From: Wu Fengguang <fengguang.wu@intel.com>
To: NeilBrown <neilb@suse.de>
Cc: "Li, Shaohua" <shaohua.li@intel.com>, Ted Ts'o <tytso@mit.edu>,
"linux-ext4@vger.kernel.org" <linux-ext4@vger.kernel.org>,
Jan Kara <jack@suse.cz>, LKML <linux-kernel@vger.kernel.org>,
"linux-fsdevel@vger.kernel.org" <linux-fsdevel@vger.kernel.org>,
"linux-raid@vger.kernel.org" <linux-raid@vger.kernel.org>,
Jens Axboe <axboe@kernel.dk>
Subject: Re: ext4 data=writeback performs worse than data=ordered now
Date: Thu, 15 Dec 2011 13:02:34 +0800 [thread overview]
Message-ID: <20111215050233.GA8959@localhost> (raw)
In-Reply-To: <20111215122759.7ce0b7b5@notabene.brown>
On Thu, Dec 15, 2011 at 09:27:59AM +0800, NeilBrown wrote:
> On Thu, 15 Dec 2011 09:00:10 +0800 Wu Fengguang <fengguang.wu@intel.com>
> wrote:
>
> > > I found sometimes one disk hasn't any request inflight, but we can't
> > > send request to the disk, because the scsi host's resource (the queue
> > > depth) is used out, looks we send too many requests from other disks and
> > > leave some disks starved. The resource imbalance in scsi isn't a new
> > > problem, even 3.1 has such issue, so I'd think writeback introduces new
> > > imbalance between the 12 disks. In fact, if I limit disk's queue depth
> > > to 10, in this way the 12 disks will not impact each other in scsi
> > > layer, the performance regression fully disappears for both writeback
> > > and order mode.
> >
> > I observe similar issue in MD. The default
> >
> > q->nr_requests = BLKDEV_MAX_RQ;
> >
> > is too small for large arrays, and I end up doing
> >
> > echo 1280 > /sys/block/md0/queue/nr_requests
> >
> > in my tests.
>
> And you find this makes a difference?
>
> That is very surprising because md devices don't use requests (and really use
> the 'queue' at all) and definitely don't make use of nr_requests.
Yes it is: /sys/block/md0/queue/nr_requests cannot be modified at all...
Sorry for the noise!
Fengguang
next prev parent reply other threads:[~2011-12-15 5:02 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-12-14 13:34 ext4 data=writeback performs worse than data=ordered now Wu Fengguang
[not found] ` <20111214140025.GA19650@localhost>
2011-12-14 14:03 ` Wu Fengguang
2011-12-14 14:30 ` Ted Ts'o
2011-12-14 14:49 ` Wu Fengguang
2011-12-14 14:52 ` Tao Ma
2011-12-14 15:02 ` Wu Fengguang
2011-12-15 1:02 ` Shaohua Li
2011-12-15 1:00 ` Wu Fengguang
2011-12-15 1:27 ` NeilBrown
2011-12-15 1:34 ` Wu Fengguang
2011-12-15 5:02 ` Wu Fengguang [this message]
2011-12-15 1:20 ` Darrick J. Wong
2011-12-15 1:42 ` Shaohua Li
2011-12-15 18:10 ` Darrick J. Wong
2011-12-16 1:47 ` Shaohua Li
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=20111215050233.GA8959@localhost \
--to=fengguang.wu@intel.com \
--cc=axboe@kernel.dk \
--cc=jack@suse.cz \
--cc=linux-ext4@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-raid@vger.kernel.org \
--cc=neilb@suse.de \
--cc=shaohua.li@intel.com \
--cc=tytso@mit.edu \
/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).