| commit | accd4f36a7d11c2d54544007eb65e10604dcf2f5 | [log] [tgz] |
|---|---|---|
| author | Eric Dumazet <edumazet@google.com> | Fri Feb 23 08:12:42 2018 -0800 |
| committer | Tejun Heo <tj@kernel.org> | Fri Feb 23 08:52:34 2018 -0800 |
| tree | 49498cc42444c9e2295a895d518cee0597513806 | |
| parent | 554fef1c39ee148623a496e04569dabb11463406 [diff] |
percpu: add a schedule point in pcpu_balance_workfn() When a large BPF percpu map is destroyed, I have seen pcpu_balance_workfn() holding cpu for hundreds of milliseconds. On KASAN config and 112 hyperthreads, average time to destroy a chunk is ~4 ms. [ 2489.841376] destroy chunk 1 in 4148689 ns ... [ 2490.093428] destroy chunk 32 in 4072718 ns Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Tejun Heo <tj@kernel.org>