performance of nvidia onboard raid1 vs. gmirror

[Ken Gunderson]

On Wed, 03 May 2006 05:00:12 -0400
Mike Jakubik <mikej at rogers.com> wrote:

> On Wed, 2006-05-03 at 02:14 -0600, Ken Gunderson wrote:
> > Is anyone aware of any benchmarks comparing the nvidia raid1 to
> > gmirror?  Or have any additional insights?  I don't have a machine free
> > I can test on at the moment but might in next week or two if anyone else
> > is interested.
> 
> I am sure many people are interested in such a benchmark, but no one has
> done it yet. If you have the resources to do so, please go ahead and
> continue. Many of us would be interested in your results.

Sorry to follow up on this twice but I have subsequently heard back
from Andras.  Also cross posting to fbsd-geom in case anyone there might be
interested...

1) Here's Andras's bonnie benchmarks w/nvidia onboard:

[13:39:05]:root at x2100:/data#/usr/local/bin/bonnie
File './Bonnie.55923', size: 104857600
Writing with putc()...done
Rewriting...done
Writing intelligently...done
Reading with getc()...done
Reading intelligently...done
Seeker 1...Seeker 2...Seeker 3...start 'em...done...done...done...
               -------Sequential Output-------- ---Sequential Input-- --Random--
               -Per Char- --Block--- -Rewrite-- -Per Char- --Block--- --Seeks---
Machine    MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU  /sec %CPU
           100 47243 42.5 58564 17.4 58202 21.7 96759 99.9 573917 100.0 52176.4 138.3

[13:39:22]:root at x2100:/data#/usr/local/bin/bonnie -s 1000
File './Bonnie.55932', size: 1048576000
Writing with putc()...done
Rewriting...done
Writing intelligently...done
Reading with getc()...done
Reading intelligently...done
Seeker 1...Seeker 2...Seeker 3...start 'em...done...done...done...
               -------Sequential Output-------- ---Sequential Input-- --Random--
               -Per Char- --Block--- -Rewrite-- -Per Char- --Block--- --Seeks---
Machine    MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU  /sec %CPU
          1000 42357 38.5 50102 15.8 48224 18.3 87487 100.0 576442 100.0 27145.9 121.7

These test were done with RELENG_6_1 (apr 29 version iirc).


2) Here's mine with gmirror. FreeBSD 6.0-RELEASE-p7 w/amd64 bits:

selway# bonnie -m selway
File './Bonnie.7135', size: 104857600
Writing with putc()...done
Rewriting...done
Writing intelligently...done
Reading with getc()...done
Reading intelligently...done
Seeker 1...Seeker 2...Seeker 3...start 'em...done...done...done...
              -------Sequential Output-------- ---Sequential Input-- --Random--
              -Per Char- --Block--- -Rewrite-- -Per Char- --Block--- --Seeks---
Machine    MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU  /sec %CPU
selway    100 68523 56.8 50932 11.3 88951 19.4 93775 99.9 1482446 99.9 79856.3 155.0


selway# bonnie -m selway -s 1000
File './Bonnie.7139', size: 1048576000
Writing with putc()...done
Rewriting...done
Writing intelligently...done
Reading with getc()...done
Reading intelligently...done
Seeker 1...Seeker 2...Seeker 3...start 'em...done...done...done...
              -------Sequential Output-------- ---Sequential Input-- --Random--
              -Per Char- --Block--- -Rewrite-- -Per Char- --Block--- --Seeks---
Machine    MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU  /sec %CPU
selway   1000 67419 57.7 64774 15.4 62163 18.3 95277 99.9 904320 99.9 28088.5 127.2

Not exactly apples to apples but you get basic idea.  The machines both use same mainboard and HD's.  Mine is running Opteron165 CPU, don't know about the other. gmirror is looking pretty good:)

-- 
Best regards,

Ken Gunderson

Q: Because it reverses the logical flow of conversation.
A: Why is putting a reply at the top of the message frowned upon?