On 5/9/06, Peggy Andrews <[EMAIL PROTECTED]> wrote:

I will be scheduling more testing for today/tomorrow and compile this
info and share answers.

A good performance monitor allows you to review the data of the runs
that you already did and analyze what caused the difference. There's
no guarantee you will see the same problem when yoiu repeat your test
tomorrow.

As suggested earlier, I would start with looking at the DASD I/O rates
and see whether you're comparing apples and pears. With the dataset
fitting completely in the 1.6G virtual machine, there's some ground
for doubts there.

Also, I thought I read something about defining/using a "virtual
sniffer" for testing - do you know anything about that?

For starters it might be enough to simply look at your network
statistics and check for fragmentation, number of packets, errors,
etc.  I think the sniffer was meant to analyze functional issues.
Though I have not seen any measurements of it, I would be surprised if
sniffing the traffic would not have a performance impact itself.

Rob
--
Rob van der Heij
Velocity Software, Inc
http://velocitysoftware.com/

----------------------------------------------------------------------
For LINUX-390 subscribe / signoff / archive access instructions,
send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit
http://www.marist.edu/htbin/wlvindex?LINUX-390

Reply via email to