Topics /

Systems & Performance

The most popular blog posts about systems & performance on Hacker News. 278 posts.

2014
242

Formal Methods in Building Robust Distributed Systems

We all know that when designing and operating applications at scale, it is persistent state management that brings the most difficult challenges. Delivering state-free applications has always been (fairly) easy. But most interesting commercial and consumer applications need to manage persistent state. Advertising…

243

EC2 Maintenance Update II

I’d like to give you an update on the EC2 Maintenance announcement that I posted last week. Late yesterday (September 30th), we completed a reboot of less than 10% of the EC2 fleet to protect you from any security risks associated with the Xen Security Advisory (XSA-108). This Xen Security Advisory was embargoed until…

244

Roshi: a CRDT system for timestamped events

Let’s talk about the stream. The SoundCloud stream represents stuff that’s relevant to you primarily via your social graph, arranged in time order, newest-first. The atom of that data model, an event, is a simple enough thing. Timestamp User who did the thing Identifier of the thing that was done For example, At…

248

Secrets of dispatch_once; x86 performance trickery

Reader Paul Kim pointed out an entry on Michael Tsai's blog about making dispatch_once fast . While the comment in the dispatch_once source code is fascinating and informative, it doesn't quite delve into the detail that some would like to see. Since this is one of my favorite hacks, for today's article I'm going to…

263

Basic Concepts of High Availability Linux

When considering to build a high availability cluster based on Linux, it’s easy to find all kinds of how-to’s explaining the basic tooling and configuration. Most of them forget to explain some of the basic concepts of high availability. In this post I’ll try to explain them. To build a high availability cluster that…