<?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: oprofile in Operating System - Linux</title>
    <link>https://community.hpe.com/t5/operating-system-linux/oprofile/m-p/4186473#M32326</link>
    <description>No, we're not using SAN disks.  We're using internal RAIDed disks in a DL580.  But thanks for the hint.  I'll check iostat.</description>
    <pubDate>Fri, 25 Apr 2008 14:26:18 GMT</pubDate>
    <dc:creator>Tim Yeung_1</dc:creator>
    <dc:date>2008-04-25T14:26:18Z</dc:date>
    <item>
      <title>oprofile</title>
      <link>https://community.hpe.com/t5/operating-system-linux/oprofile/m-p/4186471#M32324</link>
      <description>I ran oprofile on RHEL4U6 and got the following report.  What does cache refer to?  Is it referring to Linux memory cache or the processor L2 cache?  Why is my system spending so much time in cache?  Thanks.&lt;BR /&gt;&lt;BR /&gt;CPU: P4 / Xeon with 2 hyper-threads, speed 3000.38 MHz (estimated)&lt;BR /&gt;Counted GLOBAL_POWER_EVENTS events (time during which processor is not stopped) with a unit mask of 0x01 (mandatory) count 100000&lt;BR /&gt;GLOBAL_POWER_E...|&lt;BR /&gt;  samples|      %|&lt;BR /&gt;------------------&lt;BR /&gt; 14219190 78.5593 cache&lt;BR /&gt;  2596696 14.3464 vmlinux&lt;BR /&gt;   985675  5.4457 libc-2.3.4.so&lt;BR /&gt;   116542  0.6439 oprofiled&lt;BR /&gt;   105647  0.5837 tg3&lt;BR /&gt;    67943  0.3754 oprofile&lt;BR /&gt;     1601  0.0088 top&lt;BR /&gt;     1253  0.0069 ext3&lt;BR /&gt;     1064  0.0059 jbd&lt;BR /&gt;      769  0.0042 libproc-3.2.3.so&lt;BR /&gt;      713  0.0039 hald&lt;BR /&gt;      613  0.0034 libncurses.so.5.4&lt;BR /&gt;      443  0.0024 bash&lt;BR /&gt;      428  0.0024 uhci_hcd&lt;BR /&gt;      249  0.0014 ld-2.3.4.so&lt;BR /&gt;      216  0.0012 ehci_hcd&lt;BR /&gt;      121 6.7e-04 libcrypto.so.0.9.7a&lt;BR /&gt;      113 6.2e-04 cciss&lt;BR /&gt;       90 5.0e-04 libgobject-2.0.so.0.400.7&lt;BR /&gt;       85 4.7e-04 qla2xxx&lt;BR /&gt;</description>
      <pubDate>Thu, 24 Apr 2008 18:08:48 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-linux/oprofile/m-p/4186471#M32324</guid>
      <dc:creator>Tim Yeung_1</dc:creator>
      <dc:date>2008-04-24T18:08:48Z</dc:date>
    </item>
    <item>
      <title>Re: oprofile</title>
      <link>https://community.hpe.com/t5/operating-system-linux/oprofile/m-p/4186472#M32325</link>
      <description>Just a guess , but you are using fibre channel drives (qla2xxx) driver. Correct?&lt;BR /&gt;&lt;BR /&gt;I have seen huge cache hits. If the i/o to the FC drives is to high for the number of spindles attached to the LUN.&lt;BR /&gt;&lt;BR /&gt;Run iostat to see the usage. &lt;BR /&gt;&lt;BR /&gt;Are you using path management software (securepath , powerpath etc)&lt;BR /&gt;&lt;BR /&gt;Looks to me that a LUN is max'd out.&lt;BR /&gt;</description>
      <pubDate>Fri, 25 Apr 2008 09:15:02 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-linux/oprofile/m-p/4186472#M32325</guid>
      <dc:creator>Derek Whigham_1</dc:creator>
      <dc:date>2008-04-25T09:15:02Z</dc:date>
    </item>
    <item>
      <title>Re: oprofile</title>
      <link>https://community.hpe.com/t5/operating-system-linux/oprofile/m-p/4186473#M32326</link>
      <description>No, we're not using SAN disks.  We're using internal RAIDed disks in a DL580.  But thanks for the hint.  I'll check iostat.</description>
      <pubDate>Fri, 25 Apr 2008 14:26:18 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-linux/oprofile/m-p/4186473#M32326</guid>
      <dc:creator>Tim Yeung_1</dc:creator>
      <dc:date>2008-04-25T14:26:18Z</dc:date>
    </item>
    <item>
      <title>Re: oprofile</title>
      <link>https://community.hpe.com/t5/operating-system-linux/oprofile/m-p/4186474#M32327</link>
      <description>No it wasn't disks being saturated.  Turns out the application being run is called "cache".  That's what it was!&lt;BR /&gt;&lt;BR /&gt;</description>
      <pubDate>Fri, 25 Apr 2008 14:47:48 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-linux/oprofile/m-p/4186474#M32327</guid>
      <dc:creator>Tim Yeung_1</dc:creator>
      <dc:date>2008-04-25T14:47:48Z</dc:date>
    </item>
  </channel>
</rss>

