Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753105AbZJCFtB (ORCPT ); Sat, 3 Oct 2009 01:49:01 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752494AbZJCFtA (ORCPT ); Sat, 3 Oct 2009 01:49:00 -0400 Received: from mail.gmx.net ([213.165.64.20]:56559 "HELO mail.gmx.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with SMTP id S1751001AbZJCFs7 (ORCPT ); Sat, 3 Oct 2009 01:48:59 -0400 X-Authenticated: #14349625 X-Provags-ID: V01U2FsdGVkX1+Any0k0C2ASw0kR7tnYj3YshrQ8KwShxHUGhLo8s jqjR+LtNb4K42I Subject: Re: IO scheduler based IO controller V10 From: Mike Galbraith To: Jens Axboe Cc: Ingo Molnar , Linus Torvalds , Vivek Goyal , Ulrich Lukas , linux-kernel@vger.kernel.org, containers@lists.linux-foundation.org, dm-devel@redhat.com, nauman@google.com, dpshah@google.com, lizf@cn.fujitsu.com, mikew@google.com, fchecconi@gmail.com, paolo.valente@unimore.it, ryov@valinux.co.jp, fernando@oss.ntt.co.jp, jmoyer@redhat.com, dhaval@linux.vnet.ibm.com, balbir@linux.vnet.ibm.com, righi.andrea@gmail.com, m-ikeda@ds.jp.nec.com, agk@redhat.com, akpm@linux-foundation.org, peterz@infradead.org, jmarchan@redhat.com, riel@redhat.com In-Reply-To: <20091002181903.GN31616@kernel.dk> References: <20091002092839.GA26962@kernel.dk> <20091002145610.GD31616@kernel.dk> <20091002171129.GG31616@kernel.dk> <20091002172046.GA2376@elte.hu> <20091002172554.GJ31616@kernel.dk> <20091002172842.GA4884@elte.hu> <20091002173732.GK31616@kernel.dk> <1254507215.8667.7.camel@marge.simson.net> <20091002181903.GN31616@kernel.dk> Content-Type: text/plain Date: Sat, 03 Oct 2009 07:48:51 +0200 Message-Id: <1254548931.8299.18.camel@marge.simson.net> Mime-Version: 1.0 X-Mailer: Evolution 2.24.1.1 Content-Transfer-Encoding: 7bit X-Y-GMX-Trusted: 0 X-FuHaFi: 0.41 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 5762 Lines: 177 On Fri, 2009-10-02 at 20:19 +0200, Jens Axboe wrote: > If you could do a cleaned up version of your overload patch based on > this: > > http://git.kernel.dk/?p=linux-2.6-block.git;a=commit;h=1d2235152dc745c6d94bedb550fea84cffdbf768 > > then lets take it from there. If take it from there ends up meaning apply, and see who squeaks, feel free to delete the "Not", and my somewhat defective sense of humor. Block: Delay overloading of CFQ queues to improve read latency. Introduce a delay maximum dispatch timestamp, and stamp it when: 1. we encounter a known seeky or possibly new sync IO queue. 2. the current queue may go idle and we're draining async IO. 3. we have sync IO in flight and are servicing an async queue. 4 we are not the sole user of disk. Disallow exceeding quantum if any of these events have occurred recently. Protect this behavioral change with a "desktop_dispatch" knob and default it to "on".. providing an easy means of regression verification prior to hate-mail dispatch :) to CC list. Signed-off-by: Mike Galbraith Cc: Jens Axboe Cc: Linus Torvalds Cc: Andrew Morton ... others who let somewhat hacky tweak slip by LKML-Reference: --- block/cfq-iosched.c | 45 +++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 41 insertions(+), 4 deletions(-) Index: linux-2.6/block/cfq-iosched.c =================================================================== --- linux-2.6.orig/block/cfq-iosched.c +++ linux-2.6/block/cfq-iosched.c @@ -174,6 +174,9 @@ struct cfq_data { unsigned int cfq_slice_async_rq; unsigned int cfq_slice_idle; unsigned int cfq_desktop; + unsigned int cfq_desktop_dispatch; + + unsigned long desktop_dispatch_ts; struct list_head cic_list; @@ -1283,6 +1286,7 @@ static int cfq_dispatch_requests(struct struct cfq_data *cfqd = q->elevator->elevator_data; struct cfq_queue *cfqq; unsigned int max_dispatch; + unsigned long delay; if (!cfqd->busy_queues) return 0; @@ -1297,19 +1301,26 @@ static int cfq_dispatch_requests(struct /* * Drain async requests before we start sync IO */ - if (cfq_cfqq_idle_window(cfqq) && cfqd->rq_in_driver[BLK_RW_ASYNC]) + if (cfq_cfqq_idle_window(cfqq) && cfqd->rq_in_driver[BLK_RW_ASYNC]) { + cfqd->desktop_dispatch_ts = jiffies; return 0; + } /* * If this is an async queue and we have sync IO in flight, let it wait */ - if (cfqd->sync_flight && !cfq_cfqq_sync(cfqq)) + if (cfqd->sync_flight && !cfq_cfqq_sync(cfqq)) { + cfqd->desktop_dispatch_ts = jiffies; return 0; + } max_dispatch = cfqd->cfq_quantum; if (cfq_class_idle(cfqq)) max_dispatch = 1; + if (cfqd->busy_queues > 1) + cfqd->desktop_dispatch_ts = jiffies; + /* * Does this cfqq already have too much IO in flight? */ @@ -1327,6 +1338,16 @@ static int cfq_dispatch_requests(struct return 0; /* + * Don't start overloading until we've been alone for a bit. + */ + if (cfqd->cfq_desktop_dispatch) { + delay = cfqd->desktop_dispatch_ts + cfq_slice_sync; + + if (time_before(jiffies, max_delay)) + return 0; + } + + /* * we are the only queue, allow up to 4 times of 'quantum' */ if (cfqq->dispatched >= 4 * max_dispatch) @@ -1942,7 +1963,7 @@ static void cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq, struct cfq_io_context *cic) { - int old_idle, enable_idle; + int old_idle, enable_idle, seeky = 0; /* * Don't idle for async or idle io prio class @@ -1950,10 +1971,20 @@ cfq_update_idle_window(struct cfq_data * if (!cfq_cfqq_sync(cfqq) || cfq_class_idle(cfqq)) return; + if (cfqd->hw_tag) { + if (CIC_SEEKY(cic)) + seeky = 1; + /* + * If seeky or incalculable seekiness, delay overloading. + */ + if (seeky || !sample_valid(cic->seek_samples)) + cfqd->desktop_dispatch_ts = jiffies; + } + enable_idle = old_idle = cfq_cfqq_idle_window(cfqq); if (!atomic_read(&cic->ioc->nr_tasks) || !cfqd->cfq_slice_idle || - (!cfqd->cfq_desktop && cfqd->hw_tag && CIC_SEEKY(cic))) + (!cfqd->cfq_desktop && seeky)) enable_idle = 0; else if (sample_valid(cic->ttime_samples)) { if (cic->ttime_mean > cfqd->cfq_slice_idle) @@ -2483,6 +2514,9 @@ static void *cfq_init_queue(struct reque cfqd->cfq_slice_async_rq = cfq_slice_async_rq; cfqd->cfq_slice_idle = cfq_slice_idle; cfqd->cfq_desktop = 1; + cfqd->cfq_desktop_dispatch = 1; + + cfqd->desktop_dispatch_ts = INITIAL_JIFFIES; cfqd->hw_tag = 1; return cfqd; @@ -2553,6 +2587,7 @@ SHOW_FUNCTION(cfq_slice_sync_show, cfqd- SHOW_FUNCTION(cfq_slice_async_show, cfqd->cfq_slice[0], 1); SHOW_FUNCTION(cfq_slice_async_rq_show, cfqd->cfq_slice_async_rq, 0); SHOW_FUNCTION(cfq_desktop_show, cfqd->cfq_desktop, 0); +SHOW_FUNCTION(cfq_desktop_dispatch_show, cfqd->cfq_desktop_dispatch, 0); #undef SHOW_FUNCTION #define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV) \ @@ -2585,6 +2620,7 @@ STORE_FUNCTION(cfq_slice_async_store, &c STORE_FUNCTION(cfq_slice_async_rq_store, &cfqd->cfq_slice_async_rq, 1, UINT_MAX, 0); STORE_FUNCTION(cfq_desktop_store, &cfqd->cfq_desktop, 0, 1, 0); +STORE_FUNCTION(cfq_desktop_dispatch_store, &cfqd->cfq_desktop_dispatch, 0, 1, 0); #undef STORE_FUNCTION #define CFQ_ATTR(name) \ @@ -2601,6 +2637,7 @@ static struct elv_fs_entry cfq_attrs[] = CFQ_ATTR(slice_async_rq), CFQ_ATTR(slice_idle), CFQ_ATTR(desktop), + CFQ_ATTR(desktop_dispatch), __ATTR_NULL }; -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/