<?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: Can we get cpu usage through pstat_getprocessor in Operating System - HP-UX</title>
    <link>https://community.hpe.com/t5/operating-system-hp-ux/can-we-get-cpu-usage-through-pstat-getprocessor/m-p/4029558#M747486</link>
    <description>if you have a HPUX system check whether you have OVPA (formerly called measureware).  you can do this with a command called perfstat.  if it shows a process called midaemon and scope you have measureware.&lt;BR /&gt;&lt;BR /&gt;The measureware product has already collected that data per processor every 5 minutes for 6 months.&lt;BR /&gt;&lt;BR /&gt;If you do not have measureware check whether you purchased the Enterprise or Mission Critical OE.  IF you did you are entitled to a license for OVPA and glance.   &lt;BR /&gt;&lt;BR /&gt;In addition you can use glance in advisor mode to print out CPU global and per cpu metrics on a recuring basis.&lt;BR /&gt;&lt;BR /&gt;check out the sa1 man page &lt;BR /&gt;&lt;BR /&gt;man sa1  &lt;BR /&gt;&lt;BR /&gt;on how to make sar collect data for you on a regular basis.&lt;BR /&gt;&lt;BR /&gt;This way you have 3 options..&lt;BR /&gt;&lt;BR /&gt;Good luck&lt;BR /&gt;Emil</description>
    <pubDate>Sat, 30 Jun 2007 12:15:48 GMT</pubDate>
    <dc:creator>Emil Velez</dc:creator>
    <dc:date>2007-06-30T12:15:48Z</dc:date>
    <item>
      <title>Can we get cpu usage through pstat_getprocessor</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/can-we-get-cpu-usage-through-pstat-getprocessor/m-p/4029557#M747485</link>
      <description>I want to compute the cpu usage for a while.&lt;BR /&gt;First I get cpu number through pstat_getdynamic, secondly I call  pstat_getprocessor to get all states's ticks of all cpus, including CPU_IDLE, CPU_USER, CPU_KERNEL, CPU_WAIT, and so on.&lt;BR /&gt;My computing method is: the difference of CPU_IDLE and CPU_WAIT is used as the numerator, and the whole difference of all states is used as the denominator.&lt;BR /&gt;But the result is obviously different from top or sar's output.</description>
      <pubDate>Fri, 29 Jun 2007 12:51:08 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/can-we-get-cpu-usage-through-pstat-getprocessor/m-p/4029557#M747485</guid>
      <dc:creator>zdbao</dc:creator>
      <dc:date>2007-06-29T12:51:08Z</dc:date>
    </item>
    <item>
      <title>Re: Can we get cpu usage through pstat_getprocessor</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/can-we-get-cpu-usage-through-pstat-getprocessor/m-p/4029558#M747486</link>
      <description>if you have a HPUX system check whether you have OVPA (formerly called measureware).  you can do this with a command called perfstat.  if it shows a process called midaemon and scope you have measureware.&lt;BR /&gt;&lt;BR /&gt;The measureware product has already collected that data per processor every 5 minutes for 6 months.&lt;BR /&gt;&lt;BR /&gt;If you do not have measureware check whether you purchased the Enterprise or Mission Critical OE.  IF you did you are entitled to a license for OVPA and glance.   &lt;BR /&gt;&lt;BR /&gt;In addition you can use glance in advisor mode to print out CPU global and per cpu metrics on a recuring basis.&lt;BR /&gt;&lt;BR /&gt;check out the sa1 man page &lt;BR /&gt;&lt;BR /&gt;man sa1  &lt;BR /&gt;&lt;BR /&gt;on how to make sar collect data for you on a regular basis.&lt;BR /&gt;&lt;BR /&gt;This way you have 3 options..&lt;BR /&gt;&lt;BR /&gt;Good luck&lt;BR /&gt;Emil</description>
      <pubDate>Sat, 30 Jun 2007 12:15:48 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/can-we-get-cpu-usage-through-pstat-getprocessor/m-p/4029558#M747486</guid>
      <dc:creator>Emil Velez</dc:creator>
      <dc:date>2007-06-30T12:15:48Z</dc:date>
    </item>
    <item>
      <title>Re: Can we get cpu usage through pstat_getprocessor</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/can-we-get-cpu-usage-through-pstat-getprocessor/m-p/4029559#M747487</link>
      <description>Hi Emil,&lt;BR /&gt;    Thank you for your advice. Now I want to get cpu usage through programming. I believe that some system calls can help me to achive it, but I still did not find them.</description>
      <pubDate>Sun, 01 Jul 2007 14:29:27 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/can-we-get-cpu-usage-through-pstat-getprocessor/m-p/4029559#M747487</guid>
      <dc:creator>zdbao</dc:creator>
      <dc:date>2007-07-01T14:29:27Z</dc:date>
    </item>
    <item>
      <title>Re: Can we get cpu usage through pstat_getprocessor</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/can-we-get-cpu-usage-through-pstat-getprocessor/m-p/4029560#M747488</link>
      <description>An unofficial thing do do would be to look at the HP-UX-specific code in netperf.  Specifically:&lt;BR /&gt;&lt;BR /&gt;&lt;A href="http://www.netperf.org/svn/netperf2/trunk/src/netcpu_pstat.c" target="_blank"&gt;http://www.netperf.org/svn/netperf2/trunk/src/netcpu_pstat.c&lt;/A&gt;&lt;BR /&gt;&lt;BR /&gt;and the pstat_new.c versions.  &lt;BR /&gt;&lt;BR /&gt;If you would prefer GPL code, then you can look at:&lt;BR /&gt;&lt;BR /&gt;&lt;A href="http://www.netperf.org/svn/netperf4/trunk/src/netsysstats_hpux.c" target="_blank"&gt;http://www.netperf.org/svn/netperf4/trunk/src/netsysstats_hpux.c&lt;/A&gt;&lt;BR /&gt;&lt;BR /&gt;Options for what you can/should use vary with release.</description>
      <pubDate>Mon, 02 Jul 2007 11:47:47 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/can-we-get-cpu-usage-through-pstat-getprocessor/m-p/4029560#M747488</guid>
      <dc:creator>rick jones</dc:creator>
      <dc:date>2007-07-02T11:47:47Z</dc:date>
    </item>
  </channel>
</rss>

