On Fri, Sep 18, 2015 at 07:06:39PM +0800, George Wang wrote:
> Hi, Dave,
>
> I read the mail you post for "fs-writeback: drop wb->list_lock during
> blk_finish_plug()", and I
> adore you very much.
>
> I'm very curious that how you get the writeback status when running fs_mark.
>
> I will appreciate very much if you can share the way you get writeback
> status and iops, etc.
http://pcp.io/
Indeed:
http://pcp.io/testimonials.html
> And maybe people in community can use this way to do the same tests as you.
>
> The following is a part copy of the test result you got:
This is the best way to demonstrate:
https://flic.kr/p/xR9Cwn
That's a screen shot of my "coding and testing" virtual desktop when
running the fsmark test. (Yes, it's a weird size - I have 3 x 24"
monitors in portrait orientation which gives a 3600x1920 image....)
> FSUse% Count Size Files/sec App Overhead
> 0 80000 4096 106938.0 543310
> 0 160000 4096 102922.7 476362
> 0 240000 4096 107182.9 538206
> 0 320000 4096 107871.7 619821
> 0 400000 4096 99255.6 622021
> 0 480000 4096 103217.8 609943
> 0 560000 4096 96544.2 640988
> 0 640000 4096 100347.3 676237
> 0 720000 4096 87534.8 483495
> 0 800000 4096 72577.5 2556920
> 0 880000 4096 97569.0 646996
>
> <RAM fills here, sustained performance is now dependent on writeback>
You can see this from the lower chart that tracks memory usage - all
16GB gets used up pretty quickly, and it matches with changes in
writeback behaviour.
You can also see it from /proc/meminfo and Writeback iops and
throughput you can also get from 'iostat -d -m -x 5', etc. But when
you've got it in pretty, real-time graphs you can easily see
correlations between different behaviours....
Cheers,
Dave.
--
Dave Chinner
david@xxxxxxxxxxxxx
|