From: Johannes Weiner <jweiner@redhat.com>
To: Alan Cox <alan@lxorguk.ukuu.org.uk>
Cc: Mel Gorman <mgorman@suse.de>,
Andrew Morton <akpm@linux-foundation.org>,
Jan Kara <jack@suse.cz>, Andy Isaacson <adi@hexapodia.org>,
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 13:06:49 +0100 [thread overview]
Message-ID: <20111110120649.GJ3153@redhat.com> (raw)
In-Reply-To: <20111110105100.23fa78f9@lxorguk.ukuu.org.uk>
On Thu, Nov 10, 2011 at 10:51:00AM +0000, Alan Cox wrote:
> On Thu, 10 Nov 2011 10:06:16 +0000
> Mel Gorman <mgorman@suse.de> wrote:
>
> > Occasionally during large file copies to slow storage, there are still
> > reports of user-visible stalls when THP is enabled. Reports on this
> > have been intermittent and not reliable to reproduce locally but;
>
> If you want to cause a massive stall take a cheap 32GB USB flash drive
> plug it into an 8GB box and rsync a lot of small files to it. 400,000
> emails in maildir format does the trick and can easily be simulated. The
> drive drops to about 1-2 IOPS with all the small mucking around and the
> backlog becomes massive.
>
> > Internally in SUSE, I received a bug report related to stalls in firefox
> > when using Java and Flash heavily while copying from NFS
> > to VFAT on USB. It has not been confirmed to be the same problem
> > but if it looks like a duck and quacks like a duck.....
>
> With the 32GB USB flash rsync I see firefox block for up to 45 minutes
> although operating entirely on an unrelated filesystem. I suspect it may
> be a problem that is visible because an fsync is getting jammed up in
> the mess.
Compaction walks PFN ranges, oblivious to inode dirtying order, and so
transparent huge page allocations can get stuck repeatedly on pages
under writeback that are behind whatever the bdi's queue allows to be
inflight.
On all hangs I observed while writing to my 16GB USB thumb drive, it
was tasks getting stuck in migration when allocating a THP.
Can you capture /proc/`pidof firefox`/stack while it hangs to see if
what you see is, in fact, the same problem?
--
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 12:08 UTC|newest]
Thread overview: 34+ 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 10:38 ` Johannes Weiner
2011-11-10 10:51 ` Alan Cox
2011-11-10 12:06 ` Johannes Weiner [this message]
2011-11-10 14:00 ` Andrea Arcangeli
2011-11-10 14:22 ` Mel Gorman
2011-11-10 15:12 ` Minchan Kim
2011-11-10 16:13 ` Mel Gorman
2011-11-10 16:30 ` Minchan Kim
2011-11-10 16:48 ` Mel Gorman
2011-11-10 23:12 ` Andrew Morton
2011-11-10 23:37 ` David Rientjes
2011-11-11 10:14 ` Mel Gorman
2011-11-11 10:39 ` David Rientjes
2011-11-11 11:17 ` Mel Gorman
2011-11-11 14:21 ` Andrea Arcangeli
2011-11-14 23:44 ` Andrew Morton
2011-11-15 13:25 ` Mel Gorman
2011-11-15 21:07 ` David Rientjes
2011-11-15 23:48 ` Mel Gorman
2011-11-16 0:07 ` David Rientjes
2011-11-16 4:13 ` Andrea Arcangeli
2011-11-16 13:30 ` Andrea Arcangeli
2011-11-16 15:07 ` Mel Gorman
2011-11-18 17:59 ` Andrea Arcangeli
2011-11-16 14:14 ` Mel Gorman
2011-11-11 10:01 ` Mel Gorman
2011-11-15 0:03 ` Andrew Morton
2011-11-15 2:00 ` Andrea Arcangeli
2011-11-15 2:08 ` Andrea Arcangeli
2011-11-15 15:01 ` Mel Gorman
2011-11-15 15:00 ` Mel Gorman
2011-11-15 13:07 ` Mel Gorman
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=20111110120649.GJ3153@redhat.com \
--to=jweiner@redhat.com \
--cc=aarcange@redhat.com \
--cc=adi@hexapodia.org \
--cc=akpm@linux-foundation.org \
--cc=alan@lxorguk.ukuu.org.uk \
--cc=jack@suse.cz \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@suse.de \
/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;
as well as URLs for NNTP newsgroup(s).