<?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: Database Performance Comparison Tips in Operating System - HP-UX</title>
    <link>https://community.hpe.com/t5/operating-system-hp-ux/database-performance-comparison-tips/m-p/4475613#M662697</link>
    <description>I'm surprised your DBA isn't familiar with swingbench:&lt;BR /&gt;&lt;BR /&gt;&lt;A href="http://www.dominicgiles.com/swingbench.php" target="_blank"&gt;http://www.dominicgiles.com/swingbench.php&lt;/A&gt;&lt;BR /&gt;&lt;BR /&gt;I'm not sure how many of those tests you list swingbench does, but it's a reasonable starting point.&lt;BR /&gt;&lt;BR /&gt;Rememebr to run swingbench itself as a client on the same platform for all tests, otherwise you'll be skewing your tests by testing how good the Java stack is on each system as well...&lt;BR /&gt;&lt;BR /&gt;HTH&lt;BR /&gt;&lt;BR /&gt;Duncan</description>
    <pubDate>Sun, 09 Aug 2009 19:31:16 GMT</pubDate>
    <dc:creator>Duncan Edmonstone</dc:creator>
    <dc:date>2009-08-09T19:31:16Z</dc:date>
    <item>
      <title>Database Performance Comparison Tips</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/database-performance-comparison-tips/m-p/4475610#M662694</link>
      <description>DBA/Sysad Gurii,&lt;BR /&gt;&lt;BR /&gt;What could I tell my DBA as far as comparing DB performance between platforms (Itanium and PARISC and even Linux?) For the PARISC/Itanium comparison -- the same disksets and database will be used. For the Linux test -- the same database will be used but Endian converted to the Linux format.  All 3 Environments will use the exact same Storage Array with about the same FC Connections and storage layout.&lt;BR /&gt;&lt;BR /&gt;The server environments will be "fairly"  adjusted as to clock speed and CPU/Core count.&lt;BR /&gt;&lt;BR /&gt;Some of you may suggest -- why not just run your applications suite against the databases? Well -- we do not have that luxury. The DBA/Us must come up with a suite of SQL/DB stress testing acitivites to fully sterss out the Database so it exposes the total interaction of the platforms memory, busses, I/O, etc.&lt;BR /&gt;&lt;BR /&gt;I am thinking:&lt;BR /&gt;&lt;BR /&gt;- complex SQL with calculations&lt;BR /&gt;- updates&lt;BR /&gt;- db inserts&lt;BR /&gt;- complex joins&lt;BR /&gt;- RMAN backups, extracts...?&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;Any thoughts?</description>
      <pubDate>Fri, 07 Aug 2009 15:12:44 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/database-performance-comparison-tips/m-p/4475610#M662694</guid>
      <dc:creator>Alzhy</dc:creator>
      <dc:date>2009-08-07T15:12:44Z</dc:date>
    </item>
    <item>
      <title>Re: Database Performance Comparison Tips</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/database-performance-comparison-tips/m-p/4475611#M662695</link>
      <description>How about database querries.  &lt;BR /&gt;     We had a few here that were written so badly they could nearly stop a box cold on the older 10.20 version.  We saw improvement going from 10.20 to 11iv1.&lt;BR /&gt;&lt;BR /&gt;Try finding or creating a few really nasty querries that are either asking for too much or where statement forces full table lookups.  &lt;BR /&gt;&lt;BR /&gt;Just a thought,&lt;BR /&gt;Rita</description>
      <pubDate>Fri, 07 Aug 2009 16:42:12 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/database-performance-comparison-tips/m-p/4475611#M662695</guid>
      <dc:creator>Rita C Workman</dc:creator>
      <dc:date>2009-08-07T16:42:12Z</dc:date>
    </item>
    <item>
      <title>Re: Database Performance Comparison Tips</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/database-performance-comparison-tips/m-p/4475612#M662696</link>
      <description>I have no suggestions but I ask that you post your findings..&lt;BR /&gt;&lt;BR /&gt;I would find the results very interesting..&lt;BR /&gt;&lt;BR /&gt;Regards.&lt;BR /&gt;&lt;BR /&gt;</description>
      <pubDate>Fri, 07 Aug 2009 17:06:46 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/database-performance-comparison-tips/m-p/4475612#M662696</guid>
      <dc:creator>Tim Nelson</dc:creator>
      <dc:date>2009-08-07T17:06:46Z</dc:date>
    </item>
    <item>
      <title>Re: Database Performance Comparison Tips</title>
      <link>https://community.hpe.com/t5/operating-system-hp-ux/database-performance-comparison-tips/m-p/4475613#M662697</link>
      <description>I'm surprised your DBA isn't familiar with swingbench:&lt;BR /&gt;&lt;BR /&gt;&lt;A href="http://www.dominicgiles.com/swingbench.php" target="_blank"&gt;http://www.dominicgiles.com/swingbench.php&lt;/A&gt;&lt;BR /&gt;&lt;BR /&gt;I'm not sure how many of those tests you list swingbench does, but it's a reasonable starting point.&lt;BR /&gt;&lt;BR /&gt;Rememebr to run swingbench itself as a client on the same platform for all tests, otherwise you'll be skewing your tests by testing how good the Java stack is on each system as well...&lt;BR /&gt;&lt;BR /&gt;HTH&lt;BR /&gt;&lt;BR /&gt;Duncan</description>
      <pubDate>Sun, 09 Aug 2009 19:31:16 GMT</pubDate>
      <guid>https://community.hpe.com/t5/operating-system-hp-ux/database-performance-comparison-tips/m-p/4475613#M662697</guid>
      <dc:creator>Duncan Edmonstone</dc:creator>
      <dc:date>2009-08-09T19:31:16Z</dc:date>
    </item>
  </channel>
</rss>

