Question about throughput

[Mads Bondo Dydensborg]

On Mon, 6 Nov 2000, Doug Ledford wrote:

> Mads Bondo Dydensborg wrote:
> > I have tried to analyze what happens, and
> > it seems that the aic7xxx driver will only issue a single read command at
> > a time. When writing, multiple write commands will be issued.
> 
> The driver will issue as many reads to the device as the mid level and higher
> level code sends to it.  Under normal conditions, large numbers of reads are
> queued by the block device read-ahead code in the upper block layers, not by
> the SCSI subsystem.  So, in order for linux to do the same thing for your
> device, you would have to be accessing it through the block device layers
> (aka, your drive appears as any other normal disk drive and you aren't using a
> raw device to access it) and you would have to be doing sequential reads.  If
> you meet those two items, then linux should be using the tagged queueing to
> access your drive with multiple reads outstanding.

I do meet those two items. I assume tagged queueing to be the case then.

> 
> > Obviously, using the SCI network is not the same as the local case. There
> > is a greater latency for operations.
> > 
> > My question is this; are there any way to force the aic7xxx driver to
> > issue more read commands to a device?
> > 
> > Any help, hints, suggestions, comments, flames are welcome. Anything,
> > really. :-) I must defend my results in 3 weeks, and would _really_ like
> > to have solved this problem first.
> 
> I would try making a filesystem on the SCSI network device, then mounting that
> filesystem, then run the bonnie program on that filesystem to see how it
> performs under those conditions.  I assume that's not what you are doing now
> ;-)  

At the moment I am using dd to test the performance on a md raid
filesystem. I will try bonnie. (Add. info: In my thesis I used a slower
disk, and have tested that with both dd and bonnie. I now have access to
faster disks - the assymmetrical problem only takes place on these faster
disks. Very painful).

> Using bonnie on a mounted filesystem on a local disk usually results in
> sequential reads being better than writes until writes eclipse the 85MB/s
> mark, at which point they start to pass reads (on a dual PII-500 I think it
> was, and the reads were running out of CPU power for searching through the
> buffer cache before each read command was issued as I recall).

Interessting. I will try experimenting with the amount of physical ram. 
Due to some limitations in SCI, I will never be able to go above 132/2 =
66 MB/s however.

Thanks a lot for your response and help (so far! :-)

Mads

-- 
Mads Bondo Dydensborg.                               madsdyd at challenge.dk
Did you ever notice how at trade shows Microsoft is always the one giving
away stress balls...



To Unsubscribe: send mail to majordomo at FreeBSD.org
with "unsubscribe aic7xxx" in the body of the message