Metadata

 I know I should call this recent listens, but I am stuck with the series name. So here it goes. These are some recent "reads" this month. Billion Dollar Whale Reading the Billion Dollar Whale was exhausting. I am not talking about the writing, which was well-paced and packed with a lot of detail. The problem is the  subject, Jho Low , who is a slippery and soulless character, who conned Malaysia out of billions via the 1Malaysia Development Berhad sovereign wealth fund. Jho Low is a Wharton grad. He is a big  spender and party boy. Dropping millions of dollars a night for gambling and partying. His party buddies included Leonardo DiCaprio, Paris Hilton, and Jamie Foxx. Jho was a showoff and pretentious ass. What does Wharton teach these people? Do they actively recruit for this type of people? Jho was aided by the complicity of Prime Minister Najib Razak and his luxury-addicted wife. We are talking entire stores shut down for private shopping and flights hauling nothin...

Aleksey and I sat down to read this paper on Monday night. This was an experiment which aimed to share how experts read papers in real time. We haven't read this paper before to keep things raw. As it is with research, we ended up arguing with the paper (and between each other) back and forth. It was messy, and it was also awesome. We had a lot of fun. Check our discussion video below (please listen at 1.5x, I sound less horrible at that speed, ah also this thing is 2 hours long). The paper I annotated during our discussion is also available here. This paper appeared in HotOS 2025 , so it is very recent. It's a position paper arguing that the traditional F-threshold fault model in consensus protocols is outdated and even misleading. Yes, the F-threshold fault model does feel like training wheels we never took off. In his essay " the joy of sects" , Pat Helland bring this topic to tease distributed systems folk: " Distributed systems folks. These people vacilla...

This EuroSys '23 paper reads like an SOSP best paper. Maybe it helped that EuroSys 2023 was in Rome. Academic conferences are more enjoyable when the venue doubles as a vacation. The Problem Morty tackles a fundamental question: how can we improve concurrency under serializable isolation (SER), especially without giving up on interactive transactions? Unlike deterministic databases (e.g., Calvin ) that require transactions to declare read and write sets upfront, Morty supports transactions that issue dynamic reads and writes based on earlier results. Transactional systems, particularly in geo-replicated settings, struggle under contention. High WAN latency stretches transaction durations, increasing the window for conflicts. The traditional answer is blind exponential backoff, but that leads to low CPU utilization. TAPIR and Spanner replicas often idle below 17% under contention as Morty's evaluation experiments show. Morty's approach to tackle the problem is to start from...

This paper (SIGMOD '08) proposes a lightweight runtime technique to make Snapshot Isolation (SI) serializable without falling back to locking. The key idea behind Serializable SI (SSI) is to detect potentially dangerous (write-skew) executions at runtime and abort one of the transactions to guarantee serializability (SER). The goal is to offer the strong guarantees of SER without sacrificing SI's high performance and non-blocking reads. But would it make sense to implement SER by layering on MVCC SI instead of implementing it directly? Do you think an SI-based implementation would be more performant than native 2PL-based SER implementations? What about compared to OCC-based SER? The evaluation section gives some answers. The problem and insight Let's back up. Write-skew is the canonical anomaly under SI. And the canonical example for write-skew is the "doctors on-call" scenario. Consider two doctors removing themselves from a duty roster. Each transaction checks ...

ATC and OSDI ran in parallel. As is tradition, OSDI was single-track ; ATC had two parallel tracks . The schedules and papers are online as linked above. USENIX is awesome: it has been open access for its conference proceedings since 2008. So you can access all the paper pdfs through the links above now. I believe the presentation videos will be made available soon as well. Kudos to USENIX! I attended the OSDI opening remarks delivered by the PC chairs, Lidong Zhou (Microsoft) and Yuan Yuan Zhou (UCSD). OSDI saw 339 submissions this year, which is up 20% from last year. Of those, 53 were accepted, for an acceptance rate of 16%. The TPC worked through Christmas to keep the publication machine running. We really are a bunch of workaholics. Who needs family time when you have rebuttals to respond to? OSDI gave two best paper awards: Basilisk: Using Provenance Invariants to Automate Proofs of Undecidable Protocols. Tony Nuda Zhang and Keshav Singh, University of Michigan; Tej Chajed, Unive...

This week I was in Boston for ATC/OSDI’25. Downtown Boston is a unique place where two/three-hundred-year-old homes and cobblestone streets are mixed with sleek buildings and biotech towers. The people here look wicked smart and ambitious (although lacking the optimism/cheer of Bay area people). It’s a sharp contrast from Buffalo, where the ambition is more about not standing out. Boston was burning. 90°F and humid. I made the mistake of booking late, so I got the DoubleTree Boston-Downtown instead of the conference hotel. The mile-long walk to the Sheraton felt like a hike through a sauna. By the time I got there, my undershirt was soaked, and stuck to my back cold under the conference hall’s AC.  Jane Street's fitted t-shirt swag saved the day. The Sheraton looked ragged from the outside, aged on the inside, but it was functional. The conference felt underfilled, with many empty seats. Later, I learned that the total ATC+OSDI attendance was under 500. That's a big drop from e...

Chapter 7 of the Concurrency Control and Recovery in Database Systems book by Bernstein and Hadzilacos (1987) tackles the distributed commit problem: ensuring atomic commit across a set of distributed sites that may fail independently. The chapter covers these concepts: The challenges of transaction processing in distributed database systems (which wasn't around in 1987) Failure models (site and communication) and timeout-based detection The definition and guarantees of Atomic Commitment Protocols (ACPs) The Two-Phase Commit (2PC) protocol (and its cooperative termination variant) The limitations of 2PC (especially blocking) Introduction and advantages of the Three-Phase Commit (3PC) protocol Despite its rigor and methodical development, the chapter feels like a suspense movie today. We, the readers, equipped with modern tools like FLP impossibility result and Paxos protocol watch as the authors try to navigate a minefield, unaware of the lurking impossibility results that were pu...