121
Patterns of Distributed Systems (2020)
A catalog of patterns to better understand, communicate, and teach the design of distributed systems
Topics /
Systems & Performance
The most popular blog posts about systems & performance on Hacker News. 553 posts.
122
Slack’s Outage on January 4th 2021
And now we welcome the new year. Full of things that have never been. — Rainer Maria Rilke January 4th 2021 was the first working day of the year for many around the globe, and for most of us at Slack too (except of course for our on-callers and our customer experience team, who never…
123
Users are losing out against Big Sur’s sealed System
macOS 11.2, 11.2.1 and 11.2.2 have come in quick succession. What do they tell us about how difficult it is to update Big Sur’s sealed System volume? Is this the way to go?
124
The LZ4 introduced in PostgreSQL 14 provides faster compression
Haiying Tang takes you on a tour of LZ$ TOAST, the new column opton compression in PostgreSQL 14, and shows the speed and compression ratio gains.
125
Anatomy of a Terminal Emulator
How does a terminal emulator work? What are ANSI escape codes? Understanding terminal internals for development, fun and mischief.
126
Simple Systems Have Less Downtime (2020)
The Maersk Triple-E Class container ship is 1,300 feet long, carries over 18,000 containers across 11,000 miles between Europe and Asia, and… Its entire crew can fit inside a passenger van. As a former naval architect and a current marketing consultant to startups, I found that
127
2021 Williams F1 Computational Fluid Dynamics
Thanks to some clever people I was able to get a CAD model of the current 2021 Williams F1 car — that’s not something that happens every day, so of course I had to run CFD on it. CAD Ge…
128
How Facebook encodes videos
People upload hundreds of millions of videos to Facebook every day. Making sure every video is delivered at the best quality — with the highest resolution and as little buffering as possible — mean…
129
How C++ Resolves a Function Call
C is a simple language. You’re only allowed to have one function with each name. C++, on the other hand, gives you much more flexibility: You can have multiple functions …
130
Debugging a Linux network stack crash via a single register value
It’s not every day that you get to debug what may well be a packet of death. It was certainly the first time for me. What do I mean by “a packet of death”? A software bug where the network stack crashes in reaction to a single received network packet, taking down the whole operating system with it.
131
V8 Sparkplug – A non-optimizing JavaScript compiler
In V8 v9.1 we’re improving V8 performance by 5–15% with Sparkplug: a new, non-optimizing JavaScript compiler.
132
M.2 on a Raspberry Pi – The Tofu CM4 Carrier Board
Ever since the Pi 2 model B went to a 4-core processor, disk IO has often been the primary bottleneck for my Pi projects. You can use microSD cards, which aren't horrible, but... well, nevermind, they're pretty bad as a primary disk. Or you can plug in a USB 3.0 SSD and get decent speed, but you end up with a cabling…
133
Avoiding Complexity with Systemd
Using systemd to avoid having to write some risky code
134
You need to be able to run your system
"Run the unit tests" doesn't count. The complexity of your system is in the interactions between the units.
135
Writing a register based VM in less than 125 lines of C code
This tutorial is intended for intermediate C developers who want to get some coding practice and, in the process, gain valuable insights into low-level programming and how (some) Virtual Machines operate under the hood. The reader should already be comfortable with bitwise operations, hexadecimal notation, pointers…
136
137
138
139
Beating TimSort at Merging
Learn how to beat TimSort at merging sorted lists in Python by creating a C extension. Discover the performance advantages of merging lists compare...
140
Io_uring is not an event system
I’ve been hearing about io_uring on and off for the last couple of years. Its a relatively new technology in Linux to allow high-performance IO with very few overheads. Whenever its been mentioned, its usually been presented as a new alternative to select, poll and epoll. This led me to believe that it was just the…
141
Firefox's Optimized Zip Format
This post is about minimizing amount of disk IO and CPU overhead when reading Zip files. I recently saw an article about a new format that was faster than zip. This is quite surprising as to my mind, zip is one of the most flexible and low-overhead formats I’ve encountered. Some googling showed me that over past 11…
142
FreeBSD Jails for Fun and Profit (2020)
Docker has recently stormed into software development. While its concepts are powerful and valuable, similar tools have been used in systems for decades. FreeBSD’s jails in one of those tools which build upon even older chroot(2). To put it shortly, with these tools, you can make a safe environment separated from the…
143
The Pinecone Overlay Network
Matrix, the open protocol for secure decentralised communications
144
145
Benchmarking division and libdivide on Apple M1 and Intel AVX512
libdivide is fish ’s library for speeding up integer division by runtime constants. It works by replacing divide instructions with cheaper multiplications and shifts.
146
Running Nomad for a Home Server
Setting up a single node Nomad and Consul server to deploy self hosted workloads.
147
Reverse-Engineering Apple Dictionary (2020)
Personal webpage of Fabian Mentzer.
148
How X Window Managers Work, and How to Write One (2014)
How X Window Managers Work, And How To Write One (Part I)
149
My Fanless OpenBSD Desktop
After the disappointment of my X1 Nano and learning that all future Intel "Evo"-branded laptops would lack S3 suspend, I started thinking about returning to my M1 MacBook full-time or building an OpenBSD desktop. I chose the latter, building my first desktop machine in many years.
150
Apple Silicon Hardware: SPRR and Guarded Exception Levels (GXF)
Over a year ago siguza published a write-up about Apple’s APRR - a custom ARM extension that redefines pagetable permissions and protects certain parts of the kernel from itself. Since then Apple has released their M1 chip which not only features an updated version of APRR but also easily allows to run bare-metal code…