<?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 Performance Problems in Operating System - HP-UX</title>
    <link>https://community.hpe.com/t5/operating-system-hp-ux/performance-problems/m-p/2466017#M15747</link>
    <description>Hello All,&lt;BR /&gt;&lt;BR /&gt;Output from the vmstat command on one of my servers consistenly shows a high value in the b column.  I understand this to mean that these processes, and sometimes there are in excess of 100 of them, are "blocked" and waiting for resources to execute.  I am a bit puzzled by this.  This system has plenty of memory, analysis of sar output does not show anything out of the ordinary.  Yet, I continue to see these high values.  Does anybody have any ideas?  Any help would be appreciated.&lt;BR /&gt;&lt;BR /&gt;Many TIAs&lt;BR /&gt;Robert Smith &lt;BR /&gt;&lt;BR /&gt;</description>
    <pubDate>Mon, 20 Nov 2000 19:20:41 GMT</pubDate>
    <dc:creator>Rob Smith</dc:creator>
    <dc:date>2000-11-20T19:20:41Z</dc:date>
    <item>
      <title>Performance Problems</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/performance-problems/m-p/2466017#M15747</link>
      <description>Hello All,&lt;BR /&gt;&lt;BR /&gt;Output from the vmstat command on one of my servers consistenly shows a high value in the b column.  I understand this to mean that these processes, and sometimes there are in excess of 100 of them, are "blocked" and waiting for resources to execute.  I am a bit puzzled by this.  This system has plenty of memory, analysis of sar output does not show anything out of the ordinary.  Yet, I continue to see these high values.  Does anybody have any ideas?  Any help would be appreciated.&lt;BR /&gt;&lt;BR /&gt;Many TIAs&lt;BR /&gt;Robert Smith &lt;BR /&gt;&lt;BR /&gt;</description>
      <pubDate>Mon, 20 Nov 2000 19:20:41 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/performance-problems/m-p/2466017#M15747</guid>
      <dc:creator>Rob Smith</dc:creator>
      <dc:date>2000-11-20T19:20:41Z</dc:date>
    </item>
    <item>
      <title>Re: Performance Problems</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/performance-problems/m-p/2466018#M15748</link>
      <description>Remember that this is blocked for I/O, not memory.  If you have many network related tasks, these will be blocked depending on network IO.  Ditto for Disk I/O, etc...  &lt;BR /&gt;Since this vmstat is a snapshot, you can not see if the processes are really working.  Most of the  time they are.  I.E.  A DNS server has named running blocked, but information is still getting to clients.  Why is it blocked?  Someone is FTP'ing a large file, and I/O has to be controlled.  The kernel just blockes the I/O untill it can run freely.   In many cases, I/O can never run free.&lt;BR /&gt;&lt;BR /&gt;I would not be too concerned about this one.  Unless it starts to get very high and you see bottlenecks in specific areas.  I.E  memory, disk I/O.&lt;BR /&gt;&lt;BR /&gt;Regards,&lt;BR /&gt;Shannon</description>
      <pubDate>Mon, 20 Nov 2000 19:34:58 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/performance-problems/m-p/2466018#M15748</guid>
      <dc:creator>Shannon Petry</dc:creator>
      <dc:date>2000-11-20T19:34:58Z</dc:date>
    </item>
    <item>
      <title>Re: Performance Problems</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/performance-problems/m-p/2466019#M15749</link>
      <description>Shannon's answer hits the nail on the head.  Sometimes command line checks of the system are hard to interpret, to get a real handle on what your system is doing.  I recommend trying something like Glance, because you can start it running and check over the course of the day...to see what the system is doing overall and averaging at.  It helped me to get a better feel for what was going on....and helps in monitoring specific applications, etc.  There is a free trial version you could sample on your Apps CD's&lt;BR /&gt;&lt;BR /&gt;Just a suggestion,</description>
      <pubDate>Mon, 20 Nov 2000 19:41:46 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/performance-problems/m-p/2466019#M15749</guid>
      <dc:creator>Rita C Workman</dc:creator>
      <dc:date>2000-11-20T19:41:46Z</dc:date>
    </item>
  </channel>
</rss>

