diff options
| author | Namhyung Kim <namhyung@kernel.org> | 2026-02-12 01:32:20 +0300 |
|---|---|---|
| committer | Peter Zijlstra <peterz@infradead.org> | 2026-02-27 18:40:21 +0300 |
| commit | bec2ee2390c95ed0c44494340464e69e79802e4a (patch) | |
| tree | fdb7001b7fc00b57d4d74a4e75db0f04152bd90c /scripts/dev-needs.sh | |
| parent | 28c75fbfec8f024db1278194918e5f6eda4c570f (diff) | |
| download | linux-bec2ee2390c95ed0c44494340464e69e79802e4a.tar.xz | |
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 'scripts/dev-needs.sh')
0 files changed, 0 insertions, 0 deletions