From: Pavel Machek <pavel@ucw.cz>
To: Christoph Lameter <clameter@sgi.com>
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org,
akpm@linux-foundation.org, dkegel@google.com,
Peter Zijlstra <a.p.zijlstra@chello.nl>,
David Miller <davem@davemloft.net>, Nick Piggin <npiggin@suse.de>
Subject: Re: [RFC 2/9] Use NOMEMALLOC reclaim to allow reclaim if PF_MEMALLOC is set
Date: Sat, 18 Aug 2007 07:10:36 +0000 [thread overview]
Message-ID: <20070818071035.GA4667@ucw.cz> (raw)
In-Reply-To: <20070814153501.305923060@sgi.com>
Hi!
> If we exhaust the reserves in the page allocator when PF_MEMALLOC is set
> then no longer give up but call into reclaim with PF_MEMALLOC set.
>
> This is in essence a recursive call back into page reclaim with another
> page flag (__GFP_NOMEMALLOC) set. The recursion is bounded since potential
> allocations with __PF_NOMEMALLOC set will not enter that branch again.
>
> This means that allocation under PF_MEMALLOC will no longer run out of
> memory. Allocations under PF_MEMALLOC will do a limited form of reclaim
> instead.
>
> The reclaim is of particular important to stacked filesystems that may
> do a lot of allocations in the write path. Reclaim will be working
> as long as there are clean file backed pages to reclaim.
I don't get it. Lets say that we have stacked filesystem that needs
it. That filesystem is broken today.
Now you give it second chance by reclaiming clean pages, but there are
no guarantees that we have any.... so that filesystem is still broken
with your patch...?
Should we fix the filesystem instead?
Pavel
--
(english) http://www.livejournal.com/~pavelmachek
(cesky, pictures) http://atrey.karlin.mff.cuni.cz/~pavel/picture/horses/blog.html
--
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:[~2007-08-18 7:10 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-08-14 15:30 [RFC 0/9] Reclaim during GFP_ATOMIC allocs Christoph Lameter
2007-08-14 15:30 ` [RFC 1/9] Allow reclaim via __GFP_NOMEMALLOC reclaim Christoph Lameter
2007-08-14 15:30 ` [RFC 2/9] Use NOMEMALLOC reclaim to allow reclaim if PF_MEMALLOC is set Christoph Lameter
2007-08-18 7:10 ` Pavel Machek [this message]
2007-08-20 19:00 ` Christoph Lameter
2007-08-20 20:17 ` Peter Zijlstra
2007-08-20 20:27 ` Christoph Lameter
2007-08-20 21:14 ` Peter Zijlstra
2007-08-20 21:17 ` Christoph Lameter
2007-08-21 14:07 ` Peter Zijlstra
2007-08-21 0:39 ` Nick Piggin
2007-08-21 14:07 ` Peter Zijlstra
2007-08-23 3:38 ` Nick Piggin
2007-08-23 9:26 ` Peter Zijlstra
2007-08-23 10:11 ` Nikita Danilov
2007-08-23 13:58 ` Peter Zijlstra
2007-08-24 4:00 ` Nick Piggin
2007-08-14 15:30 ` [RFC 3/9] Make cond_rescheds conditional on __GFP_WAIT Christoph Lameter
2007-08-14 15:30 ` [RFC 4/9] Atomic reclaim: Save irq flags in vmscan.c Christoph Lameter
2007-08-14 20:02 ` Andi Kleen
2007-08-14 19:12 ` Christoph Lameter
2007-08-14 20:05 ` Peter Zijlstra
2007-08-14 20:34 ` Andi Kleen
2007-08-14 20:33 ` Andi Kleen
2007-08-14 20:42 ` Christoph Lameter
2007-08-14 20:44 ` Andi Kleen
2007-08-14 21:15 ` Christoph Lameter
2007-08-14 21:23 ` Andi Kleen
2007-08-14 21:26 ` Christoph Lameter
2007-08-14 21:29 ` Andi Kleen
2007-08-14 21:37 ` Christoph Lameter
2007-08-14 21:44 ` Andi Kleen
2007-08-14 21:48 ` Christoph Lameter
2007-08-14 21:56 ` Andi Kleen
2007-08-14 22:07 ` Christoph Lameter
2007-08-14 22:16 ` Andi Kleen
2007-08-14 22:20 ` Christoph Lameter
2007-08-14 22:21 ` Andi Kleen
2007-08-14 22:41 ` Christoph Lameter
2007-08-14 15:30 ` [RFC 5/9] Save irqflags on taking the mapping lock Christoph Lameter
2007-08-14 15:30 ` [RFC 6/9] Disable irqs on taking the private_lock Christoph Lameter
2007-08-14 15:30 ` [RFC 7/9] Save flags in swap.c Christoph Lameter
2007-08-14 15:30 ` [RFC 8/9] Reclaim on an atomic allocation if necessary Christoph Lameter
2007-08-14 15:30 ` [RFC 9/9] Testing: Perform GFP_ATOMIC overallocation Christoph Lameter
2007-08-16 2:49 ` [RFC 0/9] Reclaim during GFP_ATOMIC allocs Nick Piggin
2007-08-16 20:24 ` Christoph Lameter
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=20070818071035.GA4667@ucw.cz \
--to=pavel@ucw.cz \
--cc=a.p.zijlstra@chello.nl \
--cc=akpm@linux-foundation.org \
--cc=clameter@sgi.com \
--cc=davem@davemloft.net \
--cc=dkegel@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=npiggin@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