At least you got to where it is the "whole system" that is the bottleneck
and not just a single component :)

Yeah, we played with a variety of settings to get to that point. Part of me
actually enjoys those types of support calls as I get to dig in and get
dirty and learn a whole bunch :-)

If I understood you correctly you describe a situation where you put load
on Apache and each request invokes a dead simple AS/400 job?

Here is the code: http://code.midrange.com/f98a4914c1.html

That is a good scenario to optimize :) What did you find help?

We ended up prestarting a number of jobs and also modified the TCP/IP
setting (as was described earlier by somebody else), but I don't know if
they stuck with that option. Another approach I took to address such an
issue (but with another customer) is to do async web services where I
receive the request and immediate drop the connection with a simple HTTP 200
OK and then invoke a web service on their end where I then become the
client. I am not completely sold on this concept for all cases as it really
only works well for cases where the web service is a longer running process
that needs to be queued and run in batch.

Hope that helps explain it better. Note I will state again that this was
probably an extreme scenario, but it will also let you know what to look at
if your load every gets extremely high. I would recommend everyone take a
stab at using JMeter as it is a very useful and cool tool.

Aaron Bartell
http://mowyourlawn.com


On Fri, Sep 26, 2008 at 1:17 AM, Thorbjørn Ravn Andersen <ravn@xxxxxxxxxx>wrote:

Aaron Bartell skrev:
But there is only so much increasing on both sides that you can do, much
less just the OS400 job side. At some point increasing OS400 jobs will
only
slow things down because the ones currently running are waiting in line
for
their time-slice. At one point I think we had a couple hundred Apache
jobs
running and that still wasn't enough to keep up with JMeter on a powerful
desktop spawning multiple hundreds of threads at a time. Note that I put
together a very simple write-to-standard-out CGI program for these test
to
insure there was very little time spent in the OS400 job.

At least you got to where it is the "whole system" that is the
bottleneck and not just a single component :)

If I understood you correctly you describe a situation where you put
load on Apache and each request invokes a dead simple AS/400 job?

That is a good scenario to optimize :) What did you find help?

As an Amazon Associate we earn from qualifying purchases.

This thread ...

Replies:

Follow On AppleNews
Return to Archive home page | Return to MIDRANGE.COM home page

This mailing list archive is Copyright 1997-2024 by midrange.com and David Gibbs as a compilation work. Use of the archive is restricted to research of a business or technical nature. Any other uses are prohibited. Full details are available on our policy page. If you have questions about this, please contact [javascript protected email address].

Operating expenses for this site are earned using the Amazon Associate program and Google Adsense.