From: Andrew Morton <akpm@linux-foundation.org>
To: Miklos Szeredi <miklos@szeredi.hu>
Cc: wfg@mail.ustc.edu.cn, a.p.zijlstra@chello.nl, linux-mm@kvack.org,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH] remove throttle_vm_writeout()
Date: Thu, 4 Oct 2007 16:09:41 -0700 [thread overview]
Message-ID: <20071004160941.e0c0c7e5.akpm@linux-foundation.org> (raw)
In-Reply-To: <E1IdZLg-0002Wr-00@dorka.pomaz.szeredi.hu>
On Fri, 05 Oct 2007 00:39:16 +0200
Miklos Szeredi <miklos@szeredi.hu> wrote:
> > throttle_vm_writeout() should be a per-zone thing, I guess. Perhaps fixing
> > that would fix your deadlock. That's doubtful, but I don't know anything
> > about your deadlock so I cannot say.
>
> No, doing the throttling per-zone won't in itself fix the deadlock.
>
> Here's a deadlock example:
>
> Total memory = 32M
> /proc/sys/vm/dirty_ratio = 10
> dirty_threshold = 3M
> ratelimit_pages = 1M
>
> Some program dirties 4M (dirty_threshold + ratelimit_pages) of mmap on
> a fuse fs. Page balancing is called which turns all these into
> writeback pages.
>
> Then userspace filesystem gets a write request, and tries to allocate
> memory needed to complete the writeout.
>
> That will possibly trigger direct reclaim, and throttle_vm_writeout()
> will be called. That will block until nr_writeback goes below 3.3M
> (dirty_threshold + 10%). But since all 4M of writeback is from the
> fuse fs, that will never happen.
>
> Does that explain it better?
>
yup, thanks.
This is a somewhat general problem: a userspace process is in the IO path.
Userspace block drivers, for example - pretty much anything which involves
kernel->userspace upcalls for storage applications.
I solved it once in the past by marking the userspace process as
PF_MEMALLOC and I beleive that others have implemented the same hack.
I suspect that what we need is a general solution, and that the solution
will involve explicitly telling the kernel that this process is one which
actually cleans memory and needs special treatment.
Because I bet there will be other corner-cases where such a process needs
kernel help, and there might be optimisation opportunities as well.
Problem is, any such mark-me-as-special syscall would need to be
privileged, and FUSE servers presently don't require special perms (do
they?)
--
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>
next prev parent reply other threads:[~2007-10-04 23:09 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-10-04 12:25 [PATCH] remove throttle_vm_writeout() Miklos Szeredi
2007-10-04 12:40 ` Peter Zijlstra
2007-10-04 13:00 ` Miklos Szeredi
2007-10-04 13:23 ` Peter Zijlstra
2007-10-04 13:49 ` Miklos Szeredi
2007-10-04 16:47 ` Peter Zijlstra
2007-10-04 17:46 ` Andrew Morton
2007-10-04 18:10 ` Peter Zijlstra
2007-10-04 18:54 ` Andrew Morton
[not found] ` <20071005123028.GA10372@mail.ustc.edu.cn>
2007-10-05 12:30 ` Fengguang Wu
2007-10-05 17:20 ` Andrew Morton
[not found] ` <20071006023224.GA7526@mail.ustc.edu.cn>
2007-10-06 2:32 ` Fengguang Wu
2007-10-07 23:54 ` David Chinner
[not found] ` <20071008003349.GA5455@mail.ustc.edu.cn>
2007-10-08 0:33 ` Fengguang Wu
2007-10-04 21:07 ` Miklos Szeredi
2007-10-04 21:56 ` Andrew Morton
2007-10-04 22:39 ` Miklos Szeredi
2007-10-04 23:09 ` Andrew Morton [this message]
2007-10-04 23:26 ` Miklos Szeredi
2007-10-04 23:48 ` Andrew Morton
2007-10-05 0:12 ` Miklos Szeredi
2007-10-05 0:48 ` Andrew Morton
2007-10-05 8:22 ` Peter Zijlstra
2007-10-05 9:22 ` Miklos Szeredi
2007-10-05 9:47 ` Peter Zijlstra
2007-10-05 10:27 ` Miklos Szeredi
2007-10-05 10:32 ` Miklos Szeredi
2007-10-05 15:43 ` John Stoffel
2007-10-05 10:57 ` Peter Zijlstra
2007-10-05 11:27 ` Miklos Szeredi
2007-10-05 17:50 ` Trond Myklebust
2007-10-05 18:32 ` Peter Zijlstra
2007-10-05 19:20 ` Trond Myklebust
2007-10-05 19:23 ` Trond Myklebust
2007-10-05 21:07 ` Peter Zijlstra
[not found] ` <20071006004028.GA7121@mail.ustc.edu.cn>
2007-10-06 0:40 ` Fengguang Wu
2007-10-05 7:32 ` Peter Zijlstra
2007-10-05 19:54 ` Rik van Riel
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=20071004160941.e0c0c7e5.akpm@linux-foundation.org \
--to=akpm@linux-foundation.org \
--cc=a.p.zijlstra@chello.nl \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=miklos@szeredi.hu \
--cc=wfg@mail.ustc.edu.cn \
/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).