Marc Brooker's Blog

Distributed Consensus: Beating Impossibility with Probability One Distributed systems models are critical to understanding impossibility results Reading Nancy Lynch’s 1989 paper A Hundred Impossibility Proofs for Distributed Computing was the first time I…

Restricted Transactional Memory on Haswell Exploring the performance of Intel's RTM In my last post, I looked at the performance of HLE on Intel’s Haswell processor, and found that while it offered a nice speedup in some cases, it can cost performance in…

Hardware Lock Elision on Haswell Exploring the performance of Intel's HLE A couple of months ago, I bought myself a new home PC, upgrading from my old Core2 Q6600 to a shiny new Haswell-based Xeon E3-1240v3.

Beyond iostat: Storage performance analysis with blktrace An under appreciated set of IO analysis tools.

Some Patterns of Engineering Design Meetings On discussing designs.

Exploring TLA+ with two-phase commit Using testable pseudocode to test a distributed algorithm There are very few distributed algorithms more widely known by working programmers than the two-phase commit atomic commit protocol.

C++11’s atomic and volatile, under the hood on x86 How do C++11's atomic and volatile work?

Java’s Atomic and volatile, under the hood on x86 How exactly do AtomicInteger and volatile do their magic in Java?

Highly contended and fair locking in Java How do explicit locks compare to volatile access?

Are volatile reads really free?

Expect Less, Get More?

Latency lags bandwidth On the growing gap between capacity, bandwidth and latency.

The properties of crash-only software My thoughts about a classic paper Crash-only software by Candea and Fox is a very interesting paper which is well worth your time if you spend any time designing software or services.

The power of two random choices Using less information to make better decisions.

The benefits of having data Two ways to look at drive failures and temperature.