<?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: CPU Performance During Heavy Load in Operating System - HP-UX</title>
    <link>https://community.hpe.com/t5/operating-system-hp-ux/cpu-performance-during-heavy-load/m-p/2882855#M101326</link>
    <description>The answer is that it depends. If any of the processes are run in the real-time scheduler class then no system or time-sharing scheduler class processes will run at all. For this reason, great care has to been taken when using real-time processes. System class processes (like page handling and other housekeeping daemons) are next in priority.&lt;BR /&gt;Finally time-sharing processes are run. The factors which effect the which processes are run 1) time in memory, 2) priority, 3) length of time the process has been sleeping, and 4) size of the process (on most flavors of UNIX).&lt;BR /&gt;&lt;BR /&gt;If you see all the CPU's at 100% for extended periods of time then its time for a more/faster CPU's or time to schedule processes to run at off-peak periods.&lt;BR /&gt;&lt;BR /&gt;</description>
    <pubDate>Wed, 15 Jan 2003 19:15:11 GMT</pubDate>
    <dc:creator>A. Clay Stephenson</dc:creator>
    <dc:date>2003-01-15T19:15:11Z</dc:date>
    <item>
      <title>CPU Performance During Heavy Load</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/cpu-performance-during-heavy-load/m-p/2882852#M101323</link>
      <description>Can anyone tell me or point to some documentation that explains what happens within the OS when the cpu hits 100% utilization?  What occurs during cpu queing?  If all processors on a server are pegged at 100% what happens to the processes on that server?&lt;BR /&gt;&lt;BR /&gt;The servers are N class 7400's.&lt;BR /&gt;&lt;BR /&gt;Thanks!</description>
      <pubDate>Wed, 15 Jan 2003 18:46:12 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/cpu-performance-during-heavy-load/m-p/2882852#M101323</guid>
      <dc:creator>Chris_164</dc:creator>
      <dc:date>2003-01-15T18:46:12Z</dc:date>
    </item>
    <item>
      <title>Re: CPU Performance During Heavy Load</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/cpu-performance-during-heavy-load/m-p/2882853#M101324</link>
      <description>I don't believe the way processes are handled changes when CPU Usage hits 100%.  The OS still handles it the same.  Each process waits for its turn at the CPU and does whatever processing it can during it's "timeslice".  It may have to wait longer if there are more processes waiting for CPU time.&lt;BR /&gt;&lt;BR /&gt;There is no "swapping" of processes if the CPU hits 100% like there is if RAM hits 100% usage.</description>
      <pubDate>Wed, 15 Jan 2003 18:57:19 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/cpu-performance-during-heavy-load/m-p/2882853#M101324</guid>
      <dc:creator>Patrick Wallek</dc:creator>
      <dc:date>2003-01-15T18:57:19Z</dc:date>
    </item>
    <item>
      <title>Re: CPU Performance During Heavy Load</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/cpu-performance-during-heavy-load/m-p/2882854#M101325</link>
      <description>Queueing theory says that if the  utilization becomes 100%, the queue length approaches infinity and your response time will approach infinity.  &lt;BR /&gt;&lt;BR /&gt;Mott Given</description>
      <pubDate>Wed, 15 Jan 2003 19:04:58 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/cpu-performance-during-heavy-load/m-p/2882854#M101325</guid>
      <dc:creator>Mott Given</dc:creator>
      <dc:date>2003-01-15T19:04:58Z</dc:date>
    </item>
    <item>
      <title>Re: CPU Performance During Heavy Load</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/cpu-performance-during-heavy-load/m-p/2882855#M101326</link>
      <description>The answer is that it depends. If any of the processes are run in the real-time scheduler class then no system or time-sharing scheduler class processes will run at all. For this reason, great care has to been taken when using real-time processes. System class processes (like page handling and other housekeeping daemons) are next in priority.&lt;BR /&gt;Finally time-sharing processes are run. The factors which effect the which processes are run 1) time in memory, 2) priority, 3) length of time the process has been sleeping, and 4) size of the process (on most flavors of UNIX).&lt;BR /&gt;&lt;BR /&gt;If you see all the CPU's at 100% for extended periods of time then its time for a more/faster CPU's or time to schedule processes to run at off-peak periods.&lt;BR /&gt;&lt;BR /&gt;</description>
      <pubDate>Wed, 15 Jan 2003 19:15:11 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/cpu-performance-during-heavy-load/m-p/2882855#M101326</guid>
      <dc:creator>A. Clay Stephenson</dc:creator>
      <dc:date>2003-01-15T19:15:11Z</dc:date>
    </item>
  </channel>
</rss>

