From: Paolo Bonzini <pbonzini@redhat.com>
To: Anand Avati <aavati@redhat.com>
Cc: Kevin Wolf <kwolf@redhat.com>,
Anthony Liguori <aliguori@us.ibm.com>,
Vijay Bellur <vbellur@redhat.com>,
Stefan Hajnoczi <stefanha@gmail.com>,
Harsh Bora <harsh@linux.vnet.ibm.com>,
Amar Tumballi <amarts@redhat.com>,
qemu-devel@nongnu.org, "Richard W.M. Jones" <rjones@redhat.com>,
Blue Swirl <blauwirbel@gmail.com>, Avi Kivity <avi@redhat.com>,
bharata@linux.vnet.ibm.com, Daniel Veillard <veillard@redhat.com>
Subject: Re: [Qemu-devel] O_DIRECT on glusterfs (was Re: [PATCH v9 4/4] block: Support GlusterFS as a QEMU block backend)
Date: Wed, 03 Oct 2012 20:17:47 +0200 [thread overview]
Message-ID: <506C814B.1080305@redhat.com> (raw)
In-Reply-To: <506C7CD5.6090407@redhat.com>
Il 03/10/2012 19:58, Anand Avati ha scritto:
>>
>> I think these 3 lines should be removed. We're bypassing the host
>> buffer cache just by virtue of using a userspace driver, and that's what
>> cache=none cares about.
>
> O_DIRECT also has an effect on the behavior of the "client side" (the
> part within the qemu) of Gluster stack as well. I presume the intention
> of O_DIRECT is to minimize use of memory (whether as host' page cache or
> buffered data in user space). To that end it is a good idea to leave
> O_DIRECT flag set.
>
> The behavior of whether gluster bricks need to get the O_DIRECT
> propagated or not is a different issue. We are exploring the possibility
> of not sending O_DIRECT flag over the wire to mimic NFS behavior. That
> would be independent of the qemu block driver setting the open flag.
What is the effect of O_DIRECT on the client exactly?
Paolo
next prev parent reply other threads:[~2012-10-03 18:17 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-09-24 9:10 [Qemu-devel] [PATCH v9 0/4] GlusterFS support in QEMU - v9 Bharata B Rao
2012-09-24 9:10 ` [Qemu-devel] [PATCH v9 1/4] aio: Fix qemu_aio_wait() to maintain correct walking_handlers count Bharata B Rao
2012-09-24 9:12 ` [Qemu-devel] [PATCH v9 2/4] qemu: URI parsing library Bharata B Rao
2012-09-24 10:27 ` Richard W.M. Jones
2012-09-24 11:11 ` Paolo Bonzini
2012-09-27 9:03 ` Avi Kivity
2012-09-27 9:07 ` Paolo Bonzini
2012-10-02 4:59 ` Daniel Veillard
2012-10-02 6:16 ` Paolo Bonzini
2012-09-24 9:12 ` [Qemu-devel] [PATCH v9 3/4] configure: Add a config option for GlusterFS as block backend Bharata B Rao
2012-09-24 9:13 ` [Qemu-devel] [PATCH v9 4/4] block: Support GlusterFS as a QEMU " Bharata B Rao
2012-09-24 9:26 ` Paolo Bonzini
2012-09-24 9:44 ` Bharata B Rao
2012-09-26 10:00 ` Kevin Wolf
2012-09-26 10:08 ` Paolo Bonzini
2012-09-26 16:11 ` Bharata B Rao
2012-09-26 16:38 ` Paolo Bonzini
2012-09-27 6:41 ` Bharata B Rao
2012-09-27 7:19 ` Paolo Bonzini
2012-09-27 8:28 ` Bharata B Rao
2012-09-27 8:31 ` Paolo Bonzini
2012-10-03 15:50 ` [Qemu-devel] O_DIRECT on glusterfs (was Re: [PATCH v9 4/4] block: Support GlusterFS as a QEMU block backend) Paolo Bonzini
2012-10-03 17:58 ` Anand Avati
2012-10-03 18:17 ` Paolo Bonzini [this message]
2012-10-03 18:17 ` Anand Avati
2012-10-03 18:27 ` Paolo Bonzini
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=506C814B.1080305@redhat.com \
--to=pbonzini@redhat.com \
--cc=aavati@redhat.com \
--cc=aliguori@us.ibm.com \
--cc=amarts@redhat.com \
--cc=avi@redhat.com \
--cc=bharata@linux.vnet.ibm.com \
--cc=blauwirbel@gmail.com \
--cc=harsh@linux.vnet.ibm.com \
--cc=kwolf@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=rjones@redhat.com \
--cc=stefanha@gmail.com \
--cc=vbellur@redhat.com \
--cc=veillard@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).