Re: RAID0: performance oddity (2.2.0pre7)

Rik van Riel (riel@humbolt.geo.uu.nl)
Mon, 18 Jan 1999 22:40:07 +0100 (CET)


On Sun, 17 Jan 1999, Chris Evans wrote:

> I have a raid0 array of 2 disks, both of which can do ~6.5Mb/sec.
> With chunksize = 4k (default), the md0 device can shift
> ~11.5Mb/sec. Not bad.
>
> However bumping up the chunksize to 64k _decreases_ performance on
> the array to ~6Mb/sec. This is slower than either individual disk!

This is probably because your drives only read ahead 64k at a
time (maybe even less). When you get data 4k at a time both
drives can continue to fill their cache at the same time.

When using large stripes you are switching drives and not
properly streaming each drive, this causes the performance
loss you've been seeing.

It is entirely possible that the optimal is at 8, 16 or
even 32 kB -- it varies according to drive type, firmware
version and other 'fun' environmental variables...

Rik -- If a Microsoft product fails, who do you sue?
+-------------------------------------------------------------------+
| Linux memory management tour guide. riel@nl.linux.org |
| Scouting Vries cubscout leader. http://www.nl.linux.org/~riel |
+-------------------------------------------------------------------+

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/