From: Rik van Riel <riel@redhat.com>
To: Mel Gorman <mgorman@suse.de>
Cc: Richard Davies <richard@arachsys.com>,
Shaohua Li <shli@kernel.org>, Avi Kivity <avi@redhat.com>,
QEMU-devel <qemu-devel@nongnu.org>, KVM <kvm@vger.kernel.org>,
Linux-MM <linux-mm@kvack.org>,
LKML <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 5/6] mm: compaction: Cache if a pageblock was scanned and no pages were isolated
Date: Thu, 20 Sep 2012 14:55:22 -0400 [thread overview]
Message-ID: <505B669A.1000306@redhat.com> (raw)
In-Reply-To: <1348149875-29678-6-git-send-email-mgorman@suse.de>
On 09/20/2012 10:04 AM, Mel Gorman wrote:
> When compaction was implemented it was known that scanning could potentially
> be excessive. The ideal was that a counter be maintained for each pageblock
> but maintaining this information would incur a severe penalty due to a
> shared writable cache line. It has reached the point where the scanning
> costs are an serious problem, particularly on long-lived systems where a
> large process starts and allocates a large number of THPs at the same time.
>
> Instead of using a shared counter, this patch adds another bit to the
> pageblock flags called PG_migrate_skip. If a pageblock is scanned by
> either migrate or free scanner and 0 pages were isolated, the pageblock
> is marked to be skipped in the future. When scanning, this bit is checked
> before any scanning takes place and the block skipped if set.
>
> The main difficulty with a patch like this is "when to ignore the cached
> information?" If it's ignored too often, the scanning rates will still
> be excessive. If the information is too stale then allocations will fail
> that might have otherwise succeeded. In this patch
Big hammer, but I guess it is effective...
Acked-by: Rik van Riel <riel@redhat.com>
--
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/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
WARNING: multiple messages have this Message-ID (diff)
From: Rik van Riel <riel@redhat.com>
To: Mel Gorman <mgorman@suse.de>
Cc: Richard Davies <richard@arachsys.com>,
Shaohua Li <shli@kernel.org>, Avi Kivity <avi@redhat.com>,
QEMU-devel <qemu-devel@nongnu.org>, KVM <kvm@vger.kernel.org>,
Linux-MM <linux-mm@kvack.org>,
LKML <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 5/6] mm: compaction: Cache if a pageblock was scanned and no pages were isolated
Date: Thu, 20 Sep 2012 14:55:22 -0400 [thread overview]
Message-ID: <505B669A.1000306@redhat.com> (raw)
In-Reply-To: <1348149875-29678-6-git-send-email-mgorman@suse.de>
On 09/20/2012 10:04 AM, Mel Gorman wrote:
> When compaction was implemented it was known that scanning could potentially
> be excessive. The ideal was that a counter be maintained for each pageblock
> but maintaining this information would incur a severe penalty due to a
> shared writable cache line. It has reached the point where the scanning
> costs are an serious problem, particularly on long-lived systems where a
> large process starts and allocates a large number of THPs at the same time.
>
> Instead of using a shared counter, this patch adds another bit to the
> pageblock flags called PG_migrate_skip. If a pageblock is scanned by
> either migrate or free scanner and 0 pages were isolated, the pageblock
> is marked to be skipped in the future. When scanning, this bit is checked
> before any scanning takes place and the block skipped if set.
>
> The main difficulty with a patch like this is "when to ignore the cached
> information?" If it's ignored too often, the scanning rates will still
> be excessive. If the information is too stale then allocations will fail
> that might have otherwise succeeded. In this patch
Big hammer, but I guess it is effective...
Acked-by: Rik van Riel <riel@redhat.com>
WARNING: multiple messages have this Message-ID (diff)
From: Rik van Riel <riel@redhat.com>
To: Mel Gorman <mgorman@suse.de>
Cc: Richard Davies <richard@arachsys.com>, KVM <kvm@vger.kernel.org>,
QEMU-devel <qemu-devel@nongnu.org>,
LKML <linux-kernel@vger.kernel.org>,
Linux-MM <linux-mm@kvack.org>, Avi Kivity <avi@redhat.com>,
Shaohua Li <shli@kernel.org>
Subject: Re: [Qemu-devel] [PATCH 5/6] mm: compaction: Cache if a pageblock was scanned and no pages were isolated
Date: Thu, 20 Sep 2012 14:55:22 -0400 [thread overview]
Message-ID: <505B669A.1000306@redhat.com> (raw)
In-Reply-To: <1348149875-29678-6-git-send-email-mgorman@suse.de>
On 09/20/2012 10:04 AM, Mel Gorman wrote:
> When compaction was implemented it was known that scanning could potentially
> be excessive. The ideal was that a counter be maintained for each pageblock
> but maintaining this information would incur a severe penalty due to a
> shared writable cache line. It has reached the point where the scanning
> costs are an serious problem, particularly on long-lived systems where a
> large process starts and allocates a large number of THPs at the same time.
>
> Instead of using a shared counter, this patch adds another bit to the
> pageblock flags called PG_migrate_skip. If a pageblock is scanned by
> either migrate or free scanner and 0 pages were isolated, the pageblock
> is marked to be skipped in the future. When scanning, this bit is checked
> before any scanning takes place and the block skipped if set.
>
> The main difficulty with a patch like this is "when to ignore the cached
> information?" If it's ignored too often, the scanning rates will still
> be excessive. If the information is too stale then allocations will fail
> that might have otherwise succeeded. In this patch
Big hammer, but I guess it is effective...
Acked-by: Rik van Riel <riel@redhat.com>
next prev parent reply other threads:[~2012-09-20 18:55 UTC|newest]
Thread overview: 60+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-09-20 14:04 [PATCH 0/6] Reduce compaction scanning and lock contention Mel Gorman
2012-09-20 14:04 ` [Qemu-devel] " Mel Gorman
2012-09-20 14:04 ` Mel Gorman
2012-09-20 14:04 ` [PATCH 1/6] mm: compaction: Abort compaction loop if lock is contended or run too long Mel Gorman
2012-09-20 14:04 ` [Qemu-devel] " Mel Gorman
2012-09-20 14:04 ` Mel Gorman
2012-09-20 18:53 ` Rik van Riel
2012-09-20 18:53 ` [Qemu-devel] " Rik van Riel
2012-09-20 18:53 ` Rik van Riel
2012-09-20 14:04 ` [PATCH 2/6] mm: compaction: Acquire the zone->lru_lock as late as possible Mel Gorman
2012-09-20 14:04 ` [Qemu-devel] " Mel Gorman
2012-09-20 14:04 ` Mel Gorman
2012-09-20 18:54 ` Rik van Riel
2012-09-20 18:54 ` [Qemu-devel] " Rik van Riel
2012-09-20 18:54 ` Rik van Riel
2012-09-20 14:04 ` [PATCH 3/6] mm: compaction: Acquire the zone->lock " Mel Gorman
2012-09-20 14:04 ` [Qemu-devel] " Mel Gorman
2012-09-20 14:04 ` Mel Gorman
2012-09-20 18:54 ` Rik van Riel
2012-09-20 18:54 ` [Qemu-devel] " Rik van Riel
2012-09-20 18:54 ` Rik van Riel
2012-09-20 14:04 ` [PATCH 4/6] Revert "mm: have order > 0 compaction start off where it left" Mel Gorman
2012-09-20 14:04 ` [Qemu-devel] " Mel Gorman
2012-09-20 14:04 ` Mel Gorman
2012-09-20 18:54 ` Rik van Riel
2012-09-20 18:54 ` [Qemu-devel] " Rik van Riel
2012-09-20 18:54 ` Rik van Riel
2012-09-20 14:04 ` [PATCH 5/6] mm: compaction: Cache if a pageblock was scanned and no pages were isolated Mel Gorman
2012-09-20 14:04 ` [Qemu-devel] " Mel Gorman
2012-09-20 14:04 ` Mel Gorman
2012-09-20 18:55 ` Rik van Riel [this message]
2012-09-20 18:55 ` [Qemu-devel] " Rik van Riel
2012-09-20 18:55 ` Rik van Riel
2012-09-20 14:04 ` [PATCH 6/6] mm: compaction: Restart compaction from near where it left off Mel Gorman
2012-09-20 14:04 ` [Qemu-devel] " Mel Gorman
2012-09-20 14:04 ` Mel Gorman
2012-09-20 18:57 ` Rik van Riel
2012-09-20 18:57 ` [Qemu-devel] " Rik van Riel
2012-09-20 18:57 ` Rik van Riel
2012-09-21 9:13 ` [PATCH 0/6] Reduce compaction scanning and lock contention Richard Davies
2012-09-21 9:13 ` [Qemu-devel] " Richard Davies
2012-09-21 9:13 ` Richard Davies
2012-09-21 9:15 ` Richard Davies
2012-09-21 9:15 ` [Qemu-devel] " Richard Davies
2012-09-21 9:15 ` Richard Davies
2012-09-21 9:17 ` Richard Davies
2012-09-21 9:17 ` [Qemu-devel] " Richard Davies
2012-09-21 9:17 ` Richard Davies
2012-09-21 9:55 ` Mel Gorman
2012-09-21 9:55 ` [Qemu-devel] " Mel Gorman
2012-09-21 9:55 ` Mel Gorman
2012-09-21 9:18 ` Richard Davies
2012-09-21 9:18 ` [Qemu-devel] " Richard Davies
2012-09-21 9:18 ` Richard Davies
2012-09-21 9:35 ` Mel Gorman
2012-09-21 9:35 ` [Qemu-devel] " Mel Gorman
2012-09-21 9:35 ` Mel Gorman
2012-09-21 9:49 ` Richard Davies
2012-09-21 9:49 ` [Qemu-devel] " Richard Davies
2012-09-21 9:49 ` Richard Davies
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=505B669A.1000306@redhat.com \
--to=riel@redhat.com \
--cc=avi@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@suse.de \
--cc=qemu-devel@nongnu.org \
--cc=richard@arachsys.com \
--cc=shli@kernel.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 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.