<?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 System Performance in Operating System - Linux</title>
    <link>https://community.hpe.com/t5/operating-system-linux/system-performance/m-p/3696612#M67362</link>
    <description>Environment: Itanium rx4640 is connected with MSA1000 storage using Qlogic 2300 HBA. Red Hat Linux enterprise server 3.0 (64 bit) is installed with update 4 on the server.&lt;BR /&gt;&lt;BR /&gt;Problem Detail: User is complaining for system performance, comparing HP Itanium performance with Itanium of IBM (P4, P5 series) using  different commands of unix like cpio,ls,cp etc. After cpio command, System goes for processing &amp;amp; doesnot allow to work on other&lt;BR /&gt;session(s)even we can't give simple ls command.During this process system CPU &amp;amp; memory resources are on 100%. Also experiencing slow performance comparatively to IBM one for other tasks performed.Did Any body knows/face these kind of issue,please help.&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;</description>
    <pubDate>Thu, 22 Dec 2005 04:52:10 GMT</pubDate>
    <dc:creator>Muhammad Kashif</dc:creator>
    <dc:date>2005-12-22T04:52:10Z</dc:date>
    <item>
      <title>System Performance</title>
      <link>https://community.hpe.com/t5/operating-system-linux/system-performance/m-p/3696612#M67362</link>
      <description>Environment: Itanium rx4640 is connected with MSA1000 storage using Qlogic 2300 HBA. Red Hat Linux enterprise server 3.0 (64 bit) is installed with update 4 on the server.&lt;BR /&gt;&lt;BR /&gt;Problem Detail: User is complaining for system performance, comparing HP Itanium performance with Itanium of IBM (P4, P5 series) using  different commands of unix like cpio,ls,cp etc. After cpio command, System goes for processing &amp;amp; doesnot allow to work on other&lt;BR /&gt;session(s)even we can't give simple ls command.During this process system CPU &amp;amp; memory resources are on 100%. Also experiencing slow performance comparatively to IBM one for other tasks performed.Did Any body knows/face these kind of issue,please help.&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;</description>
      <pubDate>Thu, 22 Dec 2005 04:52:10 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-linux/system-performance/m-p/3696612#M67362</guid>
      <dc:creator>Muhammad Kashif</dc:creator>
      <dc:date>2005-12-22T04:52:10Z</dc:date>
    </item>
    <item>
      <title>Re: System Performance</title>
      <link>https://community.hpe.com/t5/operating-system-linux/system-performance/m-p/3696613#M67363</link>
      <description>Hi Muhammad,&lt;BR /&gt;&lt;BR /&gt;i have not direct experience on this kind of platform/os, but hanging around with google &lt;BR /&gt;i find this&lt;BR /&gt;&lt;A href="https://bugzilla.redhat.com/bugzilla/show_bug.cgi?id=120262" target="_blank"&gt;https://bugzilla.redhat.com/bugzilla/show_bug.cgi?id=120262&lt;/A&gt;&lt;BR /&gt;that talking about specific driver but then &lt;BR /&gt;redirect to&lt;BR /&gt;&lt;A href="http://rhn.redhat.com/errata/RHBA-2004-550.html" target="_blank"&gt;http://rhn.redhat.com/errata/RHBA-2004-550.html&lt;/A&gt;&lt;BR /&gt;where the solution step is , be carefully,&lt;BR /&gt;to update kernel.&lt;BR /&gt;&lt;BR /&gt;In my opinion this can be a road to follow.&lt;BR /&gt;&lt;BR /&gt;regards&lt;BR /&gt;</description>
      <pubDate>Thu, 22 Dec 2005 06:00:46 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-linux/system-performance/m-p/3696613#M67363</guid>
      <dc:creator>Piergiacomo Perini</dc:creator>
      <dc:date>2005-12-22T06:00:46Z</dc:date>
    </item>
    <item>
      <title>Re: System Performance</title>
      <link>https://community.hpe.com/t5/operating-system-linux/system-performance/m-p/3696614#M67364</link>
      <description>Shalom Muhammad,&lt;BR /&gt;&lt;BR /&gt;I recommend patching the system up fully and making sure the MSA1000 has firmware of 4.48 or above.&lt;BR /&gt;&lt;BR /&gt;SEP</description>
      <pubDate>Thu, 22 Dec 2005 09:54:16 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-linux/system-performance/m-p/3696614#M67364</guid>
      <dc:creator>Steven E. Protter</dc:creator>
      <dc:date>2005-12-22T09:54:16Z</dc:date>
    </item>
    <item>
      <title>Re: System Performance</title>
      <link>https://community.hpe.com/t5/operating-system-linux/system-performance/m-p/3696615#M67365</link>
      <description>Use top, iostat, and vmstat to see the nature of the bottleneck.  It could be memory, disk I/O, or CPU, so until you know which it is hard to comment.  Is the IBM using an MSA1000 for storage?  If not, what is it using?  How much memory is on each system.  What are the clock rates for the IBM versus Itanium processors?  Are there any page outs on the system?</description>
      <pubDate>Thu, 22 Dec 2005 21:18:46 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-linux/system-performance/m-p/3696615#M67365</guid>
      <dc:creator>Ted Buis</dc:creator>
      <dc:date>2005-12-22T21:18:46Z</dc:date>
    </item>
    <item>
      <title>Re: System Performance</title>
      <link>https://community.hpe.com/t5/operating-system-linux/system-performance/m-p/3696616#M67366</link>
      <description>Hi,&lt;BR /&gt;&lt;BR /&gt;These symptoms can also relate to some misconfigured kernel / file system parameters. Monitor these using iostat /vmstat and sar and then fine tune accordingly. Also a wrong code can cause the system to behave like this.&lt;BR /&gt;&lt;BR /&gt;HTH,&lt;BR /&gt;Devender</description>
      <pubDate>Fri, 23 Dec 2005 04:01:37 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-linux/system-performance/m-p/3696616#M67366</guid>
      <dc:creator>Devender Khatana</dc:creator>
      <dc:date>2005-12-23T04:01:37Z</dc:date>
    </item>
    <item>
      <title>Re: System Performance</title>
      <link>https://community.hpe.com/t5/operating-system-linux/system-performance/m-p/3696617#M67367</link>
      <description>Hi...&lt;BR /&gt;&lt;BR /&gt;running into the exact same problem here on the exact same platforms.  Here's what we've had to do:&lt;BR /&gt;&lt;BR /&gt;run rhel4U2&lt;BR /&gt;&lt;BR /&gt;update the QLA drivers to the HP versions&lt;BR /&gt;&lt;BR /&gt;upgrade the QLA firmware&lt;BR /&gt;&lt;BR /&gt;increase the queue lengths on the MSA to avoid contention&lt;BR /&gt;&lt;BR /&gt;reduce the load drastically on the Brocade switch, or else run reverse hlpa directly between the 4640 and the MSA (not useful for most situations, FWIW).&lt;BR /&gt;&lt;BR /&gt;You might also want to check the Hazard testing forums (hazard.boi.hp.com) for more information.</description>
      <pubDate>Fri, 23 Dec 2005 10:23:06 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-linux/system-performance/m-p/3696617#M67367</guid>
      <dc:creator>Alan_152</dc:creator>
      <dc:date>2005-12-23T10:23:06Z</dc:date>
    </item>
  </channel>
</rss>

