Re: ext3 IO latency measurements (was: Linux 2.6.29)
[Posted March 31, 2009 by corbet]
| From: |
| Alan Cox <alan-AT-lxorguk.ukuu.org.uk> |
| To: |
| Linus Torvalds <torvalds-AT-linux-foundation.org> |
| Subject: |
| Re: ext3 IO latency measurements (was: Linux 2.6.29) |
| Date: |
| Thu, 26 Mar 2009 18:59:00 +0000 |
| Message-ID: |
| <20090326185900.166a1097@lxorguk.ukuu.org.uk> |
| Cc: |
| Theodore Tso <tytso-AT-mit.edu>, Ingo Molnar <mingo-AT-elte.hu>,
Jan Kara <jack-AT-suse.cz>,
Andrew Morton <akpm-AT-linux-foundation.org>,
Arjan van de Ven <arjan-AT-infradead.org>,
Peter Zijlstra <a.p.zijlstra-AT-chello.nl>,
Nick Piggin <npiggin-AT-suse.de>,
Jens Axboe <jens.axboe-AT-oracle.com>,
David Rees <drees76-AT-gmail.com>, Jesper Krogh <jesper-AT-krogh.cc>,
Linux Kernel Mailing List <linux-kernel-AT-vger.kernel.org>,
Oleg Nesterov <oleg-AT-redhat.com>,
Roland McGrath <roland-AT-redhat.com> |
| Archive-link: |
| Article, Thread
|
> And what's the argument for not doing it in the kernel?
>
> The fact is, "atime" by default is just wrong.
It probably was a wrong default - twenty years ago. Actually it may well
have been a wrong default in Unix v6 8)
However
- atime behaviour is SuS required
- there are users with systems out there using atime and dependant on
proper atime
So we can't change the ABI on them any more than we can decide that next
week write() should return short values on writes to disk interrupted by
signals...
Letting distros flip to relatime means new installs and gradual migration
occurs and nobody gets spectacularly blown up when their archiving
system, their usage profiling and disk balancing tools and the like go
wrong.
(
Log in to post comments)
