<?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: Linux performance - Please suggest. in Operating System - Linux</title>
    <link>https://community.hpe.com/t5/operating-system-linux/linux-performance-please-suggest/m-p/4144783#M31633</link>
    <description>Shalom,&lt;BR /&gt;&lt;BR /&gt;Al I/O is going through the host system. I am not surprised at all with the results. I'm guessing the host OS is Windows which is using a lot of system resources for itself.&lt;BR /&gt;&lt;BR /&gt;SEP</description>
    <pubDate>Thu, 14 Feb 2008 13:18:35 GMT</pubDate>
    <dc:creator>Steven E. Protter</dc:creator>
    <dc:date>2008-02-14T13:18:35Z</dc:date>
    <item>
      <title>Linux performance - Please suggest.</title>
      <link>https://community.hpe.com/t5/operating-system-linux/linux-performance-please-suggest/m-p/4144781#M31631</link>
      <description>Hi,&lt;BR /&gt;&lt;BR /&gt;Please give your suggestion or opinion.&lt;BR /&gt;&lt;BR /&gt;We are running grep command on a 256MB file from a diskless client (SuSE) and the VMware virtual machine (RHEL4, VM is on ESX host). The file resides on an NFS share and both the servers have NFS share mounted on them.  With respect to resources (CPU - 1 X 2GHz &amp;amp; memory - 1GB), both are similar.&lt;BR /&gt;&lt;BR /&gt;The diskless client is better off than the VMware virtual machine.  Find below the details:&lt;BR /&gt;&lt;BR /&gt;Diskless client&lt;BR /&gt;===============&lt;BR /&gt;time grep -c "MESSAGES"&lt;BR /&gt;/crawls/crawl02/bviewer-new/boards/&lt;A href="http://www.weightwatchers.com/boardviewer.script" target="_blank"&gt;www.weightwatchers.com/boardviewer.script&lt;/A&gt; | sort | uniq -c&lt;BR /&gt;&lt;BR /&gt;      1 5394438&lt;BR /&gt;&lt;BR /&gt; &lt;BR /&gt;&lt;BR /&gt;real    0m1.229s&lt;BR /&gt;&lt;BR /&gt;user    0m1.080s&lt;BR /&gt;&lt;BR /&gt;sys     0m0.150s&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;VMware Virtual Machine&lt;BR /&gt;======================&lt;BR /&gt;&lt;BR /&gt;time grep -c "MESSAGES"&lt;BR /&gt;/crawls/bviewer-sync/boards/&lt;A href="http://www.weightwatchers.com/boardviewer.script" target="_blank"&gt;www.weightwatchers.com/boardviewer.script&lt;/A&gt; | sort | uniq -c&lt;BR /&gt;&lt;BR /&gt;      1 5394438&lt;BR /&gt;&lt;BR /&gt; &lt;BR /&gt;&lt;BR /&gt;real    0m23.688s&lt;BR /&gt;&lt;BR /&gt;user    0m23.112s&lt;BR /&gt;&lt;BR /&gt;sys     0m0.520s</description>
      <pubDate>Thu, 14 Feb 2008 01:46:13 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-linux/linux-performance-please-suggest/m-p/4144781#M31631</guid>
      <dc:creator>GnanaShekar</dc:creator>
      <dc:date>2008-02-14T01:46:13Z</dc:date>
    </item>
    <item>
      <title>Re: Linux performance - Please suggest.</title>
      <link>https://community.hpe.com/t5/operating-system-linux/linux-performance-please-suggest/m-p/4144782#M31632</link>
      <description>.. except one is a virtual machine going through various levels of abstraction before it gets to hardware (in particular network) devices, where as the other one might not have a disk, but it has direct access to the network ..&lt;BR /&gt;&lt;BR /&gt;At no time have you said how big the 'boardviewer.script' file is.  Nor have you stated how busy the network is, or what sort of network connections are in use.&lt;BR /&gt;&lt;BR /&gt;You've also not said how much memory each machine is currently using, or is swapped on each device.</description>
      <pubDate>Thu, 14 Feb 2008 03:12:04 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-linux/linux-performance-please-suggest/m-p/4144782#M31632</guid>
      <dc:creator>Stuart Browne</dc:creator>
      <dc:date>2008-02-14T03:12:04Z</dc:date>
    </item>
    <item>
      <title>Re: Linux performance - Please suggest.</title>
      <link>https://community.hpe.com/t5/operating-system-linux/linux-performance-please-suggest/m-p/4144783#M31633</link>
      <description>Shalom,&lt;BR /&gt;&lt;BR /&gt;Al I/O is going through the host system. I am not surprised at all with the results. I'm guessing the host OS is Windows which is using a lot of system resources for itself.&lt;BR /&gt;&lt;BR /&gt;SEP</description>
      <pubDate>Thu, 14 Feb 2008 13:18:35 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-linux/linux-performance-please-suggest/m-p/4144783#M31633</guid>
      <dc:creator>Steven E. Protter</dc:creator>
      <dc:date>2008-02-14T13:18:35Z</dc:date>
    </item>
    <item>
      <title>Re: Linux performance - Please suggest.</title>
      <link>https://community.hpe.com/t5/operating-system-linux/linux-performance-please-suggest/m-p/4144784#M31634</link>
      <description>How is your vmfs file? There are two posibilities to use it, as a "fat" file, looks like a oracle or sql datafile. In this mode you can gain a little bit of I/O.&lt;BR /&gt;&lt;BR /&gt;But remember, there's a virtualization layer. All the I/O process in virtualization are lower then the bare-metal. Virtualization was designed for better utilization of procs, memory and disks, not for performance.&lt;BR /&gt;&lt;BR /&gt;Rgds</description>
      <pubDate>Thu, 14 Feb 2008 23:53:39 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-linux/linux-performance-please-suggest/m-p/4144784#M31634</guid>
      <dc:creator>Venilton Junior</dc:creator>
      <dc:date>2008-02-14T23:53:39Z</dc:date>
    </item>
    <item>
      <title>Re: Linux performance - Please suggest.</title>
      <link>https://community.hpe.com/t5/operating-system-linux/linux-performance-please-suggest/m-p/4144785#M31635</link>
      <description>what did you expect? Virtualization surely has a price, unless you believe the marketing/sales talk ofcourse.&lt;BR /&gt;&lt;BR /&gt;you are sharing resources to start with, the devices presented in your VM are 'virtual' as well.&lt;BR /&gt;&lt;BR /&gt;could be that there are some params you can tune in the RH running in a VM to make it perform better, but i wouldn't count in it too much.</description>
      <pubDate>Fri, 15 Feb 2008 13:21:02 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-linux/linux-performance-please-suggest/m-p/4144785#M31635</guid>
      <dc:creator>dirk dierickx</dc:creator>
      <dc:date>2008-02-15T13:21:02Z</dc:date>
    </item>
  </channel>
</rss>

