bcache performance test problem
 

That is pretty terrible performance. If you could try digging around a
bit with perf, blktrace, etc. that'd be much appreciated - otherwise
I'll see if I can come up with some way of reproducing it as soon as I
have time. I haven't done a lot of performance testing on upstream
kernels, unfortunately.

On Wed, May 23, 2012 at 9:14 PM, Qinling <mail.qinling@huawei.com> wrote:
> Hi Kent,
>
>
>
> I have tested bcache on my platform, but the result is not good. I think
> maybe the wrong config caused it. Would you pls help me to check the config,
> or give me some advice for bcache performance testing?
>
>
>
> My SSD card is Â*a PCIe SSD card (about 120,000 IOPS), and I used 10GB.
>
>
>
> I have download the code from
> git://evilpiepirate.org/~kent/linux-bcache.git.
>
> The commands creating bcache is below:
>
> make-bcache –B /dev/sdb8
>
> make-bcache –C –w4k –b1M –writeback /dev/hioa5
>
>
>
> I use FIO to test the seq./random IO performance, and the result is below:
>
> writeÂ*Â*Â*Â* Â*Â*Â*Â*Â*Â*Â*Â*readÂ*Â*Â*Â*Â*Â*Â*Â*Â*Â* Â*Â*Â*Â*Â*Â*Â*Â*Â*randwriteÂ*Â*Â* randread
>
> bcacheÂ*Â*Â*Â*Â*Â* Â*Â*Â*Â*Â*Â*Â*Â*10809 KB/sÂ* Â*Â*164502.5 KB/sÂ*Â*Â*Â* 2713 KB/sÂ*Â*Â* 29640 KB/s
>
> cache_hit_rateÂ* 80Â*Â*Â*Â* Â*Â*Â*Â*Â*Â*Â*Â*Â*Â*Â*Â*Â*79Â*Â*Â*Â*Â*Â*Â*Â*Â*Â*Â* Â* Â*Â*Â*Â*Â*Â*Â*Â*Â*Â*Â*Â*94
> Â*Â*Â*Â*Â*92
>
>
>
>
>
> And the basic test result is:
>
> Write Â*Â*Â*Â*Â*Â*Â*Â*Â*Â*Â*Â*Â*Â*Â*Â*Â*Â*readÂ*Â*Â*Â*Â* Â*Â*Â*Â*Â*Â*Â*Â*Â*Â*Â*Â* randwriteÂ*Â*Â*Â*Â*Â*Â* Â*Â*Â*Â*Â*randread
>
> HDDÂ*Â*Â*Â*Â* 81211.6 KB/sÂ*Â*Â*Â*Â*Â* 172242 KB/sÂ*Â*Â*Â* 2606 KB/sÂ*Â*Â*Â*Â*Â*Â*Â* Â*Â*Â*Â*1855 KB/s
>
> SSDÂ*Â*Â*Â*Â*Â* 250948.2 KB/sÂ*Â*Â*Â* 813855 KB/sÂ*Â*Â*Â* 238892.7 KB/sÂ*Â*Â*Â*Â* 657319.5 KB/s
>
>

--
dm-devel mailing list
dm-devel@redhat.com
https://www.redhat.com/mailman/listinfo/dm-devel