From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
To: Konstantin Khlebnikov <khlebnikov@openvz.org>
Cc: Hugh Dickins <hughd@google.com>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
Johannes Weiner <hannes@cmpxchg.org>,
Andrew Morton <akpm@linux-foundation.org>,
Andi Kleen <andi@firstfloor.org>
Subject: Re: [PATCH v3 16/21] mm: handle lruvec relocks in compaction
Date: Tue, 28 Feb 2012 10:13:48 +0900 [thread overview]
Message-ID: <20120228101348.fb38e5f2.kamezawa.hiroyu@jp.fujitsu.com> (raw)
In-Reply-To: <20120223135256.12988.24796.stgit@zurg>
On Thu, 23 Feb 2012 17:52:56 +0400
Konstantin Khlebnikov <khlebnikov@openvz.org> wrote:
> Prepare for lru_lock splitting in memory compaction code.
>
> * disable irqs in acct_isolated() for __mod_zone_page_state(),
> lru_lock isn't required there.
>
> Signed-off-by: Konstantin Khlebnikov <khlebnikov@openvz.org>
> ---
> mm/compaction.c | 30 ++++++++++++++++--------------
> 1 files changed, 16 insertions(+), 14 deletions(-)
>
> diff --git a/mm/compaction.c b/mm/compaction.c
> index a976b28..54340e4 100644
> --- a/mm/compaction.c
> +++ b/mm/compaction.c
> @@ -224,8 +224,10 @@ static void acct_isolated(struct zone *zone, struct compact_control *cc)
> list_for_each_entry(page, &cc->migratepages, lru)
> count[!!page_is_file_cache(page)]++;
>
> + local_irq_disable();
> __mod_zone_page_state(zone, NR_ISOLATED_ANON, count[0]);
> __mod_zone_page_state(zone, NR_ISOLATED_FILE, count[1]);
> + local_irq_enable();
Why we need to disable Irq here ??
> }
>
> /* Similar to reclaim, but different enough that they don't share logic */
> @@ -262,7 +264,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
> unsigned long nr_scanned = 0, nr_isolated = 0;
> struct list_head *migratelist = &cc->migratepages;
> isolate_mode_t mode = ISOLATE_ACTIVE|ISOLATE_INACTIVE;
> - struct lruvec *lruvec;
> + struct lruvec *lruvec = NULL;
>
> /* Do not scan outside zone boundaries */
> low_pfn = max(cc->migrate_pfn, zone->zone_start_pfn);
> @@ -294,25 +296,24 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
>
> /* Time to isolate some pages for migration */
> cond_resched();
> - spin_lock_irq(&zone->lru_lock);
> for (; low_pfn < end_pfn; low_pfn++) {
> struct page *page;
> - bool locked = true;
>
> /* give a chance to irqs before checking need_resched() */
> if (!((low_pfn+1) % SWAP_CLUSTER_MAX)) {
> - spin_unlock_irq(&zone->lru_lock);
> - locked = false;
> + if (lruvec)
> + unlock_lruvec_irq(lruvec);
> + lruvec = NULL;
> }
> - if (need_resched() || spin_is_contended(&zone->lru_lock)) {
> - if (locked)
> - spin_unlock_irq(&zone->lru_lock);
> + if (need_resched() ||
> + (lruvec && spin_is_contended(&zone->lru_lock))) {
> + if (lruvec)
> + unlock_lruvec_irq(lruvec);
> + lruvec = NULL;
> cond_resched();
> - spin_lock_irq(&zone->lru_lock);
> if (fatal_signal_pending(current))
> break;
> - } else if (!locked)
> - spin_lock_irq(&zone->lru_lock);
> + }
>
> /*
> * migrate_pfn does not necessarily start aligned to a
> @@ -359,7 +360,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
> continue;
> }
>
> - if (!PageLRU(page))
> + if (!__lock_page_lruvec_irq(&lruvec, page))
> continue;
Could you add more comments onto __lock_page_lruvec_irq() ?
Thanks,
-Kame
--
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:[~2012-02-28 1:15 UTC|newest]
Thread overview: 65+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-02-23 13:51 [PATCH v3 00/21] mm: lru_lock splitting Konstantin Khlebnikov
2012-02-23 13:51 ` [PATCH v3 01/21] memcg: unify inactive_ratio calculation Konstantin Khlebnikov
2012-02-28 0:05 ` KAMEZAWA Hiroyuki
2012-02-23 13:51 ` [PATCH v3 02/21] memcg: make mm_match_cgroup() hirarchical Konstantin Khlebnikov
2012-02-23 18:03 ` Johannes Weiner
2012-02-23 19:46 ` Konstantin Khlebnikov
2012-02-23 22:06 ` Johannes Weiner
2012-02-28 0:11 ` KAMEZAWA Hiroyuki
2012-02-28 6:31 ` Konstantin Khlebnikov
2012-02-23 13:51 ` [PATCH v3 03/21] memcg: fix page_referencies cgroup filter on global reclaim Konstantin Khlebnikov
2012-02-28 0:13 ` KAMEZAWA Hiroyuki
2012-02-23 13:51 ` [PATCH v3 04/21] memcg: use vm_swappiness from target memory cgroup Konstantin Khlebnikov
2012-02-28 0:15 ` KAMEZAWA Hiroyuki
2012-02-23 13:52 ` [PATCH v3 05/21] mm: rename lruvec->lists into lruvec->pages_lru Konstantin Khlebnikov
2012-02-28 0:20 ` KAMEZAWA Hiroyuki
2012-02-28 6:04 ` Konstantin Khlebnikov
2012-02-23 13:52 ` [PATCH v3 06/21] mm: lruvec linking functions Konstantin Khlebnikov
2012-02-28 0:27 ` KAMEZAWA Hiroyuki
2012-02-28 6:09 ` Konstantin Khlebnikov
2012-02-23 13:52 ` [PATCH v3 07/21] mm: add lruvec->pages_count Konstantin Khlebnikov
2012-02-28 0:35 ` KAMEZAWA Hiroyuki
2012-02-28 6:16 ` Konstantin Khlebnikov
2012-02-23 13:52 ` [PATCH v3 08/21] mm: unify inactive_list_is_low() Konstantin Khlebnikov
2012-02-28 0:36 ` KAMEZAWA Hiroyuki
2012-02-23 13:52 ` [PATCH v3 09/21] mm: add lruvec->reclaim_stat Konstantin Khlebnikov
2012-02-28 0:38 ` KAMEZAWA Hiroyuki
2012-02-23 13:52 ` [PATCH v3 10/21] mm: kill struct mem_cgroup_zone Konstantin Khlebnikov
2012-02-28 0:41 ` KAMEZAWA Hiroyuki
2012-02-23 13:52 ` [PATCH v3 11/21] mm: move page-to-lruvec translation upper Konstantin Khlebnikov
2012-02-28 0:42 ` KAMEZAWA Hiroyuki
2012-02-23 13:52 ` [PATCH v3 12/21] mm: push lruvec into update_page_reclaim_stat() Konstantin Khlebnikov
2012-02-28 0:44 ` KAMEZAWA Hiroyuki
2012-02-23 13:52 ` [PATCH v3 13/21] mm: push lruvecs from pagevec_lru_move_fn() to iterator Konstantin Khlebnikov
2012-02-28 0:45 ` KAMEZAWA Hiroyuki
2012-02-23 13:52 ` [PATCH v3 14/21] mm: introduce lruvec locking primitives Konstantin Khlebnikov
2012-02-28 0:56 ` KAMEZAWA Hiroyuki
2012-02-28 6:23 ` Konstantin Khlebnikov
2012-02-23 13:52 ` [PATCH v3 15/21] mm: handle lruvec relocks on lumpy reclaim Konstantin Khlebnikov
2012-02-28 1:01 ` KAMEZAWA Hiroyuki
2012-02-28 6:25 ` Konstantin Khlebnikov
2012-02-23 13:52 ` [PATCH v3 16/21] mm: handle lruvec relocks in compaction Konstantin Khlebnikov
2012-02-28 1:13 ` KAMEZAWA Hiroyuki [this message]
2012-02-28 6:31 ` Konstantin Khlebnikov
2012-02-23 13:53 ` [PATCH v3 17/21] mm: handle lruvec relock in memory controller Konstantin Khlebnikov
2012-02-28 1:22 ` KAMEZAWA Hiroyuki
2012-02-23 13:53 ` [PATCH v3 18/21] mm: add to lruvec isolated pages counters Konstantin Khlebnikov
2012-02-24 5:32 ` Konstantin Khlebnikov
2012-02-28 1:38 ` KAMEZAWA Hiroyuki
2012-02-23 13:53 ` [PATCH v3 19/21] memcg: check lru vectors emptiness in pre-destroy Konstantin Khlebnikov
2012-02-28 1:43 ` KAMEZAWA Hiroyuki
2012-02-23 13:53 ` [PATCH v3 20/21] mm: split zone->lru_lock Konstantin Khlebnikov
2012-02-28 1:49 ` KAMEZAWA Hiroyuki
2012-02-28 6:39 ` Konstantin Khlebnikov
2012-02-23 13:53 ` [PATCH v3 21/21] mm: zone lru vectors interleaving Konstantin Khlebnikov
2012-02-23 14:44 ` Hillf Danton
2012-02-23 16:21 ` Andi Kleen
2012-02-23 18:48 ` [PATCH 1/2] mm: configure lruvec split by boot options Konstantin Khlebnikov
2012-02-23 18:48 ` [PATCH 2/2] mm: show zone lruvec state in /proc/zoneinfo Konstantin Khlebnikov
2012-02-25 0:05 ` [PATCH v3 00/21] mm: lru_lock splitting Tim Chen
2012-02-25 5:34 ` Konstantin Khlebnikov
2012-02-25 2:15 ` KAMEZAWA Hiroyuki
2012-02-25 5:31 ` Konstantin Khlebnikov
2012-02-26 23:54 ` KAMEZAWA Hiroyuki
2012-02-28 1:52 ` KAMEZAWA Hiroyuki
2012-02-28 6:49 ` Konstantin Khlebnikov
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=20120228101348.fb38e5f2.kamezawa.hiroyu@jp.fujitsu.com \
--to=kamezawa.hiroyu@jp.fujitsu.com \
--cc=akpm@linux-foundation.org \
--cc=andi@firstfloor.org \
--cc=hannes@cmpxchg.org \
--cc=hughd@google.com \
--cc=khlebnikov@openvz.org \
--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: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox