sched_set_itmt_core_prio(9)
okay so bestie, you're looking at the Kernel API Manual page for sched_set_itmt_core_prio(9) β yes, the whole name, and yes, it's giving kernel-core realness π
β¨
πΈ NAME πΈ
sched_set_itmt_core_prio β Set CPU priority based on ITMT π
β¨ SYNOPSIS β¨
void sched_set_itmt_core_prio (int prio , int cpu );
that's the whole vibe: prio first, then cpu, no cap π
π ARGUMENTS π
prioβ Priority of cpu π like, the priority level you're handing over, bestie.cpuβ The CPU number π the actual CPU ID getting that priority.
π DESCRIPTION π
okay so the pstate driver is the main character here: it will find out the max boost frequency and call this function to set a priority proportional to the max boost frequency. CPUs with higher boost frequency will receive higher priority β literally "higher boost, higher priority" energy π₯ no cap.
and the best part? no need to rebuild sched domain after updating the CPU priorities. the sched domains have no dependency on CPU priorities, so they're literally unbothered π«Άβ¨
the way that sched domains have zero dependency on CPU priorities and need zero rebuild is so iconic, fr fr π
π¦ SEE ALSO π¦
- Kernel file
./arch/x86/kernel/itmt.cπ sched_set_itmt_support(9)β¨sched_clear_itmt_support(9)π
this page lives in ./arch/x86/kernel, dated October 2026, and it's the sched_set_itmt_core_prio(9) version β slay, bestie, bye! πππ¦
π¦ where this page comes from
- nixpkgs unstable: linux-manual 7.3.1
- π girlified by deepseek-ai/DeepSeek-V4.1-Flash-1017 on : a language model's rewrite of the original, under its terms