From: Mel Gorman <mgorman@suse.de>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Jan Kara <jack@suse.cz>, Andy Isaacson <adi@hexapodia.org>,
Johannes Weiner <jweiner@redhat.com>,
Andrea Arcangeli <aarcange@redhat.com>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: Re: [PATCH] mm: Do not stall in synchronous compaction for THP allocations
Date: Thu, 10 Nov 2011 14:22:03 +0000 [thread overview]
Message-ID: <20111110142202.GE3083@suse.de> (raw)
In-Reply-To: <20111110100616.GD3083@suse.de>
On Thu, Nov 10, 2011 at 10:06:16AM +0000, Mel Gorman wrote:
> than stall. It was suggested that __GFP_NORETRY be used instead of
> __GFP_NO_KSWAPD. This would look less like a special case but would
> still cause compaction to run at least once with sync compaction.
>
This comment is bogus - __GFP_NORETRY would have caught THP allocations
and would not call sync compaction. The issue was that it would also
have caught any hypothetical high-order GFP_THISNODE allocations that
end up calling compaction here
/*
* High-order allocations do not necessarily loop after
* direct reclaim and reclaim/compaction depends on
* compaction being called after reclaim so call directly if
* necessary
*/
page = __alloc_pages_direct_compact(gfp_mask, order,
zonelist, high_zoneidx,
nodemask,
alloc_flags, preferred_zone,
migratetype, &did_some_progress,
sync_migration);
__GFP_NORETRY is used in a bunch of places and while the most
of them are not high-order, some of them potentially are like in
sound/core/memalloc.c. Using __GFP_NO_KSWAPD as the flag allows
these callers to continue using sync compaction. It could be argued
that they would prefer __GFP_NORETRY but the potential side-effects
should be taken should be taken into account and the comment updated
if that happens.
--
Mel Gorman
SUSE Labs
WARNING: multiple messages have this Message-ID (diff)
From: Mel Gorman <mgorman@suse.de>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Jan Kara <jack@suse.cz>, Andy Isaacson <adi@hexapodia.org>,
Johannes Weiner <jweiner@redhat.com>,
Andrea Arcangeli <aarcange@redhat.com>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: Re: [PATCH] mm: Do not stall in synchronous compaction for THP allocations
Date: Thu, 10 Nov 2011 14:22:03 +0000 [thread overview]
Message-ID: <20111110142202.GE3083@suse.de> (raw)
In-Reply-To: <20111110100616.GD3083@suse.de>
On Thu, Nov 10, 2011 at 10:06:16AM +0000, Mel Gorman wrote:
> than stall. It was suggested that __GFP_NORETRY be used instead of
> __GFP_NO_KSWAPD. This would look less like a special case but would
> still cause compaction to run at least once with sync compaction.
>
This comment is bogus - __GFP_NORETRY would have caught THP allocations
and would not call sync compaction. The issue was that it would also
have caught any hypothetical high-order GFP_THISNODE allocations that
end up calling compaction here
/*
* High-order allocations do not necessarily loop after
* direct reclaim and reclaim/compaction depends on
* compaction being called after reclaim so call directly if
* necessary
*/
page = __alloc_pages_direct_compact(gfp_mask, order,
zonelist, high_zoneidx,
nodemask,
alloc_flags, preferred_zone,
migratetype, &did_some_progress,
sync_migration);
__GFP_NORETRY is used in a bunch of places and while the most
of them are not high-order, some of them potentially are like in
sound/core/memalloc.c. Using __GFP_NO_KSWAPD as the flag allows
these callers to continue using sync compaction. It could be argued
that they would prefer __GFP_NORETRY but the potential side-effects
should be taken should be taken into account and the comment updated
if that happens.
--
Mel Gorman
SUSE Labs
--
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:[~2011-11-10 14:22 UTC|newest]
Thread overview: 68+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-11-10 10:06 [PATCH] mm: Do not stall in synchronous compaction for THP allocations Mel Gorman
2011-11-10 10:06 ` Mel Gorman
2011-11-10 10:38 ` Johannes Weiner
2011-11-10 10:38 ` Johannes Weiner
2011-11-10 10:51 ` Alan Cox
2011-11-10 10:51 ` Alan Cox
2011-11-10 12:06 ` Johannes Weiner
2011-11-10 12:06 ` Johannes Weiner
2011-11-10 14:00 ` Andrea Arcangeli
2011-11-10 14:00 ` Andrea Arcangeli
2011-11-10 14:22 ` Mel Gorman [this message]
2011-11-10 14:22 ` Mel Gorman
2011-11-10 15:12 ` Minchan Kim
2011-11-10 15:12 ` Minchan Kim
2011-11-10 16:13 ` Mel Gorman
2011-11-10 16:13 ` Mel Gorman
2011-11-10 16:30 ` Minchan Kim
2011-11-10 16:30 ` Minchan Kim
2011-11-10 16:48 ` Mel Gorman
2011-11-10 16:48 ` Mel Gorman
2011-11-10 23:12 ` Andrew Morton
2011-11-10 23:12 ` Andrew Morton
2011-11-10 23:37 ` David Rientjes
2011-11-10 23:37 ` David Rientjes
2011-11-11 10:14 ` Mel Gorman
2011-11-11 10:14 ` Mel Gorman
2011-11-11 10:39 ` David Rientjes
2011-11-11 10:39 ` David Rientjes
2011-11-11 11:17 ` Mel Gorman
2011-11-11 11:17 ` Mel Gorman
2011-11-11 14:21 ` Andrea Arcangeli
2011-11-11 14:21 ` Andrea Arcangeli
2011-11-14 23:44 ` Andrew Morton
2011-11-14 23:44 ` Andrew Morton
2011-11-15 13:25 ` Mel Gorman
2011-11-15 13:25 ` Mel Gorman
2011-11-15 21:07 ` David Rientjes
2011-11-15 21:07 ` David Rientjes
2011-11-15 23:48 ` Mel Gorman
2011-11-15 23:48 ` Mel Gorman
2011-11-16 0:07 ` David Rientjes
2011-11-16 0:07 ` David Rientjes
2011-11-16 4:13 ` Andrea Arcangeli
2011-11-16 4:13 ` Andrea Arcangeli
2011-11-16 13:30 ` Andrea Arcangeli
2011-11-16 13:30 ` Andrea Arcangeli
2011-11-16 15:07 ` Mel Gorman
2011-11-16 15:07 ` Mel Gorman
2011-11-18 17:59 ` Andrea Arcangeli
2011-11-18 17:59 ` Andrea Arcangeli
2011-11-16 14:14 ` Mel Gorman
2011-11-16 14:14 ` Mel Gorman
2011-11-11 10:01 ` Mel Gorman
2011-11-11 10:01 ` Mel Gorman
2011-11-15 0:03 ` Andrew Morton
2011-11-15 0:03 ` Andrew Morton
2011-11-15 2:00 ` Andrea Arcangeli
2011-11-15 2:00 ` Andrea Arcangeli
2011-11-15 2:08 ` Andrea Arcangeli
2011-11-15 2:08 ` Andrea Arcangeli
2011-11-15 15:01 ` Mel Gorman
2011-11-15 15:01 ` Mel Gorman
2011-11-15 15:00 ` Mel Gorman
2011-11-15 15:00 ` Mel Gorman
2011-11-15 13:07 ` Mel Gorman
2011-11-15 13:07 ` Mel Gorman
2011-11-15 15:47 ` Andrea Arcangeli
2011-11-15 15:47 ` Andrea Arcangeli
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=20111110142202.GE3083@suse.de \
--to=mgorman@suse.de \
--cc=aarcange@redhat.com \
--cc=adi@hexapodia.org \
--cc=akpm@linux-foundation.org \
--cc=jack@suse.cz \
--cc=jweiner@redhat.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: 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.