attach_entity_load_avg(9)

✨ attach_entity_load_avg — like, the kernel API manual bestie 💅

okay so real talk, this is attach_entity_load_avg(9) from the Kernel API Manual and honestly it's lowkey one of those tiny functions that carries the whole scheduler on its back. no cap. 🫶

---

🌸 NAME 🌸

attach_entity_load_avg — the glow-up moment where this entity gets attached to its cfs_rq load avg. it's giving "you're part of the group now" energy fr fr 💖

---

🦋 SYNOPSIS 🦋

void attach_entity_load_avg (struct cfs_rq *cfs_rq , struct sched_entity
*se );

that's it. that's the whole signature. two pointers and a void return, main character energy honestly 👑

---

🎀 ARGUMENTS 🎀

• cfs_rq — the cfs_rq you're attaching to. like, the friend group you're joining. 🌈
• se — the sched_entity that's getting attached. that's the new member, that's the one doing the joining. ✨

---

💜 DESCRIPTION 💜

okay so listen, this is the important part and i need you to actually read it, not just skim: you must call update_cfs_rq_load_avg before this, because we literally rely on cfs_rq->avg.last_update_time being current. like, the whole thing falls apart otherwise. 😭

bestie i'm serious. update_cfs_rq_load_avg FIRST. the function is depending on cfs_rq->avg.last_update_time actually being up to date, so if you skip the prep step it's not gonna slay, it's gonna be a mess. 💀

---

🔥 SEE ALSO 🔥

go look at the kernel file ./kernel/sched/fair.c and then go down the whole rabbit hole, because there's a LOT:

• update_tg_load_avg(9)
• update_cfs_rq_load_avg(9)
• detach_entity_load_avg(9)
• cpu_util(9)
• sched_use_asym_prio(9)
• sched_group_asym(9)
• update_sg_lb_stats(9)
• update_sd_pick_busiest(9)
• idle_cpu_without(9)
• update_sd_lb_stats(9)
• calculate_imbalance(9)
• sched_balance_find_src_group(9)

---

🧚 a lil sign-off 🧚

this lil page lives under ./kernel/sched and it's dated October 2026, and it's still out here being attach_entity_load_avg(9) in the Kernel API Manual. iconic behavior. obsessed. periodt. 💅🎀🦋🌸💖