Re: About Triton DMA IDE vs. SCSI performance
> What have you used for testing? [disk drive performance].
> I'm curious to test my own system.
> Something more sophisticated than hdparm -t?
Hdparm and "/bin/time dd". I was mostly interested in transfer
rate. Note that you have to not read the same data twice, as otherwise
you get fooled by the Linux disk block cache.
> So from this it sounds like if you have two IDE drives, you are better
> off to put one on each IDE bus. Is that true? I looked for some info
> about this, but never found any.
I am assuming that I get concurrency that way.
> Also, I started using the md (RAID0) driver on a couple of machines,
> and it seems to work well. However, you can't test performance with
> hdparm since it doesn't understand md devices. Is there a good
> alternative?
"dd" is simple-minded, but that's not necessarily bad. There are disk
benchmarks available, but I am not familiar with them.
> The md HOWTO says that you can stripe drives of different makes and
> sizes, but it doesn't say when it makes sense (performance wise) to do
> this. I did it (just to try it out) with a 1GIG Fireball and a 500MB
> Caviar. Could this actually be a win? I know that you have two
> mechanisms doing the fetching, but if one drives is slower than the
> other, it seems that you might have a problem...
I have one old Caviar 2340 that I have tried on the same machine, and it
is less than half the speed of the Quantum. You'd have to run a benchmark
to see how the thing performed.
Bruce
Reply to: