diff options
| author | Namhyung Kim <namhyung@kernel.org> | 2026-02-11 14:32:20 -0800 |
|---|---|---|
| committer | Peter Zijlstra <peterz@infradead.org> | 2026-02-27 16:40:21 +0100 |
| commit | bec2ee2390c95ed0c44494340464e69e79802e4a (patch) | |
| tree | fdb7001b7fc00b57d4d74a4e75db0f04152bd90c /kernel | |
| parent | 28c75fbfec8f024db1278194918e5f6eda4c570f (diff) | |
perf/core: Try to allocate task_ctx_data quickly
The attach_global_ctx_data() has O(N^2) algorithm to allocate the
context data for each thread. This caused perfomance problems on large
systems with O(100k) threads.
Because kmalloc(GFP_KERNEL) can go sleep it cannot be called under the
RCU lock. So let's try with GFP_NOWAIT first so that it can proceed in
normal cases.
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/20260211223222.3119790-3-namhyung@kernel.org
Diffstat (limited to 'kernel')
| -rw-r--r-- | kernel/events/core.c | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/kernel/events/core.c b/kernel/events/core.c index 90b0c9324cbf..d357714fc02e 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -5489,6 +5489,12 @@ again: cd = NULL; } if (!cd) { + /* + * Try to allocate context quickly before + * traversing the whole thread list again. + */ + if (!attach_task_ctx_data(p, ctx_cache, true, GFP_NOWAIT)) + continue; get_task_struct(p); goto alloc; } |