From: Mark Kirkwood <mark.kirkwood@catalyst.net.nz>
To: Somnath Roy <Somnath.Roy@sandisk.com>, Sage Weil <sweil@redhat.com>
Cc: "Ma, Jianpeng" <jianpeng.ma@intel.com>,
"Samuel Just (sam.just@inktank.com)" <sam.just@inktank.com>,
"ceph-devel@vger.kernel.org" <ceph-devel@vger.kernel.org>
Subject: Re: Deadlock in ceph journal
Date: Sat, 23 Aug 2014 10:38:33 +1200 [thread overview]
Message-ID: <53F7C669.9010800@catalyst.net.nz> (raw)
In-Reply-To: <755F6B91B3BE364F9BCA11EA3F9E0C6F264745A2@SACMBXIP01.sdcorp.global.sandisk.com>
On 23/08/14 10:22, Somnath Roy wrote:
> I think it is using direct io for non-aio mode as well.
>
> Thanks & Regards
> Somnath
>
> One thing that does still concern me - if I understand what is happening here correctly: we write to the journal using aio until we want to stop doing writes (presumably pre closing it), then use normal io to write at that point.
>
> Given that we appear to be using direct io whenever we use aio, does this mean we end up mixing direct and buffered io to the journal [1] (or is the normal i.e non aio write still using direct io)?
>
>
Thanks Somnath,
I think you are correct (I missed the bit in FileJournal::_open that
seems to cover this):
if (forwrite) {
flags = O_RDWR;
if (directio)
flags |= O_DIRECT | O_DSYNC;
i.e the journal is opened with DIRECT, so all writes (async or not) will
be direct.
Cheers
Mark
next prev parent reply other threads:[~2014-08-22 22:38 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <755F6B91B3BE364F9BCA11EA3F9E0C6F2646AE7B@SACMBXIP02.sdcorp.global.sandisk.com>
2014-08-20 3:55 ` Deadlock in ceph journal Sage Weil
2014-08-20 4:38 ` Somnath Roy
2014-08-20 4:50 ` Sage Weil
2014-08-20 4:52 ` Somnath Roy
2014-08-20 15:33 ` Sage Weil
2014-08-21 1:54 ` Ma, Jianpeng
2014-08-21 3:52 ` Sage Weil
2014-08-21 7:30 ` Ma, Jianpeng
2014-08-21 8:17 ` Mark Kirkwood
2014-08-21 15:23 ` Sage Weil
2014-08-22 0:45 ` Mark Kirkwood
2014-08-22 0:49 ` Sage Weil
2014-08-22 22:18 ` Mark Kirkwood
2014-08-22 22:22 ` Somnath Roy
2014-08-22 22:32 ` Sage Weil
2014-08-22 22:38 ` Mark Kirkwood [this message]
2014-08-25 1:03 ` Ma, Jianpeng
2014-08-25 2:14 ` Sage Weil
2014-08-25 3:32 ` Ma, Jianpeng
2014-08-20 4:58 ` Mark Kirkwood
2014-08-20 5:04 ` Mark Kirkwood
2014-08-20 4:49 ` Somnath Roy
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=53F7C669.9010800@catalyst.net.nz \
--to=mark.kirkwood@catalyst.net.nz \
--cc=Somnath.Roy@sandisk.com \
--cc=ceph-devel@vger.kernel.org \
--cc=jianpeng.ma@intel.com \
--cc=sam.just@inktank.com \
--cc=sweil@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.