<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic Re: Multi CPU HPUX 11.23 default Process CPU distribution in Operating System - HP-UX</title>
    <link>https://community.hpe.com/t5/operating-system-hp-ux/multi-cpu-hpux-11-23-default-process-cpu-distribution/m-p/4506870#M365360</link>
    <description>&amp;gt; Did i understand you right that the&lt;BR /&gt;  scheduler dynamical (during process&lt;BR /&gt;  runtime) decides to change the cpu&lt;BR /&gt;  of a given process if he think that &lt;BR /&gt;  the other cpu gives the faster result ?&lt;BR /&gt;&lt;BR /&gt;Yes looking at the length of the queue of threads waiting on each cpu queues in READY state ( this queue is named runqueue). So only READY threads but not RUNNING processes are switched to an other processor queue.&lt;BR /&gt;&lt;BR /&gt;The scheduler tries to balance runqueue length when they are larger than some values.&lt;BR /&gt;&lt;BR /&gt;&amp;gt; Die i understand you right, that the&lt;BR /&gt;&amp;gt; screenshot i take is not static belonging&lt;BR /&gt;&amp;gt; the process/cpu#. So that it can be that&lt;BR /&gt;&amp;gt; in some time later the same process is on&lt;BR /&gt;&amp;gt; the other cpu (of cause a optimization &lt;BR /&gt;&amp;gt; decision in the scheduler) ?&lt;BR /&gt;&lt;BR /&gt;Yes, except if your threads/processes are bound to a cpu through pset, mpsched(1)  or mpctl(2).&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;</description>
    <pubDate>Mon, 05 Oct 2009 07:05:12 GMT</pubDate>
    <dc:creator>Laurent Menase</dc:creator>
    <dc:date>2009-10-05T07:05:12Z</dc:date>
    <item>
      <title>Multi CPU HPUX 11.23 default Process CPU distribution</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/multi-cpu-hpux-11-23-default-process-cpu-distribution/m-p/4506864#M365354</link>
      <description>I'm interesting for an answer of the following question:&lt;BR /&gt;&lt;BR /&gt;how HPUX 11.23 distributes the processes to the CPU into an dual CPU System per default ?&lt;BR /&gt;&lt;BR /&gt;The attachment shows the output from top.&lt;BR /&gt;I see there that some processes belong to CPU 0 and others to CPU 1.&lt;BR /&gt;&lt;BR /&gt;many thanks for all feedbacks.&lt;BR /&gt;&lt;BR /&gt;Olaf</description>
      <pubDate>Fri, 02 Oct 2009 07:54:49 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/multi-cpu-hpux-11-23-default-process-cpu-distribution/m-p/4506864#M365354</guid>
      <dc:creator>Kasper_USB</dc:creator>
      <dc:date>2009-10-02T07:54:49Z</dc:date>
    </item>
    <item>
      <title>Re: Multi CPU HPUX 11.23 default Process CPU distribution</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/multi-cpu-hpux-11-23-default-process-cpu-distribution/m-p/4506865#M365355</link>
      <description>regularly the kernel evaluate the length of the run queues of each cpu, and tries to spread the ready threads over all the cpus.&lt;BR /&gt;&lt;BR /&gt;you can control on which cpu your process is running with mpctl()</description>
      <pubDate>Fri, 02 Oct 2009 10:29:13 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/multi-cpu-hpux-11-23-default-process-cpu-distribution/m-p/4506865#M365355</guid>
      <dc:creator>Laurent Menase</dc:creator>
      <dc:date>2009-10-02T10:29:13Z</dc:date>
    </item>
    <item>
      <title>Re: Multi CPU HPUX 11.23 default Process CPU distribution</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/multi-cpu-hpux-11-23-default-process-cpu-distribution/m-p/4506866#M365356</link>
      <description>Once a given process is assigned to a given CPU, the scheduler tries to keep that process running there.  That will allow for a better chance for the various caches to be used.&lt;BR /&gt;This is not exclusive, just a factor the scheduler uses in deciding where to start a thread when it becomes runnable. Like a gravety force, or a leash. But 'when you gotta go, you gotta go'.&lt;BR /&gt;There are mutliple scheduler choices (realtime, timeshare) and run time tweaks (mpsched) on hpux so 'it depends'.&lt;BR /&gt;Please note that the exact behavior may be release dependent (this is the stuff that gets tweaked for better (TPC-C) benchmark results) and platform dependent (Cellboards, numa)&lt;BR /&gt;Several papers / forum topics have been written on this before. Check with google using keywords such as affinity and mpsched.&lt;BR /&gt;&lt;BR /&gt;hth,&lt;BR /&gt;Hein van den Heuvel&lt;BR /&gt;HvdH Performance Consulting.&lt;BR /&gt;</description>
      <pubDate>Fri, 02 Oct 2009 10:43:17 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/multi-cpu-hpux-11-23-default-process-cpu-distribution/m-p/4506866#M365356</guid>
      <dc:creator>Hein van den Heuvel</dc:creator>
      <dc:date>2009-10-02T10:43:17Z</dc:date>
    </item>
    <item>
      <title>Re: Multi CPU HPUX 11.23 default Process CPU distribution</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/multi-cpu-hpux-11-23-default-process-cpu-distribution/m-p/4506867#M365357</link>
      <description>Hello Hein van den Heuvel&lt;BR /&gt;&lt;BR /&gt;Did i understand you right that the scheduler dynamical (during process runtime) decides to change the cpu of a given process if he think that the other cpu gives the faster result ?&lt;BR /&gt;&lt;BR /&gt;Die i understand you right, that the screenshot i take is not static belonging the process/cpu#. So that it can be that in some time later the same process is on the other cpu (of cause a optimization decision in the scheduler) ?&lt;BR /&gt;&lt;BR /&gt;Thanks for feedback.&lt;BR /&gt;&lt;BR /&gt;Olaf</description>
      <pubDate>Fri, 02 Oct 2009 10:58:35 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/multi-cpu-hpux-11-23-default-process-cpu-distribution/m-p/4506867#M365357</guid>
      <dc:creator>Kasper_USB</dc:creator>
      <dc:date>2009-10-02T10:58:35Z</dc:date>
    </item>
    <item>
      <title>Re: Multi CPU HPUX 11.23 default Process CPU distribution</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/multi-cpu-hpux-11-23-default-process-cpu-distribution/m-p/4506868#M365358</link>
      <description>&amp;gt;decides to change the CPU of a given process if he thinks that the other CPU gives the faster result?&lt;BR /&gt;&lt;BR /&gt;Or is just less busy.&lt;BR /&gt;&lt;BR /&gt;&amp;gt;some time later the same process is on the other CPU (of cause a optimization decision in the scheduler)?&lt;BR /&gt;&lt;BR /&gt;Yes.</description>
      <pubDate>Fri, 02 Oct 2009 11:17:54 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/multi-cpu-hpux-11-23-default-process-cpu-distribution/m-p/4506868#M365358</guid>
      <dc:creator>Dennis Handly</dc:creator>
      <dc:date>2009-10-02T11:17:54Z</dc:date>
    </item>
    <item>
      <title>Re: Multi CPU HPUX 11.23 default Process CPU distribution</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/multi-cpu-hpux-11-23-default-process-cpu-distribution/m-p/4506869#M365359</link>
      <description>every second the monarch processor calculates the CPU utilization of all of the CPUS.  IF the busiest and least busiest differ by over 20% then it may move a  thread from the busiest cpu to the least busiest cpu.&lt;BR /&gt;&lt;BR /&gt;If this is a cell based system it does this for the cpus in a cell then across cells.</description>
      <pubDate>Sat, 03 Oct 2009 02:24:58 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/multi-cpu-hpux-11-23-default-process-cpu-distribution/m-p/4506869#M365359</guid>
      <dc:creator>Emil Velez</dc:creator>
      <dc:date>2009-10-03T02:24:58Z</dc:date>
    </item>
    <item>
      <title>Re: Multi CPU HPUX 11.23 default Process CPU distribution</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/multi-cpu-hpux-11-23-default-process-cpu-distribution/m-p/4506870#M365360</link>
      <description>&amp;gt; Did i understand you right that the&lt;BR /&gt;  scheduler dynamical (during process&lt;BR /&gt;  runtime) decides to change the cpu&lt;BR /&gt;  of a given process if he think that &lt;BR /&gt;  the other cpu gives the faster result ?&lt;BR /&gt;&lt;BR /&gt;Yes looking at the length of the queue of threads waiting on each cpu queues in READY state ( this queue is named runqueue). So only READY threads but not RUNNING processes are switched to an other processor queue.&lt;BR /&gt;&lt;BR /&gt;The scheduler tries to balance runqueue length when they are larger than some values.&lt;BR /&gt;&lt;BR /&gt;&amp;gt; Die i understand you right, that the&lt;BR /&gt;&amp;gt; screenshot i take is not static belonging&lt;BR /&gt;&amp;gt; the process/cpu#. So that it can be that&lt;BR /&gt;&amp;gt; in some time later the same process is on&lt;BR /&gt;&amp;gt; the other cpu (of cause a optimization &lt;BR /&gt;&amp;gt; decision in the scheduler) ?&lt;BR /&gt;&lt;BR /&gt;Yes, except if your threads/processes are bound to a cpu through pset, mpsched(1)  or mpctl(2).&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;</description>
      <pubDate>Mon, 05 Oct 2009 07:05:12 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/multi-cpu-hpux-11-23-default-process-cpu-distribution/m-p/4506870#M365360</guid>
      <dc:creator>Laurent Menase</dc:creator>
      <dc:date>2009-10-05T07:05:12Z</dc:date>
    </item>
  </channel>
</rss>

