Performance results on Experimental branch

Performance results on Experimental branch

[Steven Pratt]

Have completed the first run of the experimental  branch on my RAID 
system and the results are encouraging.

Compared to 2.6.29-rc2:
Large file creates  increase 50% plus across all thread counts.
Mail Server is up about 20%
Random reads  are pretty much flat
Random Writes are up 50% or more
Sequential reads took a 10% hit on single thread, but 20% gain on 128 
threads.

All in all good progress.  Results and graphs can be found here:

http://btrfs.boxacle.net/repository/raid/history/History.html

Steve

Re: Performance results on Experimental branch

[Diego Calleja]

On Mi=E9rcoles 25 Febrero 2009 22:07:33 Steven Pratt escribi=F3:

> All in all good progress.  Results and graphs can be found here:
>=20
> http://btrfs.boxacle.net/repository/raid/history/History.html


Some graphs seem to be broken...btrfs gets a "transparent" color.

=46or example here:
http://btrfs.boxacle.net/repository/raid/history/History_Mail_server_si=
mulation._num_threads=3D16.FFSB_Ops_per_Sec.png
--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs" =
in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: Performance results on Experimental branch

[Steven Pratt]

Diego Calleja wrote:
> On Mi=E9rcoles 25 Febrero 2009 22:07:33 Steven Pratt escribi=F3:
>
>  =20
>> All in all good progress.  Results and graphs can be found here:
>>
>> http://btrfs.boxacle.net/repository/raid/history/History.html
>>    =20
>
>
> Some graphs seem to be broken...btrfs gets a "transparent" color.
>  =20
Unless I am missing something,  what you are referring to is a simple=20
wraping/alignment issue in the key on the long name on the experimental=
=20
btrfs.  It is the Brown bar.  Let me know if this is not the issue.

Steve

> For example here:
> http://btrfs.boxacle.net/repository/raid/history/History_Mail_server_=
simulation._num_threads=3D16.FFSB_Ops_per_Sec.png
> --
> To unsubscribe from this list: send the line "unsubscribe linux-btrfs=
" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
>  =20

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

Re: Performance results on Experimental branch

[Diego Calleja]

On Mi=E9rcoles 25 Febrero 2009 23:55:08 Steven Pratt escribi=F3:

> Unless I am missing something,  what you are referring to is a simple=
=20
> wraping/alignment issue in the key on the long name on the experiment=
al=20
> btrfs.  It is the Brown bar.  Let me know if this is not the issue.

doh, you're right. Sorry, it's time to sleep here ;(
--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs" =
in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html