resctrl_arch...ycles_lat_fn(9)

πŸ“¦ version 7.3.1, in nixpkgs unstable

✨ NAME ✨

okay so this is from the Kernel API Manual, and the manual page is filed under the truncated little handle resctrl_arch...ycles_lat_fn(9). The actual main character is resctrl_arch_measure_cycles_lat_fn β€” it measures cycle latency to read pseudo-locked memory πŸŽ€


πŸ¦‹ SYNOPSIS πŸ¦‹

int resctrl_arch_measure_cycles_lat_fn (void *_plr );

🌸 ARGUMENTS 🌸

  • _plr β€” the pseudo-lock region to measure, bestie. That's the thing we're checking on πŸ’…

πŸ’– DESCRIPTION πŸ’–

ngl, there is no deterministic way to test if a memory region is cached. Like, none. So one way is to measure how long it takes to read the memory β€” the speed of access is a good way to learn how close to the cpu the data was ✨

Even more iconic: if the prefetcher is disabled and the memory is read at a stride of half the cache line, then a cache miss will be easy to spot, since the read of the first half would be significantly slower than the read of the second half πŸ‘‘


⭐ RETURN ⭐

  • 0 β€” waiter on waitqueue will be woken on completion. slay πŸ’«

🫢 SEE ALSO 🫢


and that's the vibe check, bestie πŸ’œ this cutie lives in the source tree at ./arch/x86/kernel/cpu/resctrl, dated October 2026, and signs off as resctrl_arch...ycles_lat_fn(9) β€” mwah πŸ’‹πŸŽ€

πŸ“¦ where this page comes from