From: Mel Gorman <mel@csn.ul.ie> To: Andrew Morton <akpm@linux-foundation.org> Cc: Arthur Marsh <arthur.marsh@internode.on.net>, Clemens Ladisch <cladisch@googlemail.com>, Andrea Arcangeli <aarcange@redhat.com>, Mel Gorman <mel@csn.ul.ie>, Linux-MM <linux-mm@kvack.org>, Linux Kernel Mailing List <linux-kernel@vger.kernel.org> Subject: [PATCH 1/2] mm: compaction: Minimise the time IRQs are disabled while isolating free pages Date: Fri, 25 Feb 2011 20:04:58 +0000 [thread overview] Message-ID: <1298664299-10270-2-git-send-email-mel@csn.ul.ie> (raw) In-Reply-To: <1298664299-10270-1-git-send-email-mel@csn.ul.ie> compaction_alloc() isolates free pages to be used as migration targets. While its scanning, IRQs are disabled on the mistaken assumption the scanning should be short. Analysis showed that IRQs were in fact being disabled for substantial time. A simple test was run using large anonymous mappings with transparent hugepage support enabled to trigger frequent compactions. A monitor sampled what the worst IRQ-off latencies were and a post-processing tool found the following; Total sampled time IRQs off (not real total time): 22355 Event compaction_alloc..compaction_alloc 8409 us count 1 Event compaction_alloc..compaction_alloc 7341 us count 1 Event compaction_alloc..compaction_alloc 2463 us count 1 Event compaction_alloc..compaction_alloc 2054 us count 1 Event shrink_inactive_list..shrink_zone 1864 us count 1 Event shrink_inactive_list..shrink_zone 88 us count 1 Event save_args..call_softirq 36 us count 1 Event save_args..call_softirq 35 us count 2 Event __make_request..__blk_run_queue 24 us count 1 Event __alloc_pages_nodemask..__alloc_pages_nodemask 6 us count 1 i.e. compaction is disabled IRQs for a prolonged period of time - 8ms in one instance. The full report generated by the tool can be found at http://www.csn.ul.ie/~mel/postings/minfree-20110225/irqsoff-vanilla-micro.report . This patch reduces the time IRQs are disabled by simply disabling IRQs at the last possible minute. An updated IRQs-off summary report then looks like; Total sampled time IRQs off (not real total time): 5493 Event shrink_inactive_list..shrink_zone 1596 us count 1 Event shrink_inactive_list..shrink_zone 1530 us count 1 Event shrink_inactive_list..shrink_zone 956 us count 1 Event shrink_inactive_list..shrink_zone 541 us count 1 Event shrink_inactive_list..shrink_zone 531 us count 1 Event split_huge_page..add_to_swap 232 us count 1 Event save_args..call_softirq 36 us count 1 Event save_args..call_softirq 35 us count 2 Event __wake_up..__wake_up 1 us count 1 A full report is again available at http://www.csn.ul.ie/~mel/postings/minfree-20110225/irqsoff-minimiseirq-free-v1r4-micro.report . . As should be obvious, IRQ disabled latencies due to compaction are almost elimimnated for this particular test. [aarcange@redhat.com: Fix initialisation of isolated] Signed-off-by: Mel Gorman <mel@csn.ul.ie> --- mm/compaction.c | 18 +++++++++++++----- 1 files changed, 13 insertions(+), 5 deletions(-) diff --git a/mm/compaction.c b/mm/compaction.c index 8be430b8..11d88a2 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -155,7 +155,6 @@ static void isolate_freepages(struct zone *zone, * pages on cc->migratepages. We stop searching if the migrate * and free page scanners meet or enough free pages are isolated. */ - spin_lock_irqsave(&zone->lock, flags); for (; pfn > low_pfn && cc->nr_migratepages > nr_freepages; pfn -= pageblock_nr_pages) { unsigned long isolated; @@ -178,9 +177,19 @@ static void isolate_freepages(struct zone *zone, if (!suitable_migration_target(page)) continue; - /* Found a block suitable for isolating free pages from */ - isolated = isolate_freepages_block(zone, pfn, freelist); - nr_freepages += isolated; + /* + * Found a block suitable for isolating free pages from. Now + * we disabled interrupts, double check things are ok and + * isolate the pages. This is to minimise the time IRQs + * are disabled + */ + isolated = 0; + spin_lock_irqsave(&zone->lock, flags); + if (suitable_migration_target(page)) { + isolated = isolate_freepages_block(zone, pfn, freelist); + nr_freepages += isolated; + } + spin_unlock_irqrestore(&zone->lock, flags); /* * Record the highest PFN we isolated pages from. When next @@ -190,7 +199,6 @@ static void isolate_freepages(struct zone *zone, if (isolated) high_pfn = max(high_pfn, pfn); } - spin_unlock_irqrestore(&zone->lock, flags); /* split_free_page does not map the pages */ list_for_each_entry(page, freelist, lru) { -- 1.7.2.3
WARNING: multiple messages have this Message-ID (diff)
From: Mel Gorman <mel@csn.ul.ie> To: Andrew Morton <akpm@linux-foundation.org> Cc: Arthur Marsh <arthur.marsh@internode.on.net>, Clemens Ladisch <cladisch@googlemail.com>, Andrea Arcangeli <aarcange@redhat.com>, Mel Gorman <mel@csn.ul.ie>, Linux-MM <linux-mm@kvack.org>, Linux Kernel Mailing List <linux-kernel@vger.kernel.org> Subject: [PATCH 1/2] mm: compaction: Minimise the time IRQs are disabled while isolating free pages Date: Fri, 25 Feb 2011 20:04:58 +0000 [thread overview] Message-ID: <1298664299-10270-2-git-send-email-mel@csn.ul.ie> (raw) In-Reply-To: <1298664299-10270-1-git-send-email-mel@csn.ul.ie> compaction_alloc() isolates free pages to be used as migration targets. While its scanning, IRQs are disabled on the mistaken assumption the scanning should be short. Analysis showed that IRQs were in fact being disabled for substantial time. A simple test was run using large anonymous mappings with transparent hugepage support enabled to trigger frequent compactions. A monitor sampled what the worst IRQ-off latencies were and a post-processing tool found the following; Total sampled time IRQs off (not real total time): 22355 Event compaction_alloc..compaction_alloc 8409 us count 1 Event compaction_alloc..compaction_alloc 7341 us count 1 Event compaction_alloc..compaction_alloc 2463 us count 1 Event compaction_alloc..compaction_alloc 2054 us count 1 Event shrink_inactive_list..shrink_zone 1864 us count 1 Event shrink_inactive_list..shrink_zone 88 us count 1 Event save_args..call_softirq 36 us count 1 Event save_args..call_softirq 35 us count 2 Event __make_request..__blk_run_queue 24 us count 1 Event __alloc_pages_nodemask..__alloc_pages_nodemask 6 us count 1 i.e. compaction is disabled IRQs for a prolonged period of time - 8ms in one instance. The full report generated by the tool can be found at http://www.csn.ul.ie/~mel/postings/minfree-20110225/irqsoff-vanilla-micro.report . This patch reduces the time IRQs are disabled by simply disabling IRQs at the last possible minute. An updated IRQs-off summary report then looks like; Total sampled time IRQs off (not real total time): 5493 Event shrink_inactive_list..shrink_zone 1596 us count 1 Event shrink_inactive_list..shrink_zone 1530 us count 1 Event shrink_inactive_list..shrink_zone 956 us count 1 Event shrink_inactive_list..shrink_zone 541 us count 1 Event shrink_inactive_list..shrink_zone 531 us count 1 Event split_huge_page..add_to_swap 232 us count 1 Event save_args..call_softirq 36 us count 1 Event save_args..call_softirq 35 us count 2 Event __wake_up..__wake_up 1 us count 1 A full report is again available at http://www.csn.ul.ie/~mel/postings/minfree-20110225/irqsoff-minimiseirq-free-v1r4-micro.report . . As should be obvious, IRQ disabled latencies due to compaction are almost elimimnated for this particular test. [aarcange@redhat.com: Fix initialisation of isolated] Signed-off-by: Mel Gorman <mel@csn.ul.ie> --- mm/compaction.c | 18 +++++++++++++----- 1 files changed, 13 insertions(+), 5 deletions(-) diff --git a/mm/compaction.c b/mm/compaction.c index 8be430b8..11d88a2 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -155,7 +155,6 @@ static void isolate_freepages(struct zone *zone, * pages on cc->migratepages. We stop searching if the migrate * and free page scanners meet or enough free pages are isolated. */ - spin_lock_irqsave(&zone->lock, flags); for (; pfn > low_pfn && cc->nr_migratepages > nr_freepages; pfn -= pageblock_nr_pages) { unsigned long isolated; @@ -178,9 +177,19 @@ static void isolate_freepages(struct zone *zone, if (!suitable_migration_target(page)) continue; - /* Found a block suitable for isolating free pages from */ - isolated = isolate_freepages_block(zone, pfn, freelist); - nr_freepages += isolated; + /* + * Found a block suitable for isolating free pages from. Now + * we disabled interrupts, double check things are ok and + * isolate the pages. This is to minimise the time IRQs + * are disabled + */ + isolated = 0; + spin_lock_irqsave(&zone->lock, flags); + if (suitable_migration_target(page)) { + isolated = isolate_freepages_block(zone, pfn, freelist); + nr_freepages += isolated; + } + spin_unlock_irqrestore(&zone->lock, flags); /* * Record the highest PFN we isolated pages from. When next @@ -190,7 +199,6 @@ static void isolate_freepages(struct zone *zone, if (isolated) high_pfn = max(high_pfn, pfn); } - spin_unlock_irqrestore(&zone->lock, flags); /* split_free_page does not map the pages */ list_for_each_entry(page, freelist, lru) { -- 1.7.2.3 -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/ Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2011-02-25 20:05 UTC|newest] Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top 2011-02-25 20:04 [PATCH 0/2] Reduce the amount of time compaction disables IRQs for V2 Mel Gorman 2011-02-25 20:04 ` Mel Gorman 2011-02-25 20:04 ` Mel Gorman [this message] 2011-02-25 20:04 ` [PATCH 1/2] mm: compaction: Minimise the time IRQs are disabled while isolating free pages Mel Gorman 2011-02-25 22:34 ` Johannes Weiner 2011-02-25 22:34 ` Johannes Weiner 2011-02-28 1:55 ` KAMEZAWA Hiroyuki 2011-02-28 1:55 ` KAMEZAWA Hiroyuki 2011-02-28 22:08 ` Minchan Kim 2011-02-28 22:08 ` Minchan Kim 2011-02-25 20:04 ` [PATCH 2/2] mm: compaction: Minimise the time IRQs are disabled while isolating pages for migration Mel Gorman 2011-02-25 20:04 ` Mel Gorman 2011-02-25 22:32 ` Johannes Weiner 2011-02-25 22:32 ` Johannes Weiner 2011-02-26 0:16 ` Andrea Arcangeli 2011-02-26 0:16 ` Andrea Arcangeli 2011-02-28 2:17 ` KAMEZAWA Hiroyuki 2011-02-28 2:17 ` KAMEZAWA Hiroyuki 2011-02-28 5:48 ` Andrea Arcangeli 2011-02-28 5:48 ` Andrea Arcangeli 2011-02-28 5:54 ` KAMEZAWA Hiroyuki 2011-02-28 5:54 ` KAMEZAWA Hiroyuki 2011-02-28 9:28 ` Mel Gorman 2011-02-28 9:28 ` Mel Gorman 2011-02-28 9:42 ` KAMEZAWA Hiroyuki 2011-02-28 9:42 ` KAMEZAWA Hiroyuki 2011-02-28 10:18 ` Mel Gorman 2011-02-28 10:18 ` Mel Gorman 2011-02-28 23:42 ` KAMEZAWA Hiroyuki 2011-02-28 23:42 ` KAMEZAWA Hiroyuki 2011-03-01 4:11 ` Minchan Kim 2011-03-01 4:11 ` Minchan Kim 2011-03-01 4:49 ` KAMEZAWA Hiroyuki 2011-03-01 4:49 ` KAMEZAWA Hiroyuki 2011-02-28 23:01 ` Minchan Kim 2011-02-28 23:01 ` Minchan Kim 2011-02-28 23:07 ` Andrea Arcangeli 2011-02-28 23:07 ` Andrea Arcangeli 2011-02-28 23:25 ` Minchan Kim 2011-02-28 23:25 ` Minchan Kim 2011-03-01 22:15 ` Andrew Morton 2011-03-01 22:15 ` Andrew Morton 2011-02-25 20:07 ` [PATCH 0/2] Reduce the amount of time compaction disables IRQs for V2 Andrea Arcangeli 2011-02-25 20:07 ` Andrea Arcangeli -- strict thread matches above, loose matches on Subject: below -- 2011-02-25 18:00 [PATCH 0/2] Reduce the amount of time compaction disables IRQs for Mel Gorman 2011-02-25 18:00 ` [PATCH 1/2] mm: compaction: Minimise the time IRQs are disabled while isolating free pages Mel Gorman 2011-02-25 18:00 ` Mel Gorman
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=1298664299-10270-2-git-send-email-mel@csn.ul.ie \ --to=mel@csn.ul.ie \ --cc=aarcange@redhat.com \ --cc=akpm@linux-foundation.org \ --cc=arthur.marsh@internode.on.net \ --cc=cladisch@googlemail.com \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-mm@kvack.org \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.