Theepan | 2 Sep 2003 15:48
Picon
Favicon

Re: IDE Performance issues

From: "Bartlomiej Zolnierkiewicz" <B.Zolnierkiewicz <at> elka.pw.edu.pl>
To: "Theepan" <tornado <at> linuxfromscratch.org>
Cc: <linux-ide <at> vger.kernel.org>
Sent: Tuesday, September 02, 2003 2:19 PM
Subject: Re: IDE Performance issues

> > (I tried to send his mail to both linux-ide <at>  and linux-raid <at>  lists, but
it
> > only arrived at linux-raid <at>  - I guess one cannot specify multiple
targets
> > in the To: field, which is why I'm resending to this list only. I've
also
> > edited this email to exclude RAID details.)
>
> I think I've seen this mail on linux-ide <at>  previously.

The reason I thought it never arrived was simply because I didn't get this
e-mail back myself. It seems that I have been unsubscribed automatically
some time ago. Anyway, I am subscribed again and I didn't want to send
another mail to apologize the doubles, which would only create more traffic.
Consider this e-mail the apology e-mail. :)

> > zcav, a tool from bonnie++ package, was used to measure the sequential
read
> > rate. All disks were able to sustain minimum 30MB/s when accessed
> > seperately. When accessed simultaneously I get these results:
> >
> > When accessing 1 disk, the read rate was 30MB/s (as expected).
> > When accessing 2 disks, the read rate was 60MB/s (30MB/s on each disk,
as
> > expected)
> > When accessing 3 disks, the read rate was 60MB/s (20MB/s on each disk,
> > dropping 10Mb/s)
> > When accessing 4 disks, the read rate was 60MB/s (15MB/s on each disk,
> > dropping 15Mb/s)
>
> Have you tried with RAID0?
> What makes you think its IDE issue, not a RAID one?

It wouldn't do any good trying RAID0 if the underlying layer cannot deliver
the data faster. The 4 above "benchmarks" are performed directly on the
disks rather than on the RAID setup, which eliminates any overhead RAID may
bring.

--
Theepan

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


Gmane