From: Andrea Arcangeli <andrea@suse.de>
To: Rik van Riel <riel@conectiva.com.br>
Cc: Andrew Morton <akpm@zip.com.au>,
Martin Schwidefsky <schwidefsky@de.ibm.com>,
linux-kernel@vger.kernel.org, Alan Cox <alan@lxorguk.ukuu.org.uk>
Subject: Re: Bug with shared memory.
Date: Tue, 21 May 2002 01:46:22 +0200 [thread overview]
Message-ID: <20020520234622.GL21806@dualathlon.random> (raw)
In-Reply-To: <20020520141523.GB21806@dualathlon.random> <Pine.LNX.4.44L.0205201618110.24352-100000@imladris.surriel.com>
On Mon, May 20, 2002 at 04:24:37PM -0300, Rik van Riel wrote:
> On Mon, 20 May 2002, Andrea Arcangeli wrote:
>
> > With memclass_related_bhs() we automatically maximixed the amount of ram
> > available as inodes/indirects and everything else ZONE_NORMAL, after
>
> OK, a question and a remark:
>
> 1) does memclass_related_bhs() work if the bufferheads are
> on another node ? (NUMA-Q)
yes of course. With all the numa fixes all the classzone logic is
indipendent from the pgdat layer, not only during the
memclass_related_bhs check. The faster way to understand how the logic
works is to read the zone_idx/memclass define in mmzone.h.
> 2) memclass_related_bhs() will definately not work if the
> data structure is pinned indirectly, say struct address_space
> which is pinned by mere the existance of the page cache page
> and cannot easily be freed
memclass_related_bhs is just for the bhs, it has nothing to do with the
address space. It's in the page->buffer side of the page, not the
page->mapping, so I don't understand very well.
the inode problem is a separate thing, nothing to do with
memclass_related_bhs(), the fix will be local to prune_icache.
For the memclass_related_bhs() fix in -aa, that's in the testing TODO
list of Martin (on the multi giga machines), he also nicely proposed to
compare it to the other throw-away-all-bh-regardless patch from Andrew
(that I actually didn't seen floating around yet but it's clear how it
works, it's a subset of memclass_related_bhs). However the right way to
test the memclass_related_bhs vs throw-away-all-bh, is to run a rewrite
test that fits in cache, so write,fsync,write,fsync,write,fsync. specweb
or any other read-only test will obviously perform exactly the same both
ways (actually theoretically a bit cpu-faster in throw-away-all-bh
because it doesn't check the bh list).
> > > or three, so he may not see your words.
> >
> > Ok. We CC'ed Rik so I assume it won't get lost in the mail flood.
>
> I'm on holidays, don't expect patches soon :)
you shouldn't read emails either then, you know it is strictly forbidden
to read emails during vacations :). I'm kidding of course, thanks for
the fast reply!
Andrea
next prev parent reply other threads:[~2002-05-20 23:48 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2002-05-14 15:13 Bug with shared memory Martin Schwidefsky
2002-05-14 19:33 ` Andrew Morton
2002-05-15 22:42 ` Mike Kravetz
2002-05-15 23:07 ` Andrew Morton
2002-05-17 17:53 ` Bill Davidsen
2002-05-17 20:07 ` Mike Kravetz
2002-05-17 20:29 ` Anton Blanchard
2002-05-20 4:30 ` Andrea Arcangeli
2002-05-20 5:21 ` Andrew Morton
2002-05-20 11:34 ` Andrey Savochkin
2002-05-20 14:15 ` Andrea Arcangeli
2002-05-20 19:24 ` Rik van Riel
2002-05-20 23:46 ` Andrea Arcangeli [this message]
2002-05-21 0:14 ` Martin J. Bligh
2002-05-21 1:40 ` Andrea Arcangeli
2002-05-20 16:22 ` Martin J. Bligh
2002-05-20 19:38 ` Rik van Riel
2002-05-20 20:06 ` William Lee Irwin III
2002-05-20 16:13 ` Martin J. Bligh
2002-05-20 16:37 ` Andrea Arcangeli
2002-05-20 17:23 ` Martin J. Bligh
2002-05-20 17:32 ` William Lee Irwin III
2002-05-24 7:33 ` inode highmem imbalance fix [Re: Bug with shared memory.] Andrea Arcangeli
2002-05-24 7:51 ` William Lee Irwin III
2002-05-24 8:04 ` Andrew Morton
2002-05-24 15:20 ` Andrea Arcangeli
2002-05-24 11:47 ` Ed Tomlinson
2002-05-30 11:25 ` Denis Lunev
2002-05-30 17:59 ` Andrea Arcangeli
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=20020520234622.GL21806@dualathlon.random \
--to=andrea@suse.de \
--cc=akpm@zip.com.au \
--cc=alan@lxorguk.ukuu.org.uk \
--cc=linux-kernel@vger.kernel.org \
--cc=riel@conectiva.com.br \
--cc=schwidefsky@de.ibm.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).