Faisal Nawab
PhD Candidate, UCSB.


Faisal Nawab is a Ph.D. candidate at the University of California, Santa Barbara. His dissertation research lies at the intersection of Big Data management and distributed cloud computing systems. Specifically, he is interested in the challenges that arise in geographically-distributed data management systems. Faisal has also worked with HP Labs and Microsoft Research on data management systems over emerging memory technology such as Non-Volatile Memory. His research is published in leading database conferences, such as VLDB, SIGMOD, and ICDE.

Talk Information

  • Efficient Coordination for Global-Scale Data Management
  • Monday 4/17, 10:00 AM
  • 2250 WEB

  • Abstract
    Replicating data across datacenters (geo-replication) provides higher levels of fault-tolerance and data availability. The Wide-Area Network (WAN) latency separating datacenters is orders of magnitude larger than traditional network latency within a datacenter. This makes it expensive to preserve the consistency of data copies. However, consistency and high-level access abstractions like database transactions are favored by developers because they hide the complexity of the underlying replica and concurrency control. This has led to the adoption of consistent transactions in large-scale geo-replicated systems. In this talk, I will present the fundamental challenges in designing geo-replicated data management systems. Specifically, transaction latency is high due to the need to coordinate between datacenters spread across the world. Traditionally, coordination is performed by polling other datacenters for permissions to execute. This made a Round-Trip Time (RTT) latency inevitable. In geo-replication, this is an expensive cost and thus leads to the question: Is it possible to avoid the polling paradigm of coordination? Message Futures is a protocol that demonstrates a new paradigm of continuous, proactive coordination. In this paradigm, transactions can coordinate in sub-RTT latency. Breaking the RTT latency barrier invites the next part of the talk where I derive a lower bound for coordination latency. The proposed lower-bound model inspires a design of a coordination protocol called Helios that targets achieving the lower-bound latency. The talk will also discuss many of the practical aspects of building scalable large-scale data management and communication platforms for geo-replicated systems. I conclude the talk with future opportunities for global-scale data management in the context of edge computing, Internet of Things, and data science.


    2017-04-16 18:00:00DinnerRyan Stutsman and Feifei LiTBD

    2017-04-17 08:00:00BreakfastMatthew FlattPick up at Monaco
    2017-04-17 09:30:00Talk PrepTalk Prep2250 WEB
    2017-04-17 09:50:00TalkTalk2250 WEB
    2017-04-17 11:30:001-1Ryan StutsmanMEB 3436
    2017-04-17 12:00:00LunchRyan and JasonTBD
    2017-04-17 13:30:001-1Jeff PhillipsMEB 3442
    2017-04-17 14:00:001-1Hari SundarMEB 3454
    2017-04-17 14:30:001-1Mahdi BojnordiMEB 3418
    2017-04-17 15:00:00SoC DirectorRoss WhitakerMEB 3190
    2017-04-17 15:30:001-1Alexander LexWEB 3887
    2017-04-17 16:00:001-1Bei WangWEB 4608
    2017-04-17 16:30:001-1Eric Eide3476 MEB
    2017-04-17 17:00:00Break at HotelUber back to hotelHotel Monaco
    2017-04-17 18:30:00DinnerJohn Regehr and Alex LexTBD

    2017-04-18 08:00:00BreakfastMary HallPick up at Monaco
    2017-04-18 09:30:001-1Feifei LiWEB 2692
    2017-04-18 10:00:00Office 1-1Ganesh Gopalakrishnan3428 MEB
    2017-04-18 10:30:001-1Zvonimir RakamaricMEB 3424
    2017-04-18 11:00:001-1Rajeev BalasubramonianMEB 3414
    2017-04-18 11:30:001-1Mike KirbyDirector's Office
    2017-04-18 12:00:00LunchStudent LunchMEB 3490
    2017-04-18 13:30:00meetRobert RicciMEB 3490B
    2017-04-18 14:00:00meetJohn RegehrMEB 3470
    2017-04-18 14:30:00CoE DeanRichard BrownWEB 1650
    2017-04-18 15:00:00To AirportUber back to SLC

    Sign Up

    Add Homepage Link?