<?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: Physical Memory management - Performance problems in Operating System - Tru64 Unix</title>
    <link>https://community.hpe.com/t5/operating-system-tru64-unix/physical-memory-management-performance-problems/m-p/3899590#M18029</link>
    <description>You can try changing the swap allocation mode to avoid the "reservation" of space.&lt;BR /&gt;&lt;BR /&gt;Set vm_swap_eager to 0, to do that, do the following. Create a file called /tmp/sysconfig.stanza like this:&lt;BR /&gt;&lt;BR /&gt;vm:&lt;BR /&gt;  vm_swap_eager = 0&lt;BR /&gt;&lt;BR /&gt;Run the command:&lt;BR /&gt;&lt;BR /&gt;sysconfigdb -m -f /tmp/sysconfig.stanza&lt;BR /&gt;&lt;BR /&gt;Reboot the system.&lt;BR /&gt;&lt;BR /&gt;From the output I can see that your system is swapping, if your system continues swapping after this modification, probably you don't have enough RAM memory to support your load, or some application is using more memory than normal.</description>
    <pubDate>Tue, 21 Nov 2006 08:07:15 GMT</pubDate>
    <dc:creator>Ivan Ferreira</dc:creator>
    <dc:date>2006-11-21T08:07:15Z</dc:date>
    <item>
      <title>Physical Memory management - Performance problems</title>
      <link>https://community.hpe.com/t5/operating-system-tru64-unix/physical-memory-management-performance-problems/m-p/3899587#M18026</link>
      <description>I have a HP DS25 server running Tru64 5.1B.&lt;BR /&gt;My software run some java applications (everything on the server) sending them to several X clients (pc workstations running Exceed, linux workstations, ...).&lt;BR /&gt;I am monitoring the system activity with 'dxsysinfo'.&lt;BR /&gt;I have noticed that when I start to launch java applications, "In-use memory" starts to grow (as it would be expected).&lt;BR /&gt;But when "In-use memory" reaches 50%, then it suddenly drops and get stuck to around 25 %, starting to use swap a lot more!&lt;BR /&gt;After that moment, the java applications behaviour in the workstations drops in terms of performance (freezing for a long time), I believe because of the greater swapping.&lt;BR /&gt;Why does the system don´t allow a greater occupancy of physical memory? Why at some moment it drops to 25% usage, and get stuck to that value?&lt;BR /&gt;Is it possible to change that policy, for instance, changing some kernel parameters?</description>
      <pubDate>Thu, 16 Nov 2006 11:37:14 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-tru64-unix/physical-memory-management-performance-problems/m-p/3899587#M18026</guid>
      <dc:creator>Hugo Martins</dc:creator>
      <dc:date>2006-11-16T11:37:14Z</dc:date>
    </item>
    <item>
      <title>Re: Physical Memory management - Performance problems</title>
      <link>https://community.hpe.com/t5/operating-system-tru64-unix/physical-memory-management-performance-problems/m-p/3899588#M18027</link>
      <description>Please post the output of:&lt;BR /&gt;&lt;BR /&gt;sysconfig -q vm vm_swap_eager&lt;BR /&gt;sysconfig -q vm |grep free&lt;BR /&gt;&lt;BR /&gt;And when the "problem" starts:&lt;BR /&gt;swapon -s&lt;BR /&gt;vmstat 5 (At least 20 samples)</description>
      <pubDate>Thu, 16 Nov 2006 12:57:27 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-tru64-unix/physical-memory-management-performance-problems/m-p/3899588#M18027</guid>
      <dc:creator>Ivan Ferreira</dc:creator>
      <dc:date>2006-11-16T12:57:27Z</dc:date>
    </item>
    <item>
      <title>Re: Physical Memory management - Performance problems</title>
      <link>https://community.hpe.com/t5/operating-system-tru64-unix/physical-memory-management-performance-problems/m-p/3899589#M18028</link>
      <description>Here I send the log you ask for.&lt;BR /&gt;Thank you for the help.&lt;BR /&gt;&lt;BR /&gt;Hugo</description>
      <pubDate>Fri, 17 Nov 2006 15:49:11 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-tru64-unix/physical-memory-management-performance-problems/m-p/3899589#M18028</guid>
      <dc:creator>Hugo Martins</dc:creator>
      <dc:date>2006-11-17T15:49:11Z</dc:date>
    </item>
    <item>
      <title>Re: Physical Memory management - Performance problems</title>
      <link>https://community.hpe.com/t5/operating-system-tru64-unix/physical-memory-management-performance-problems/m-p/3899590#M18029</link>
      <description>You can try changing the swap allocation mode to avoid the "reservation" of space.&lt;BR /&gt;&lt;BR /&gt;Set vm_swap_eager to 0, to do that, do the following. Create a file called /tmp/sysconfig.stanza like this:&lt;BR /&gt;&lt;BR /&gt;vm:&lt;BR /&gt;  vm_swap_eager = 0&lt;BR /&gt;&lt;BR /&gt;Run the command:&lt;BR /&gt;&lt;BR /&gt;sysconfigdb -m -f /tmp/sysconfig.stanza&lt;BR /&gt;&lt;BR /&gt;Reboot the system.&lt;BR /&gt;&lt;BR /&gt;From the output I can see that your system is swapping, if your system continues swapping after this modification, probably you don't have enough RAM memory to support your load, or some application is using more memory than normal.</description>
      <pubDate>Tue, 21 Nov 2006 08:07:15 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-tru64-unix/physical-memory-management-performance-problems/m-p/3899590#M18029</guid>
      <dc:creator>Ivan Ferreira</dc:creator>
      <dc:date>2006-11-21T08:07:15Z</dc:date>
    </item>
    <item>
      <title>Re: Physical Memory management - Performance problems</title>
      <link>https://community.hpe.com/t5/operating-system-tru64-unix/physical-memory-management-performance-problems/m-p/3899591#M18030</link>
      <description>&lt;BR /&gt;It looks like dxsysinfo is confused or gives confusing output (I never use the tool). Try alternatives: collect+collgui; the vmstat you show; or vmubc perhaps.&lt;BR /&gt;&lt;BR /&gt;The VMSTAT output clearly shows a system which ran out of free memory, and the performance knee you describe matches that.&lt;BR /&gt;Free pages dropping to a fre hundred, and pout starting at the same time indicated overcommited memory.&lt;BR /&gt;&lt;BR /&gt;You can probably gain a little room by lowering vm: ubc_min from the 10 it appears to be down to 3 or 4, but that in turn may hurt performance.&lt;BR /&gt;&lt;BR /&gt;You need either to - buy more memory! - reduce the load, or - reduce the java memory usage by setting lower per process upper limites and chosing a more aggressive garbage collecting method/setting.&lt;BR /&gt;&lt;BR /&gt;Normally I like lazy swapping (eager=0), but here I don;t think it will help, and it may put the system stability at risk if the memory remains overcommited.&lt;BR /&gt;&lt;BR /&gt;Hth,&lt;BR /&gt;&lt;BR /&gt;Hein van den Heuvel&lt;BR /&gt;HvdH Performance Consulting&lt;BR /&gt;&lt;BR /&gt;</description>
      <pubDate>Tue, 21 Nov 2006 13:50:55 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-tru64-unix/physical-memory-management-performance-problems/m-p/3899591#M18030</guid>
      <dc:creator>Hein van den Heuvel</dc:creator>
      <dc:date>2006-11-21T13:50:55Z</dc:date>
    </item>
  </channel>
</rss>

