Linux Performance Analysis (2015)
You log in to a Linux server with a performance issue: what do you check in the first minute?
Every blog post that took off on Hacker News, ranked by the votes of its best submission. 2,560 posts.
You log in to a Linux server with a performance issue: what do you check in the first minute?
Continuous aggregates are one of Timescale's most popular features, but you can’t fully understand them without some context on Postgres views and materialized.
A recap of Sai Srirampur's POSETTE 2026 talk on storage performance in Postgres, with a local NVMe vs. EBS benchmark and the production setup behind it.
The v0.9 release of the Windows Terminal has arrived! This is the last version of the Terminal that will include new features before the v1 release. You
TL;DR: x86_64 decoding is hard, and the number and variety of implementations available for it makes it uniquely suited to differential fuzzing. We’re open sourcing mishegos, a differential fuzzer for instruction decoders. You can use it to discover discrepancies in your own decoders and analysis tools! In the…
We announced the t2.nano instances earlier this year. Like their larger siblings (t2.micro, t2.small, t2.medium, and t2.large), these instances provide a baseline level of processing power, along with the ability to save up unused cycles and use them when the need arises. As I noted in my earlier post (New T2.Large…
Posted by Mateusz Jurczyk of Google Project ZeroPatch diffing is a common technique of comparing ...
CockroachDB uses RocksDB for its storage engine because of RocksDB's rich feature set, which is necessary for a complex product like a distributed SQL database.
Tendermint is a server and a protocol for building linearizable (or sequentially consistent) byzantine fault-tolerant applications. Tendermint validators accept transactions from clients over HTTP, and replicate them to the other validators in the cluster, forming a totally ordered sequence of transactions. Each…
Here are some notes that may help newcomers understand what is actually happening with QEMU devices:
The "stack clash" series of vulnerabilities were a prime opportunity to demonstrate the strength of grsecurity's approach to security. Unlike upstream Linux and other OSes, the issues uncovered were unexploitable under grsecurity for many years.
In this deep-dive, we identified and worked through sporadic latency issues with services running on Kubernetes in our environment.
Unikernels, once a niche computing topic, have become a subject of intense interest and exploration. One particular evolution in this domain is “Going Full Unikernel.” Continue readingGone Full Unikernel
In two previous posts we've discussed how to receive 1M UDP packets per second and how to reduce the round trip time. We did the experiments on Linux and the performance was very good considering it's a general purpose operating system.
A new post-training training quantization paradigm for diffusion models, which quantize both the weights and activations of FLUX.1 to 4 bits, achieving 3.5× memory and 8.7× latency reduction on a 16GB laptop 4090 GPU. Code: https://www.github.com/mit-han-lab/nunchaku
In time-series databases the querying pattern differs from the write pattern. We usually write data in time order by updating many series every second. But querying is a different story. We usually want to read only a handful of series leaving most of the data behind. Here lies the biggest problem, which is we don’t…
Posted by Gal Beniamini, Project ZeroIn this blog post we'll continue our journey into gaining re...
What happens when you query Postgres? Data can actually come from many different places like the application cache, buffer cache, and even down into the physical disk cache. This post surveys the data storage and flow of Postgres data.