From: Trond Myklebust <trond.myklebust@primarydata.com>
To: Sage Weil <sage@newdream.net>
Cc: Zach Brown <zab@redhat.com>, Dave Chinner <david@fromorbit.com>,
Alexander Viro <viro@zeniv.linux.org.uk>,
Linux FS-devel Mailing List <linux-fsdevel@vger.kernel.org>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
Linux API Mailing List <linux-api@vger.kernel.org>
Subject: Re: [PATCH RFC] vfs: add a O_NOMTIME flag
Date: Thu, 7 May 2015 21:23:24 -0400 [thread overview]
Message-ID: <CAHQdGtQjMHA8rVPkggB2zMz=k3O667+APH_1EY_2FtYmHL7-hw@mail.gmail.com> (raw)
In-Reply-To: <alpine.DEB.2.00.1505071752520.28239@cobra.newdream.net>
On Thu, May 7, 2015 at 9:01 PM, Sage Weil <sage@newdream.net> wrote:
> On Thu, 7 May 2015, Zach Brown wrote:
>> On Thu, May 07, 2015 at 10:26:17AM +1000, Dave Chinner wrote:
>> > On Wed, May 06, 2015 at 03:00:12PM -0700, Zach Brown wrote:
>> > > The criteria for using O_NOMTIME is the same as for using O_NOATIME:
>> > > owning the file or having the CAP_FOWNER capability. If we're not
>> > > comfortable allowing owners to prevent mtime/ctime updates then we
>> > > should add a tunable to allow O_NOMTIME. Maybe a mount option?
>> >
>> > I dislike "turn off safety for performance" options because Joe
>> > SpeedRacer will always select performance over safety.
>>
>> Well, for ceph there's no safety concern. They never use cmtime in
>> these files.
>>
>> So are you suggesting not implementing this and making them rework their
>> IO paths to avoid the fs maintaining mtime so that we don't give Joe
>> Speedracer more rope? Or are we talking about adding some speed bumps
>> that ceph can flip on that might give Joe Speedracer pause?
>
> I think this is the fundamental question: who do we give the ammunition
> to, the user or app writer, or the sysadmin?
>
> One might argue that we gave the user a similar power with O_NOATIME (the
> power to break applications that assume atime is accurate). Here we give
> developers/users the power to not update mtime and suffer the consequences
> (like, obviously, breaking mtime-based backups). It should be pretty
> obvious to anyone using the flag what the consequences are.
>
> Note that we can suffer similar lapses in mtime with fdatasync followed by
> a system crash. And as Andy points out it's semi-broken for writable
> mmap. The crash case is obviously a slightly different thing, but the
> idea that mtime can't always be trusted certainly isn't crazy talk.
>
> Or, we can be conservative and require a mount option so that the admin
> has to explicitly allow behavior that might break some existing
> assumptions about mtime/ctime ('-o user_noatime' I guess?).
>
> I'm happy either way, so long as in the end an unprivileged ceph daemon
> avoids the useless work. In our case we always own the entire mount/disk,
> so a mount option is just fine.
>
So, what is the expectation here for filesystems that cannot support
this flag? NFSv3 in particular would break pretty catastrophically if
someone decided on a whim to turn off mtime: they will have turned off
the client's ability to detect cache incoherencies.
Cheers
Trond
next prev parent reply other threads:[~2015-05-08 1:23 UTC|newest]
Thread overview: 52+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-05-06 22:00 [PATCH RFC] vfs: add a O_NOMTIME flag Zach Brown
2015-05-06 22:14 ` Trond Myklebust
2015-05-06 22:19 ` Sage Weil
2015-05-06 22:41 ` Zach Brown
2015-05-06 22:46 ` Sage Weil
2015-05-06 23:21 ` Theodore Ts'o
2015-05-07 0:26 ` Dave Chinner
2015-05-07 17:20 ` Zach Brown
2015-05-07 18:43 ` Zach Brown
2015-05-07 19:09 ` Richard Weinberger
2015-05-07 19:53 ` Andy Lutomirski
[not found] ` <554BC4D8.9010507@nod.at>
2015-05-07 20:06 ` Andy Lutomirski
2015-05-08 2:42 ` Dave Chinner
2015-07-14 11:44 ` Pavel Machek
2015-05-08 1:01 ` Sage Weil
2015-05-08 1:23 ` Trond Myklebust [this message]
2015-05-08 15:19 ` Sage Weil
2015-05-08 22:13 ` Dave Chinner
2015-05-08 22:24 ` Sage Weil
2015-05-10 23:13 ` Trond Myklebust
2015-05-11 7:31 ` Dave Chinner
2015-05-11 16:39 ` Sage Weil
2015-05-11 17:12 ` Trond Myklebust
2015-05-11 17:30 ` Sage Weil
2015-05-12 1:21 ` Dave Chinner
2015-05-12 23:12 ` Sage Weil
2015-05-13 0:57 ` Dave Chinner
2015-05-12 13:41 ` John Stoffel
2015-05-11 14:47 ` Theodore Ts'o
2015-05-11 16:24 ` Sage Weil
2015-05-11 23:10 ` Theodore Ts'o
2015-05-12 5:08 ` Kevin Easton
2015-05-12 11:45 ` Austin S Hemmelgarn
2015-05-12 13:54 ` John Stoffel
2015-05-12 14:36 ` J. Bruce Fields
2015-05-12 14:53 ` Austin S Hemmelgarn
2015-05-12 21:51 ` Dave Chinner
2015-05-13 15:16 ` Austin S Hemmelgarn
2015-05-12 22:39 ` NeilBrown
2015-07-14 13:13 ` Pavel Machek
2015-07-15 4:54 ` NeilBrown
2015-07-22 13:47 ` Pavel Machek
2015-05-12 21:35 ` Sage Weil
2015-05-13 12:32 ` Jan Kara
2015-05-08 14:29 ` John Stoffel
2015-07-14 11:50 ` Pavel Machek
2015-05-08 14:43 ` Austin S Hemmelgarn
2015-05-08 17:11 ` Zach Brown
2015-05-08 2:37 ` Dave Chinner
2015-05-08 3:24 ` Andy Lutomirski
2015-05-08 14:44 ` Eric Sandeen
2015-05-11 20:36 ` J. Bruce Fields
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='CAHQdGtQjMHA8rVPkggB2zMz=k3O667+APH_1EY_2FtYmHL7-hw@mail.gmail.com' \
--to=trond.myklebust@primarydata.com \
--cc=david@fromorbit.com \
--cc=linux-api@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=sage@newdream.net \
--cc=viro@zeniv.linux.org.uk \
--cc=zab@redhat.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).