cpu_latency_...date_request(9)

📦 version 7.3.1, in nixpkgs unstable

💅 cpu_latency_qos_update_request(9) 💅

okay so bestie, welcome to the kernel API manual — this one's from cpu_latency_...date_request(9), and it's lowkey about tweaking a CPU latency QoS request you already made. yes, "update", not "create". we're editing, not starting fresh ✨

✨ NAME ✨

cpu_latency_qos_update_request — Modify existing CPU latency QoS request.

like, the request is already there, and you're giving it a glow-up. no cap 🫶

🌸 SYNOPSIS 🌸

void cpu_latency_qos_update_request (struct pm_qos_request *req , s32
new_value );

that's it, that's the whole vibe check. takes a pointer and a number, returns void — it's giving "I do the work, I don't report back" main character energy 💅

🎀 ARGUMENTS 🎀

  • req — the QoS request to update. bestie, this is the one you're modifying, so it better already exist 🙈
  • new_value — the new requested constraint value. it's an s32, and it's literally the new number you want the request to hold ✨

🦋 DESCRIPTION 🦋

so here's the tea: you use new_value to update the QoS request represented by req in the CPU latency QoS list, along with updating the effective constraint value for that list. 🔥

both things happen — the request itself gets the new value, and the list's effective constraint value gets refreshed. one call, two updates, iconic behavior fr fr 👑

🌈 SEE ALSO 🌈

Kernel file ./kernel/power/qos.c, plus the whole friend group:

bestie, go read the neighbours too — you'll understand the whole QoS friend group way better, iykyk 🧚

and that's the page!! sourced from ./kernel/power, dated October 2026 — mwah, slay, periodt 💖🎀🦋

📦 where this page comes from