From: mel@skynet.ie (Mel Gorman)
To: Christoph Lameter <clameter@sgi.com>
Cc: linux-kernel@vger.kernel.org,
Peter Zijlstra <a.p.zijlstra@chello.nl>,
Nick Piggin <nickpiggin@yahoo.com.au>, Paul Jackson <pj@sgi.com>,
Dave Chinner <dgc@sgi.com>, Andi Kleen <ak@suse.de>
Subject: Re: [RFC 0/8] Variable Order Page Cache
Date: Fri, 20 Apr 2007 15:14:06 +0100 [thread overview]
Message-ID: <20070420141406.GB16878@skynet.ie> (raw)
In-Reply-To: <20070419163504.11948.58487.sendpatchset@schroedinger.engr.sgi.com>
On (19/04/07 09:35), Christoph Lameter didst pronounce:
> Variable Order Page Cache Patchset
>
> This patchset modifies the core VM so that higher order page cache pages
> become possible. The higher order page cache pages are compound pages
> and can be handled in the same way as regular pages.
>
> The order of the pages is determined by the order set up in the mapping
> (struct address_space). By default the order is set to zero.
> This means that higher order pages are optional. There is no attempt here
> to generally change the page order of the page cache. 4K pages are effective
> for small files.
>
> However, it would be good if the VM would support I/O to higher order pages
> to enable efficient support for large scale I/O. If one wants to write a
> long file of a few gigabytes then the filesystem should have a choice of
> selecting a larger page size for that file and handle larger chunks of
> memory at once.
>
Interesting stuff. It seems promising.
> The support here is only for buffered I/O and only for one filesystem (ramfs).
> Modification of other filesystems to support higher order pages may require
> extensive work of other components of the kernel. But I hope this shows that
> there is a relatively easy way to that goal that could be taken in steps..
>
And having ramfs even remotely aware of compound pages is a step in the
direction of collaping hugetlbfs and ramfs into being two sides of the
same coin. I haven't thought about it much but it seems plausible.
> Note that the higher order pages are subject to reclaim. This works in general
> since we are always operating on a single page struct. Reclaim is fooled to
> think that it is touching page sized objects (there are likely issues to be
> fixed there if we want to go down this road).
>
I believe there is an assumption in parts of reclaim that LRU pages are
order-0. An interesting bug or two is likely to rear its head there.
> What is currently not supported:
> - Buffer heads for higher order pages (possible with the compound pages in mm
> that do not use page->private requires upgrade of the buffer cache layers).
> - Higher order pages in the block layer etc.
> - Mmapping higher order pages
>
> Note that this is proof-of-concept. Lots of functionality is missing and
> various issues have not been dealt with. Use of higher order pages may cause
> memory fragmentation. Mel Gorman's anti-fragmentation work is probably
> essential if we want to do this. We likely need actual defragmentation
> support.
>
Ok, anti-fragmentation will help up to a point but it's awkward with ramfs
because those pages are not reclaimable or migratable no matter what the
order. Normal filesystems would fare much better fragmentation-wise.
The problem is that the mapping gfp_mask is normally GFP_HIGH_MOVABLE but it's
GFP_HIGHUSER for ramfs. This patchset will increase the number of non-movable
high-order allocations quite considerably and it will tend to fragment memory
worse than we do currently. I can think of ways it can be dealt with
(even marking them RECLAIMABLE would help) so I'm not massively worried
now but I'll keep it in mind as things develop.
> The main point of this patchset is to demonstrates that it is basically
> possible to have higher order support with straightforward changes to the
> VM.
>
> The ramfs driver can be used to test higher order page cache functionality
> (and may help troubleshoot the VM support until we get some real filesystem
> and real devices supporting higher order pages).
>
> If you apply this patch and then you can f.e. try this:
>
> mount -tramfs -o10 none /media
>
> Mounts a ramfs filesystem with order 10 pages (4 MB)
>
> cp linux-2.6.21-rc7.tar.gz /media
>
> Populate the ramfs. Note that we allocate 14 pages of 4M each
> instead of 13508..
>
> umount /media
>
> Gets rid of the large pages again
>
> Comments appreciated.
>
> -
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at http://www.tux.org/lkml/
--
--
Mel Gorman
Part-time Phd Student Linux Technology Center
University of Limerick IBM Dublin Software Lab
next prev parent reply other threads:[~2007-04-20 14:14 UTC|newest]
Thread overview: 58+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-04-19 16:35 Christoph Lameter
2007-04-19 16:35 ` [RFC 1/8] Add order field to address_space struct Christoph Lameter
2007-04-19 16:35 ` [RFC 2/8] Basic allocation for higher order page cache pages Christoph Lameter
2007-04-20 10:55 ` Mel Gorman
2007-04-19 16:35 ` [RFC 3/8] Flushing and zeroing " Christoph Lameter
2007-04-20 11:02 ` Mel Gorman
2007-04-20 16:15 ` Christoph Lameter
2007-04-20 16:51 ` William Lee Irwin III
2007-04-19 16:35 ` [RFC 4/8] Enhance fallback functions in libs to support higher order pages Christoph Lameter
2007-04-19 18:48 ` Adam Litke
2007-04-19 19:10 ` Christoph Lameter
2007-04-19 22:50 ` David Chinner
2007-04-20 1:15 ` Christoph Lameter
2007-04-20 8:21 ` Jens Axboe
2007-04-20 16:01 ` Christoph Lameter
2007-04-20 16:51 ` Jens Axboe
2007-04-20 11:05 ` Mel Gorman
2007-04-20 18:50 ` Dave Kleikamp
2007-04-20 19:10 ` Christoph Lameter
2007-04-20 19:27 ` Dave Kleikamp
2007-04-24 23:00 ` Matt Mackall
2007-04-19 16:35 ` [RFC 5/8] Enhance generic_read/write " Christoph Lameter
2007-04-19 16:35 ` [RFC 6/8] Account for pages in the page cache in terms of base pages Christoph Lameter
2007-04-19 17:45 ` Nish Aravamudan
2007-04-19 17:52 ` Christoph Lameter
2007-04-19 17:54 ` Avi Kivity
2007-04-19 16:35 ` [RFC 7/8] Enhance ramfs to support higher order pages Christoph Lameter
2007-04-20 13:42 ` Mel Gorman
2007-04-20 14:47 ` William Lee Irwin III
2007-04-20 16:30 ` Christoph Lameter
2007-04-20 17:11 ` William Lee Irwin III
2007-04-20 17:15 ` Christoph Lameter
2007-04-20 17:19 ` William Lee Irwin III
2007-04-20 17:57 ` Christoph Lameter
2007-04-20 19:21 ` William Lee Irwin III
2007-04-20 17:59 ` Christoph Lameter
2007-04-20 18:01 ` Christoph Lameter
2007-04-20 18:02 ` Christoph Lameter
2007-04-20 16:20 ` Christoph Lameter
2007-04-19 16:35 ` [RFC 8/8] Add some debug output Christoph Lameter
2007-04-19 19:09 ` [RFC 0/8] Variable Order Page Cache Badari Pulavarty
2007-04-19 19:12 ` Christoph Lameter
2007-04-19 19:11 ` Andi Kleen
2007-04-19 19:15 ` Christoph Lameter
2007-04-20 14:37 ` Mel Gorman
2007-04-19 22:42 ` David Chinner
2007-04-20 1:14 ` Christoph Lameter
2007-04-20 6:32 ` Jens Axboe
2007-04-20 7:48 ` David Chinner
2007-04-21 22:18 ` Andrew Morton
2007-04-19 23:58 ` Maxim Levitsky
2007-04-20 1:15 ` Christoph Lameter
2007-04-20 4:47 ` William Lee Irwin III
2007-04-20 5:27 ` Christoph Lameter
2007-04-20 6:22 ` William Lee Irwin III
2007-04-20 8:42 ` David Chinner
2007-04-20 14:14 ` Mel Gorman [this message]
2007-04-20 16:23 ` 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=20070420141406.GB16878@skynet.ie \
--to=mel@skynet.ie \
--cc=a.p.zijlstra@chello.nl \
--cc=ak@suse.de \
--cc=clameter@sgi.com \
--cc=dgc@sgi.com \
--cc=linux-kernel@vger.kernel.org \
--cc=nickpiggin@yahoo.com.au \
--cc=pj@sgi.com \
/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
all inboxes | Powered by JetHome®