in reply to Re^3: Multithreaded process on AIX slow
in thread Multithreaded process on AIX slow

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

  • Comment on Re^4: Multithreaded process on AIX slow

Replies are listed 'Best First'.
Re^5: Multithreaded process on AIX slow
by BrowserUk (Patriarch) on Nov 14, 2013 at 14:07 UTC
    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.
[reply]

      Appreciate the thought.

      No - that's fine - I agree - it is the exact same code. Your point is well taken. My concern is how that is acting differently on AIX.

      It's not the code itself you as you point out. There's not an *inherent* bottleneck since it runs quickly enough on Linux. It's the interaction between that new small portion and AIX that's of issue, and, I was wondering if there was something to do with the REST::Client or HTTP::Request modules and AIX going on that anyone else had encountered, or possibly how they are interacting with the context switching on AIX.

      Kind regards

      Derek

[reply]
        My concern is how that is acting differently on AIX.

        That is exactly my point. You are in the enviable position of having the debugger's holy grail:

        Repeatable scenarios that differentiate exactly on the bug description.

        But, rather than exploiting that perfect tool, you appear to want to debug by crowd-sourced guessing....

        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.
[reply]

In Section Seekers of Perl Wisdom