[rescue] Sun 711

George Adkins george at webbastard.org
Thu May 2 16:26:35 CDT 2002


On Thursday 02 May 2002 12:10 am, you wrote:
> 90-95 out of 120 theoretical max is just under 80%, which is the rate I
> predicted for good quality equipment. A 3 channel card that performs up to
> that rate is doing an excellent job. I would have guessed you be closer to
> 75-80 MB/s/. Also that your PCI bus can push that much through surprises me
> especially with the relatively small cache.
>
> Just one question, how are you deriving that number? I'm not doubting you I
> just want to know your testing method and software for future reference.
> Personally I tend to use IOZone and Bonnie for UNIX and IOMeter for windows
> (yeah I know IOMeter has issues), and I tend to do large numbers of test
> runs with variable parameters (file sizes, chunk sizes, record size, cache
> flushes etc...) I guess I'm just a cynic when it comes to benchmark
> numbers. I always expect (and often get) the worst ;-)
>

Actually not any benchmark package, just cat some mpegs together and split(1) 
off a 1024*1024 byte chunk and then cat data.file >> target to = 1 Gig size.
Then :
date;cat data.file > /dev/null;date 
a few times and average the run times to whatever degree of accuracy you 
like... then divide 1024 by the number of seconds to get MB/Sec.

Is this unsound for figuring raw read performance?


> As to the SmartArray, any experience with them? I've used some older model
> stuff (Its been a few months since I've worked with any Compaq gear in a
> meaningful way, and maybe a year since I've dealt with Compaq RAID at all)
> but none of their newer gear.
>
Yeah, I have had a few of the older PCI Raid controllers in my Compaq Box 
(6500R) and I've always found the performance to be excelent.



More information about the rescue mailing list