1 / 20

Real-time Stream Processing Architecture for Comcast IP Video

Real-time Stream Processing Architecture for Comcast IP Video. Strata Conference + Hadoop World 2013 Chris Lintz Gabriel Commeau. Agenda. Comcast VIPER Overview Architecture Overview Q & A. Comcast Video IP Engineering and Research (VIPER).

aminia
Download Presentation

Real-time Stream Processing Architecture for Comcast IP Video

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Real-time Stream Processing Architecture for Comcast IP Video Strata Conference + HadoopWorld 2013 Chris Lintz Gabriel Commeau

  2. Agenda • Comcast VIPER Overview • Architecture Overview • Q & A

  3. Comcast Video IP Engineering and Research (VIPER) Preparation Delivery Video Players Packaging Storage Transcoding Origination Samsung iOS Video Players Xbox Live Android Analysis Storm

  4. Why Do We Focus on Real-time? • Proactively diagnose issues • Form real-time intelligence • Help deliver best possible video experience Viewership Prime Time

  5. Video Player Analytics Protocol • Live and On Demand • JSON event objects • Key metrics • Bitrate • Frame rate • Fragments • Errors We collect and use all data in accordance with best consumer privacy practices and applicable laws

  6. Player Sessions: Key In Understanding Video Experience

  7. High Level Architecture And Data Flow

  8. Flume: Data collection Tier • Collect, aggregate and move large amounts of data • Distributed, scalable, reliable, customizable • Multi-tier architecture

  9. Storm: Stream Processing Tier

  10. Player Sessions in Real-time • Sessions in Flume? • Technical issues: consistent hash and exactly-once semantics • Design goals • Separation of concerns • Session write-through rate?

  11. Flume Edge Tier: Video Player Analytics End Point • Analytics events over HTTPS • HTTP Source • Re-batch with inner sink and source

  12. Flume Mid Tier: Processing and Routing Data • Video Player Event processing • Geo-location, asset metadata, validation, to-storm • Replication channel processor: • HDFS sink • Storm sink

  13. Bridging Flume to Storm: Flume2Storm Connector • Service discovery • Distributed, scalable and reliable • Low latency

  14. Simplified Video Player Storm Topology

  15. Requirements for Read/Writes from Storm Bolts • Functionality beyond key/value stores • Real-time and historic window queries • Speed of in-memory writes and durability of disk

  16. Utilizing MemSQL for Persistence • Distributed in-memory SQL database • ACID, highly available, fault tolerant • Aggregators route queries to leaves • Leaves are auto-sharded • Solves our intense read/writes

  17. Isolated Analysts and Ingest Aggregators

  18. Achievements In Utilizing MemSQL • Complex queries in milliseconds • Fault-tolerant Storm bolt state • Joins now available outside of Storm bolts • Foreign key shards • Complex data streams • Dynamic alters without locks or down time • JSON type

  19. Wrapping Up • Real-time at Comcast scale • Millions of video players • Horizontal scale everywhere • Aggregated metrics across US and complex analysis • Real-time API • Builds foundation • Advanced real-time analytics • Better platform for innovation • Alerts on complex objects • Supplemental real-time data back to clients • Popularity-based CDN

  20. Thank You christopher_lintz@cable.comcast.com gabriel_commea@cable.comcast.com

More Related