Re: [LKP] [aio] 6098b45b32e: 2200.00% xfstests.generic.239.seconds

From: Gu Zheng
Date: Sun Dec 14 2014 - 22:14:52 EST


Hi Huang,
On 12/15/2014 09:02 AM, Huang Ying wrote:

> FYI, we noticed the below changes on
>
> commit 6098b45b32e6baeacc04790773ced9340601d511 ("aio: block exit_aio() until all context requests are completed")

This patch added a wait step (which is lacked before) for all submitted aio
missions (iocbs) to complete in exit_aio(), so the cost-time increasing is
expected.

Thanks,
Gu

>
>
> testbox/testcase/testparams: vm-vp-2G/xfstests/4HDD-btrfs-generic-quick
>
> 2ff396be602f10b5 6098b45b32e6baeacc04790773
> ---------------- --------------------------
> %stddev %change %stddev
> \ | \
> 26352 ± 9% -13.6% 22774 ± 1% vmstat.system.cs
> 10342 ± 6% -12.3% 9066 ± 0% vmstat.system.in
> 37 ± 4% -12.1% 32 ± 3% time.percent_of_cpu_this_job_got
> 1197 ± 2% -14.2% 1028 ± 0% vmstat.io.bi
> 18470 ± 2% -10.1% 16609 ± 1% vmstat.io.bo
> 157 ± 3% +13.7% 179 ± 0% time.elapsed_time
>
> vm-vp-2G: qemu-system-x86_64 -enable-kvm -cpu Penryn
> Memory: 2G
>
> xfstests.generic.239.seconds
>
> 30 ++-----------O---------------------------------------------------------+
> | O O O O |
> 25 ++ O |
> | O O O O O O O O O O O O |
> | O |
> 20 O+ |
> | |
> 15 ++ |
> | |
> 10 ++ |
> | |
> | |
> 5 ++ |
> | |
> 0 *+-*-*--*-*--*-*--*-*--*-*--*-*--*--*-*--*-*--*-*--*-*--*-*--*-*--*-*--*
>
>
> [*] bisect-good sample
> [O] bisect-bad sample
>
> To reproduce:
>
> apt-get install ruby ruby-oj
> git clone git://git.kernel.org/pub/scm/linux/kernel/git/wfg/lkp-tests.git
> cd lkp-tests
> bin/setup-local job.yaml # the job file attached in this email
> bin/run-local job.yaml
>
>
> Disclaimer:
> Results have been estimated based on internal Intel analysis and are provided
> for informational purposes only. Any difference in system hardware or software
> design or configuration may affect actual performance.
>
>
> Thanks,
> Fengguang
>
>
>
>
> _______________________________________________
> LKP mailing list
> LKP@xxxxxxxxxxxxxxx
>


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/