Re: sys_epoll_wait high CPU load in 2.6.37

[Shawn Bohrer <shawn.bohrer@gmail.com>]

On Wed, Jan 26, 2011 at 05:13:29PM +0100, Eric Dumazet wrote:
> Le mercredi 26 janvier 2011 à 16:59 +0100, Eric Dumazet a écrit :
> > Le mercredi 26 janvier 2011 à 07:52 -0800, Davide Libenzi a écrit :
> > 
> > > For "above", I meant the current epoll expire time calculation, which was 
> > > described above in the message ;)
> > 
> > Well, problem was not an overflow, but doing a loop 2.000.000 times ;)
> > 
> > > The hint for a timespec_add_ms() was because we must be doing something 
> > > similar in poll, don't we (/me got no code in front ATM)?
> > 
> > Apparently its done differently in poll(), using
> > poll_select_set_timeout() helper.
> > 
> > 
> > Give me some minutes I'll try to cook an alternate patch
> > 
> 
> Here is the alternate patch, using poll_select_set_timeout() helper
> 
> Thanks
> 
> [PATCH v2] epoll: epoll_wait() should not use timespec_add_ns()
> 
> commit 95aac7b1cd224f (epoll: make epoll_wait() use the hrtimer range
> feature) added a performance regression because it uses
> timespec_add_ns() with potential very large 'ns' values.
> 
> Use poll_select_set_timeout() helper like poll()/select()
> 
> Reported-by: Simon Kirby <sim@hostway.ca>
> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
> CC: Shawn Bohrer <shawn.bohrer@gmail.com>
> CC: Davide Libenzi <davidel@xmailserver.org>
> CC: Thomas Gleixner <tglx@linutronix.de>
> CC: Andrew Morton <akpm@linux-foundation.org>
> ---
>  fs/eventpoll.c |    4 ++--
>  1 file changed, 2 insertions(+), 2 deletions(-)
> 
> diff --git a/fs/eventpoll.c b/fs/eventpoll.c
> index cc8a9b7..94d887b 100644
> --- a/fs/eventpoll.c
> +++ b/fs/eventpoll.c
> @@ -1125,8 +1125,8 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
>  	ktime_t expires, *to = NULL;
>  
>  	if (timeout > 0) {
> -		ktime_get_ts(&end_time);
> -		timespec_add_ns(&end_time, (u64)timeout * NSEC_PER_MSEC);
> +		poll_select_set_timeout(&end_time, timeout / MSEC_PER_SEC,
> +				NSEC_PER_MSEC * (timeout % MSEC_PER_SEC));
>  		slack = select_estimate_accuracy(&end_time);
>  		to = &expires;
>  		*to = timespec_to_ktime(end_time);

poll_select_set_timeout() jumps through some extra hoops that
aren't necessary in the epoll case so I actually like your previous
patch better.

--
Shawn