31
A 40-line fix eliminated a 400x performance gap
How a 40-line OpenJDK fix swapped slow /proc parsing for a single clock_gettime syscall, closing a 400x thread CPU-time gap hidden for 20 years.
Topics /
Systems & Performance
The most popular blog posts about systems & performance on Hacker News. 178 posts.
32
To study how chips work, MIT researchers built their own operating system
The new "Fractal" operating system kernel, developed at MIT, gives researchers a clearer look at how computer chips work internally. It was used to study the branch predictors inside Apple's M1 processor, where it revealed a potential vulnerability to major speculative attacks.
33
Jepsen: ParticleDB 1.1.4
Modern applications often spread state across a variety of systems: databases, caches, queues, data warehouses, search indices, and so on. Coordinating these systems is challenging: caches are often stale, the analytics platform might lag days behind the primary database, the search index might lose data, and…
34
It took a year to ship WebAssembly in Anubis
After a year of work, hundreds of commits, 5 generations of pull requests, dozens of tests, rewriting part of Anubis in Rust, the first compiler bug of my career, and at least three times making my tower run out of ram I think I have finally done it. The next version of Anubis will ship with WebAssembly-based proof of…
35
Building durable workflows on Postgres
Explaining the concept of a Postgres-backed durable execution system like DBOS and comparing it to external workflow orchestration systems like Temporal.
36
Haiku R1/beta6 has been released
After about two years since the last beta, and only about a week after Haiku’s 25th birthday, Haiku R1/beta6 has been released! See “Release Notes” for the release notes, “Press contact”, for press inquiries … and …
37
Performance Improvements in .NET 11
Take a tour through hundreds of performance improvements in .NET 11.
38
During Helene, I just wanted a plain text website
We recently passed the one-year anniversary of Hurricane Helene and its devastating impact on Western North Carolina. As a web developer, I am thinking again about my experience with the mobile web on the day after the storm.
39
We replaced Redis with MySQL for inventory reservations and it scaled
How we used SKIP LOCKED, composite primary keys, and connection visibility to hit our scale targets.
40
Gentoo Linux 2025 Review
News and information from Gentoo Linux
41
Idempotency is easy until the second request is different
Idempotency is not just an HTTP header or a key lookup. This article covers the failure cases that bite real APIs: different requests with the same key, concurrent retries, partial success, downstream uncertainty, response replay, expiry, and duplicate message handling.
42
Running Gemma 4 26B at 5 tokens/sec on a 13-year-old Xeon with no GPU
A storage appliance that shipped before AVX2 existed now runs Google's Gemma 4 26B in my basement, no GPU. Here's how we got a modern MoE model onto a CPU older than the instructions its inference engine assumed were there.
43
NetBSD 11.0
The NetBSD project is pleased to (finally) announce the NetBSD 11.0 release ! See the release announcement for details.
44
Fearless SIMD v1.0
Fearless SIMD v1.0 is here
45
Libreboot 26.10 "Ominous Olive" released with UEFI, Chromebook support
Libreboot – Libreboot 26.10 “Ominous Olive” released! With full UEFI support.
46
Linux 7.2
Igalia is an open source consulting firm specialised in the development of innovative projects and solutions. Our engineers have expertise in a wide range of technological areas, including browsers and client-side web technologies, graphics pipeline, compilers and virtual machines. We have the most WPE, WebKit…
47
Beginning fully autonomous operations with the 6th-generation Waymo driver
Waymo will begin fully autonomous operations with its 6th-generation Driver —an important step in bringing our technology to more riders in more cities. This latest system serves as the primary engine for our next era of expansion, with a streamlined configuration that drives down costs while maintaining our…
48
The scourge of x86 emulation
Welcome to the first feature article on our site. We’re going to cover an ongoing problem with x86 emulation that affects every application that we emulate. This comes down to a single over-arching term that has wide-reaching ramifications; Emulating the x86 Total Store Ordering memory model (x86-TSO) .
49
Kernel bugs hide for 2 years on average. Some hide for 20
What I learned mining 125,000 vulnerabilities from Linux git history. The average kernel bug lives 2.1 years before discovery, but some subsystems are far worse.
50
Firecracker VM Escape: PwnEscape Part 2
Firecracker is supposed to keep untrusted code inside a microVM. We escaped it and achieved code execution as root on the host.
51
FFmpeg at Meta: Media Processing at Scale
FFmpeg is truly a multi-tool for media processing. As an industry-standard tool it supports a wide variety of audio and video codecs and container formats. It can also orchestrate complex chains of…
52
Asynchronous I/O in DuckDB: Work, Thread, Work
Starting with v2.0, scheduled for fall 2026, DuckDB will support asynchronous reads of Parquet and CSV files. This can significantly speed up queries when synchronous I/O does not saturate the available bandwidth, as is typical in EC2/S3 compute-storage setups.
53
Neki – Sharded Postgres
Neki, sharded Postgres by PlanetScale, is now available in platform preview.
54
Node.js needs a virtual file system
Node.js now has a virtual filesystem. Learn why VFS matters for testing, sandboxing, Single Executable Apps, and running generated code directly in me
55
30 Years of ReactOS
ReactOS is a free, opensource reimplementation of windows
56
It's the memory latency, stupid
When your database CPU is at 100%, what is it actually doing? Memory stalls, CPU caches, and how radix partitioning makes GROUP BY faster.
57
Nano-vLLM: How a vLLM-style inference engine works
When deploying large language models in production, the inference engine becomes a critical piece of infrastructure.
58
Smaller, faster, safer: running Kimi and GLM at scale
Serving frontier models like Kimi and GLM means fighting for GPU memory. Here's how we quantize KV caches, compress model weights, and add integrity checks to serve them faster, cheaper, and safely.
59
Why is the x86 undefined instruction called ud2? Why 2?
It came after ud0 and ud1.
60
Why we built yet another Postgres connection pooler
PgDog is a connection pooler, load balancer, and sharding proxy for PostgreSQL. Scale Postgres horizontally without rewriting your application.