From: Arjan van de Ven <arjan@infradead.org>
To: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>,
Suleiman Souhlal <ssouhlal@freebsd.org>,
Andrew Morton <akpm@linux-foundation.org>,
linux-kernel@vger.kernel.org,
Suleiman Souhlal <suleiman@google.com>,
linux-mm <linux-mm@kvack.org>, hugh <hugh@veritas.com>
Subject: Re: [PATCH] mm: avoid dirtying shared mappings on mlock
Date: Fri, 12 Oct 2007 07:53:17 -0700 [thread overview]
Message-ID: <20071012075317.591212ef@laptopd505.fenrus.org> (raw)
In-Reply-To: <1192186222.27435.22.camel@twins>
On Fri, 12 Oct 2007 12:50:22 +0200
> > > The pages will still be read-only due to dirty tracking, so the
> > > first write will still do page_mkwrite().
> >
> > Which can SIGBUS, no?
>
> Sure, but that is no different than any other mmap'ed write. I'm not
> seeing how an mlocked region is special here.
>
> I agree it would be nice if mmap'ed writes would have better error
> reporting than SIGBUS, but such is life.
well... there's another consideration
people use mlock() in cases where they don't want to go to the
filesystem for paging and stuff as well (think the various iscsi
daemons and other things that get in trouble).. those kind of uses
really use mlock to avoid
1) IO to the filesystem
2) Needing memory allocations for pagefault like things
at least for the more "hidden" cases...
prefaulting everything ready pretty much gives them that... letting
things fault on demand... nicely breaks that.
next prev parent reply other threads:[~2007-10-12 14:55 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-07-26 23:52 [PATCH] Don't needlessly dirty mlocked pages when initially faulting them in Suleiman Souhlal
2007-07-27 0:23 ` Andrew Morton
2007-07-27 6:33 ` Peter Zijlstra
2007-10-12 6:50 ` Suleiman Souhlal
2007-10-12 9:03 ` [PATCH] mm: avoid dirtying shared mappings on mlock Peter Zijlstra
2007-10-11 16:57 ` Nick Piggin
2007-10-11 17:07 ` Nick Piggin
2007-10-12 10:37 ` Peter Zijlstra
2007-10-11 18:14 ` Nick Piggin
2007-10-12 10:50 ` Peter Zijlstra
2007-10-12 12:23 ` Nick Piggin
2007-10-12 14:53 ` Arjan van de Ven [this message]
2007-10-12 14:58 ` Peter Zijlstra
2007-10-12 17:45 ` Suleiman Souhlal
2007-10-12 17:53 ` Arjan van de Ven
2007-10-12 18:02 ` Peter Zijlstra
2007-10-12 13:10 ` [PATCH] Don't needlessly dirty mlocked pages when initially faulting them in Mauro Giachero
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=20071012075317.591212ef@laptopd505.fenrus.org \
--to=arjan@infradead.org \
--cc=a.p.zijlstra@chello.nl \
--cc=akpm@linux-foundation.org \
--cc=hugh@veritas.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=nickpiggin@yahoo.com.au \
--cc=ssouhlal@freebsd.org \
--cc=suleiman@google.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®