Devel::NYTProf is not currently thread safe or multiplicity safe.

Sorry. I don't use NYTProf myself, so I've never encountered the limitation. I only mentioned it because it seems to be what everyone else recommends.

This application cannot be run - or rewritten to run - without threads.

There would be no point to doing so as the bottlenecks would undoubtedly move.

But, the core of my advise above remains. You will need to profile.

I tend to do this manually. I find that profiling every line takes too long and produces far too much output to be useful.

So, I start course-grained at first till I find the points of interest, then more and more fine-grained around those points of interest until I find what I'm looking for.

So, for a queue consumer thread I will just trace:

printf STDERR "[%3d] %u %s:%d %s\n", threads->tid, time(), __FILE__, _
+_LINE__, $workitem;
[download]

once for each loop of the queue processing loop.

That should have negligible affect on overall performance of the code, but should give sufficient information to see if one or more your threads and/or particular work items are significantly slower on the AIX machine that the others.

Once you get some indication of where the differences lie, you can then disable or remove the irrelevant traces and add a few more in the appropriate places to allow you to zoom in on the cause(s).

One possibility -- based upon something you said in one of your other replies above --

Because historically, if you configure a VM with equal or more of any of those than the actual machine it runs on has, then it can lead to some very bad interactions between the host and guest OS schedulers and lead to diabolically bad performance. Just a thought.

Appreciate the further suggestions. Always good to get more perspectives.

As it happens however, my code is already littered at thread id level with print STDERR debugging. I turn it on and off with a Getopt::Long + flag where I can choose multiple levels of debugging depending on how many -v's I specify when I start the script, and I can monitor by thread. I wrap calls that way when I need to check what's causing them to be slow, or otherwise debug.

The issue isn't "what" is causing the problem so much - I already know that in *essence* - it's the multiple calls to REST services that this particular instance of the server has added. That's what's new. What I'm curious about is *why* that's happening. Hence my wondering about the modules and / or context switch throttling.

There is no virtualization in use. It makes no sense to run any of this virtualized. The Xeon machine is the headnode of a supercomputer cluster. Want things running as fast as possible - while still being written in Perl for a host of other reasons. The AIX machine is a 20-way CPU with 64G of memory. I use as much of it natively also as I need when I need to.

Kind regards

Derek

The issue isn't "what" is causing the problem so much - I already know that in *essence* - it's the multiple calls to REST services that this particular instance of the server has added.

So, isn't the xeon version of the code doing the same thing?

And therefore the difference between them ... never mind.

---

With the rise and rise of 'Social' network sites: 'Computers are making people easier to use everyday'

Examine what is said, not who speaks -- Silence betokens consent -- Love the truth but pardon error.

"Science is about questioning the status quo. Questioning authority".

In the absence of evidence, opinion is indistinguishable from prejudice.