121
Spotting and avoiding heap fragmentation in Rust applications
One of our Rust services started to show an odd memory profile. This is the story of how we investigated the issue.
122
123
Memory Copy Hunting
I have a super power. I want to share it in this blog post so that you, my dear reader, also have it!
124
Reducing Tailscale’s binary size on macOS
Tailscale v1.36 for macOS features a significantly reduced binary size (going from 92MB to 56MB). The effort started out with a chance observation about a surprisingly large executable, and ended up involving some creative approaches using dlopen.
125
Postgres WAL Files and Sequence Numbers
Go inside the WAL file with this in-depth look at WAL file Log Sequence Number (LSN), WAL segment positions, WAL file names, and pg_switch_wal.
126
Prompt – A terminal for a container-oriented desktop
Prompt is a terminal that marries the best of GNOME Builder’s seamless container support, the beauty of GNOME Text Editor, and the robustness of VTE. I like to think of it as a companion terminal to Builder. Though it's also useful for immutable/container-oriented desktops like Fedora Silverblue or Project Bluefin…
127
On-Crash Backtraces in Swift
The new Swift 5.9 release contains a number of helpful, new features for debugging code, including an out-of-process, interactive crash handler to inspect crashes in real time, the ability to trigger the debugger for just-in-time debugging, along with concurrency-aware backtracing to make it easier to understand…
128
x86 is dead, long live x86
The last couple of years have been quite revolutionary in the Silicon industry as a whole. With the resurgence of horizo
129
-Werror Is not your friend (2017)
22 May 2017 by Phillip Johnston • Last updated 27 October 2023I want to make a few points up front to short-circuit common misunderstandings with this article: I have a zero warning policy on my projects. I turn on a lot of warnings. -Wall, -Wextra, and a whole host of specific warning flags. I supplement … Continue…
130
PostgreSQL Logical Replication Explained
Vigneshwaran C explained the internals of PostgreSQL Logical Replication during PGConf India - if you were not able to attend, you can read all here.
131
Box64 and RISC-V
Box64 and RISC-V, the challenges of wrtting the Dynarec, and benchmarks
132
Batch computing and the coming age of AI systems
There’s a lot of excitement right now about human-in-the-loop systems supercharged by foundation models including chat assistants ( ChatGPT ), word processing ( Microsoft Office ), graphic design ( Stable Diffusion ), and code editing ( Copilot ). However, these systems only begin to scratch the surface of the role…
133
Chapel 1.32
A summary of highlights from the September 2023 release of Chapel 1.32.0
134
We Built a Streaming SQL Engine
A streaming SQL engine keeps queries’ results up to date without ever having to recalculate them, even as the underlying data changes. To explain this, imagine a simple query, such as SELECT count(*) FROM humans
135
AI’s compute fragmentation: what matrix multiplication teaches us
AI is powered by a virtuous circle of data, algorithms (“models”), and compute. Growth in one pushes needs in the others and can grossly affect the developer experience on aspects like usability and performance. Today, we have more data and more AI model research than ever before, but compute isn’t scaling at the same…
136
Would we still create Nebula today?
Spoiler: Yes. (But the "why" matters. A lot.)
137
Haiku's (Kernel) Condition Variables API: Design and Implementation
A few months after my contract with Haiku, Inc. began, I rewrote the implementation of the Haiku kernel’s condition variables (as opposed to our userspace condition variables, which are from POSIX.) As this new implementation has run in Haiku …
138
GCC always assumes aligned pointer accesses (2020)
Explore the risks associated with unaligned pointer accesses in GCC. Understand how these assumptions can lead to unexpected program behavior and potential security vulnerabilities. Learn best practices to mitigate these risks and write secure code.
139
Gaia-1 a 9B parameter generative world model for autonomous driving
Scaling GAIA-1: a 9-billion parameter generative world model for autonomous driving
140
Nix Survival Mode: macOS upgrades won't break Nix anymore
For years, macOS upgrades have broken Nix. We've updated the Determinate Nix Installer to ensure that this no longer happens, eliminating yet another annoyance for macOS users.
141
Envisioning a Simplified Intel Architecture
Intel investigated architectural enhancements and modifications for a 64-bit mode-only architecture.
142
Service Weaver: A Framework for Writing Distributed Applications
The latest news from Google on open source releases, major projects, events, and outreach programs for early career developers.
143
How Turborepo is porting from Go to Rust
Our strategy for making updates and maintaining stability while we migrate languages.
144
Real-time Ubuntu is now generally available
Real-time Ubuntu brings end-to-end security and reliability to the time-bound workloads of modern enterprises. With support for real-time compute, Canonical furthers its commitment to providing a best-in-class experience for open-source software consumption. 14 February 2023, London: Canonical today announced the…
145
Strong Consistency with Raft and SQLite
In the recent past, a typical client/server environment consisted of multiple clients connected to a central database server. A central database architecture is a system where all data is stored in a single centralized location. When client A from Si...
146
Google's response to Reptar CPU vulnerability
Just as Vulnerability Research is an important area of focus at Google, so is Vulnerability Response to critical and complex vulnerabilities. Vulnerability Response at Google not only helps secure Google’s products and users, but in certain cases, it affects millions of devices across the Internet. In this post, we'll…
147
Kubernetes and Kernel Panics
How Netflix’s Container Platform Connects Linux Kernel Panics to Pods
148
ReactOS Newsletter 103 – Late 2023 News
ReactOS is a free, opensource reimplementation of windows
149
Making GHC faster at emitting code (2022)
How we gained 2–3% improvements in compile times by making GHC better at printing code.
150
Continuous batching to increase LLM inference throughput and reduce p50 latency
In this blog, we discuss continuous batching, a critical systems-level optimization that improves both throughput and latency under load for LLMs.