Skip site navigation (1)Skip section navigation (2)
Date:      Fri, 08 Sep 2000 00:06:34 -0400
From:      "Francisco Reyes" <fran@reyes.somos.net>
To:        "Mike Tancsa" <mike@sentex.net>
Cc:        "freebsd-hardware@FreeBSD.ORG" <freebsd-hardware@FreeBSD.ORG>
Subject:   Re: Problems installing 4.1 on 3ware RAID 5200 & 6200
Message-ID:  <200009080358.XAA14596@sanson.reyes.somos.net>
In-Reply-To: <39b83e75.1385408832@smtp.sentex.ca>

next in thread | previous in thread | raw e-mail | index | archive | help
On Fri, 08 Sep 2000 01:21:03 GMT, Mike Tancsa wrote:

>>I only played briefly  yesterday. Ran Bonnie and RAID0 seemed
>>about twice as fast. RAID1 seemed about 20% faster. I will do
>>some more tests today and by the weekend I will post all the
>>results.

>20% faster than what ? Than before you mean ? Can you by chance do
>a bonnie on the individual drive on an ata33 controller
>bonnie on the same drives in RAID0, RAID1 ?

My initial tests were off the MB controller.
I will post all the details and configuration when i have all
the results, but basically I did some bonnie test on 3 drives. 1
7200RPM ATA66 and 2 5400RPM ATA66. I did 256MB and 1000MB tests.

The reason I only did one 7200RPM is because I had not installed
the second 7200RPM by the time of the test.

The 5400RPM were set on a RAID 1 and the 7200RPM on a RAID 0.

I have yet another 3Ware card that I have to install this
weekend (a 2 port). I am hoping to have all tests by monday
somewhere on a web page for all interested.

I would also welcome suggestions for tests.. although it is a
bit late since now I built the array.. but I have more computers
coming with 3ware that I may need to re-do. I tried looking at
the ports and Bonnie seems the most appropiate. I tried a couple
of others and either didn't like them or the results were not
very good... ie. the byte "native" tests has 2 comparison
numbers from supposedly previous tests and the faster CPU had
slower marks, yet my machine which was faster than both had
higher numbers. In other words a faster CPU is supposed to have
higher number, yet their reference machines failed that
principle.


francisco
Moderator of the Corporate BSD list
http://www.egroups.com/group/BSD_Corporate




To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-hardware" in the body of the message




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200009080358.XAA14596>