Showing posts from November, 2021


World chess championship is on. Magnus is the clear favorite, but Nepomniachtchi is coming strong. It is a lot of fun. I haven't been posting for sometime. And this seems like a good time to talk about chess. My journey picking up on chess, again As a kid I wasn't much interested in chess. My younger brother was into chess, he would buy books to review grandmasters' games. I didn't go further than playing casual games with him. Maybe it was the quarantine that triggered this, but in the last year I started playing some chess on the smartphone. I had an Android phone for the last 3 years, and I used a random chess app downloaded at Play Store. I thought the app was very neat because it let me play against the computer at different levels and it allowed me to go back and try different things. Like Git, you know. The app also suggested me hints. I thought this was a dope way to improve one's chess skills. Little did I know, I was just scratching the surface. Three yea

What’s Really New with NewSQL?

This paper is by Andy Pavlo and Matthew Aslett, and it appeared in Sigmod 2016.   NoSQL managed to scale horizontally, but this came at the expense of losing transaction and rich querying capability. NewSQL followed NoSQL to amend things and restore balance to the force. NewSQL is a class of modern relational DBMSs that seek to provide on-par scalability to NoSQL for OLTP read-write workloads while still maintaining ACID guarantees for transactions. Let's dissect this definition. The biggest benefit of NewSQL is that developers do not have to write code to deal with eventually consistent updates as they would in a NoSQL system, because they will be able to use ACID transactions and SQL-like rich querying capabilities. NewSQL is about OLTP (online transaction processing), not OLAP (online data analysis like in data warehouse systems). Well, with the caveat that it can also be about HTAP (hybrid transactional-analytical processing), as the paper mentions under the future trends secti

Rabia: Simplifying State-Machine Replication Through Randomization (SOSP'21)

This paper appeared in SOSP'21 . I took notes and screen-snapshots during the presentation of this paper, and decided to put together a summary of what I understood from it. The paper has a simple idea and a somewhat unexpected result. It will be interesting to dive deep and explore to the extent this idea can be applied in practice.  Here is the idea. State-machine replication through Paxos , more accurately MultiPaxos, is commonly used in practice. (Yes, that includes state-machine replication through Raft, if I have to spell this out to the Rafters among us.) The MultiPaxos leader drives the protocol. It is basically one round, phase-2 execution of "accept this!" "yes, boss" between the leader and followers, where phase3 commit can be piggybacked to phase-2 message. This is as simple and efficient as it gets. You can't beat it! Or can you? The paper argues that, although the happy path of MultiPaxos based state-machine replication is simple and efficient

Popular posts from this blog

Learning about distributed systems: where to start?

Hints for Distributed Systems Design

Foundational distributed systems papers

Metastable failures in the wild

Scalable OLTP in the Cloud: What’s the BIG DEAL?

SIGMOD panel: Future of Database System Architectures

The end of a myth: Distributed transactions can scale

There is plenty of room at the bottom

Distributed Transactions at Scale in Amazon DynamoDB

Dude, where's my Emacs?