From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753531Ab1AZSpn (ORCPT ); Wed, 26 Jan 2011 13:45:43 -0500 Received: from mail-ww0-f42.google.com ([74.125.82.42]:48979 "EHLO mail-ww0-f42.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751728Ab1AZSpm (ORCPT ); Wed, 26 Jan 2011 13:45:42 -0500 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=subject:from:to:cc:in-reply-to:references:content-type:date :message-id:mime-version:x-mailer:content-transfer-encoding; b=iCr0UtzNrWjnOv4JCAL/5E45YDjub0jEas2buSEuLoHwzFGQCENo+0Hxqinc9erXDl uk4AxckTo6IBJdB81xrxLIZCL3Q5SUbitbZ4qnvC2PqmD4a+XmedMezBwEzwSQxw2Z3V VCwrk/HibkFuhSC1OonbADiLKYZv6ERxBcdAQ= Subject: Re: sys_epoll_wait high CPU load in 2.6.37 From: Eric Dumazet To: Davide Libenzi Cc: Shawn Bohrer , Simon Kirby , Linux Kernel Mailing List , Andrew Morton , Thomas Gleixner In-Reply-To: <1296065900.2899.108.camel@edumazet-laptop> References: <20110126000932.GA23089@hostway.ca> <1296026298.2633.19.camel@edumazet-laptop> <1296040578.2899.59.camel@edumazet-laptop> <1296056600.2899.66.camel@edumazet-laptop> <1296057590.2899.73.camel@edumazet-laptop> <1296058409.2899.81.camel@edumazet-laptop> <20110126172006.GA9568@BohrerMBP.rgmadvisors.com> <1296064311.2899.90.camel@edumazet-laptop> <1296065900.2899.108.camel@edumazet-laptop> Content-Type: text/plain; charset="UTF-8" Date: Wed, 26 Jan 2011 19:45:37 +0100 Message-ID: <1296067537.2899.153.camel@edumazet-laptop> Mime-Version: 1.0 X-Mailer: Evolution 2.30.3 Content-Transfer-Encoding: 8bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Le mercredi 26 janvier 2011 à 19:18 +0100, Eric Dumazet a écrit : > Le mercredi 26 janvier 2011 à 10:06 -0800, Davide Libenzi a écrit : > > > Eric, if you look at fs/select.c (~line 925), poll does exactly the same > > thing as epoll do. > > It too, ignores the eventual return value of poll_select_set_timeout(), so > > maybe a little bit more optimized ktime_get_ts+timespec_add_ms could make > > sense. > > > > OK, I'll post a V3 ;) Well in the poll() case we handle a zero timeout, not in epoll(). So the helper function cannot be shared and can be static to epoll. [PATCH v3] 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. Reported-by: Simon Kirby Signed-off-by: Eric Dumazet CC: Shawn Bohrer CC: Davide Libenzi CC: Thomas Gleixner CC: Andrew Morton --- fs/eventpoll.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) diff --git a/fs/eventpoll.c b/fs/eventpoll.c index cc8a9b7..d517aa3 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1114,6 +1114,17 @@ static int ep_send_events(struct eventpoll *ep, return ep_scan_ready_list(ep, ep_send_events_proc, &esed); } +static inline struct timespec epoll_set_mstimeout(long ms) +{ + struct timespec now, ts = { + .tv_sec = ms / MSEC_PER_SEC, + .tv_nsec = NSEC_PER_MSEC * (ms % MSEC_PER_SEC), + }; + + ktime_get_ts(&now); + return timespec_add_safe(now, ts); +} + static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, int maxevents, long timeout) { @@ -1121,12 +1132,11 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, unsigned long flags; long slack; wait_queue_t wait; - struct timespec end_time; ktime_t expires, *to = NULL; if (timeout > 0) { - ktime_get_ts(&end_time); - timespec_add_ns(&end_time, (u64)timeout * NSEC_PER_MSEC); + struct timespec end_time = epoll_set_mstimeout(timeout); + slack = select_estimate_accuracy(&end_time); to = &expires; *to = timespec_to_ktime(end_time);