lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <4e5e476b0912181303v3efbd846le61a0deacffe6a49@mail.gmail.com>
Date:	Fri, 18 Dec 2009 22:03:05 +0100
From:	Corrado Zoccolo <czoccolo@...il.com>
To:	Jeff Moyer <jmoyer@...hat.com>
Cc:	Linux-Kernel <linux-kernel@...r.kernel.org>,
	Jens Axboe <jens.axboe@...cle.com>,
	Vivek Goyal <vgoyal@...hat.com>
Subject: Re: [PATCH] cfq-iosched: reduce write depth only if sync was delayed

Thanks Jeff.
Your tests show that with the patch, low_latency doesn't penalize
writeback any more on fast hardware, so the goal of the patch is
fulfilled. Lowering slice_async doesn't change the picture (I was
expecting an improvement in seq write bandwidth).
I'm still puzzled of why with 2.6.29 your SAN could achieve 300 MB/s
sequential writes, and it can't achieve it any more.
Can you try lowering slice_idle, trying e.g. 2ms?

Thanks
Corrado

On Fri, Dec 18, 2009 at 4:32 PM, Jeff Moyer <jmoyer@...hat.com> wrote:
> Corrado Zoccolo <czoccolo@...il.com> writes:
>
>> Hi Jeff,
>> On Wed, Dec 9, 2009 at 7:09 PM, Jeff Moyer <jmoyer@...hat.com> wrote:
>>> Corrado Zoccolo <czoccolo@...il.com> writes:
>>>
>>>> The numbers look good. Now, there is no penalty in having low_latency
>>>> set for sequential writes, and just a small penalty for random ones.
>>>> The fact that random reads are faster with low_latency set is interesting.
>>>> Is the test is running with your patched tiobench (so that the number
>>>> of random operations is comparable with sequential ones)?
>>>
>>> No, I forgot all about that.  The number of random operations defaults
>>> to 4000, which is pretty low.  I'll re-run the tests with a number
>>> comparable to the sequential runs.  Sorry about that.
>>>
>> N.P.
>> if you have time, can you also re-run the test changing:
>> iosched/fifo_expire_async to 8 ?
>> I hope that reducing the expire_async, will make cfq quicker at switching
>> between the different threads, allowing more parallelism for seq
>> writers on your hw.
>> If this is the case, I think I can try to estimate the
>> fifo_expire_async in the autotuning patch.
>
> Sorry this took so long.  I've been rather busy of late.
>
> Cheers,
> Jeff
>
> low_latency=1, fifo_expire_async=8
>
> Unit information
> ================
> File size = megabytes
> Blk Size  = bytes
> Rate      = megabytes per second
> CPU%      = percentage of CPU used during the test
> Latency   = milliseconds
> Lat%      = percent of requests that took longer than X seconds
> CPU Eff   = Rate divided by CPU% - throughput per cpu load
>
> Sequential Reads
>                              File  Blk   Num                   Avg      Maximum      Lat%     Lat%    CPU
> Identifier                    Size  Size  Thr   Rate  (CPU%)  Latency    Latency      >2s      >10s    Eff
> ---------------------------- ------ ----- ---  ------ ------ --------- -----------  -------- -------- -----
> 2.6.32                        8192  65536   8   88.39 89.74%    16.388     2032.62   0.00000  0.00000    98
> 2.6.32                        8192  65536  16   90.77 185.3%    32.213     2175.99   0.00000  0.00000    49
>
> Random Reads
>                              File  Blk   Num                   Avg      Maximum      Lat%     Lat%    CPU
> Identifier                    Size  Size  Thr   Rate  (CPU%)  Latency    Latency      >2s      >10s    Eff
> ---------------------------- ------ ----- ---  ------ ------ --------- -----------  -------- -------- -----
> 2.6.32                        8192  65536   8   19.62 25.74%    71.827     3397.26   0.00000  0.00000    76
> 2.6.32                        8192  65536  16   23.82 55.01%   103.361     4075.53   0.00000  0.00000    43
>
> Sequential Writes
>                              File  Blk   Num                   Avg      Maximum      Lat%     Lat%    CPU
> Identifier                    Size  Size  Thr   Rate  (CPU%)  Latency    Latency      >2s      >10s    Eff
> ---------------------------- ------ ----- ---  ------ ------ --------- -----------  -------- -------- -----
> 2.6.32                        8192  65536   8  108.28 1007.%    12.984     5643.55   0.00076  0.00000    11
> 2.6.32                        8192  65536  16  112.40 2014.%    25.430     8592.98   0.00839  0.00000     6
>
> Random Writes
>                              File  Blk   Num                   Avg      Maximum      Lat%     Lat%    CPU
> Identifier                    Size  Size  Thr   Rate  (CPU%)  Latency    Latency      >2s      >10s    Eff
> ---------------------------- ------ ----- ---  ------ ------ --------- -----------  -------- -------- -----
> 2.6.32                        8192  65536   8   63.94 337.7%    22.885     6047.22   0.00076  0.00000    19
> 2.6.32                        8192  65536  16   61.94 662.5%    46.997    12759.69   0.15411  0.00000     9
>
>
> low_latency=0, fifo_expire_async=8
>
> Unit information
> ================
> File size = megabytes
> Blk Size  = bytes
> Rate      = megabytes per second
> CPU%      = percentage of CPU used during the test
> Latency   = milliseconds
> Lat%      = percent of requests that took longer than X seconds
> CPU Eff   = Rate divided by CPU% - throughput per cpu load
>
> Sequential Reads
>                              File  Blk   Num                   Avg      Maximum      Lat%     Lat%    CPU
> Identifier                    Size  Size  Thr   Rate  (CPU%)  Latency    Latency      >2s      >10s    Eff
> ---------------------------- ------ ----- ---  ------ ------ --------- -----------  -------- -------- -----
> 2.6.32                        8192  65536   8   89.13 88.30%    15.872     3101.39   0.00000  0.00000   101
> 2.6.32                        8192  65536  16   86.78 161.7%    30.794     4909.02   0.00000  0.00000    54
>
> Random Reads
>                              File  Blk   Num                   Avg      Maximum      Lat%     Lat%    CPU
> Identifier                    Size  Size  Thr   Rate  (CPU%)  Latency    Latency      >2s      >10s    Eff
> ---------------------------- ------ ----- ---  ------ ------ --------- -----------  -------- -------- -----
> 2.6.32                        8192  65536   8   20.21 26.64%    69.863     4285.42   0.00000  0.00000    76
> 2.6.32                        8192  65536  16   20.10 52.75%   139.761     5986.94   0.00076  0.00000    38
>
> Sequential Writes
>                              File  Blk   Num                   Avg      Maximum      Lat%     Lat%    CPU
> Identifier                    Size  Size  Thr   Rate  (CPU%)  Latency    Latency      >2s      >10s    Eff
> ---------------------------- ------ ----- ---  ------ ------ --------- -----------  -------- -------- -----
> 2.6.32                        8192  65536   8  108.74 1020.%    13.070     5331.78   0.00076  0.00000    11
> 2.6.32                        8192  65536  16  112.18 2020.%    25.559     7903.16   0.00992  0.00000     6
>
> Random Writes
>                              File  Blk   Num                   Avg      Maximum      Lat%     Lat%    CPU
> Identifier                    Size  Size  Thr   Rate  (CPU%)  Latency    Latency      >2s      >10s    Eff
> ---------------------------- ------ ----- ---  ------ ------ --------- -----------  -------- -------- -----
> 2.6.32                        8192  65536   8   64.53 337.8%    22.671     5388.77   0.00000  0.00000    19
> 2.6.32                        8192  65536  16   61.75 668.9%    47.265    13271.37   0.12894  0.00000     9
>



-- 
__________________________________________________________________________

dott. Corrado Zoccolo                          mailto:czoccolo@...il.com
PhD - Department of Computer Science - University of Pisa, Italy
--------------------------------------------------------------------------
The self-confidence of a warrior is not the self-confidence of the average
man. The average man seeks certainty in the eyes of the onlooker and calls
that self-confidence. The warrior seeks impeccability in his own eyes and
calls that humbleness.
                               Tales of Power - C. Castaneda

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ