From: Fengguang Wu <fengguang.wu@intel.com>
To: lkp@lists.01.org
Subject: Re: [blk-lib] 6a0608544e5: fileio -77.4% max latency, -5.7% throughput
Date: Wed, 05 Mar 2014 10:07:46 +0800 [thread overview]
Message-ID: <20140305020746.GA14711@localhost> (raw)
In-Reply-To: <20140305012352.GR13647@dastard>
[-- Attachment #1: Type: text/plain, Size: 2244 bytes --]
On Wed, Mar 05, 2014 at 12:23:53PM +1100, Dave Chinner wrote:
> On Wed, Mar 05, 2014 at 09:16:45AM +0800, Fengguang Wu wrote:
> > On Tue, Mar 04, 2014 at 01:52:25PM -0800, Kent Overstreet wrote:
> > > On Tue, Mar 04, 2014 at 09:21:30PM +0800, Fengguang Wu wrote:
> > > > Hi Kent,
> > > >
> > > > FYI, we noticed the below changes on
> > > >
> > > > git://evilpiepirate.org/~kent/linux-bcache.git for-jens
> > > > commit 6a0608544e5672bd9a044c285119547eae41abe5 ("blk-lib.c: generic_make_request() handles large bios now")
> > > >
> > > > test case: snb-drag/sysbench/fileio/600s-100%-1HDD-ext4-64G-1024-seqrewr-sync
> >
> > snb-drag is the test machine, it's a SNB desktop.
> >
> > The test command is
> >
> > mkfs -t ext4 -q /dev/sda2
> > mount -t ext4 /dev/sda2 /fs/sda2
> > cd /fs/sda2
> >
> > for i in $(seq 0 1023)
> > do
> > fallocate -l 67108864 test_file.$i
> > done
> >
> > sysbench --test=fileio --max-requests=0 --num-threads=4 --max-time=600 --file-test-mode=seqrewr --file-total-size=68719476736 --file-io-mode=sync --file-num=1024 run
> >
> >
> > > I'm trying to figure out how to parse this and the graphs - where do I find the
> > > test? And is there anything you can point me to for the graphs, or is that
> > > output from that test?
> > >
> > > >
> > > > 11541d5f5b7002b 6a0608544e5672bd9a044c285
> > > > --------------- -------------------------
> > > > 1885 ~60% -77.4% 426 ~ 7% TOTAL fileio.request_latency_max_ms
> >
> > The ~XX% numbers are stddev percent.
> > The [+-]XX% is change percent.
>
> Can you put this in as column headers so that people don't have to
> this every time they see a report from you?
Good idea!
> > The below graph shows all samples collected during the bisect
> >
> > [*] bisect-good
> > [O] bisect-bad
> >
> > In which you can see the stableness of the change and bisect.
>
> Oh, so that's what the graphs contain. :/
>
> Again - perhaps you should include this information with the graphs
> rather than just dumping unlabelled data on people ;)
Yeah sure. I'll follow your nice suggestions!
Thanks,
Fengguang
WARNING: multiple messages have this Message-ID (diff)
From: Fengguang Wu <fengguang.wu@intel.com>
To: Dave Chinner <david@fromorbit.com>
Cc: Kent Overstreet <kmo@daterainc.com>,
LKML <linux-kernel@vger.kernel.org>,
lkp@01.org, linux-fsdevel@vger.kernel.org
Subject: Re: [blk-lib] 6a0608544e5: fileio -77.4% max latency, -5.7% throughput
Date: Wed, 5 Mar 2014 10:07:46 +0800 [thread overview]
Message-ID: <20140305020746.GA14711@localhost> (raw)
In-Reply-To: <20140305012352.GR13647@dastard>
On Wed, Mar 05, 2014 at 12:23:53PM +1100, Dave Chinner wrote:
> On Wed, Mar 05, 2014 at 09:16:45AM +0800, Fengguang Wu wrote:
> > On Tue, Mar 04, 2014 at 01:52:25PM -0800, Kent Overstreet wrote:
> > > On Tue, Mar 04, 2014 at 09:21:30PM +0800, Fengguang Wu wrote:
> > > > Hi Kent,
> > > >
> > > > FYI, we noticed the below changes on
> > > >
> > > > git://evilpiepirate.org/~kent/linux-bcache.git for-jens
> > > > commit 6a0608544e5672bd9a044c285119547eae41abe5 ("blk-lib.c: generic_make_request() handles large bios now")
> > > >
> > > > test case: snb-drag/sysbench/fileio/600s-100%-1HDD-ext4-64G-1024-seqrewr-sync
> >
> > snb-drag is the test machine, it's a SNB desktop.
> >
> > The test command is
> >
> > mkfs -t ext4 -q /dev/sda2
> > mount -t ext4 /dev/sda2 /fs/sda2
> > cd /fs/sda2
> >
> > for i in $(seq 0 1023)
> > do
> > fallocate -l 67108864 test_file.$i
> > done
> >
> > sysbench --test=fileio --max-requests=0 --num-threads=4 --max-time=600 --file-test-mode=seqrewr --file-total-size=68719476736 --file-io-mode=sync --file-num=1024 run
> >
> >
> > > I'm trying to figure out how to parse this and the graphs - where do I find the
> > > test? And is there anything you can point me to for the graphs, or is that
> > > output from that test?
> > >
> > > >
> > > > 11541d5f5b7002b 6a0608544e5672bd9a044c285
> > > > --------------- -------------------------
> > > > 1885 ~60% -77.4% 426 ~ 7% TOTAL fileio.request_latency_max_ms
> >
> > The ~XX% numbers are stddev percent.
> > The [+-]XX% is change percent.
>
> Can you put this in as column headers so that people don't have to
> this every time they see a report from you?
Good idea!
> > The below graph shows all samples collected during the bisect
> >
> > [*] bisect-good
> > [O] bisect-bad
> >
> > In which you can see the stableness of the change and bisect.
>
> Oh, so that's what the graphs contain. :/
>
> Again - perhaps you should include this information with the graphs
> rather than just dumping unlabelled data on people ;)
Yeah sure. I'll follow your nice suggestions!
Thanks,
Fengguang
next prev parent reply other threads:[~2014-03-05 2:07 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-03-04 13:21 [blk-lib] 6a0608544e5: fileio -77.4% max latency, -5.7% throughput Fengguang Wu
2014-03-04 13:21 ` Fengguang Wu
2014-03-04 21:52 ` Kent Overstreet
2014-03-04 21:52 ` Kent Overstreet
2014-03-05 1:16 ` Fengguang Wu
2014-03-05 1:16 ` Fengguang Wu
2014-03-05 1:23 ` Dave Chinner
2014-03-05 1:23 ` Dave Chinner
2014-03-05 2:07 ` Fengguang Wu [this message]
2014-03-05 2:07 ` Fengguang Wu
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=20140305020746.GA14711@localhost \
--to=fengguang.wu@intel.com \
--cc=lkp@lists.01.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 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.