From: Christoph Lameter <clameter@sgi.com>
To: Mel Gorman <mel@skynet.ie>
Cc: linux-kernel@vger.kernel.org,
Peter Zijlstra <a.p.zijlstra@chello.nl>,
Nick Piggin <nickpiggin@yahoo.com.au>, Andi Kleen <ak@suse.de>,
Paul Jackson <pj@sgi.com>, Dave Chinner <dgc@sgi.com>
Subject: Re: [RFC 3/8] Flushing and zeroing higher order page cache pages
Date: Fri, 20 Apr 2007 09:15:25 -0700 (PDT) [thread overview]
Message-ID: <Pine.LNX.4.64.0704200910440.20232@schroedinger.engr.sgi.com> (raw)
In-Reply-To: <20070420110244.GB12075@skynet.ie>
On Fri, 20 Apr 2007, Mel Gorman wrote:
> While this looks fine, it seems that clear_huge_page() and
> clear_mapping_page() could share a common helper. I also note that
> clear_huge_page() calls cond_reched() and this doesn't which may be the
> type of different behavior we want to avoid.
I am really thinking that this variable order page cache approach
is likely going to result in the final death of the huge page subsystem. I
would like to keep huge pages separate from this so that the huge page
subsystem can be removed at some point without too much trouble. Right now
it is a very sore point at least from a performance standpoint since the
hugetlb subsystem is serialized with a single lock. There is a weird maze
of locking and accounting constraints in there that makes it difficult to
fix this.
> That said, if this goes ahead, it might be an excuse to look at using
> ramfs as the basis for hugetlbfs instead of it's current approach. I
> believe using ramfs for hugepages is something that wli wants anyway.
Right. There is no reason for hugetlbfs to exist anymore. We will have
very transparent and flexible support for huge pages.
next prev parent reply other threads:[~2007-04-20 16:15 UTC|newest]
Thread overview: 58+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-04-19 16:35 [RFC 0/8] Variable Order Page Cache 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 [this message]
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
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=Pine.LNX.4.64.0704200910440.20232@schroedinger.engr.sgi.com \
--to=clameter@sgi.com \
--cc=a.p.zijlstra@chello.nl \
--cc=ak@suse.de \
--cc=dgc@sgi.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mel@skynet.ie \
--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®