From: Andrew Morton <akpm@digeo.com>
To: "Martin J. Bligh" <mbligh@aracnet.com>
Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: Re: 2.5.68-mm2
Date: Wed, 23 Apr 2003 14:46:48 -0700 [thread overview]
Message-ID: <20030423144648.5ce68d11.akpm@digeo.com> (raw)
In-Reply-To: <18400000.1051109459@[10.10.2.4]>
"Martin J. Bligh" <mbligh@aracnet.com> wrote:
>
> > . I got tired of the objrmap code going BUG under stress, so it is now in
> > disgrace in the experimental/ directory.
>
> Any chance of some more info on that? BUG at what point in the code,
> and with what test to reproduce?
A bash-shared-mapping (from ext3 CVS) will quickly knock it over. It gets
its PageAnon/page->mapping state tangled up.
Must confess that I have trouble getting excited over objrmap. It introduces
- inconsistency (pte_chains versus vma-list scanning)
- code complexity
- a quadratic search
- nasty, nasty problems with remap_file_pages(). I'd rather not have to
nobble remap_file_pages() functionality for this reason.
and what do we gain from it all? The small fork/exec boost isn't very
significant. What we gain is more lowmem space on
going-away-real-soon-now-we-sincerely-hope highmem boxes.
Ingo-rmap seems a better solution to me. It would be a fairly large change
though - we'd have to hold the four atomic kmaps across an entire pte page
in copy_page_range(), for example. But it will then have good locality of
reference between adjacent pages and may well be quicker than pte_chains.
next prev parent reply other threads:[~2003-04-23 21:36 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2003-04-23 8:20 2.5.68-mm2 Andrew Morton
2003-04-23 9:59 ` 2.5.68-mm2 William Lee Irwin III
2003-04-23 16:50 ` 2.5.68-mm2 Robert Love
2003-04-23 16:57 ` 2.5.68-mm2 Martin J. Bligh
2003-04-23 17:11 ` 2.5.68-mm2 Robert Love
2003-04-24 9:14 ` 2.5.68-mm2 William Lee Irwin III
2003-04-23 14:51 ` 2.5.68-mm2 Martin J. Bligh
2003-04-23 15:14 ` 2.5.68-mm2 Alex Tomas
2003-04-23 21:46 ` Andrew Morton [this message]
2003-04-23 21:47 ` 2.5.68-mm2 Martin J. Bligh
2003-04-24 3:39 ` 2.5.68-mm2 Benjamin LaHaise
2003-04-24 21:13 ` 2.5.68-mm2 Martin J. Bligh
2003-04-24 23:13 ` objrmap (was 2.5.68-mm2) Martin J. Bligh
2003-04-24 3:36 ` 2.5.68-mm2 Benjamin LaHaise
2003-04-24 20:24 ` 2.5.68-mm2 Bill Davidsen
2003-04-24 20:33 ` 2.5.68-mm2 Benjamin LaHaise
2003-04-25 17:56 ` 2.5.68-mm2 Bill Davidsen
2003-04-25 18:20 ` 2.5.68-mm2 Randy.Dunlap
2003-04-25 18:27 ` 2.5.68-mm2 Robert Love
2003-04-25 18:49 ` 2.5.68-mm2 Martin J. Bligh
2003-04-26 10:34 ` 2.5.68-mm2 Bill Davidsen
2003-04-26 15:34 ` 2.5.68-mm2 Martin J. Bligh
2003-05-01 6:19 ` [BUG] 2.5.68-mm2 and list.h Alexander Hoogerhuis
2003-05-01 6:31 ` Andrew Morton
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=20030423144648.5ce68d11.akpm@digeo.com \
--to=akpm@digeo.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mbligh@aracnet.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;
as well as URLs for NNTP newsgroup(s).