提交 b4fe5182 编写于 作者: O Oleg Nesterov 提交者: Linus Torvalds

do_wait() wakeup optimization: child_wait_callback: check __WNOTHREAD case

Suggested by Roland.

do_wait(__WNOTHREAD) can only succeed if the caller is either ptracer, or
it is ->real_parent and the child is not traced. IOW, caller == p->parent
otherwise we should not wake up.

Change child_wait_callback() to check this. Ratan reports the workload with
CPU load >99% caused by unnecessary wakeups, should be fixed by this patch.
Signed-off-by: NOleg Nesterov <oleg@redhat.com>
Acked-by: NRoland McGrath <roland@redhat.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Ratan Nalumasu <rnalumasu@gmail.com>
Cc: Vitaly Mayatskikh <vmayatsk@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
上级 0b7570e7
......@@ -1581,6 +1581,9 @@ static int child_wait_callback(wait_queue_t *wait, unsigned mode,
if (!eligible_child(wo, p))
return 0;
if ((wo->wo_flags & __WNOTHREAD) && wait->private != p->parent)
return 0;
return default_wake_function(wait, mode, sync, key);
}
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册