Andrew Morton | 1 Jun 02:36 2009

Re: [RESEND] [PATCH] readahead:add blk_run_backing_dev

On Fri, 29 May 2009 14:35:55 +0900 Hisashi Hifumi <hifumi.hisashi <at> oss.ntt.co.jp> wrote:

> I added blk_run_backing_dev on page_cache_async_readahead
> so readahead I/O is unpluged to improve throughput on 
> especially RAID environment. 

I skipped the last version of this because KOSAKI Motohiro
<kosaki.motohiro <at> jp.fujitsu.com> said "Please attach blktrace analysis ;)".

I'm not sure why he asked for that, but he's a smart chap and
presumably had his reasons.

If you think that such an analysis is unneeded, or isn't worth the time
to generate then please tell us that.  But please don't just ignore the
request!

Thanks.

--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo <at> vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Hisashi Hifumi | 1 Jun 03:04 2009
Picon

Re: [RESEND] [PATCH] readahead:add blk_run_backing_dev


At 09:36 09/06/01, Andrew Morton wrote:
>On Fri, 29 May 2009 14:35:55 +0900 Hisashi Hifumi 
><hifumi.hisashi <at> oss.ntt.co.jp> wrote:
>
>> I added blk_run_backing_dev on page_cache_async_readahead
>> so readahead I/O is unpluged to improve throughput on 
>> especially RAID environment. 
>
>I skipped the last version of this because KOSAKI Motohiro
><kosaki.motohiro <at> jp.fujitsu.com> said "Please attach blktrace analysis ;)".
>
>I'm not sure why he asked for that, but he's a smart chap and
>presumably had his reasons.
>
>If you think that such an analysis is unneeded, or isn't worth the time
>to generate then please tell us that.  But please don't just ignore the
>request!

Hi Andrew.

Sorry for this.

I did not ignore KOSAKI Motohiro's request.
I've got blktrace output for both with and without the patch, 
but I just did not clarify the reason for throuput improvement
from this result.

I do not notice any difference except around unplug behavior by dd.
Comments?
(Continue reading)

Hisashi Hifumi | 1 Jun 03:39 2009
Picon

Re: [PATCH] readahead:add blk_run_backing_dev


At 11:23 09/05/28, KOSAKI Motohiro wrote:
>> Hi Andrew.
>> Please merge following patch.
>> Thanks.
>> 
>> ---
>> 
>> I added blk_run_backing_dev on page_cache_async_readahead
>> so readahead I/O is unpluged to improve throughput on 
>> especially RAID environment. 
>> 
>> Following is the test result with dd.
>> 
>> #dd if=testdir/testfile of=/dev/null bs=16384
>> 
>> -2.6.30-rc6
>> 1048576+0 records in
>> 1048576+0 records out
>> 17179869184 bytes (17 GB) copied, 224.182 seconds, 76.6 MB/s
>> 
>> -2.6.30-rc6-patched
>> 1048576+0 records in
>> 1048576+0 records out
>> 17179869184 bytes (17 GB) copied, 206.465 seconds, 83.2 MB/s
>> 
>> My testing environment is as follows:
>> Hardware: HP DL580 
>> CPU:Xeon 3.2GHz *4 HT enabled
>> Memory:8GB
(Continue reading)

KOSAKI Motohiro | 1 Jun 04:23 2009

Re: [PATCH] readahead:add blk_run_backing_dev

> 
> At 11:23 09/05/28, KOSAKI Motohiro wrote:
> >> Hi Andrew.
> >> Please merge following patch.
> >> Thanks.
> >> 
> >> ---
> >> 
> >> I added blk_run_backing_dev on page_cache_async_readahead
> >> so readahead I/O is unpluged to improve throughput on 
> >> especially RAID environment. 
> >> 
> >> Following is the test result with dd.
> >> 
> >> #dd if=testdir/testfile of=/dev/null bs=16384
> >> 
> >> -2.6.30-rc6
> >> 1048576+0 records in
> >> 1048576+0 records out
> >> 17179869184 bytes (17 GB) copied, 224.182 seconds, 76.6 MB/s
> >> 
> >> -2.6.30-rc6-patched
> >> 1048576+0 records in
> >> 1048576+0 records out
> >> 17179869184 bytes (17 GB) copied, 206.465 seconds, 83.2 MB/s
> >> 
> >> My testing environment is as follows:
> >> Hardware: HP DL580 
> >> CPU:Xeon 3.2GHz *4 HT enabled
> >> Memory:8GB
(Continue reading)

Wu Fengguang | 1 Jun 04:37 2009
Picon

Re: [PATCH] readahead:add blk_run_backing_dev

On Wed, May 27, 2009 at 11:06:37AM +0800, Hisashi Hifumi wrote:
> 
> At 11:57 09/05/27, Wu Fengguang wrote:
> >On Wed, May 27, 2009 at 10:47:47AM +0800, Hisashi Hifumi wrote:
> >> 
> >> At 11:36 09/05/27, Wu Fengguang wrote:
> >> >On Wed, May 27, 2009 at 10:21:53AM +0800, Hisashi Hifumi wrote:
> >> >>
> >> >> At 11:09 09/05/27, Wu Fengguang wrote:
> >> >> >On Wed, May 27, 2009 at 08:25:04AM +0800, Hisashi Hifumi wrote:
> >> >> >>
> >> >> >> At 08:42 09/05/27, Andrew Morton wrote:
> >> >> >> >On Fri, 22 May 2009 10:33:23 +0800
> >> >> >> >Wu Fengguang <fengguang.wu <at> intel.com> wrote:
> >> >> >> >
> >> >> >> >> > I tested above patch, and I got same performance number.
> >> >> >> >> > I wonder why if (PageUptodate(page)) check is there...
> >> >> >> >>
> >> >> >> >> Thanks!  This is an interesting micro timing behavior that
> >> >> >> >> demands some research work.  The above check is to confirm if it's
> >> >> >> >> the PageUptodate() case that makes the difference. So why that case
> >> >> >> >> happens so frequently so as to impact the performance? Will it also
> >> >> >> >> happen in NFS?
> >> >> >> >>
> >> >> >> >> The problem is readahead IO pipeline is not running smoothly, which is
> >> >> >> >> undesirable and not well understood for now.
> >> >> >> >
> >> >> >> >The patch causes a remarkably large performance increase.  A 9%
> >> >> >> >reduction in time for a linear read? I'd be surprised if the workload
> >> >> >>
(Continue reading)

Hisashi Hifumi | 1 Jun 04:51 2009
Picon

Re: [PATCH] readahead:add blk_run_backing_dev


At 11:37 09/06/01, Wu Fengguang wrote:
>On Wed, May 27, 2009 at 11:06:37AM +0800, Hisashi Hifumi wrote:
>> 
>> At 11:57 09/05/27, Wu Fengguang wrote:
>> >On Wed, May 27, 2009 at 10:47:47AM +0800, Hisashi Hifumi wrote:
>> >> 
>> >> At 11:36 09/05/27, Wu Fengguang wrote:
>> >> >On Wed, May 27, 2009 at 10:21:53AM +0800, Hisashi Hifumi wrote:
>> >> >>
>> >> >> At 11:09 09/05/27, Wu Fengguang wrote:
>> >> >> >On Wed, May 27, 2009 at 08:25:04AM +0800, Hisashi Hifumi wrote:
>> >> >> >>
>> >> >> >> At 08:42 09/05/27, Andrew Morton wrote:
>> >> >> >> >On Fri, 22 May 2009 10:33:23 +0800
>> >> >> >> >Wu Fengguang <fengguang.wu <at> intel.com> wrote:
>> >> >> >> >
>> >> >> >> >> > I tested above patch, and I got same performance number.
>> >> >> >> >> > I wonder why if (PageUptodate(page)) check is there...
>> >> >> >> >>
>> >> >> >> >> Thanks!  This is an interesting micro timing behavior that
>> >> >> >> >> demands some research work.  The above check is to confirm if it's
>> >> >> >> >> the PageUptodate() case that makes the difference. So why that case
>> >> >> >> >> happens so frequently so as to impact the performance? Will it also
>> >> >> >> >> happen in NFS?
>> >> >> >> >>
>> >> >> >> >> The problem is readahead IO pipeline is not running smoothly, 
>which is
>> >> >> >> >> undesirable and not well understood for now.
>> >> >> >> >
(Continue reading)

Wu Fengguang | 1 Jun 05:02 2009
Picon

Re: [PATCH] readahead:add blk_run_backing_dev

On Mon, Jun 01, 2009 at 10:51:56AM +0800, Hisashi Hifumi wrote:
> 
> At 11:37 09/06/01, Wu Fengguang wrote:
> >On Wed, May 27, 2009 at 11:06:37AM +0800, Hisashi Hifumi wrote:
> >> 
> >> At 11:57 09/05/27, Wu Fengguang wrote:
> >> >On Wed, May 27, 2009 at 10:47:47AM +0800, Hisashi Hifumi wrote:
> >> >> 
> >> >> At 11:36 09/05/27, Wu Fengguang wrote:
> >> >> >On Wed, May 27, 2009 at 10:21:53AM +0800, Hisashi Hifumi wrote:
> >> >> >>
> >> >> >> At 11:09 09/05/27, Wu Fengguang wrote:
> >> >> >> >On Wed, May 27, 2009 at 08:25:04AM +0800, Hisashi Hifumi wrote:
> >> >> >> >>
> >> >> >> >> At 08:42 09/05/27, Andrew Morton wrote:
> >> >> >> >> >On Fri, 22 May 2009 10:33:23 +0800
> >> >> >> >> >Wu Fengguang <fengguang.wu <at> intel.com> wrote:
> >> >> >> >> >
> >> >> >> >> >> > I tested above patch, and I got same performance number.
> >> >> >> >> >> > I wonder why if (PageUptodate(page)) check is there...
> >> >> >> >> >>
> >> >> >> >> >> Thanks!  This is an interesting micro timing behavior that
> >> >> >> >> >> demands some research work.  The above check is to confirm if it's
> >> >> >> >> >> the PageUptodate() case that makes the difference. So why that case
> >> >> >> >> >> happens so frequently so as to impact the performance? Will it also
> >> >> >> >> >> happen in NFS?
> >> >> >> >> >>
> >> >> >> >> >> The problem is readahead IO pipeline is not running smoothly, 
> >which is
> >> >> >> >> >> undesirable and not well understood for now.
(Continue reading)

KOSAKI Motohiro | 1 Jun 05:06 2009

Re: [PATCH] readahead:add blk_run_backing_dev

> > >> >I mean, you should get >300MB/s throughput with 7 disks, and you
> > >> >should seek ways to achieve that before testing out this patch :-)
> > >> 
> > >> Throughput number of storage array is very from one product to another.
> > >> On my hardware environment I think this number is valid and
> > >> my patch is effective.
> > >
> > >What's your readahead size? Is it large enough to cover the stripe width?
> > 
> > Do you mean strage's readahead size?
> 
> What's strage? I mean if your RAID's block device file is /dev/sda, then

I guess it's typo :-)
but I recommend he use sane test environment...

> 
>         blockdev --getra /dev/sda
> 
> will tell its readahead size in unit of 512 bytes.
> 
> Thanks,
> Fengguang
> 

--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo <at> vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

(Continue reading)

Hisashi Hifumi | 1 Jun 05:07 2009
Picon

Re: [PATCH] readahead:add blk_run_backing_dev


At 12:02 09/06/01, Wu Fengguang wrote:
>On Mon, Jun 01, 2009 at 10:51:56AM +0800, Hisashi Hifumi wrote:
>> 
>> At 11:37 09/06/01, Wu Fengguang wrote:
>> >On Wed, May 27, 2009 at 11:06:37AM +0800, Hisashi Hifumi wrote:
>> >> 
>> >> At 11:57 09/05/27, Wu Fengguang wrote:
>> >> >On Wed, May 27, 2009 at 10:47:47AM +0800, Hisashi Hifumi wrote:
>> >> >> 
>> >> >> At 11:36 09/05/27, Wu Fengguang wrote:
>> >> >> >On Wed, May 27, 2009 at 10:21:53AM +0800, Hisashi Hifumi wrote:
>> >> >> >>
>> >> >> >> At 11:09 09/05/27, Wu Fengguang wrote:
>> >> >> >> >On Wed, May 27, 2009 at 08:25:04AM +0800, Hisashi Hifumi wrote:
>> >> >> >> >>
>> >> >> >> >> At 08:42 09/05/27, Andrew Morton wrote:
>> >> >> >> >> >On Fri, 22 May 2009 10:33:23 +0800
>> >> >> >> >> >Wu Fengguang <fengguang.wu <at> intel.com> wrote:
>> >> >> >> >> >
>> >> >> >> >> >> > I tested above patch, and I got same performance number.
>> >> >> >> >> >> > I wonder why if (PageUptodate(page)) check is there...
>> >> >> >> >> >>
>> >> >> >> >> >> Thanks!  This is an interesting micro timing behavior that
>> >> >> >> >> >> demands some research work.  The above check is to confirm 
>if it's
>> >> >> >> >> >> the PageUptodate() case that makes the difference. So why 
>that case
>> >> >> >> >> >> happens so frequently so as to impact the performance? 
>Will it also
(Continue reading)

Wu Fengguang | 1 Jun 06:30 2009
Picon

Re: [PATCH] readahead:add blk_run_backing_dev

On Mon, Jun 01, 2009 at 11:07:42AM +0800, Hisashi Hifumi wrote:
> 
> At 12:02 09/06/01, Wu Fengguang wrote:
> >On Mon, Jun 01, 2009 at 10:51:56AM +0800, Hisashi Hifumi wrote:
> >> 
> >> At 11:37 09/06/01, Wu Fengguang wrote:
> >> >On Wed, May 27, 2009 at 11:06:37AM +0800, Hisashi Hifumi wrote:
> >> >> 
> >> >> At 11:57 09/05/27, Wu Fengguang wrote:
> >> >> >On Wed, May 27, 2009 at 10:47:47AM +0800, Hisashi Hifumi wrote:
> >> >> >> 
> >> >> >> At 11:36 09/05/27, Wu Fengguang wrote:
> >> >> >> >On Wed, May 27, 2009 at 10:21:53AM +0800, Hisashi Hifumi wrote:
> >> >> >> >>
> >> >> >> >> At 11:09 09/05/27, Wu Fengguang wrote:
> >> >> >> >> >On Wed, May 27, 2009 at 08:25:04AM +0800, Hisashi Hifumi wrote:
> >> >> >> >> >>
> >> >> >> >> >> At 08:42 09/05/27, Andrew Morton wrote:
> >> >> >> >> >> >On Fri, 22 May 2009 10:33:23 +0800
> >> >> >> >> >> >Wu Fengguang <fengguang.wu <at> intel.com> wrote:
> >> >> >> >> >> >
> >> >> >> >> >> >> > I tested above patch, and I got same performance number.
> >> >> >> >> >> >> > I wonder why if (PageUptodate(page)) check is there...
> >> >> >> >> >> >>
> >> >> >> >> >> >> Thanks!  This is an interesting micro timing behavior that
> >> >> >> >> >> >> demands some research work.  The above check is to confirm 
> >if it's
> >> >> >> >> >> >> the PageUptodate() case that makes the difference. So why 
> >that case
> >> >> >> >> >> >> happens so frequently so as to impact the performance? 
(Continue reading)


Gmane