Tag
A technical deep-dive explaining how traditional lock coupling in concurrent binary trees suffers from physical lock contention at the root node, limiting scalability as CPU core counts grow, with benchmark results on a 16-core system.
This article provides a detailed comparison of arena architecture in malloc() algorithms, discussing memory allocation problems in multithreaded programs and the evolution of frontend and backend designs in memory allocators.
A comprehensive guide on how an HTTP server works, covering networking protocols, chunked encoding, state machines, parser writing, and concurrency basics, with instructions to build one yourself.
The article introduces Linux restartable sequences (rseq), a kernel feature that enables thread-safe data structures without locks or atomics, achieving dramatic performance improvements on many-core CPUs. It provides a tutorial and demonstrates up to 43x speedup on a 96-core AMD Threadripper.