511
Optimizing an Important Atom Primitive
We are archiving Atom and all projects under the Atom organization for an official sunset on December 15, 2022.
Topics /
Systems & Performance
The most popular blog posts about systems & performance on Hacker News. 2,560 posts.
512
November 2022 Progress Report
Porting Linux to Apple Silicon
513
Windows Package Manager Preview
We are thrilled to announce the Windows Package Manager preview! If you’re already familiar with what a package manager is, feel free to skip this
514
Going down the rabbit hole of Git's new bundle-URI
Git's new bundle-uri could help significantly speed up clones, but what bugs lurk within?
515
How We Designed for Performance and Scale
Deliver modern applications with NGINX. Explore high-performance load balancing, API gateways, and web server solutions trusted by top global enterprises.
516
The cost of forsaking C
The C programming language is not trendy. The most recent edition of the canonical C text (the excitingly named The C Programming Language)…
517
The Road to 2M Websocket Connections in Phoenix
If you have been paying attention on Twitter recently, you have likely seen some increasing numbers regarding the number of simultaneous connections the Phoenix web framework can handle. This post documents some of the techniques used to perform the benchmarks.
518
Do we really need swap on modern systems?
Optimize virtual memory management in Red Hat Enterprise Linux: Learn how to configure swap for optimal performance
519
Linux on Snapdragon X Elite: Linaro and Tuxedo Pave the Way for ARM64 Laptops
Linaro Connect 2025 showcases progress in bringing Linux on Snapdragon-Powered Devices
520
The hunt for a cluster-killer Erlang bug (2021)
A 20 minute Kafka outage brought down our entire Erlang cluster for hours. How could this happen? Follow this fascinating investigation!
521
To Message Bus or Not: Distributed Systems Design (2017)
Realize the speed, agility and performance of a scalable, composable web architecture with Netlify. Explore the composable web platform now!
522
Speed, scale and reliability: 25 years of Google datacenter networking evolution
Google networking leaders reflect on the milestones that led to Jupiter supporting 13 petabits per second bandwidth, and what comes next.
523
524
Composable multi-threaded parallelism in Julia
Software performance depends more and more on exploiting multiple processor cores....
525
526
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.
527
Containers and Distributed Systems: Where They Came from and Where They’re Going
Tips from experts, thoughts from leaders, news from the front line. Join the conversation beyond hyperconverged infrastructure to the enterprise cloud.
528
Sieve is simpler than LRU
SIEVE is Simpler than LRU: an Efficient Turn-Key Eviction Algorithm for Web Caches
529
Building a highly-available web service without a database
In this viral post, we explain a new paradigm of building simple clean apps: from prototyping to scaling up.
530
I have come to bury the BIOS, not to open it [video]
Historically, proprietary systems created the need for binary machine interfaces. This extended to the deepest layers of the system, where the PC BIOS was…
531
Fedora 27 released
The Fedora Project proudly announces the release of Fedora 27, its latest leading-edge operating system. Download it free and experience it today.
532
Running three hours of Ruby tests in under three minutes
Stripe uses Sorbet to type check our 15 million lines of Ruby code, making engineers more productive. Here's why we love Sorbet.
533
Keeping Figma Fast: perf-testing the WASM editor
When a laptop crashed in an empty office, we knew it was time to overhaul our performance testing framework.
534
FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-Precision
FlashAttention-3 achieves up to 75% GPU utilization on H100s, making AI models up to 2x faster and enabling efficient processing of longer text inputs. It allows for faster training and inference of LLMs, supports lower precision operations for improved efficiency.
535
Why SQLite is so great for the edge
Everyone already knows that SQLite is great. This article makes the praise much more specific though — it explains why we, the developers of libSQL, think that SQLite is a great choice for bringing your data to the edge.
536
Sourcehut network outage post-mortem
sourcehut is a network of useful open source tools for software project maintainers and collaborators, including git repos, bug tracking, continuous integration, and mailing lists.
537
First in-the-wild UEFI bootkit bypassing UEFI Secure Boot
ESET researchers are the first to publish an analysis of BlackLotus, the first in-the-wild UEFI bootkit capable of bypassing UEFI Secure Boot.
538
Remote iPhone exploitation part 2: a remote ASLR bypass
Posted by Samuel Groß, Project ZeroThis post is the second in a series about a remote, interactio...
539
io_uring is faster than mmap
Sourcing data directly from disk IS faster than caching in memory. I brought receipts. Because hardware got wider but not faster, the old methods don't get you there. You need new tools to use what is scaling and avoid what isn't.
540
Modernizing C arrays for greater memory safety: a case study in the Linux kernel
How to modernize C arrays for greater memory safety: a case-study in refactoring the Linux kernel and a look to the future Kees Cook C i...