Field notes on NUMA, tail latency, thread pinning, and the parts of Linux performance most Rust runtimes leave on the table.https://numaperf.skelfresearch.com/en-ushttps://numaperf.skelfresearch.com/blog/reading-numastat-without-lying/https://numaperf.skelfresearch.com/blog/reading-numastat-without-lying/numastat will happily tell you a story that confirms whatever you wanted to believe. Here’s how to read it like a hostile witness.Thu, 21 May 2026 00:00:00 GMTobservabilitynumatoolinghttps://numaperf.skelfresearch.com/blog/pinning-vs-scheduling/https://numaperf.skelfresearch.com/blog/pinning-vs-scheduling/Async runtimes are excellent at one thing and indifferent at another. Knowing which is which is the difference between a clean p99 and an angry pager.Thu, 09 Apr 2026 00:00:00 GMTruntimeschedulingrusthttps://numaperf.skelfresearch.com/blog/when-numa-actually-matters/https://numaperf.skelfresearch.com/blog/when-numa-actually-matters/Most workloads don’t need explicit NUMA control. The ones that do, very badly do. A practical recipe for figuring out which one you’re running.Wed, 04 Mar 2026 00:00:00 GMTnumatail latencyrust