linux-btrfs.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Andrea Gelmini <andrea.gelmini@gmail.com>
To: David Sterba <dsterba@suse.cz>, Andrea Gelmini <gelma@gelma.net>,
	Linux BTRFS <linux-btrfs@vger.kernel.org>
Subject: Re: Request about "Page cache invalidation failure on direct I/O."
Date: Thu, 26 Mar 2020 14:53:52 +0100	[thread overview]
Message-ID: <CAK-xaQYSEHsxeXRJS9kzTPjzpUaQCYYeYcoKN0VGCTQfbCn=6Q@mail.gmail.com> (raw)
In-Reply-To: <20200317002945.GV12659@twin.jikos.cz>

Il giorno mar 17 mar 2020 alle ore 01:30 David Sterba
<dsterba@suse.cz> ha scritto:
> without tuning of the rate I can't say if the buffered vs dio happens
> all the time or just once. For the 'once' case I would not be worried.

Thanks a lot David for your interest.

Well, with latest kernel (5.5.13), I still see it, but a lot less than
before (same setup, hardware and
software versions).

After a few hours of work I just got this bouch of warnings (btw, no
boot of virtual machine guest, it was in status saved/suspended).

[gio mar 26 05:22:58 2020] Page cache invalidation failure on direct
I/O.  Possible data corruption due to collision with buffered I/O!
[gio mar 26 05:22:58 2020] File:
/mnt/4TB/piastrelli/home/virtual/VirtualBox
VMs/Zuccotti/Snapshots/{23d5aff0-4514-46b9-ab38-76ae59b3acbf}.vdi P
ID: 25176 Comm: kworker/4:3
[gio mar 26 05:28:41 2020] Page cache invalidation failure on direct
I/O.  Possible data corruption due to collision with buffered I/O!
[gio mar 26 05:28:41 2020] File:
/mnt/4TB/piastrelli/home/virtual/VirtualBox
VMs/Zuccotti/Snapshots/{23d5aff0-4514-46b9-ab38-76ae59b3acbf}.vdi P
ID: 35075 Comm: kworker/4:1
[gio mar 26 05:44:00 2020] Page cache invalidation failure on direct
I/O.  Possible data corruption due to collision with buffered I/O!
[gio mar 26 05:44:00 2020] File:
/mnt/4TB/piastrelli/home/virtual/VirtualBox
VMs/Zuccotti/Snapshots/{23d5aff0-4514-46b9-ab38-76ae59b3acbf}.vdi P
ID: 38801 Comm: kworker/4:4
[gio mar 26 05:54:48 2020] Page cache invalidation failure on direct
I/O.  Possible data corruption due to collision with buffered I/O!
[gio mar 26 05:54:48 2020] File:
/mnt/4TB/piastrelli/home/virtual/VirtualBox
VMs/Zuccotti/Snapshots/{23d5aff0-4514-46b9-ab38-76ae59b3acbf}.vdi P
ID: 44366 Comm: kworker/4:1
[gio mar 26 06:02:43 2020] Page cache invalidation failure on direct
I/O.  Possible data corruption due to collision with buffered I/O!
[gio mar 26 06:02:43 2020] File:
/mnt/4TB/piastrelli/home/virtual/VirtualBox
VMs/Zuccotti/Snapshots/{23d5aff0-4514-46b9-ab38-76ae59b3acbf}.vdi P
ID: 44366 Comm: kworker/4:1
[gio mar 26 06:02:43 2020] Page cache invalidation failure on direct
I/O.  Possible data corruption due to collision with buffered I/O!
[gio mar 26 06:02:43 2020] File:
/mnt/4TB/piastrelli/home/virtual/VirtualBox
VMs/Zuccotti/Snapshots/{23d5aff0-4514-46b9-ab38-76ae59b3acbf}.vdi P
ID: 53354 Comm: kworker/4:2
[gio mar 26 06:02:43 2020] Page cache invalidation failure on direct
I/O.  Possible data corruption due to collision with buffered I/O!
[gio mar 26 06:02:43 2020] File:
/mnt/4TB/piastrelli/home/virtual/VirtualBox
VMs/Zuccotti/Snapshots/{23d5aff0-4514-46b9-ab38-76ae59b3acbf}.vdi P
ID: 55712 Comm: kworker/4:6

I have no problem at the moment (this is happening on the test setup
to evaluate BTRFS), but maybe it's important to spot it for you all
devs.
If it help you, I can test the same setup with ext4 or another fs.

Thanks again,
Gelma


Ciao,
Gelma

      reply	other threads:[~2020-03-26 13:54 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-03-11 20:42 Request about "Page cache invalidation failure on direct I/O." Andrea Gelmini
2020-03-17  0:29 ` David Sterba
2020-03-26 13:53   ` Andrea Gelmini [this message]

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='CAK-xaQYSEHsxeXRJS9kzTPjzpUaQCYYeYcoKN0VGCTQfbCn=6Q@mail.gmail.com' \
    --to=andrea.gelmini@gmail.com \
    --cc=dsterba@suse.cz \
    --cc=gelma@gelma.net \
    --cc=linux-btrfs@vger.kernel.org \
    /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).