public inbox for [email protected]
 help / color / mirror / Atom feed
From: Jeremy Allison <[email protected]>
To: Jens Axboe <[email protected]>
Cc: Pavel Begunkov <[email protected]>,
	Stefan Metzmacher <[email protected]>,
	io-uring <[email protected]>,
	Samba Technical <[email protected]>,
	[email protected]
Subject: Re: Data Corruption bug with Samba's vfs_iouring and Linux 5.6.7/5.7rc3
Date: Thu, 7 May 2020 11:31:40 -0700	[thread overview]
Message-ID: <20200507183140.GD25085@jeremy-acer> (raw)
In-Reply-To: <[email protected]>

On Thu, May 07, 2020 at 10:50:40AM -0600, Jens Axboe wrote:
> On 5/7/20 10:48 AM, Jeremy Allison wrote:
> > On Thu, May 07, 2020 at 10:43:17AM -0600, Jens Axboe wrote:
> >>
> >> Just like for regular system calls, applications must be able to deal
> >> with short IO.
> > 
> > Thanks, that's a helpful definitive reply. Of course, the SMB3
> > protocol is designed to deal with short IO replies as well, and
> > the Samba and linux kernel clients are well-enough written that
> > they do so. MacOS and Windows however..
> 
> I'm honestly surprised that such broken clients exists! Even being
> a somewhat old timer cynic...
> 
> > Unfortunately they're the most popular clients on the planet,
> > so we'll probably have to fix Samba to never return short IOs.
> 
> That does sound like the best way forward, short IOs is possible
> with regular system calls as well, but will definitely be a lot
> more frequent with io_uring depending on the access patterns,
> page cache, number of threads, and so on.

OK, I just want to be *REALLY CLEAR* what you're telling me
(I've already written the pread/pwrite wrappers for Samba
that deal with short IO but want to ensure I understand
fully before making any changes to Samba).

You're saying that on a bog-standard ext4 disk file:

ret = pread(fd, buf, count, offset);

can return *less* than count bytes if there's no IO
error and the file size is greater than offset+count
and no one else is in the middle of a truncate etc. ?

And:

ret = pwrite(fd, buf, count, offset);

can return less* than count bytes if there's no IO
error and there's ample space on disk ?

I have to say I've *never* seen that happen, and
Samba is widely enough used that IO corruption from
short reads/writes from MacOSX and Windows clients
would have been widely reported by now.

Look at how quickly someone spotted disk corruption
because of the change in userspace-visible behavior
of the io_uring interface. We only shipped that code
03 March 2020 and someone *already* found it.

Jeremy.

  reply	other threads:[~2020-05-07 18:31 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-05-05 10:04 Data Corruption bug with Samba's vfs_iouring and Linux 5.6.7/5.7rc3 Stefan Metzmacher
2020-05-05 14:41 ` Jens Axboe
2020-05-05 15:44   ` Jens Axboe
2020-05-05 16:53     ` Jens Axboe
2020-05-05 17:39       ` Jens Axboe
2020-05-05 17:48         ` Jeremy Allison
2020-05-05 17:50           ` Jens Axboe
     [not found]           ` <[email protected]>
2020-05-06 10:33             ` Stefan Metzmacher
2020-05-06 10:41               ` Stefan Metzmacher
     [not found]               ` <[email protected]>
2020-05-06 14:08                 ` Stefan Metzmacher
2020-05-06 14:43                   ` Andreas Schneider
2020-05-06 14:46                   ` Andreas Schneider
2020-05-06 15:06                     ` Stefan Metzmacher
2020-05-06 17:03                   ` Jeremy Allison
2020-05-06 17:13                     ` Jeremy Allison
2020-05-06 18:01                     ` Jeremy Allison
2020-05-05 20:19       ` Stefan Metzmacher
2020-05-06 12:55         ` Pavel Begunkov
2020-05-06 15:20           ` Stefan Metzmacher
2020-05-06 15:42             ` Pavel Begunkov
2020-05-07 16:43               ` Jens Axboe
2020-05-07 16:48                 ` Jeremy Allison
2020-05-07 16:50                   ` Jens Axboe
2020-05-07 18:31                     ` Jeremy Allison [this message]
2020-05-07 18:35                       ` Jens Axboe
2020-05-07 18:55                         ` Jeremy Allison
2020-05-07 18:58                           ` Jens Axboe

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=20200507183140.GD25085@jeremy-acer \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    /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