COMPASS Talk by Alberto Lerner (University of Fribourg): Rethinking the Interactions between In-Memory Databases and Storage

27.02.2020 10:00

Thursday27 February 2020, 10:00-11:00  CAB E 72

Speaker: Alberto Lerner (University of Fribourg)

Title: Rethinking the Interactions between In-Memory Databases and Storage







In-memory databases rely on non-volatile storage devices for services such as durability and recovery. SSDs can provide the high-performance these services require. However, there are at least two problems with the way these systems currently interact. First, when performance problems occur, SSDs offer no mechanism to help analyze them. The only alternative is to instrument the database side of the problem and conjecture about what might be the cause of performance degradation. The second problem is that adequately scheduling an in-memory database workload can benefit from having storage and database exchange signals, which is not feasible using the currently accepted separation of concerns between these systems.

In this talk, we present how we are designing solutions for both problems with the help of an open-source firmware SSD device. The device allows us to change and add to the existing logic that an SSD implements internally. We also discuss how some specific changes in the architecture of SSDs could greatly benefit in-memory database workloads. We believe that SSDs with such flexibility are an essential tool towards co-designing a new class of high-performance storage/database stack.


Alberto Lerner is a Senior Researcher at the eXascale Infolab at the University of Fribourg, Switzerland. His interests include systems that explore closely coupling of hardware and software in order to realize untapped performance and/or functionality. Previously, he spent years in the industry consulting for large, data-hungry verticals such as finance and advertisement. He had also been part of the teams behind a few different database engines: IBM's DB2, working on robustness aspects of the query optimizer, Google's Bigtable, on elasticity aspects, and MongoDB, on general architecture. Alberto received his Ph.D. from ENST - Paris (now ParisTech), having done his thesis research work at INRIA/Rocquencourt and NYU. He's also done post-doctoral work at IBM Research (both at T.J. Watson and Almaden).