<?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: process blocked on cache in Operating System - HP-UX</title>
    <link>https://community.hpe.com/t5/operating-system-hp-ux/process-blocked-on-cache/m-p/3539552#M222979</link>
    <description>Thanks for the response.  Sorry for the delay in responding and giving points.&lt;BR /&gt;&lt;BR /&gt;Appreciate the feedback.&lt;BR /&gt;&lt;BR /&gt;Tim&lt;BR /&gt;</description>
    <pubDate>Mon, 23 May 2005 14:33:14 GMT</pubDate>
    <dc:creator>Tim Nelson</dc:creator>
    <dc:date>2005-05-23T14:33:14Z</dc:date>
    <item>
      <title>process blocked on cache</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/process-blocked-on-cache/m-p/3539550#M222977</link>
      <description>I have seen a number of posts about this but have not yet been able to find a solution, if ther is any.&lt;BR /&gt;&lt;BR /&gt;I have a process that uses a temporary sort space on disk.  Almost all the sort is running out of cache as I see 99% cache hit rate and almost all io for the process is logical io.  The process spends most of it's time 60% or so blocked on Cache.  I have been fiddling with filesystem mounts for this space using the tmplog and nodatainlog but cannot seem to free up or lower this % waiting on Cache.&lt;BR /&gt;&lt;BR /&gt;Any suggestions ?  I am sure the process is running very well, just looking for options to try to make it run better.  ( maybe making something good = better is not worth the time)&lt;BR /&gt;</description>
      <pubDate>Fri, 06 May 2005 14:31:56 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/process-blocked-on-cache/m-p/3539550#M222977</guid>
      <dc:creator>Tim Nelson</dc:creator>
      <dc:date>2005-05-06T14:31:56Z</dc:date>
    </item>
    <item>
      <title>Re: process blocked on cache</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/process-blocked-on-cache/m-p/3539551#M222978</link>
      <description>Well, if it is doing almost all logical i/o as opposed to physical i/o, there's not much that can be done from an OS/filesystem tuning perspective. The real fix is the application itself. It looks as though it should be doing much more in-memory activity than it currently is. You don't bother to mention your OS relase but 11.11 is more efficient at searching the buffer cache than is 11.0. In a few case, I've actually seen improvements by decreasing the size of the buffer cache -- which is counter-intuitive.&lt;BR /&gt;It would also help to know if your box is under any memory pressure. I would also suggest that you go with a static buffer cache because that makes analyzing results much, much easier.</description>
      <pubDate>Fri, 06 May 2005 16:49:56 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/process-blocked-on-cache/m-p/3539551#M222978</guid>
      <dc:creator>A. Clay Stephenson</dc:creator>
      <dc:date>2005-05-06T16:49:56Z</dc:date>
    </item>
    <item>
      <title>Re: process blocked on cache</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/process-blocked-on-cache/m-p/3539552#M222979</link>
      <description>Thanks for the response.  Sorry for the delay in responding and giving points.&lt;BR /&gt;&lt;BR /&gt;Appreciate the feedback.&lt;BR /&gt;&lt;BR /&gt;Tim&lt;BR /&gt;</description>
      <pubDate>Mon, 23 May 2005 14:33:14 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/process-blocked-on-cache/m-p/3539552#M222979</guid>
      <dc:creator>Tim Nelson</dc:creator>
      <dc:date>2005-05-23T14:33:14Z</dc:date>
    </item>
  </channel>
</rss>

