors. These fundamental blocks allow to read and write data, which is stored in different type of sources, in a unified and distributed way. In this sense, Apache Beam is not an exception - it provides a rich API to develop a new connector with your favorite SDK and easily integrate it with Beam runners. In this talk we are going to show you how to write your own IO connector (in Java). We will see what are the differences between bounded and unbounded sources, how to implement efficient sources and sinks and where we need to pay more attention during the development, what kind of API your connector should provide to users and how it can be tested. To achieve this we will rely on examples from existing Beam connectors. We will also give a brief overview of a rather recent feature/pattern in Beam IO - Composable IO connectors and the Splittable DoFn API. We will discuss the advantages of modular IO API design and some new IO design patterns allowed by this style. This talk will be interesting for people, who consider to write their own IO connectors or want to contribute to existing ones, as well as for Beam users, who wish to understand how existing Beam connectors work under the hood.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1020", "audienceId": "", "typeId": "11", "locationId": "1003", "speakerIds": [ "2012", "2008" ], "languageId": "1" }, { "id": "1309", "start": "2019-09-11T17:45:00", "end": "2019-09-11T18:35:00", "title": "Simple, Portable data pipelines with Apache Beam SQL", "abstractText": "Apache Beam is a unified data processing framework, allowing you to write batch and streaming pipelines that run anywhere, including Apache Flink, Apache Spark, and Google Cloud Dataflow. With the SQL extension you can now write a pipeline in pure SQL. If you need more, you can write user defined functions in Java or even embed SQL into your existing Java pipeline. This talk will start with a demo pipeline written in pure SQL. We will review how streaming SQL came from collaboration between the Apache Beam, Apache Calcite and Apache Flink communities. Finally, we will deep-dive into the architecture of Beam’s implementation and the work we are doing to make Apache Beam SQL the default choice for writing new streaming pipelines.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1020", "audienceId": "", "typeId": "11", "locationId": "1003", "speakerIds": [ "2013" ], "languageId": "1" }, { "id": "1310", "start": "2019-09-11T11:00:00", "end": "2019-09-11T11:50:00", "title": "Beam Introductory Workshop", "abstractText": "An intro to Beam and hands on exercises writing Beam pipelines. \n\nSuitable for Beginners.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1020", "audienceId": "", "typeId": "11", "locationId": "1004", "speakerIds": [ "2014" ], "languageId": "1" }, { "id": "1311", "start": "2019-09-11T12:00:00", "end": "2019-09-11T12:50:00", "title": "Beam Introductory Workshop", "abstractText": "An intro to Beam and hands on exercises writing Beam pipelines. \n\nSuitable for Beginners.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1020", "audienceId": "", "typeId": "11", "locationId": "1004", "speakerIds": [ "2014" ], "languageId": "1" }, { "id": "1312", "start": "2019-09-11T14:15:00", "end": "2019-09-11T15:05:00", "title": "Beam Introductory Workshop", "abstractText": "An intro to Beam and hands on exercises writing Beam pipelines. \n\nSuitable for Beginners.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1020", "audienceId": "", "typeId": "11", "locationId": "1004", "speakerIds": [ "2014" ], "languageId": "1" }, { "id": "1313", "start": "2019-09-11T15:15:00", "end": "2019-09-11T16:05:00", "title": "Beam Introductory Workshop", "abstractText": "An intro to Beam and hands on exercises writing Beam pipelines. \n\nSuitable for Beginners.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1020", "audienceId": "", "typeId": "11", "locationId": "1004", "speakerIds": [ "2014" ], "languageId": "1" }, { "id": "1314", "start": "2019-09-11T16:45:00", "end": "2019-09-11T17:35:00", "title": "Beam Introductory Workshop", "abstractText": "An intro to Beam and hands on exercises writing Beam pipelines.\n\nSuitable for Beginners.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1020", "audienceId": "", "typeId": "11", "locationId": "1004", "speakerIds": [ "2014" ], "languageId": "1" }, { "id": "1315", "start": "2019-09-11T17:45:00", "end": "2019-09-11T18:35:00", "title": "Beam Introductory Workshop", "abstractText": "An intro to Beam and hands on exercises writing Beam pipelines. \n\nSuitable for Beginners.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1020", "audienceId": "", "typeId": "11", "locationId": "1004", "speakerIds": [ "2014" ], "languageId": "1" }, { "id": "1316", "start": "2019-09-12T09:00:00", "end": "2019-09-12T09:50:00", "title": "Running Apache Flink and Apache Beam on Kubernetes", "abstractText": "Access to real-time data is increasingly important for many organizations. At Lyft, we process millions of events per second in real-time to compute prices, balance marketplace dynamics, detect fraud, among many other use cases. To do so, we run dozens of Apache Flink and Apache Beam pipelines. Flink provides a powerful framework that makes it easy for non-experts to write correct, high-scale streaming jobs, while Beam extends that power to our large base of Python programmers.\nHistorically, we have run Flink clusters on bare, custom-managed EC2 instances. In order to achieve greater elasticity and reliability, we decided to rebuild our streaming platform on top of Kubernetes. In this session, I'll cover how we designed and built an open-source Kubernetes operator for Flink and Beam, some of the unique challenges of running a complex, stateful application on Kubernetes, and some of the lessons we learned along the way.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1020", "audienceId": "", "typeId": "11", "locationId": "1003", "speakerIds": [ "2015" ], "languageId": "1" }, { "id": "1317", "start": "2019-09-12T10:00:00", "end": "2019-09-12T10:50:00", "title": "Driving dynamic Beam pipelines", "abstractText": "Using Apache Beam to get data in your data lake? In a agile company you don’t want to re-compile your ingestion pipeline every time a sprint finished. In this talk we go over all mechanisms and building blocks you need to make dynamic pipelines really work.\n We’ll see why schemas are so important. How do we get these schemas in our pipelines and discuss methods to protect ourselves from data corruption and incompatible schema evolution. \n The new features like schema aware PCollection get a thorough deep dive and finally we go over real world examples and position Apache Beam in the new PLT (Push Load Transform) world.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1020", "audienceId": "", "typeId": "11", "locationId": "1003", "speakerIds": [ "2016" ], "languageId": "1" }, { "id": "1318", "start": "2019-09-12T13:00:00", "end": "2019-09-12T13:50:00", "title": "A Guided Walkthrough of the Apache Beam Go SDK", "abstractText": "This session will walk through the internals of what the Go SDK does to execute a pipeline. Describing the structure of the SDK, where code is located, and the why of the structure, and how it does it with the particular features of the Go language, which notably has strict types but no generics.\nParticular effort will be spent on what the Go SDK does for ease of use, and to reduce DoFn execution overhead.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1020", "audienceId": "", "typeId": "11", "locationId": "1003", "speakerIds": [ "2017" ], "languageId": "1" }, { "id": "1321", "start": "2019-09-12T16:30:00", "end": "2019-09-12T17:20:00", "title": "Samza Portable Runner for Beam", "abstractText": "In this talk we are going to cover how we have leveraged portability of Beam and make Stream Processing in Python possible on top of Apache Samza. We will first touch points on Apache Samza in general, and how it stands out as the stream processing engine at LinkedIn that scales to over a trillion messages processed per day, with strong state support and flexible deployment models. Next we introduce Samza Runner for Beam, particularly the portable runner. We will cover the efforts we have done to leverage Beam and make stream processing in Python available at LinkedIn, followed by a few use cases. The talk will conclude with our plan for future work.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1020", "audienceId": "", "typeId": "11", "locationId": "1003", "speakerIds": [ "2020" ], "languageId": "1" }, { "id": "1322", "start": "2019-09-12T17:30:00", "end": "2019-09-12T18:20:00", "title": "Creating a Stream Data Pipeline on Google Cloud Platform using Apache Beam", "abstractText": "We built a scalable and flexible stream data pipeline for our microservices on Google Cloud Platform (GCP), using Cloud Pub/Sub, Google Cloud Storage, BigQuery, and Cloud Dataflow, using Apache Beam. The stream data pipeline is working on the production system for Mercari, one of the biggest C2C e-commerce services in Japan. The pipeline currently accepts logs from 5+ microservices, and the number will increase soon.\n Our microservice architecture is based on the following three concepts:\n 1. Split the log collection and data processing phases to keep the system simple.\n 2. Use stream processing in order to achieve low latency. \n 3. Don’t just accumulate raw data—support structured output that is easier to use.\n Based on these concepts, we built a data pipeline in GCP.\n For each microservice, we will provide a Cloud Pub/Sub “Ramp” to send logs to. Cloud Pub/Sub can have messages that contain an optional byte array in their payloads. The entire message that is ingested into the Ramp uses Cloud Dataflow streaming processing to collect them in the “RawDataHub,” a Cloud Pub/Sub topic for collection. When this happens, the PubsubMessage payload is not changed at all; the metadata necessary for subsequent processing (destination and schema information, data necessary for pipeline metrics, etc.) is provided in the PubsubMessage’s attribute map. This Dataflow job does not do processing for each service or topic—it treats all messages uniformly.\n The raw data from RawDataHub is then output to two independent Cloud DataFlow streaming processes: “RawDataLake”(the infrastructure is in Google Cloud Storage, or “GCS”) and “StructuredDataHub”, another Cloud Pub/Sub topic. The StructuredDataHub has structured avro records. \n The structured data from StructuredDataHub is then sent to more two independent Cloud DataFlow streaming processes: “StructuredDataLake” on GCS and “Data WareHouse” (Google BigQuery).", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1020", "audienceId": "", "typeId": "11", "locationId": "1003", "speakerIds": [ "2021" ], "languageId": "1" }, { "id": "1323", "start": "2019-09-12T09:00:00", "end": "2019-09-12T09:50:00", "title": "Apache Arrow + Apache Beam: A vision for cross-language, columnar data pipelines, and Large Scale Streaming Analytics with Apache Beam", "abstractText": "Part I:\n\n Apache Arrow and Apache Beam deserve to be together. It is a stated goal of both projects to provide mechanisms for performing data processing tasks across many languages. To accomplish this, both projects define a common binary “model” and provide multiple language implementations of that model. \n However, they are approaching the overarching problem of cross-language data processing from two very different angles: Arrow is primarily concerned with moving columnar data across language boundaries with minimal overhead and providing optimized computation primitives to operate on that data, while Beam seeks to enable users to write scalable data pipelines in their language of choice and execute them on any distributed data-processing system. There is significant overlap between these two problem spaces, and we should consider using these models together for the benefit of both projects. \n In this talk, I will describe both of these projects at a high-level, and present a vision for how they can be used together. I will also discuss some of the concerns around using a batched columnar data format in the Beam model, along with potential solutions.\n\nPart II:\n\nIn this session we will illustrate how Sky moved from an on-premise, batch-focused Hadoop based analytical system, to a streaming-oriented analytics pipeline deployed using Apache Beam and Google Cloud Dataflow. We will go through the architecture of the system, including the design decision made along the way, as well as learnings from the implementation and deployment process. We will end the session with an end-to-end demo and code examples!", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1020", "audienceId": "", "typeId": "11", "locationId": "1004", "speakerIds": [ "2025", "2063" ], "languageId": "1" }, { "id": "1324", "start": "2019-09-12T10:00:00", "end": "2019-09-12T10:50:00", "title": "Stream processing for the masses with Beam, Python and Flink", "abstractText": "Python is a widely used programming language that is characterized by a low barrier to entry. As many other companies in the industry, Yelp has used Python as the main programming language to implement back-end services. Unfortunately, when it comes to stream processing Python presents several challenges, including performance limitations, lack of proper multi-threading support and limited framework options. \n When the use cases for more advanced stream processing started to arise, at Yelp we decided to leverage Flink and introduce a Scala/Java stack for our Data Pipeline. Over the course of two years we built our connector ecosystem in Flink and exposed to developers a very lightweight stream processing API based on Flink SQL. \n While Flink SQL was quickly adopted by our developers, we soon realized that more complex use cases cannot easily be solved in Flink SQL. At the same time, the alternative engineering cost to develop and maintain a complex production application in an unfamiliar JVM based language was not convenient for our product teams. \n At the beginning of the year, we started looking at Apache Beam with the goal of filling the gap between the high level Flink SQL api and the low level advanced Java Flink streaming API. In this talk I’ll cover the motivations and use cases that brought us to adopt Apache Beam, the challenges we faced integrating Beam with an existing Flink infrastructure and the strategy we followed to deploy and productionize at scale.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1020", "audienceId": "", "typeId": "11", "locationId": "1004", "speakerIds": [ "2027" ], "languageId": "1" }, { "id": "1325", "start": "2019-09-12T13:00:00", "end": "2019-09-12T13:50:00", "title": "Apache Beam for production machine learning: Tensorflow Extended (TFX) / Beaming Deep Learning with Ludwig", "abstractText": "Part I\nDeveloping ML and deep learning applications to be deployed in production is much more than just training a model. Google has taken years of experience in developing production ML pipelines and offered the open source community TensorFlow Extended (TFX), an open source version of the ML platform that Google uses internally. Pipeline processing is a core requirement of any production ML platform, and the TFX has chosen Apache Beam to implement their pipeline. \n Learn from Google’s experience in applying Beam for ML pipelines, including how TFX uses Beam and why Beam was chosen.\n \nPart II\nLudwig is a code-free Deep Learning toolbox based on TensorFlow open-sourced by Uber AI Labs. Ludwig is unique in its ability to help make deep learning easier to understand for non-experts and enable faster model improvement iteration cycles for experienced machine learning developers and researchers alike. By using Ludwig, experts and researchers can simplify the prototyping process and streamline data processing so that they can focus on developing deep learning architectures rather than data wrangling. \n Ludwig introduces the notion of data type-specific encoders and decoders, which results in a highly modularized and extensible architecture: each type of data supported (text, images, categories, and so on) has a specific preprocessing function. \n In this talk, we’ll be looking at building Beam pipelines to programmatically create Deep Learning models with Ludwig for different input data types for both model training and inference using Beam-Python SDK. We will be showing 2 examples of training deep learning classifiers with text and images on an unbounded source and running inference on that.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1020", "audienceId": "", "typeId": "11", "locationId": "1004", "speakerIds": [ "2028" ], "languageId": "1" }, { "id": "1326", "start": "2019-09-12T14:00:00", "end": "2019-09-12T14:50:00", "title": "Pricing Lyft rides with Apache Beam - a case study in migrating from a worker-based workflow to streaming", "abstractText": "Ride-sharing is a two-sided marketplace; balancing supply and demand with price in real time is critical to maintaining an efficient system. Dynamic pricing creates fairness for drivers (by raising rates when there is a lot of demand) and maintains good experiences for passengers (by satisfying pick-up time SLAs). This complex system makes real-time decisions using various data sources; machine learning models; and a streaming infrastructure for low latency, reliability and scalability. In this streaming infrastructure, our system consumes a massive number of events from different sources to make these pricing decisions.\n \n Reacting to these events in a cron scheduler based legacy infrastructure with inherent latency becomes a challenge, especially where timely reactions are required to balance market conditions. By leveraging Apache Beam, Lyft’s Streaming Platform powers pricing by bringing together the best of two worlds: ML models in Python and Apache Flink on JVM as the streaming engine.Topics covered in this talk include:\n * A brief discussion of dynamic pricing, including motivation and high-level problem formulation\n * Comparison of legacy architecture and new streaming architecture\n * Overview of streaming platform architecture and technology stack\n * Major gains from streaming architecture\n * Lessons learned ", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1020", "audienceId": "", "typeId": "11", "locationId": "1004", "speakerIds": [ "2029" ], "languageId": "1" }, { "id": "1327", "start": "2019-09-12T15:30:00", "end": "2019-09-12T16:20:00", "title": "Writing the Hazelcast Jet Runner", "abstractText": "Hazelcast Jet is a distributed data processing engine that treats all data as a stream. Jet is built on top of Hazelcast IMDG and thanks to this the Jet cluster can also play the role of the data source and sink. If you use Jet this way, you can achieve perfect data locality and top-of- the-class throughputs.\n Jet uses cooperative multithreading (comparable to green threads), its processors correspond to standalone single-threaded tasks that process streams of data. By not depending on OS-level thread scheduling Jet can achieve greater throughput and better saturate the CPU cores. Since the theory underlying Apache Beam has also influenced the development of Jet and there are many conceptual similarities, attempting to write a Runner based on Jet came naturally to us. When we started however the first big obstacle we hit was the relative lack of documentation. Figuring out what exactly a Runner needed to do required reverse engineering existing runners.\n A second obstacle turned out to be the generic nature of the user defined functions used by Beam. While Jet's cooperative execution model allows for great performance, it requires the processing of the data to be non-blocking and this is hard to assure when running completely opaque and generic DoFns.\n Yet another difficulty was presented by trying to adapt Jet's fault tolerance and processing guarantee mechanism for the Runner, a process that, even though difficult, might be more solvable than the above mentioned non-blocking requirement.\n Despite these difficulties implementing an initial version of our runner turned out to be quite doable, even though experimental it's quite capable of running a majority of the existing Beam test suits and we are proud to say that we are now listed on the Capability Matrix. We can also showcase Nexmark test results of our runner and describe possible avenues for future development.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1020", "audienceId": "", "typeId": "11", "locationId": "1004", "speakerIds": [ "2030" ], "languageId": "1" }, { "id": "1328", "start": "2019-09-12T16:30:00", "end": "2019-09-12T17:20:00", "title": "Creating Custom Streaming Events to Learn Apache Beam", "abstractText": "Learning a streaming framework like Apache Beam is exciting but with 'Hello World!' examples aren't fun. There aren't a lot of free and interesting streaming data sources for beginners to play with, it's very easy to give up learning if it's boring. To keep myself learning something new, I find myself need incentives and accomplishments to continue. If you are like me need some motivation to keep learning, this talk will give you some inspiration.\n In this talk, I will share my experience of learning Apache Beam by showing demos to you on how I create a streaming data with my custom 'Marvel Fights Stream Producer'. I will discuss how I went through with the Apache Beam Programming Guide and replaced the official examples with Marvel streaming data I produced. I will also talk about what I learn from creating my custom data stream producer and how that helps me learn Apache Beam better. ", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1020", "audienceId": "", "typeId": "11", "locationId": "1004", "speakerIds": [ "2031" ], "languageId": "1" }, { "id": "1329", "start": "2019-09-12T17:30:00", "end": "2019-09-12T18:20:00", "title": "Production-ready stream data pipeline in Merpay, Inc", "abstractText": "We’ve started to provide our stream based data pipeline by using Google Cloud Dataflow and Apache Beam since 2018 fall. It collects event logs from microservices running on GKE, then transforms and forwards the logs to GCS and BigQuery to use for analytics, etc. As you know, implementing and operating streaming jobs are challenging. We’re encountered various issues during that time.\n I’d like to share our knowledge on development and operation perspective. There are 3 topics in the development part, 1) Implementing stream jobs with using spotify/scio, 2) How to debug the jobs, especially having DynamicDestination, 3) How to load testing, to ensure our jobs stable. And topics in the next part, 1) How to deploy new jobs safely(with avoiding data loss), 2) How to monitor the jobs and surrounding systems, and misc.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1020", "audienceId": "", "typeId": "11", "locationId": "1004", "speakerIds": [ "2032" ], "languageId": "1" }, { "id": "1330", "start": "2019-09-09T09:00:00", "end": "2019-09-09T13:00:00", "title": "Workshop: Apache OpenWhisk Bootcamp", "abstractText": "This workshop will teach you how to develop serverless applications, composed of loosely coupled microservice-like functions, using the Apache OpenWhisk open-source serverless platform.\n\n Starting with getting the development environment set up, it’ll move onto creating, deploying and invoking serverless functions for multiple runtimes. Once you are comfortable creating serverless functions, the next step is to connect functions to events, like message queues, allowing microservices to fire automatically. Finally, we’ll demonstrate how to expose serverless functions as public API endpoints, allowing to build serverless web applications.\n\n Welcome to the future of cloud development, you’ll never want to manage another server again!", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "11", "locationId": "1012", "speakerIds": [ "2035", "2042", "2043" ], "languageId": "1" }, { "id": "1333", "start": "2019-09-10T18:00:00", "end": "2019-09-10T18:50:00", "title": "Apache@Google, an account of the success of open source practices at Google Cloud", "abstractText": "We'll share with the Apache Community the journey that Google Cloud has had since we donated the first project to the foundation. We'll share our experiences from the commercial vendor point of view and also what we have learned while trying to embrace an 'open source first' culture.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1008", "audienceId": "", "typeId": "11", "locationId": "1004", "speakerIds": [ "1023" ], "languageId": "1" }, { "id": "1334", "start": "2019-09-11T10:00:00", "end": "2019-09-11T10:15:00", "title": "Keynote: Open Source in Tencent: Why and How We Adopt The Apache Way?", "abstractText": "As one of the largest internet company in the world, Tencent is doing more and more contributions to open source world, include: open source more than 70 projects, and join many open source community with developing features and patches and contribute back. In Tencent, we have an official open source department to drive and support open source project from incubating stage. In practice, we actually adopt Apache way to manage whole process in a way of bottom-up. In this talk, we will show why we adopt Apache way and how we do it in a local company with a different culture.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "11", "locationId": "1000", "speakerIds": [ "2058" ], "languageId": "1" }, { "id": "1335", "start": "2019-09-11T10:15:00", "end": "2019-09-11T10:30:00", "title": "Keynote: Yet Another Resource Negotiator for Big Data? How Google Cloud is enhancing data lake processing with Kubernetes", "abstractText": "The core of Google Cloud's approach to data analytics is meeting customer needs, which means embracing the best of Apache technologies. In this session, we will give a brief overview of the work that the Google Cloud team is doing to make Apache big data software cloud native, yet portable, through Kubernetes enhancements.\n\nJoin this session to learn more about our Kubernetes approach to big data and our development of open source Kubernetes Operators that provide packaged control planes for running Apache applications inside of a Kubernetes cluster. These operators help abstract Google?s knowledge of running massive data analytics systems into open source software. This session will also include a short primer on using Kubernetes for data processing, a comparison of YARN vs Kubernetes, our current offerings, and our future plans", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "11", "locationId": "1000", "speakerIds": [ "2064" ], "languageId": "1" }, { "id": "1336", "start": "2019-09-09T19:00:00", "end": "2019-09-09T20:50:00", "title": "Geospatial BoF", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1009", "audienceId": "", "typeId": "11", "locationId": "1013", "speakerIds": [ ], "languageId": "1" }, { "id": "1337", "start": "2019-09-09T19:00:00", "end": "2019-09-09T19:50:00", "title": "BoF: Vulnerability handling with security@apache.org", "abstractText": "A discussion with some of the security team around vulnerability handling in the ASF with possible topics including:\n - The process we use for managing security vulnerabilities in projects reported to security@apache.org\n - CVE names and the process, upcoming changes expected to the Apache CNA, security metadata and advisories\n - How to keep security patches and issues private in an open organisation, what some ASF projects do now, what worked and what didn't", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "11", "locationId": "1012", "speakerIds": [ "2045" ], "languageId": "1" }, { "id": "1338", "start": "2019-09-11T20:30:00", "end": "2019-09-11T22:00:00", "title": "BOFs - Birds of a Feather sessions - all rooms.", "abstractText": "Birds of a Feather sesions are self-organizing sessions on any topic. See https://www.apachecon.com/acna19/bof.html for the full schedule. Contact Rich - rbowen@apache.org - to schedule yours.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1", "speakerIds": [ ], "languageId": "1" }, { "id": "1339", "start": "2019-09-12T19:00:00", "end": "2019-09-12T22:00:00", "title": "BOFs - Birds of a Feather sessions - all rooms.", "abstractText": "Birds of a Feather sesions are self-organizing sessions on any topic. See https://www.apachecon.com/acna19/bof.html for the full schedule. Contact Rich - rbowen@apache.org - to schedule yours.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "", "locationId": "1", "speakerIds": [ ], "languageId": "1" }, { "id": "1340", "start": "2019-09-10T15:30:00", "end": "2019-09-10T16:20:00", "title": "Jena, Kafka, Mina: Configuration Management Using Apache Components", "abstractText": "How we utilized Jena (an RDF data store), Mina (the SSH implementation) and Kafka to implement a system to monitor and verify configurations of devices in a protected network. This talk discusses how we implemented an application framework that gathers information about devices (Servers, IoT, applications, etc) in secured networks and passes that data to a processing environment where analysis on the configurations are performed to determine if any configuration has become non-compliant. We will touch on the use of RDF over Kafka and RDF datastores to create schema less data repositories that support reasoning and advanced machine learning strategies.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "11", "locationId": "1000", "speakerIds": [ "2038" ], "languageId": "1" }, { "id": "1341", "start": "2019-09-09T14:00:00", "end": "2019-09-09T18:00:00", "title": "Workshop: Apache Spark and Scala Hands On", "abstractText": "Join our hands-on workshop with Jeremy Nilmeier, Data Scientist, and Dilip Biswal, Apache Spark expert, to learn how to get started with Scala and Apache Spark. After this training you will be able to write and run a sample Scala application using Apache Spark.\n \n Attendees will learn:\n - Fundamentals of Scala\n - Why Scala is best for leveraging Apache Spark (we will also review other languages: Python, R)\n - Fundamentals of Apache Spark\n - Coding examples from all of the main libraries of Apache Spark (SparkSQL, MLlib, GraphX, Spark Streaming, and SparkR)", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "11", "locationId": "1012", "speakerIds": [ "2039", "2040" ], "languageId": "1" }, { "id": "1342", "start": "2019-09-09T20:00:00", "end": "2019-09-09T20:50:00", "title": "Movie Night: Fear, Uncertainty, and Doubt", "abstractText": "Join us for \n \n - a screening of “FUD - Fear Uncertainty Doubt”, the Wyona Pictures film on the rise of the Open Source/Free Software Movement; and\n \n - a preview of the documentary on The Apache Software Foundation that will be filmed during ApacheCon Las Vegas and Berlin\n \n Meet the filmmakers, grab some popcorn and refreshments, and enjoy the show\n \n Meet the filmmakers, grab some popcorn and refreshments, and enjoy the show!\n \n To support this project, visit https://s.apache.org/trillions ", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "11", "locationId": "1000", "speakerIds": [ "2047", "2048" ], "languageId": "1" }, { "id": "1343", "start": "2019-09-12T11:00:00", "end": "2019-09-12T11:30:00", "title": "Closing Plenary", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "11", "locationId": "1000", "speakerIds": [ ], "languageId": "1" }, { "id": "1344", "start": "2019-09-12T11:30:00", "end": "2019-09-12T13:00:00", "title": "Lunch", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "11", "locationId": "1", "speakerIds": [ ], "languageId": "1" }, { "id": "1345", "start": "2019-09-11T10:30:00", "end": "2019-09-11T11:00:00", "title": "Coffee Break", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "11", "locationId": "1", "speakerIds": [ ], "languageId": "1" }, { "id": "1346", "start": "2019-09-11T13:00:00", "end": "2019-09-11T14:15:00", "title": "Lunch", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "11", "locationId": "1", "speakerIds": [ ], "languageId": "1" }, { "id": "1347", "start": "2019-09-11T16:15:00", "end": "2019-09-11T16:45:00", "title": "Coffee Break", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "11", "locationId": "1", "speakerIds": [ ], "languageId": "1" }, { "id": "1348", "start": "2019-09-11T19:00:00", "end": "2019-09-11T20:15:00", "title": "Lightning Talks", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "11", "locationId": "1000", "speakerIds": [ ], "languageId": "1" }, { "id": "1349", "start": "2019-09-11T14:15:00", "end": "2019-09-11T15:05:00", "title": "The Road To Portability", "abstractText": "Apache Beam's early vision was to create a framework agnostic of execution engines or languages. This vision was not fully realized from the early beginnings. At first, Beam was only agnostic of executions engines but very much tight to one language: Java.\n In the recent years much effort has been undergone to implement a language portability layer, to finally realize the vision of portability.\n In this talk we want to take a look at the state of portability, how it works, and what new use cases it unlocks.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1020", "audienceId": "", "typeId": "11", "locationId": "1003", "speakerIds": [ "2049","2050" ], "languageId": "1" }, { "id": "1320", "start": "2019-09-12T15:30:00", "end": "2019-09-12T16:20:00", "title": "Unifying Batch and Stream Data Processing with Apache Calcite and Apache Beam", "abstractText": " At LinkedIn, we have a large and ever-expanding corpus of big data processing code written using batch processing frameworks like Pig, Hive, and Spark. These data processing pipelines produce derived data artifacts like metrics, dimensions, and features and are generally run at daily or hourly end-to-end latencies. For a subset of these artifacts, there often arises a need to produce them at a faster cadence, say minutely or even continuously. At that point, the common practice used to be that the developer would re-write the same derivation logic using a stream processing framework (Apache Samza in case of LinkedIn). This causes two problems: \n 1. The time to go from a pipeline that generates data at hourly grain to a pipeline that generates the same data continuously is governed by developer time to understand the batch code and rewrite it in streaming language; typically weeks to a month to fully operationalize this pipeline. \n 2. The rewritten pipeline may not be exactly the same as the batch pipeline because of subtle differences in the logic or UDFs across the two code bases. Over time these pipelines can continue to diverge especially if different teams own the batch and streaming pipelines.\n \n In this talk, we present our solution to this batch-stream divide; a system that can auto-generate streaming code from batch logic and employ the Lambda architecture to transparently deliver merged results to data consumers. Technically, our Lambda architecture is very similar to the traditional Lambda architecture; however, our users only need to maintain a single code base in batch logic. This code base serves as a single source of truth to specify what users want to compute. If they need fresher results, they just need to turn on the streaming flag.\n \n We will deep-dive into technical details for this system which is built using open source components: Apache Beam and Apache Calcite. We’ll also share our experience using this system to auto-migrate batch scripts in our unified metrics platform into near realtime pipelines running on Apache Samza and our plans in the future to share this with the community.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "1020", "audienceId": "", "typeId": "11", "locationId": "1003", "speakerIds": [ "2019" ], "languageId": "1" }, { "id": "1331", "start": "2019-09-11T14:15:00", "end": "2019-09-11T15:05:00", "title": "Real time performance diagnosis in distributed databases", "abstractText": "Good and predictable performance is a common expectation across customers of Elasticsearch, an unstructured, distributed database. Elasticsearch, however, is not built with performance diagnosis as a design tenet and this makes it hard for customers to troubleshoot performance problems or provision a cluster. Attend this talk to learn about Performance Analyzer, a feature we built on Open Distro for Elasticsearch, to enable real time performance diagnosis on your Elasticsearch clusters. We will cover the abstractions for observability and root cause analysis, and walk through the design choices we made when building Performance Analyzer on Elasticsearch and the JVM. We will also show a live demo of how Performance Analyzer can help you troubleshoot an issue on your Elasticsearch cluster.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "11", "locationId": "1014", "speakerIds": [ "2056", 2057 ], "languageId": "1" }, { "id": "1332", "start": "2019-09-12T09:00:00", "end": "2019-09-12T09:50:00", "title": "Tencent Data Lake Solution based on Open Source Projects", "abstractText": "Data Lake is a system of data stored, processed and managed in its natural/raw format, user could store data as-is, without having to first structure the data, and run different types of analytics. With the increasing adoption of big data - from dashboards and visualizations to big data processing, real-time analytics, and machine learning to guide better decisions, data warehouse itself cannot satisfy the changing of workload patterns, Data Lake, as the generalization of data warehouse, becomes a buzzword in recent years.\n \n Public cloud providers announced their own Data Lake services one after another, trying to mitigate the gaps in traditional data warehouse solution. Tencent, one of top 3 ISP in China, also has a such requirement. Unlike other companies who built it with their in-house solutions. Tencent fully embraces the open source community and uses open source softwares to build a production ready Data Lake solution.\n \n In this talk, we will introduce you what is Data Lake, and how to build a Data Lake solution. Especially, we will introduce you the Tencent solution which uses open source technologies to build a large scale, production ready Data Lake solution. Last but not least, we will also show you own contributions back to the community. Through this talk, audience will get a full understanding of Data Lake and Tencent way to build this solution.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "11", "locationId": "1009", "speakerIds": [ "2058", "2059" ], "languageId": "1" }, { "id": "1013", "start": "2019-09-10T14:30:00", "end": "2019-09-10T15:20:00", "title": "Ballerina - Re-inventing Middleware in a Programming Language", "abstractText": "A large proportion of code written today either provides or consumes APIs, using HTTP, JSON, REST, gRPC, WebSockets, Kafka, and other network paradigms. Ballerina is a new programming language that is designed around this problem. The type-system, security model, syntax, core concepts all take into account network endpoints, payloads and the semantics of network distributed apps. If you are interested in what that looks like and why that might improve your coding of APIs, services and cloud-native applications, come to this session. There will be a high chance of seeing the presenter go bright red as he attempts a live coding demo.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "11", "locationId": "1009", "speakerIds": [ "1332" ], "languageId": "1" }, { "id": "1350", "start": "2019-09-11T19:00:00", "end": "2019-09-11T19:50:00", "title": "Apache Pulsar User BoF", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "11", "locationId": "1014", "speakerIds": [ ], "languageId": "1" }, { "id": "1018", "start": "2019-09-11T10:30:00", "end": "2019-09-11T18:00:00", "title": "Ballerina Hackathon", "abstractText": "Come hack some Ballerina code! Ballerina is a statically typed, concurrent programming language, focusing on network interaction and structured data. It is intended to be the core of a language-centric middleware platform. At the Ballerina Hackathon room, you can meet the language creators and learn\n\n - The basics of the language\n - How you can design and implement microservices using Ballerina\n - How to easily deploy Ballerina artifacts to Kubernetes and Docker\n \n Join us at Lake Mead I and II on Wednesday, September 11 on the lower level. Hack some code and win 4 front row tickets to the #1 greatest show in Las Vegas history - Absinthe. Learn more at https://ballerina.io.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "11", "locationId": "1066", "speakerIds": [ ], "languageId": "1" }, { "id": "1352", "start": "2019-09-10T20:30:00", "end": "2019-09-10T21:50:00", "title": "BoF: China Projects", "abstractText": "A discussion of Apaache projects which are primarily based in China.", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "11", "locationId": "1005", "speakerIds": [ ], "languageId": "1" }, { "id": "1353", "start": "2019-09-10T20:30:00", "end": "2019-09-10T21:20:00", "title": "BoF: Cassandra", "abstractText": "", "demo": false, "simultan": false, "veryPopular": false, "fullyBooked": false, "numberOfFavorites": 0, "keywords": { "en": [ ] }, "documents": { "slides": null, "manuscript": null, "other": null }, "trackId": "", "audienceId": "", "typeId": "11", "locationId": "1010", "speakerIds": [ ], "languageId": "1" } ], "speakers": [ { "id": "1183", "name": "Josh Fischer", "firstname": "Josh", "lastname": "Fischer", "company": "", "bio": "", "photoId": "", "eventIds": [ "1190" ] }, { "id": "1123", "name": "Carlos Rolo", "firstname": "Carlos", "lastname": "Rolo", "company": "", "bio": "", "photoId": "", "eventIds": [ "1126" ] }, { "id": "1171", "name": "Haisheng Yuan", "firstname": "Haisheng", "lastname": "Yuan", "company": "", "bio": "", "photoId": "", "eventIds": [ "1178" ] }, { "id": "1174", "name": "Lee Rhodes", "firstname": "Lee", "lastname": "Rhodes", "company": "", "bio": "", "photoId": "", "eventIds": [ "1181" ] }, { "id": "1105", "name": "Wei Zhou", "firstname": "Wei", "lastname": "Zhou", "company": "", "bio": "", "photoId": "", "eventIds": [ "1109" ] }, { "id": "1053", "name": "Christina Lin", "firstname": "Christina", "lastname": "Lin", "company": "", "bio": "", "photoId": "", "eventIds": [ "1055" ] }, { "id": "1083", "name": "Serge Huber", "firstname": "Serge", "lastname": "Huber", "company": "", "bio": "", "photoId": "", "eventIds": [ "1086", "1210" ] }, { "id": "1016", "name": "Julian Feinauer", "firstname": "Julian", "lastname": "Feinauer", "company": "", "bio": "", "photoId": "", "eventIds": [ "1016", "1078" ] }, { "id": "1055", "name": "Sheng Wu", "firstname": "Sheng", "lastname": "Wu", "company": "", "bio": "", "photoId": "", "eventIds": [ "1058" ] }, { "id": "1188", "name": "Nir Sopher", "firstname": "Nir", "lastname": "Sopher", "company": "", "bio": "", "photoId": "", "eventIds": [ "1197" ] }, { "id": "1127", "name": "Liang Zhang", "firstname": "Liang", "lastname": "Zhang", "company": "", "bio": "", "photoId": "", "eventIds": [ "1129" ] }, { "id": "1113", "name": "Holden Karau", "firstname": "Holden", "lastname": "Karau", "company": "", "bio": "", "photoId": "", "eventIds": [ "1115" ] }, { "id": "1132", "name": "Hiroyuki Yamada", "firstname": "Hiroyuki", "lastname": "Yamada", "company": "", "bio": "Hiroyuki Yamada is CTO and CEO at Scalar, Inc. He has been passionate about parallel and distributed data management systems for more than 15 years. Prior to Scalar, he worked at IIS UTokyo, Yahoo, IBM. Ph.D. from the University of Tokyo.", "photoId": "yamada.jpg", "eventIds": [ "1139" ] }, { "id": "1115", "name": "Riona MacNamara", "firstname": "Riona", "lastname": "MacNamara", "company": "", "bio": "", "photoId": "", "eventIds": [ "1116" ] }, { "id": "1007", "name": "Suresh Kumar Anaparti", "firstname": "Suresh", "lastname": "Kumar", "company": "", "bio": "", "photoId": "", "eventIds": [ "1007", "1017", "1037" ] }, { "id": "1182", "name": "Penghui Li", "firstname": "Penghui", "lastname": "Li", "company": "", "bio": "", "photoId": "", "eventIds": [ "1189" ] }, { "id": "1087", "name": "Tanzhongyi", "firstname": "Tanzhongyi", "lastname": "", "company": "", "bio": "", "photoId": "", "eventIds": [ "1092" ] }, { "id": "1077", "name": "Steve Lawrence", "firstname": "Steve", "lastname": "Lawrence", "company": "", "bio": "", "photoId": "", "eventIds": [ "1081" ] }, { "id": "1125", "name": "Pengchao Wang", "firstname": "Pengchao", "lastname": "Wang", "company": "", "bio": "", "photoId": "", "eventIds": [ "1128" ] }, { "id": "1044", "name": "Dave Neuman", "firstname": "Dave", "lastname": "Neuman", "company": "", "bio": "", "photoId": "", "eventIds": [ "1045" ] }, { "id": "1178", "name": "Aman Sinha", "firstname": "Aman", "lastname": "Sinha", "company": "", "bio": "", "photoId": "", "eventIds": [ "1185" ] }, { "id": "1203", "name": "Andy Shi", "firstname": "Andy", "lastname": "Shi", "company": "", "bio": "Andy is a developer advocate for cloud native platform group in Alibaba Cloud. His main interest is in cloud native application architecture. He has rich industry software development experience, especially in distributed tech., reliable web architecture and performance tuning.", "photoId": "", "eventIds": [ "1213" ] }, { "id": "1074", "name": "Xiangdong Huang", "firstname": "Xiangdong", "lastname": "Huang", "company": "", "bio": "", "photoId": "", "eventIds": [ "1078" ] }, { "id": "1019", "name": "Jason Tucker", "firstname": "Jason", "lastname": "Tucker", "company": "", "bio": "", "photoId": "", "eventIds": [ "1020" ] }, { "id": "1140", "name": "Igal Sapir", "firstname": "Igal", "lastname": "Sapir", "company": "", "bio": "", "photoId": "", "eventIds": [ "1148" ] }, { "id": "1143", "name": "George Percivall", "firstname": "George", "lastname": "Percivall", "company": "", "bio": "", "photoId": "", "eventIds": [ "1150" ] }, { "id": "1180", "name": "Blake Eggleston", "firstname": "Blake", "lastname": "Eggleston", "company": "", "bio": "", "photoId": "", "eventIds": [ "1188" ] }, { "id": "1204", "name": "Pratik Patel", "firstname": "Pratik", "lastname": "Patel", "company": "", "bio": "", "photoId": "", "eventIds": [ "1214" ] }, { "id": "1100", "name": "Anjana Fernando", "firstname": "Anjana", "lastname": "Fernando", "company": "", "bio": "", "photoId": "", "eventIds": [ "1103" ] }, { "id": "1146", "name": "Ganesh Raju", "firstname": "Ganesh", "lastname": "Raju", "company": "", "bio": "", "photoId": "", "eventIds": [ "1155" ] }, { "id": "1124", "name": "Tyler Wilson", "firstname": "Tyler", "lastname": "Wilson", "company": "", "bio": "", "photoId": "", "eventIds": [ "1127" ] }, { "id": "1114", "name": "Aizhamal Nurmamat kyzy", "firstname": "Aizhamal", "lastname": "Nurmamat", "company": "", "bio": "", "photoId": "", "eventIds": [ "1116", "1032" ] }, { "id": "1195", "name": "Marek Sadowski", "firstname": "Marek", "lastname": "Sadowski", "company": "", "bio": "", "photoId": "", "eventIds": [ "1206" ] }, { "id": "1121", "name": "Steve Sanders", "firstname": "Steve", "lastname": "Sanders", "company": "", "bio": "", "photoId": "", "eventIds": [ "1122" ] }, { "id": "1102", "name": "Anton Epple", "firstname": "Anton", "lastname": "Epple", "company": "", "bio": "", "photoId": "", "eventIds": [ "1106", "1123" ] }, { "id": "1004", "name": "Robert O Butts", "firstname": "Robert", "lastname": "Butts", "company": "", "bio": "", "photoId": "", "eventIds": [ "1005" ] }, { "id": "1099", "name": "Jeff Callahan", "firstname": "Jeff", "lastname": "Callahan", "company": "", "bio": "", "photoId": "", "eventIds": [ "1102" ] }, { "id": "1162", "name": "Seunghyun Lee", "firstname": "Seunghyun", "lastname": "Lee", "company": "", "bio": "", "photoId": "", "eventIds": [ "1169" ] }, { "id": "1018", "name": "Jeffrey Kriegsman", "firstname": "Jeffrey", "lastname": "Kriegsman", "company": "", "bio": "", "photoId": "", "eventIds": [ "1019","1127" ] }, { "id": "1023", "name": "Kenneth Knowles", "firstname": "Kenneth", "lastname": "Knowles", "company": "", "bio": "Kenn Knowles is a founder and current PMC Chair for Apache Beam and a member of the Apache Software Foundation. Kenn has been working on Google Cloud Dataflow - Google’s Beam backend since he joined the company. Prior to that, he built backends for startups such as Cityspan, Inkling, and Dimagi. Kenn holds a PhD in programming languages from the University of California, Santa Cruz.", "photoId": "", "eventIds": [ "1024", "1191", "1333", "1306" ] }, { "id": "1065", "name": "Anthony Grasso", "firstname": "Anthony", "lastname": "Grasso", "company": "", "bio": "", "photoId": "", "eventIds": [ "1068" ] }, { "id": "1202", "name": "Von gosling", "firstname": "Von", "lastname": "gosling", "company": "", "bio": "", "photoId": "", "eventIds": [ "1213" ] }, { "id": "1170", "name": "Márton Elek", "firstname": "Márton", "lastname": "Elek", "company": "", "bio": "", "photoId": "", "eventIds": [ "1177" ] }, { "id": "1130", "name": "Andrija Panić", "firstname": "Andrija", "lastname": "Panić", "company": "", "bio": "", "photoId": "", "eventIds": [ "1134" ] }, { "id": "1063", "name": "Mike Bates", "firstname": "Mike", "lastname": "Bates", "company": "", "bio": "", "photoId": "", "eventIds": [ "1065" ] }, { "id": "1037", "name": "Roman Shaposhnik", "firstname": "Roman", "lastname": "Shaposhnik", "company": "", "bio": "", "photoId": "", "eventIds": [ "1038", "1131" ] }, { "id": "1156", "name": "Josh Patterson", "firstname": "Josh", "lastname": "Patterson", "company": "", "bio": "", "photoId": "", "eventIds": [ "1165" ] }, { "id": "1157", "name": "Ryan Blue", "firstname": "Ryan", "lastname": "Blue", "company": "", "bio": "", "photoId": "", "eventIds": [ "1166" ] }, { "id": "1052", "name": "Alexander Stock", "firstname": "Alexander", "lastname": "Stock", "company": "", "bio": "", "photoId": "", "eventIds": [ "1053" ] }, { "id": "1108", "name": "Paul Angus", "firstname": "Paul", "lastname": "Angus", "company": "", "bio": "", "photoId": "", "eventIds": [ "1112", "1137" ] }, { "id": "1175", "name": "Jagadish Venkatraman", "firstname": "Jagadish", "lastname": "Venkatraman", "company": "", "bio": "", "photoId": "", "eventIds": [ "1182" ] }, { "id": "1150", "name": "Rakesh Venkatesh", "firstname": "Rakesh", "lastname": "Venkatesh", "company": "", "bio": "", "photoId": "", "eventIds": [ "1161" ] }, { "id": "1076", "name": "Adina Crainiceanu", "firstname": "Adina", "lastname": "Crainiceanu", "company": "", "bio": "", "photoId": "", "eventIds": [ "1080", "1115" ] }, { "id": "1117", "name": "Mohamed Sarwat", "firstname": "Mohamed", "lastname": "Sarwat", "company": "", "bio": "", "photoId": "", "eventIds": [ "1117" ] }, { "id": "1038", "name": "Nicolas Vazquez", "firstname": "Nicolas", "lastname": "Vazquez", "company": "", "bio": "", "photoId": "", "eventIds": [ "1040" ] }, { "id": "1003", "name": "Coty Sutherland", "firstname": "Coty", "lastname": "Sutherland", "company": "", "bio": "", "photoId": "", "eventIds": [ "1004" ] }, { "id": "1131", "name": "Chengzhi Zhao", "firstname": "Chengzhi", "lastname": "Zhao", "company": "", "bio": "", "photoId": "", "eventIds": [ "1138" ] }, { "id": "1041", "name": "Soenke Liebau", "firstname": "Soenke", "lastname": "Liebau", "company": "", "bio": "", "photoId": "", "eventIds": [ "1043" ] }, { "id": "1149", "name": "Devlin Duldulao", "firstname": "Devlin", "lastname": "Duldulao", "company": "", "bio": "", "photoId": "", "eventIds": [ "1159" ] }, { "id": "1054", "name": "Jim Jagielski", "firstname": "Jim", "lastname": "Jagielski", "company": "", "bio": "Jim Jagielski is a well known and acknowledged expert and visionary in open source, an accomplished coder, and frequent engaging presenter on all things open, web and cloud-related. As a developer, he’s made substantial code contributions to just about every core technology behind the internet and web and in 2012 was awarded the O’Reilly Open Source Award and in 2015 received the Innovation Luminary Award from the EU. He is likely best known as one of the developers and co-founders of the Apache Software Foundation, where he has previously served as both Chairman and President and where he’s been on the Board of Directors since day one through last year. He’s served as President of the Outercurve Foundation and was also a director of the Open Source Initiative (OSI) as well as other Open Source organizations. He works at ConsenSys as their Open Source Chief. Jim credits his wife Eileen with keeping him sane.", "photoId": "jimjag.jpg", "eventIds": [ "1056", "1057", "1073", "64" ] }, { "id": "1086", "name": "Lars Eilebrecht", "firstname": "Lars", "lastname": "Eilebrecht", "company": "", "bio": " Lars is co-founder and former Vice President of The Apache Software Foundation, and started contributing to the Apache HTTP Server project in 1996. He is also a member of the ASF Security Team and Press Team. Apart from his involvement with the ASF he is an independent IT consultant based in London with more than 20 years of accumulated expertise in information and security technology. He has worked for companies such as the BBC, Channel 4, Cable & Wireless and Pearson.", "photoId": "eilebrecht.png", "eventIds": [ "1090", "1091", "64" ] }, { "id": "1181", "name": "Jia Zhai", "firstname": "Jia", "lastname": "Zhai", "company": "", "bio": "", "photoId": "", "eventIds": [ "1189" ] }, { "id": "1103", "name": "Kai Waehner", "firstname": "Kai", "lastname": "Waehner", "company": "", "bio": "", "photoId": "", "eventIds": [ "1107", "1124", "1160", "1195" ] }, { "id": "1073", "name": "Dominik Riemer", "firstname": "Dominik", "lastname": "Riemer", "company": "", "bio": "", "photoId": "", "eventIds": [ "1077" ] }, { "id": "1163", "name": "De Li", "firstname": "De", "lastname": "Li", "company": "", "bio": "", "photoId": "", "eventIds": [ "1170" ] }, { "id": "1139", "name": "Vitor Wakim", "firstname": "Vitor", "lastname": "Wakim", "company": "", "bio": "", "photoId": "", "eventIds": [ "1147" ] }, { "id": "1194", "name": "Jesse MacFadyen", "firstname": "Jesse", "lastname": "MacFadyen", "company": "", "bio": "", "photoId": "", "eventIds": [ "1205", "1207" ] }, { "id": "1196", "name": "JB Onofré", "firstname": "JB", "lastname": "Onofré", "company": "", "bio": "", "photoId": "", "eventIds": [ "1208" ] }, { "id": "1101", "name": "Bharat Viswanadham", "firstname": "Bharat", "lastname": "Viswanadham", "company": "", "bio": "", "photoId": "", "eventIds": [ "1104" ] }, { "id": "1165", "name": "Weiwei Yang", "firstname": "Weiwei", "lastname": "Yang", "company": "", "bio": "", "photoId": "", "eventIds": [ "1173" ] }, { "id": "1136", "name": "Rohit Yadav", "firstname": "Rohit", "lastname": "Yadav", "company": "", "bio": "", "photoId": "", "eventIds": [ "1143", "1157" ] }, { "id": "1025", "name": "Adam Zegelin", "firstname": "Adam", "lastname": "Zegelin", "company": "", "bio": "", "photoId": "", "eventIds": [ "1026" ] }, { "id": "1173", "name": "Daoyuan Wang", "firstname": "Daoyuan", "lastname": "Wang", "company": "", "bio": "", "photoId": "", "eventIds": [ "1180" ] }, { "id": "1197", "name": "Dmitry Vasilyev", "firstname": "Dmitry", "lastname": "Vasilyev", "company": "", "bio": "", "photoId": "", "eventIds": [ "1209" ] }, { "id": "1168", "name": "Chen Liang", "firstname": "Chen", "lastname": "Liang", "company": "", "bio": "", "photoId": "", "eventIds": [ "1175" ] }, { "id": "1056", "name": "Andrea Tarocchi", "firstname": "Andrea", "lastname": "Tarocchi", "company": "", "bio": "", "photoId": "", "eventIds": [ "1059", "1142" ] }, { "id": "1012", "name": "Lohit VijayaRenu", "firstname": "Lohit", "lastname": "VijayaRenu", "company": "", "bio": "", "photoId": "", "eventIds": [ "1012" ] }, { "id": "1069", "name": "Tim Allison", "firstname": "Tim", "lastname": "Allison", "company": "", "bio": "", "photoId": "", "eventIds": [ "1072" ] }, { "id": "1148", "name": "Makoto Yui", "firstname": "Makoto", "lastname": "Yui", "company": "", "bio": "", "photoId": "", "eventIds": [ "1158" ] }, { "id": "1094", "name": "Boris Stoyanov - aka Bobby", "firstname": "Boris", "lastname": "Stoyanov", "company": "", "bio": "", "photoId": "", "eventIds": [ "1098" ] }, { "id": "1159", "name": "vinoth chandar", "firstname": "vinoth", "lastname": "chandar", "company": "", "bio": "", "photoId": "", "eventIds": [ "1168" ] }, { "id": "1191", "name": "Ruth Holloway", "firstname": "Ruth", "lastname": "Holloway", "company": "", "bio": "", "photoId": "", "eventIds": [ "1200" ] }, { "id": "1042", "name": "Lars Francke", "firstname": "Lars", "lastname": "Francke", "company": "", "bio": "", "photoId": "", "eventIds": [ "1043" ] }, { "id": "1057", "name": "Nicola Ferraro", "firstname": "Nicola", "lastname": "Ferraro", "company": "", "bio": "", "photoId": "", "eventIds": [ "1059", "1142" ] }, { "id": "1024", "name": "Monal Daxini", "firstname": "Monal", "lastname": "Daxini", "company": "", "bio": "", "photoId": "", "eventIds": [ "1025" ] }, { "id": "1198", "name": "Saeid Mirzaei", "firstname": "Saeid", "lastname": "Mirzaei", "company": "", "bio": "", "photoId": "", "eventIds": [ "1209" ] }, { "id": "1011", "name": "Vinay Chella", "firstname": "Vinay", "lastname": "Chella", "company": "", "bio": "", "photoId": "", "eventIds": [ "1010", "1054", "1075" ] }, { "id": "1009", "name": "Anuj Wadhera", "firstname": "Anuj", "lastname": "Wadhera", "company": "", "bio": "", "photoId": "", "eventIds": [ "1008" ] }, { "id": "1154", "name": "James Hughes", "firstname": "James", "lastname": "Hughes", "company": "", "bio": "", "photoId": "", "eventIds": [ "1164" ] }, { "id": "1045", "name": "Dan Kirkwood", "firstname": "Dan", "lastname": "Kirkwood", "company": "", "bio": "", "photoId": "", "eventIds": [ "1046" ] }, { "id": "1166", "name": "Zhankun Tang", "firstname": "Zhankun", "lastname": "Tang", "company": "", "bio": "", "photoId": "", "eventIds": [ ] }, { "id": "1090", "name": "Qing Lan", "firstname": "Qing", "lastname": "Lan", "company": "", "bio": "", "photoId": "", "eventIds": [ "1094" ] }, { "id": "1027", "name": "Patrick McFadin", "firstname": "Patrick", "lastname": "McFadin", "company": "DataStax", "bio": "Patrick McFadin is the VP of Developer Relations at DataStax, where he leads a team devoted to making users of DataStax products successful. He has also worked as Chief Evangelist for Apache Cassandra and consultant for DataStax, where he helped build some of the largest and most exciting deployments in production. Previous to DataStax, he was Chief Architect at Hobsons and an Oracle DBA/Developer for over 15 years.", "photoId": "PatrickMcFadin.jpg", "eventIds": [ "1028" ] }, { "id": "1201", "name": "George Miranda", "firstname": "George", "lastname": "Miranda", "company": "", "bio": "", "photoId": "", "eventIds": [ "1212" ] }, { "id": "1010", "name": "Marcus Sorensen", "firstname": "Marcus", "lastname": "Sorensen", "company": "", "bio": "", "photoId": "", "eventIds": [ "1009", "1018", "1039" ] }, { "id": "1026", "name": "Dinesh Joshi", "firstname": "Dinesh", "lastname": "Joshi", "company": "", "bio": "", "photoId": "", "eventIds": [ "1027" ] }, { "id": "1072", "name": "Scott Andreas", "firstname": "Scott", "lastname": "Andreas", "company": "", "bio": "", "photoId": "", "eventIds": [ "1076" ] }, { "id": "1145", "name": "Alvaro Santos Andrés", "firstname": "Alvaro", "lastname": "Santos", "company": "", "bio": "", "photoId": "", "eventIds": [ "1153" ] }, { "id": "1067", "name": "Vincent Royer", "firstname": "Vincent", "lastname": "Royer", "company": "", "bio": "", "photoId": "", "eventIds": [ "1070" ] }, { "id": "1184", "name": "Julian Hyde", "firstname": "Julian", "lastname": "Hyde", "company": "", "bio": "", "photoId": "", "eventIds": [ "1191" ] }, { "id": "1036", "name": "Hari Krishna Patnala", "firstname": "Hari", "lastname": "Krishna", "company": "", "bio": "", "photoId": "", "eventIds": [ "1036" ] }, { "id": "1059", "name": "Chong Sun", "firstname": "Chong", "lastname": "Sun", "company": "", "bio": "", "photoId": "", "eventIds": [ "1061" ] }, { "id": "1048", "name": "Jitendra Pandey", "firstname": "Jitendra", "lastname": "Pandey", "company": "", "bio": "", "photoId": "", "eventIds": [ "1049" ] }, { "id": "1050", "name": "Tushar Pathare", "firstname": "Tushar", "lastname": "Pathare", "company": "", "bio": "", "photoId": "", "eventIds": [ "1051" ] }, { "id": "1096", "name": "Sid Kattoju", "firstname": "Sid", "lastname": "Kattoju", "company": "", "bio": "", "photoId": "", "eventIds": [ "1100" ] }, { "id": "1091", "name": "Jordan West", "firstname": "Jordan", "lastname": "West", "company": "", "bio": "", "photoId": "", "eventIds": [ "1095" ] }, { "id": "1005", "name": "Joey Lynch", "firstname": "Joey", "lastname": "Lynch", "company": "", "bio": "", "photoId": "", "eventIds": [ "1006", "1010", "1011", "1054", "1075" ] }, { "id": "1079", "name": "Jean-Frederic Clere", "firstname": "Jean-Frederic", "lastname": "Clere", "company": "", "bio": "", "photoId": "", "eventIds": [ "1083", "1135", "1136", "1156" ] }, { "id": "1144", "name": "Rob Tompkins", "firstname": "Rob", "lastname": "Tompkins", "company": "", "bio": "", "photoId": "", "eventIds": [ "1152", "1154" ] }, { "id": "1064", "name": "Owen O'Malley", "firstname": "Owen", "lastname": "O'Malley", "company": "", "bio": "", "photoId": "", "eventIds": [ "1066", "1067" ] }, { "id": "1001", "name": "Christopher Schultz", "firstname": "Christopher", "lastname": "Schultz", "company": "", "bio": "", "photoId": "", "eventIds": [ "1001", "1003" ] }, { "id": "1116", "name": "Jia Yu", "firstname": "Jia", "lastname": "Yu", "company": "", "bio": "", "photoId": "", "eventIds": [ "1117" ] }, { "id": "1161", "name": "Jackie Jiang", "firstname": "Jackie", "lastname": "Jiang", "company": "", "bio": "", "photoId": "", "eventIds": [ "1169" ] }, { "id": "1155", "name": "Eddie Pickle", "firstname": "Eddie", "lastname": "Pickle", "company": "", "bio": "", "photoId": "", "eventIds": [ "1164" ] }, { "id": "1138", "name": "Jay Vyas", "firstname": "Jay", "lastname": "Vyas", "company": "", "bio": "", "photoId": "", "eventIds": [ "1146" ] }, { "id": "1119", "name": "Thomas Delteil", "firstname": "Thomas", "lastname": "Delteil", "company": "", "bio": "", "photoId": "", "eventIds": [ "1119" ] }, { "id": "1047", "name": "Wangda Tan", "firstname": "Wangda", "lastname": "Tan", "company": "", "bio": "", "photoId": "", "eventIds": [ "1049", "1173", "1196" ] }, { "id": "1021", "name": "Ted Dunning", "firstname": "Ted", "lastname": "Dunning", "company": "", "bio": "", "photoId": "", "eventIds": [ "1022" ] }, { "id": "1043", "name": "Hazem Saleh", "firstname": "Hazem", "lastname": "Saleh", "company": "", "bio": "", "photoId": "", "eventIds": [ "1044", "1201", "1203" ] }, { "id": "1071", "name": "Ben Bromhead", "firstname": "Ben", "lastname": "Bromhead", "company": "", "bio": "", "photoId": "", "eventIds": [ "1076" ] }, { "id": "1068", "name": "Nick Burch", "firstname": "Nick", "lastname": "Burch", "company": "", "bio": "", "photoId": "", "eventIds": [ "1071" ] }, { "id": "1134", "name": "Deepak Dixit", "firstname": "Deepak", "lastname": "Dixit", "company": "", "bio": "", "photoId": "", "eventIds": [ "1140" ] }, { "id": "1002", "name": "Jeff Elsloo", "firstname": "Jeff", "lastname": "Elsloo", "company": "", "bio": "", "photoId": "", "eventIds": [ "1002" ] }, { "id": "1112", "name": "Dinesh A. Joshi", "firstname": "Dinesh", "lastname": "A.", "company": "", "bio": "", "photoId": "", "eventIds": [ "1115" ] }, { "id": "1142", "name": "Sudarshan Vasudevan", "firstname": "Sudarshan", "lastname": "Vasudevan", "company": "", "bio": "", "photoId": "", "eventIds": [ "1149" ] }, { "id": "1029", "name": "Qian Wang", "firstname": "Qian", "lastname": "Wang", "company": "", "bio": "", "photoId": "", "eventIds": [ "1030" ] }, { "id": "1153", "name": "Frank Greguska", "firstname": "Frank", "lastname": "Greguska", "company": "", "bio": "", "photoId": "", "eventIds": [ "1163" ] }, { "id": "1051", "name": "Ellen Friedman", "firstname": "Ellen", "lastname": "Friedman", "company": "", "bio": "", "photoId": "", "eventIds": [ "1052", "1115" ] }, { "id": "1186", "name": "Xiaolong.Ran", "firstname": "Xiaolong.Ran", "lastname": "", "company": "", "bio": "", "photoId": "", "eventIds": [ "1193" ] }, { "id": "1017", "name": "Suresh Sadhu", "firstname": "Suresh", "lastname": "Sadhu", "company": "", "bio": "", "photoId": "", "eventIds": [ "1017" ] }, { "id": "1118", "name": "Andy LoPresto", "firstname": "Andy", "lastname": "LoPresto", "company": "", "bio": "", "photoId": "", "eventIds": [ "1118" ] }, { "id": "1066", "name": "Hyo-Kyung Joe Lee", "firstname": "Hyo-Kyung", "lastname": "Joe", "company": "", "bio": "", "photoId": "", "eventIds": [ "1069" ] }, { "id": "1128", "name": "Mohammad Islam", "firstname": "Mohammad", "lastname": "Islam", "company": "", "bio": "", "photoId": "", "eventIds": [ "1132" ] }, { "id": "1151", "name": "Sebastian Bretschneider", "firstname": "Sebastian", "lastname": "Bretschneider", "company": "", "bio": "", "photoId": "", "eventIds": [ "1162" ] }, { "id": "1177", "name": "Chris Lohfink", "firstname": "Chris", "lastname": "Lohfink", "company": "", "bio": "", "photoId": "", "eventIds": [ "1184" ] }, { "id": "1095", "name": "Daniel Gruno", "firstname": "Daniel", "lastname": "Gruno", "company": "", "bio": "", "photoId": "", "eventIds": [ "1099" ] }, { "id": "1147", "name": "Takuya Kitazawa", "firstname": "Takuya", "lastname": "Kitazawa", "company": "", "bio": "", "photoId": "", "eventIds": [ "1158" ] }, { "id": "1015", "name": "David Kjerrumgaard", "firstname": "David", "lastname": "Kjerrumgaard", "company": "", "bio": "", "photoId": "", "eventIds": [ "1015" ] }, { "id": "1061", "name": "John Clem", "firstname": "John", "lastname": "Clem", "company": "", "bio": "", "photoId": "", "eventIds": [ "1063" ] }, { "id": "1081", "name": "Luciano Resende", "firstname": "Luciano", "lastname": "Resende", "company": "", "bio": "", "photoId": "", "eventIds": [ "1085", "1089" ] }, { "id": "1126", "name": "Michael Costello", "firstname": "Michael", "lastname": "Costello", "company": "", "bio": "", "photoId": "", "eventIds": [ "1130" ] }, { "id": "1092", "name": "Justin Mclean", "firstname": "Justin", "lastname": "Mclean", "company": "", "bio": "", "photoId": "", "eventIds": [ "1096", "1105", "1115", "1120", "1172" ] }, { "id": "1039", "name": "Matt Ryan", "firstname": "Matt", "lastname": "Ryan", "company": "", "bio": "", "photoId": "", "eventIds": [ "1041" ] }, { "id": "1035", "name": "Pavan Kumar Aravapalli", "firstname": "Pavan", "lastname": "Kumar", "company": "", "bio": "", "photoId": "", "eventIds": [ "1036" ] }, { "id": "1080", "name": "Ruth Suehle", "firstname": "Ruth", "lastname": "Suehle", "company": "", "bio": "", "photoId": "", "eventIds": [ "1084" ] }, { "id": "1030", "name": "Johnnie Zhang", "firstname": "Johnnie", "lastname": "Zhang", "company": "", "bio": "", "photoId": "", "eventIds": [ "1030" ] }, { "id": "1085", "name": "Junfeng Liu", "firstname": "Junfeng", "lastname": "Liu", "company": "", "bio": "", "photoId": "", "eventIds": [ "1088" ] }, { "id": "1032", "name": "Paul King", "firstname": "Paul", "lastname": "King", "company": "", "bio": "", "photoId": "", "eventIds": [ "1033" ] }, { "id": "1046", "name": "Jamie Panagos", "firstname": "Jamie", "lastname": "Panagos", "company": "", "bio": "", "photoId": "", "eventIds": [ "1047" ] }, { "id": "1189", "name": "Matt Jackson", "firstname": "Matt", "lastname": "Jackson", "company": "", "bio": "", "photoId": "", "eventIds": [ "1198" ] }, { "id": "1070", "name": "Dikang Gu", "firstname": "Dikang", "lastname": "Gu", "company": "", "bio": "", "photoId": "", "eventIds": [ "1074", "1139" ] }, { "id": "1014", "name": "Boris Galitsky", "firstname": "Boris", "lastname": "Galitsky", "company": "", "bio": "", "photoId": "", "eventIds": [ "1014" ] }, { "id": "1008", "name": "Laxmikant Upadhyay", "firstname": "Laxmikant", "lastname": "Upadhyay", "company": "", "bio": "", "photoId": "", "eventIds": [ "1008" ] }, { "id": "1089", "name": "Asias He", "firstname": "Asias", "lastname": "He", "company": "", "bio": "", "photoId": "", "eventIds": [ "1093" ] }, { "id": "1152", "name": "Christian Elmer", "firstname": "Christian", "lastname": "Elmer", "company": "", "bio": "", "photoId": "", "eventIds": [ "1162" ] }, { "id": "1098", "name": "Sebastien Allamand", "firstname": "Sebastien", "lastname": "Allamand", "company": "", "bio": "", "photoId": "", "eventIds": [ "1101" ] }, { "id": "1122", "name": "Denis Magda", "firstname": "Denis", "lastname": "Magda", "company": "", "bio": "", "photoId": "", "eventIds": [ "1125" ] }, { "id": "1135", "name": "Claus Ibsen", "firstname": "Claus", "lastname": "Ibsen", "company": "", "bio": "", "photoId": "", "eventIds": [ "1141" ] }, { "id": "1133", "name": "Jay Zhuang", "firstname": "Jay", "lastname": "Zhuang", "company": "", "bio": "", "photoId": "", "eventIds": [ "1139" ] }, { "id": "1109", "name": "Dave Fisher", "firstname": "Dave", "lastname": "Fisher", "company": "", "bio": "", "photoId": "", "eventIds": [ "1113" ] }, { "id": "1060", "name": "Jonathan Gray", "firstname": "Jonathan", "lastname": "Gray", "company": "", "bio": "", "photoId": "", "eventIds": [ "1062" ] }, { "id": "1167", "name": "Sunil Govind", "firstname": "Sunil", "lastname": "Govind", "company": "", "bio": "", "photoId": "", "eventIds": [ ] }, { "id": "1000", "name": "Nick Knize", "firstname": "Nick", "lastname": "Knize", "company": "", "bio": "", "photoId": "", "eventIds": [ "1000" ] }, { "id": "1104", "name": "Anurag Awasthi", "firstname": "Anurag", "lastname": "Awasthi", "company": "", "bio": "", "photoId": "", "eventIds": [ "1108", "1143" ] }, { "id": "1040", "name": "Michaël Figuière", "firstname": "Michaël", "lastname": "Figuière", "company": "", "bio": "", "photoId": "", "eventIds": [ "1042" ] }, { "id": "1006", "name": "Harikrishna Patnala", "firstname": "Harikrishna", "lastname": "Patnala", "company": "", "bio": "", "photoId": "", "eventIds": [ "1007", "1037" ] }, { "id": "1185", "name": "Boyang Jerry Peng", "firstname": "Boyang", "lastname": "Jerry", "company": "", "bio": "", "photoId": "", "eventIds": [ "1192" ] }, { "id": "1160", "name": "Balaji Varadarajan", "firstname": "Balaji", "lastname": "Varadarajan", "company": "", "bio": "", "photoId": "", "eventIds": [ "1168" ] }, { "id": "1129", "name": "Xinli Shang", "firstname": "Xinli", "lastname": "Shang", "company": "", "bio": "", "photoId": "", "eventIds": [ "1132" ] }, { "id": "1093", "name": "Rafael Weingärtner", "firstname": "Rafael", "lastname": "Weingärtner", "company": "", "bio": "", "photoId": "", "eventIds": [ "1097", "1144" ] }, { "id": "1111", "name": "Myrle Krantz", "firstname": "Myrle", "lastname": "Krantz", "company": "", "bio": "", "photoId": "", "eventIds": [ "1115" ] }, { "id": "1033", "name": "Sami Adranly", "firstname": "Sami", "lastname": "Adranly", "company": "", "bio": "", "photoId": "", "eventIds": [ "1034" ] }, { "id": "1120", "name": "Tianqi Chen", "firstname": "Tianqi", "lastname": "Chen", "company": "", "bio": "", "photoId": "", "eventIds": [ "1121" ] }, { "id": "1020", "name": "Ted Liu", "firstname": "Ted", "lastname": "Liu", "company": "", "bio": "", "photoId": "", "eventIds": [ "1021" ] }, { "id": "1164", "name": "Surekha Saharan", "firstname": "Surekha", "lastname": "Saharan", "company": "", "bio": "", "photoId": "", "eventIds": [ "1171" ] }, { "id": "1097", "name": "Jean Armel Luce", "firstname": "Jean", "lastname": "Armel", "company": "", "bio": "", "photoId": "", "eventIds": [ "1101" ] }, { "id": "1158", "name": "John Youngseok Yang", "firstname": "John", "lastname": "Youngseok", "company": "", "bio": "", "photoId": "", "eventIds": [ "1167" ] }, { "id": "1084", "name": "Susan Hinrichs", "firstname": "Susan", "lastname": "Hinrichs", "company": "", "bio": "", "photoId": "", "eventIds": [ "1087" ] }, { "id": "1106", "name": "Jonathan Koppenhofer", "firstname": "Jonathan", "lastname": "Koppenhofer", "company": "", "bio": "", "photoId": "", "eventIds": [ "1110" ] }, { "id": "1200", "name": "Allen Wittenauer", "firstname": "Allen", "lastname": "Wittenauer", "company": "", "bio": "", "photoId": "", "eventIds": [ "1211" ] }, { "id": "1141", "name": "Jay Sen", "firstname": "Jay", "lastname": "Sen", "company": "", "bio": "", "photoId": "", "eventIds": [ "1149" ] }, { "id": "1031", "name": "Paul Brebner", "firstname": "Paul", "lastname": "Brebner", "company": "", "bio": "", "photoId": "", "eventIds": [ "1031", "1187" ] }, { "id": "1137", "name": "Garret Wilson", "firstname": "Garret", "lastname": "Wilson", "company": "", "bio": "", "photoId": "", "eventIds": [ "1145" ] }, { "id": "1107", "name": "Bob Paulin", "firstname": "Bob", "lastname": "Paulin", "company": "", "bio": "", "photoId": "", "eventIds": [ "1111", "1151" ] }, { "id": "1187", "name": "Valentin Zickner", "firstname": "Valentin", "lastname": "Zickner", "company": "", "bio": "", "photoId": "", "eventIds": [ "1194" ] }, { "id": "1179", "name": "Nicola Mazzoni", "firstname": "Nicola", "lastname": "Mazzoni", "company": "", "bio": "", "photoId": "", "eventIds": [ "1186" ] }, { "id": "1022", "name": "Griselda Cuevas Zambrano", "firstname": "Griselda", "lastname": "Cuevas", "company": "", "bio": "", "photoId": "", "eventIds": [ "1023", "1032" ] }, { "id": "1078", "name": "Daniel Takabayashi", "firstname": "Daniel", "lastname": "Takabayashi", "company": "", "bio": "", "photoId": "", "eventIds": [ "1082" ] }, { "id": "1088", "name": "Matija Gobec", "firstname": "Matija", "lastname": "Gobec", "company": "", "bio": "", "photoId": "", "eventIds": [ "1093" ] }, { "id": "1169", "name": "Dinesh Chitlangia", "firstname": "Dinesh", "lastname": "Chitlangia", "company": "", "bio": "", "photoId": "", "eventIds": [ "1176" ] }, { "id": "1199", "name": "George Ye", "firstname": "George", "lastname": "Ye", "company": "", "bio": "", "photoId": "", "eventIds": [ "1209" ] }, { "id": "1176", "name": "Wenli Zhang", "firstname": "Wenli", "lastname": "Zhang", "company": "", "bio": "", "photoId": "", "eventIds": [ "1183" ] }, { "id": "1192", "name": "Mary Grygleski", "firstname": "Mary", "lastname": "Grygleski", "company": "", "bio": "", "photoId": "", "eventIds": [ "1202" ] }, { "id": "1062", "name": "Alan Carroll", "firstname": "Alan", "lastname": "Carroll", "company": "", "bio": "", "photoId": "", "eventIds": [ "1064" ] }, { "id": "1075", "name": "Christofer Dutz", "firstname": "Christofer", "lastname": "Dutz", "company": "codecentric AG", "website": "https://www.codecentric.de/team/christofer-dutz/", "twitter": "https://twitter.com/ChristoferDutz", "linkedin": "https://www.linkedin.com/in/christofer-dutz-4249b649/", "bio": "Likes to swim outside the mainstream. He is really passionate about walking new paths. Some times this means making a new technology useable for the masses or by creating new combinations of established strategies. His solutions are usually unconventional but simple, highly efficient and sexy.", "photoId": "cdutz.png", "eventIds": [ "1079", "1131", "1133" ] }, { "id": "1082", "name": "Leucir Marin", "firstname": "Leucir", "lastname": "Marin", "company": "", "bio": "", "photoId": "", "eventIds": [ "1085" ] }, { "id": "1190", "name": "Geoff Genz", "firstname": "Geoff", "lastname": "Genz", "company": "", "bio": "", "photoId": "", "eventIds": [ "1199" ] }, { "id": "1034", "name": "Remy Maucherat", "firstname": "Remy", "lastname": "Maucherat", "company": "", "bio": "", "photoId": "", "eventIds": [ "1035", "1048" ] }, { "id": "1110", "name": "Evan Zelkowitz", "firstname": "Evan", "lastname": "Zelkowitz", "company": "", "bio": "", "photoId": "", "eventIds": [ "1114" ] }, { "id": "1172", "name": "Masahiro Ito", "firstname": "Masahiro", "lastname": "Ito", "company": "", "bio": "", "photoId": "", "eventIds": [ "1179" ] }, { "id": "1058", "name": "Marko A. Rodriguez", "firstname": "Marko", "lastname": "Rodriguez", "company": "", "bio": "", "photoId": "", "eventIds": [ "1060" ] }, { "id": "2000", "name": "Sam Ruby", "firstname": "Sam", "lastname": "Ruby", "company": "", "bio": "Sam Ruby is the President of The Apache Software Foundation (ASF). He has been a member of the Board of Directors for 13 years, and has served as ASF Secretary, Treasurer, Vice President Legal Affairs, Vice President ASF Infrastructure, and Vice President of the Jakarta project.\n He joined IBM’s Federal Systems Division in 1981, and became part of the IBM Software Group in 1991. In 1999 he started working on Open Source and open standards, where he gained industry wide recognition and leadership positions in multiple organizations. He served as co-Chair of the W3C HTML5 Working Group; Secretary of the IETF Atom Working Group; \n Convener of ECMA C# and .Net CLI Working Groups; Editor and Working Group member of ECMAScript (JavaScript); and a member of the PHP Core Group. He is the author of Agile Web Development with Rails 5 (Pragmatic Programming, 2009-present) and RESTful Web Services (O'Reilly, 2007). \n Ruby’s tenure at IBM has entered its 39th year with his role as Senior Technical Staff Member in the Emerging Technologies Group.", "photoId": "samruby.jpg", "eventIds": [ "68" ] }, { "id": "2001", "name": "David Brin", "firstname": "David", "lastname": "Brin", "company": "", "bio": "David Brin is an astrophysicist whose international best-selling novels include The Postman, Earth, and recently Existence. Dr. Brin serves on advisory boards (e.g. NASA's Innovative and Advanced Concepts program or NIAC) and speaks or consults on a wide range of topics including AI, SETI, privacy and national security. His nonfiction book about the information age - The Transparent Society - won the Freedom of Speech Award of the American Library Association. (http://www.davidbrin.com)", "photoId": "brin.png", "eventIds": [ "65" ] }, { "id": "2002", "name": "Samaira Mehta", "firstname": "Samira", "lastname": "Mehta", "bio": "Featured in TIME, CNBC and at NBC Universal, 11-year-old Samaira invented a STEM coding board game, CoderBunnyz, at the age of 7 with the goal of teaching coding to kids aged four to 104 and also help bridge the gender gap in technology.\n She’s led more than 100 workshops with her board game in Silicon Valley, including at Google, Microsoft, Intel, libraries, schools, teaching thousands of kids how to code, and has also started an initiative to teach coding to underrepresented girls. Last summer, she invented the world's first-ever AI board game, CoderMindz. Her goal is to help one billion kids gain access to coding tools by the time she goes to college, and she’s very well on her way with her 1 Billion Kids Can Code initiative. At 10, Samaira is among one of the youngest keynote speakers and has been speaking at various corporations, events, and conferences including the world-famous Mobile World Congress MWC, Barcelona, attended by 107,000 attendees. Samaira has been covered by news, print, and media in over 100 countries. She’s also a singer, composer, blog writer, and loves to play guitar.", "company": "", "photoId": "samaira.png", "eventIds": [ "1300", "207" ] }, { "id": "2003", "name": "James Gosling", "firstname": "James", "lastname": "Gosling", "company": "", "bio": "James Gosling received a BSc in Computer Science from the University of Calgary, Canada in 1977. He received a PhD in Computer Science from Carnegie-Mellon University in 1983. The title of his thesis was 'The Algebraic Manipulation of Constraints'. He has built satellite data acquisition systems, a multiprocessor version of Unix, several compilers, mail systems and window managers. He has also built a WYSIWYG text editor, a constraint based drawing editor and a text editor called 'Emacs' for Unix systems. He spent many years as a VP and Fellow at Sun Microsystems. At Sun his early activity was as lead engineer of the NeWS window system. He did the original design of the Java programming language and implemented its original compiler and virtual machine. He has been a contributor to the Real-Time Specification for Java, and a researcher at Sun labs where his primary interest was software development tools. He then was the Chief Technology Officer of Sun's Developer Products Group and the CTO of Sun's Client Software Group. He briefly worked for Oracle after the acquisition of Sun in 2010. After a brief stint at Google, he became the chief software architect at Liquid Robotics where he spent his time writing software for the Waveglider, an autonomous ocean-going robot. In May of 2017 he became a Distinguished Engineer at Amazon Web Services. Awards: The Economist Innovation Award, The Flame Award USENIX Lifetime Achievement Award, Officer of the Order of Canada, a fellow of the Association for Computing Machinery, the IEEE John von Neumann Medal, and a long list of patents.", "photoId": "gosling.png", "eventIds": [ "1301" ] }, { "id": "2004", "name": "Abhishek Kumar", "firstname": "Abhishek", "lastname": "Kumar", "company": "", "bio": "Software developer by profession, interested in contributing to open-source. Love bringing ideas to life. For a number of years, I had been working on developing desktop and mobile applications and have recently transitioned into the infrastructure domain.", "photoId": "", "eventIds": [ "3001" ] }, { "id": "2005", "name": "K B Shiv Kumar", "firstname": "Shiv", "lastname": "Kumar", "company": "", "bio": "Shiv is Co-Founder and CTO of IndiQus Technologies Pvt. Ltd. and a CloudStack user turned evangelist since 2013. He loves tinkering on CloudStack and the possibilities it offers. He has deployed multiple public and private clouds running CloudStack in the South Asian region and has also integrated legacy systems with CloudStack. He would love to share his experiences with like minded professionals.", "photoId": "", "eventIds": [ "3002" ] }, { "id": "2006", "name": "Jeffrey Carpenter", "firstname": "Jeffrey", "lastname": "Carpenter", "company": "DataStax", "bio": "Jeff Carpenter is the director of developer advocacy at DataStax, where he leverages his background in system architecture, microservices, and Apache Cassandra to help empower developers and operations engineers to build distributed systems that are scalable, reliable, and secure. Jeff has worked on projects ranging from a complex battle planning system in an austere network environment to a cloud-based hotel reservation system and is the author of the second edition of Cassandra: The Definitive Guide.", "photoId": "jcarpenter.jpg", "eventIds": [ "1302" ] }, { "id": "2007", "name": "Kyle Weaver", "firstname": "Kyle", "lastname": "Weaver", "company": "", "bio": "", "photoId": "", "eventIds": [ "1304" ] }, { "id": "2008", "name": "Ismaël Mejía", "firstname": "Ismaël", "lastname": "Mejía", "company": "", "bio": "", "photoId": "", "eventIds": [ "1304" ] }, { "id": "2009", "name": "Jason Kuster", "firstname": "Jason", "lastname": "Kuster", "company": "", "bio": "", "photoId": "", "eventIds": [ "1305" ] }, { "id": "2010", "name": "Alan Myrvold", "firstname": "Alan", "lastname": "Myrvold", "company": "", "bio": "", "photoId": "", "eventIds": [ "1305" ] }, { "id": "2011", "name": "Etienne Chauchot", "firstname": "Etienne", "lastname": "Chauchot", "company": "", "bio": "", "photoId": "", "eventIds": [ "1307" ] }, { "id": "2012", "name": "Alexey Romanenko", "firstname": "Alexey", "lastname": "Romanenko", "company": "", "bio": "", "photoId": "", "eventIds": [ "1308" ] }, { "id": "2013", "name": "Andrew Pilloud", "firstname": "Andrew", "lastname": "Pilloud", "company": "", "bio": "", "photoId": "", "eventIds": [ "1309" ] }, { "id": "2014", "name": "Austin Bennett", "firstname": "Austin", "lastname": "Bennett", "company": "", "bio": "", "photoId": "", "eventIds": [ "1310", "1311", "1312", "1313", "1314", "1315" ] }, { "id": "2015", "name": "Micah Wylde", "firstname": "Micah", "lastname": "Wylde", "company": "", "bio": "", "photoId": "", "eventIds": [ "1316" ] }, { "id": "2016", "name": "Alex Van Boxel", "firstname": "Alex", "lastname": "Van Boxel", "company": "", "bio": "", "photoId": "", "eventIds": [ "1317" ] }, { "id": "2017", "name": "Robert Burke", "firstname": "Robert", "lastname": "Burke", "company": "", "bio": "", "photoId": "", "eventIds": [ "1318" ] }, { "id": "2019", "name": "Khai Tran", "firstname": "Khai", "lastname": "Tran", "company": "", "bio": "", "photoId": "", "eventIds": [ "1320" ] }, { "id": "2020", "name": "Hai Lu", "firstname": "Hai", "lastname": "Lu", "company": "", "bio": "", "photoId": "", "eventIds": [ "1321" ] }, { "id": "2021", "name": "Shuichi Suzuki", "firstname": "Shuichi", "lastname": "Suzuki ", "company": "", "bio": "", "photoId": "", "eventIds": [ "1322" ] }, { "id": "2022", "name": "Suma Shivaprasad", "firstname": "Suma", "lastname": "Shivaprasad", "company": "", "bio": "", "photoId": "", "eventIds": [ "1049" ] }, { "id": "2023", "name": "Anu Engineer", "firstname": "Anu", "lastname": "Engineer", "company": "", "bio": "", "photoId": "", "eventIds": [ "1104" ] }, { "id": "2024", "name": "Joan Touzet", "firstname": "Joan", "lastname": "Touzet", "company": "", "bio": "Joan Touzet is an independent contractor, managing commercial and OSS software and hardware development since 1993. Based in Toronto, Joan has worked in embedded systems, big data, finance, bio-informatics, advertising, natural resources and infrastructure tooling. Prior to returning to independent contracting, she was Senior SW Development Manager for IBM Cloudant. Joan is a Director and Member of the Apache Software Foundation, and sits on the PMC for Apache CouchDB. Recent speaking engagements include a keynote at the Texas Linux Fest 2015, ApacheCon NA 2018, ApacheCon EU 2014, Velocity 2014, and OSCon 2014.", "photoId": "touzet.jpg", "eventIds": [ "1115" ] }, { "id": "2025", "name": "Brian Hulette", "firstname": "Brian", "lastname": "Hulette", "company": "", "bio": "", "photoId": "", "eventIds": [ "1323" ] }, { "id": "2026", "name": "Jan Doms", "firstname": "Jan", "lastname": "Doms", "company": "", "bio": "", "photoId": "", "eventIds": [ "" ] }, { "id": "2027", "name": "Enrico Canzonieri", "firstname": "Enrico", "lastname": "Canzonieri", "company": "", "bio": "", "photoId": "", "eventIds": [ "1324" ] }, { "id": "2028", "name": "Suneel Marthi", "firstname": "Suneel", "lastname": "Marthi", "company": "", "bio": "", "photoId": "", "eventIds": [ "1325" ] }, { "id": "2029", "name": "Rakesh Kumar", "firstname": "Rakesh", "lastname": "Kumar", "company": "", "bio": "", "photoId": "", "eventIds": [ "1326" ] }, { "id": "2030", "name": "Jozsef Bartok", "firstname": "Jozsef", "lastname": "Bartok", "company": "", "bio": "", "photoId": "", "eventIds": [ "1327" ] }, { "id": "2031", "name": "Chengzhi Zhao", "firstname": "Chengzhi", "lastname": "Zhao", "company": "", "bio": "", "photoId": "", "eventIds": [ "1328" ] }, { "id": "2032", "name": "syucream", "firstname": "syucream", "lastname": "syucream", "company": "", "bio": "", "photoId": "", "eventIds": [ "1329" ] }, { "id": "2033", "name": "Jay Taylor", "firstname": "Jay", "lastname": "Taylor", "company": "", "bio": "", "photoId": "", "eventIds": [ "1014" ] }, { "id": "2034", "name": "Christopher Ferris", "firstname": "Christopher", "lastname": "Ferris", "company": "IBM", "bio": "An IBM Fellow and CTO Open Technology for IBM, Chris has been involved in the architecture, design, and engineering of distributed systems for most of his 39+ year career in IT. He has been actively engaged in open standards and open source development since 1999. He has overall responsibility for setting the strategy and overseeing the execution of IBM's strategic open source and open standards initiatives. He represents IBM on the Hyperledger Technical Steering Committee which he chaired for the first two and a half years, and is a maintainer of the Hyperledger Fabric project.", "photoId": "ChrisFerris.jpg", "eventIds": [ "66" ] }, { "id": "2035", "name": "Upkar Lidder", "firstname": "Upkar", "lastname": "Lidder", "company": "IBM", "bio": "Upkar Lidder is a Full Stack Developer and Data Wrangler with a decade of development experience in a variety of roles. He can be seen speaking at various conferences and participating in local tech groups and meetups. He is currently curious about magic behind Machine Learning and Deep Learning, specifically use of NLP in chatbots. Upkar went to graduate school in Canada and currently resides in the United States.", "photoId": "UpkarLidder.jpg", "eventIds": [ "1330" ] }, { "id": "2036", "name": "Brian Tang", "firstname": "Brian", "lastname": "Tang", "company": "", "bio": "", "photoId": "", "eventIds": [ "1061" ] }, { "id": "2037", "name": "Javier Santos Andres", "firstname": "Javier", "lastname": "Santos", "company": "", "bio": "", "photoId": "", "eventIds": [ "1153" ] }, { "id": "2038", "name": "Claude Warren", "firstname": "Claude", "lastname": "Warren", "company": "", "bio": "Claude Warren is a Principal Software Engineer with over 25 years experience. He is currently employed by a multi-national company in Galway, Ireland where he works on innovative solutions to technical problems. He is open to considering other employment opportunities. He is also a Committer and Project Management Committee member on the Apache Jena project and has several small open source projects on Github. He has presented papers at several conferences and has several papers published both in the popular IT press and in refereed journals. He is a founding member of the Denver Mad Scientists Club and winner of the original Critter Crunch competition.", "photoId": "", "eventIds": [ "1340" ] }, { "id": "2039", "name": "Jeremy Nilmeier", "firstname": "Jeremy", "lastname": "Nilmeier", "company": "IBM", "bio": "Data Scientist and Developer Advocate, IBM Jeremy Nilmeier is a developer advocate, data scientist, and member of the IBM Center for Open-Source Data & AI Technologies (CODAIT), where he works with with open source frameworks for big data, machine learning, and deep learning. He completed the Insight data engineering program. He holds a BS in chemical engineering from the University of California, Berkeley, and a PhD in computational biophysics from the University of California, San Diego, which he followed with postdoctoral research in biophysics and bioinformatics at UC Berkeley, Lawrence Berkeley and Livermore Laboratories, and Stanford as an OpenMM fellow.", "photoId": "", "eventIds": [ "1341" ] }, { "id": "2040", "name": "Dilip Biswal", "firstname": "Dilip", "lastname": "Biswal", "company": "IBM", "bio": "Dilip Biswal is a Senior software engineer at the Center for Open-Source Data & AI Technologies (CODAIT) at IBM. He is an active Apache Spark contributor and works in the open source community. He is experienced in Relational Databases, Distributed Computing and Big Data Analytics. He has extensively worked on SQL engines like Informix, Derby, and Big SQL", "photoId": "", "eventIds": [ "1341" ] }, { "id": "2041", "name": "Jonathan Ellis", "firstname": "Jonathan", "lastname": "Ellis", "company": "DataStax", "bio": "As Chief Technology Officer and co-founder at DataStax, Jonathan sets the technical direction for the company. Prior to DataStax, Jonathan led Rackspace's Cassandra team and built the Cassandra community into an open source success. Previously, Jonathan built an object storage system based on Reed-Solomon encoding for data backup provider Mozy that scaled to petabytes of data and gigabits per second throughput.", "photoId": "JEllis.jpg", "eventIds": [ "67" ] }, { "id": "2042", "name": "Morgan Bauer", "firstname": "Morgan", "lastname": "Bauer", "company": "IBM", "bio": "After contributing to Docker & Kubernetes for the last 3 years, Morgan has gained valuable insight into the varying culture around open source container technology. Pivoting towards blockchain technologies has landed Morgan in Hyperledger Fabric. Morgan is a maintainer on the core Docker Engine and also a founding contributor of the Kubernetes Service-Catalog.", "photoId": "", "eventIds": [ "1330" ] }, { "id": "2043", "name": "John Walicki", "firstname": "John", "lastname": "Walicki", "company": "IBM", "bio": "John Walicki is the CTO for Edge/IoT Advocacy in the Developer Ecosystem Group of IBM Cognitive Applications Group. As an IBM Developer Advocate with deep expertise in IoT, he inspires developers to build solutions with the powerful Watson IoT capabilities, Watson Cognitive APIs and IBM Cloud. He helps developers create custom IoT and embedded Linux solutions for their industrial and educational use cases. He previously held roles as the IBM I/T Workplace of the Future Strategist, where he led the internal IBM Open Computing strategy, and as the IBM I/T Client Platform Architect, where he was responsible for the IBM internal strategy for Windows, Linux, and Mac. He established the Bring Your Own Device strategy at IBM and is an expert on mobile devices, desktop virtualization, and open standards. He led the open-standards-based Browser Independence deployment of Firefox within IBM. John was also a manager in the Watson Information Services Department at the IBM T.J. Watson Research Center. In addition to over 29 years of IBM experience, John holds a BS in Electrical Engineering from Lehigh University.", "photoId": "", "eventIds": [ "1330" ] }, { "id": "2044", "name": "Zhenzhao Wang", "firstname": "Zhenzhao", "lastname": "Wang", "company": "", "bio": "", "photoId": "", "eventIds": [ "1012" ] }, { "id": "2045", "name": "Mark Cox", "firstname": "Mark", "lastname": "Cox", "company": "", "bio": "Mark J Cox is an Open Source evangelist and Maker, working at Red Hat and with OpenSSL and Apache to improve software security. An Apache developer since 1995, he continues contributing to the Apache Software Foundation currently as VP Security. When not awake at night worrying about vulnerabilities he is an avid cosplayer.", "photoId": "markcox.jpg", "eventIds": [ "1337", "64" ] }, { "id": "2046", "name": "Roy Fielding", "firstname": "Roy", "lastname": "Fielding", "company": "", "bio": "Roy T. Fielding, Senior Principal Scientist at Adobe, is known for his pioneering work on the World Wide Web, open source, and software architecture. He wrote the standards for HTTP and URI, contributed to many other Web technologies, and defined the REST architectural style. Dr. Fielding is a founder of the Apache HTTP Server Project, incorporator and first chairman of the Apache Software Foundation, and former member of the ASF board of directors. He has been honored with the ACM Software System Award, the ACM SIGSOFT Impact Paper Award, the 2010 ICSE Most Influential Paper, and the O'Reilly Open Source 2000 Appaloosa Award for Vision. Dr. Fielding was also among the first elected members of the W3C Technical Architecture Group and the first selected members of the TR100 by MIT Technology Review.", "photoId": "fielding.jpg", "eventIds": [ "64" ] }, { "id": "2047", "name": "Michael Wechner", "firstname": "Michael", "lastname": "Wechner", "company": "", "bio": "Michael studied mathematical physics at ETH and did computer simulations of dendritic growth at the Max-Plack-Institute. He co-founded the software development company Wyona in 2000 and is the original creator of various Open Source projects like for example Apache Lenya, whereas in 2004 he became an Apache Member. At this time Michael started Wyona Pictures, because he loves stories and movies and directed his first documentary 'FUD - Fear Uncertainty Doubt' about people involved in Open Source and the fundamental questions of collaboration within Open Source communities.", "photoId": "wechner.jpg", "eventIds": [ "1342" ] }, { "id": "2048", "name": "Sally Khudairi", "firstname": "Sally", "lastname": "Khudairi", "company": "", "bio": "Active in the Web since 1993, Sally Khudairi is the publicist behind some of the industry's most prominent standards and organizations. Sally is a long-time champion of collaborative innovation, notably as the former deputy to Sir Tim Berners-Lee and Head of Communications for the World Wide Web Consortium (W3C). She helped launch The Apache Software Foundation in 1999, and was elected its first female and non-technical member. Sally is Vice President of Marketing and Publicity for The Apache Software Foundation, and Chief Executive of luxury brand communications consultancy HALO Worldwide. She is co-Founder and CMO of P2P Cloud Computing/IoT/eco-friendly cryptocurrency mining company, OptDyn.", "photoId": "khudairi.jpg", "eventIds": [ "1342" ] }, { "id": "2049", "name": "Thomas Weise", "firstname": "Thomas", "lastname": "Weise", "company": "", "bio": "", "photoId": "", "eventIds": [ "1349" ] }, { "id": "2050", "name": "Max Michels", "firstname": "Max", "lastname": "Michels", "company": "", "bio": "", "photoId": "", "eventIds": [ "1349" ] }, { "id": "2051", "name": "Konstantin Shvachko", "firstname": "Konstantin", "lastname": "Shvachko", "company": "", "bio": "", "photoId": "", "eventIds": [ "1175" ] }, { "id": "2052", "name": "Brian Behlendorf", "firstname": "Brian", "lastname": "Behlendorf", "company": "", "bio": "Brian Behlendorf is Executive Director of Hyperledger, an initiative at the Linux Foundation focused on blockchain technology. Brian is also a member of the Board of Directors at the Electronic Frontier Foundation and the Mozilla Foundation. Previously Brian has worked as CTO for the World Economic Forum, as a co-founder and CTO for CollabNet and Organic, as an advisor to the Obama White House. Brian was part of the original team that launched the Apache Project in 1995, and was root@apache from then to 2002 so he may have created your committer shell account. ", "photoId": "behlendorf.jpg", "eventIds": [ "64" ] }, { "id": "2053", "name": "Kequi Hu", "firstname": "Kequi", "lastname": "Hu", "company": "", "bio": "", "photoId": "", "eventIds": [ "1196" ] }, { "id": "2054", "name": "Charles Chen", "firstname": "Charles", "lastname": "Chen", "company": "", "bio": "", "photoId": "", "eventIds": [ "1325" ] }, { "id": "2055", "name": "Reza Rokni", "firstname": "Reza", "lastname": "Rokni", "company": "", "bio": "", "photoId": "", "eventIds": [ "1306" ] }, { "id": "2056", "name": "Partha Kanuparthy", "firstname": "Partha", "lastname": "Kanuparthy", "company": "Amazon", "bio": "", "photoId": "", "eventIds": [ "1331" ] }, { "id": "2057", "name": "Alolita Sharma", "firstname": "Alolita", "lastname": "Sharma", "company": "Amazon", "bio": "", "photoId": "", "eventIds": [ "1331" ] }, { "id": "2058", "name": "Junping Du", "firstname": "Junping", "lastname": "Du", "company": "Tencent", "bio": "Junping Du, Chair of Tencent Open Source Alliance, Director of Tencent Big Data Apartment. As ASF Member, Apache Hadoop committer and PMC Member, He is also a long term contributor in open source world and focus on research and development in cloud, big data area for more than 10 years.", "photoId": "", "eventIds": [ "1334", "1332" ] }, { "id": "2059", "name": "Jerry(Saisai) Shao", "firstname": "Jerry(Saisai)", "lastname": "Shao", "company": "Tencent", "bio": "Jerry(Saisai) Shao works as senior software engineer at Tencent Cloud, mainly focused on Apache Spark area, especially Spark core, Spark on Yarn and Spark Streaming. He is an Apache Spark committer, PMC member and Apache Livy PPMC. Prior to Tencent, he was a Member of Technical Staff at Hortonworks working on open source Big Data area.", "photoId": "", "eventIds": [ "1332" ] }, { "id": "2060", "name": "Pavi Subenderan", "firstname": "Pavi", "lastname": "Subenderan", "company": "", "bio": "", "photoId": "", "eventIds": [ "1132" ] }, { "id": "1332", "name": "Paul Fremantle", "firstname": "Paul", "lastname": "Fremantle", "company": "WSO2", "bio": "Paul is the CTO and Co-Founder of WSO2. He has a long history of working in open source, including work on Apache Axis, Axis2, Synapse, and WSO2 Carbon. Paul?s PhD looked at how personal middleware can improve IoT security and privacy. Paul has numerous publications including 3 co-authored books and numerous peer-reviewed papers. Paul is a keen evangelist of the Ballerina language and other emerging open source projects.", "photoId": "", "eventIds": [ "1013" ] }, { "id": "2061", "name": "Mayank Shrivastava", "firstname": "Mayank", "lastname": "Shrivastava", "company": "", "bio": "", "photoId": "", "eventIds": [ "1169" ] }, { "id": "2062", "name": "Cliff Skolnick", "firstname": "Cliff", "lastname": "Skolnick", "company": "", "bio": "Cliff Skolnick has more than two decades of experience in Internet servers, security, and connectivity. He was a co-founder and chief information officer of Organic Online, where he designed the network and server architecture used by such high-profile clients as Volvo, Levi’s, Sybase, MCI, Netscape, Saturn, and Microsoft. Before Organic, Cliff applied his networking and software skills at Sun Microsystems in the Internet engineering group as the project lead on one of the Internet Firewall Projects. He also worked at Sun as a developer in the Clustered Systems group and as part of the Sun Professional Services organization. He is a founding member of Apache Group/Apache Software Foundation, the most popular web server used on the Internet. Cliff started DJing in 1980, and still thinks every band needs a synthesizer.", "photoId": "", "eventIds": [ "64" ] }, { "id": "2063", "name": "Matthias Baetens", "firstname": "Matthias", "lastname": "Baetens", "company": "", "bio": "", "photoId": "", "eventIds": [ "1323", "1032" ] }, { "id": "2064", "name": "Christopher Crosbie", "firstname": "Christopher", "lastname": "Crosbie", "company": "Google", "bio": "Christopher has been building and deploying data and analytics applications for the past 15+ years and is currently a Product Manager at Google, focused on open source data and analytics.\n\n Chris came to Google from Amazon where he held two different positions. The first was a solutions architect for AWS, where he was awarded the 2015 solutions architect of the year distinction. The second and more recent position was as a Data Engineering Manager for an R&D group known as 'Grand Challenges'. Previous to joining Amazon, he headed up the data science team at Memorial Sloan Kettering Cancer Center where he managed a team of statisticians and software developers. He started his career as a software engineer at the NSABP, a not-for-profit clinical trials cooperative group supported by the National Cancer Institute. He holds an MPH in Biostatistics and an MS in Information Science.", "photoId": "", "eventIds": [ "1335" ] }, { "id": "2065", "name": "Sid Mani", "firstname": "Sid", "lastname": "Mani", "company": "", "bio": "", "photoId": "", "eventIds": [ "1146" ] }, { "id": "1013", "name": "WS02 Team", "firstname": "WS02", "lastname": "Team", "company": "WS02", "bio": "", "photoId": "", "eventIds": [ "1018" ] }, { "id": "2066", "name": "Sander Striker", "firstname": "Sander", "lastname": "Striker", "company": "", "bio": "Sander Striker is passionate about people, collaboration, technology and its impact. As a Product Manager for Developer Experience (DevX) at Bloomberg, he aims to continuously improve the workflows and tools of developers.\n Prior to Bloomberg, Sander served in senior leadership roles in media and technology related startups.\n At the Apache Software Foundation he served as its third President, Executive Vice President, and member of the Board of Directors.", "photoId": "sander.jpg", "eventIds": [ "64" ] } ] }