<?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: ipcs queues full, system slows down in Operating System - HP-UX</title>
    <link>https://community.hpe.com/t5/operating-system-hp-ux/ipcs-queues-full-system-slows-down/m-p/2838431#M90670</link>
    <description>Some more info by the developer :&lt;BR /&gt;&lt;BR /&gt;I find a situation where lisp can't write to a queue&lt;BR /&gt;because another queue is full. Once this happens,&lt;BR /&gt;attempts to write the empty queue fail.&lt;BR /&gt;&lt;BR /&gt;When the ber module queue is full, there are a few more&lt;BR /&gt;writes to the OI queue and then this stops too.&lt;BR /&gt;&lt;BR /&gt;When the full queue is first emptied, writing to the&lt;BR /&gt;other queue also resumes.&lt;BR /&gt;&lt;BR /&gt;This problem is reproducible. You can test it by calling&lt;BR /&gt;&lt;BR /&gt;  kill -STOP &lt;AS ber_module="" pid=""&gt;&lt;BR /&gt;&lt;BR /&gt;the RAI queue will slowly fill up. When it is full,&lt;BR /&gt;the user interface blocks. When you call&lt;BR /&gt;&lt;BR /&gt;  kill -CONT &lt;AS ber_module="" pid=""&gt;&lt;BR /&gt;&lt;BR /&gt;everything gets back to normal.&lt;BR /&gt;&lt;BR /&gt;This looks very much like it is an HP-UX problem.&lt;BR /&gt;&lt;BR /&gt;During this period, another process (pid=1800) using an&lt;BR /&gt;entirely different queue also can't write messages. The output&lt;BR /&gt;of ipcs seems corrupt: QBYTES is 554, but QNUM is 0!&lt;BR /&gt;We have seen this before, but now I see there is a relation&lt;BR /&gt;with the situation above.&lt;/AS&gt;&lt;/AS&gt;</description>
    <pubDate>Tue, 05 Nov 2002 06:28:29 GMT</pubDate>
    <dc:creator>kestens jan</dc:creator>
    <dc:date>2002-11-05T06:28:29Z</dc:date>
    <item>
      <title>ipcs queues full, system slows down</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/ipcs-queues-full-system-slows-down/m-p/2838429#M90668</link>
      <description>Hi all,&lt;BR /&gt;&lt;BR /&gt;I'm currently testing network management software on HP WS (C3X00, B2600, B180) &amp;amp;K-servers (HPUX 10.20 + general release patches dec 2001).&lt;BR /&gt;&lt;BR /&gt;I noticed that when a certain message queue (ipcs) fills up to almost its maximum value the system slows down (GUI, dcp's,....).&lt;BR /&gt;I talked with the developers and they suspect HPUX.&lt;BR /&gt;&lt;BR /&gt;Does anyone have some experience with this ?&lt;BR /&gt;&lt;BR /&gt;I included a part of an ipcs trace.&lt;BR /&gt;&lt;BR /&gt;Greetz&lt;BR /&gt;&lt;BR /&gt;Jan K</description>
      <pubDate>Mon, 04 Nov 2002 15:42:38 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/ipcs-queues-full-system-slows-down/m-p/2838429#M90668</guid>
      <dc:creator>kestens jan</dc:creator>
      <dc:date>2002-11-04T15:42:38Z</dc:date>
    </item>
    <item>
      <title>Re: ipcs queues full, system slows down</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/ipcs-queues-full-system-slows-down/m-p/2838430#M90669</link>
      <description>Developers normally try to point the finger at the part of the system for which they are not responsible :)&lt;BR /&gt;&lt;BR /&gt;Does the message queue fill up if the NMS is not running?  If not, the NMS is to blame.  &lt;BR /&gt;&lt;BR /&gt;If the queue fills up when the NMS is not running, are there any other non-system processes running at the time?</description>
      <pubDate>Mon, 04 Nov 2002 20:32:29 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/ipcs-queues-full-system-slows-down/m-p/2838430#M90669</guid>
      <dc:creator>Chris Wilshaw</dc:creator>
      <dc:date>2002-11-04T20:32:29Z</dc:date>
    </item>
    <item>
      <title>Re: ipcs queues full, system slows down</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/ipcs-queues-full-system-slows-down/m-p/2838431#M90670</link>
      <description>Some more info by the developer :&lt;BR /&gt;&lt;BR /&gt;I find a situation where lisp can't write to a queue&lt;BR /&gt;because another queue is full. Once this happens,&lt;BR /&gt;attempts to write the empty queue fail.&lt;BR /&gt;&lt;BR /&gt;When the ber module queue is full, there are a few more&lt;BR /&gt;writes to the OI queue and then this stops too.&lt;BR /&gt;&lt;BR /&gt;When the full queue is first emptied, writing to the&lt;BR /&gt;other queue also resumes.&lt;BR /&gt;&lt;BR /&gt;This problem is reproducible. You can test it by calling&lt;BR /&gt;&lt;BR /&gt;  kill -STOP &lt;AS ber_module="" pid=""&gt;&lt;BR /&gt;&lt;BR /&gt;the RAI queue will slowly fill up. When it is full,&lt;BR /&gt;the user interface blocks. When you call&lt;BR /&gt;&lt;BR /&gt;  kill -CONT &lt;AS ber_module="" pid=""&gt;&lt;BR /&gt;&lt;BR /&gt;everything gets back to normal.&lt;BR /&gt;&lt;BR /&gt;This looks very much like it is an HP-UX problem.&lt;BR /&gt;&lt;BR /&gt;During this period, another process (pid=1800) using an&lt;BR /&gt;entirely different queue also can't write messages. The output&lt;BR /&gt;of ipcs seems corrupt: QBYTES is 554, but QNUM is 0!&lt;BR /&gt;We have seen this before, but now I see there is a relation&lt;BR /&gt;with the situation above.&lt;/AS&gt;&lt;/AS&gt;</description>
      <pubDate>Tue, 05 Nov 2002 06:28:29 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/ipcs-queues-full-system-slows-down/m-p/2838431#M90670</guid>
      <dc:creator>kestens jan</dc:creator>
      <dc:date>2002-11-05T06:28:29Z</dc:date>
    </item>
  </channel>
</rss>

