<?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: EVA6000 I/O calculation in Disk Enclosures</title>
    <link>https://community.hpe.com/t5/disk-enclosures/eva6000-i-o-calculation/m-p/3705408#M19047</link>
    <description>The EVA6000 uses the same controller (HSV200) like the EVA4000 - the controller does not know if it is working in an EVA4000 or 6000 ;-)&lt;BR /&gt;&lt;BR /&gt;The EVA3000/5000 use a chunk size of 128 KBytes - my guess is that the 4000/6000/8000 use the same size.&lt;BR /&gt;&lt;BR /&gt;The formular only makes sense for large sequential transfers - random I/Os with large seek distances will kill result in smaller MB/s throughput.</description>
    <pubDate>Mon, 09 Jan 2006 15:34:36 GMT</pubDate>
    <dc:creator>Uwe Zessin</dc:creator>
    <dc:date>2006-01-09T15:34:36Z</dc:date>
    <item>
      <title>EVA6000 I/O calculation</title>
      <link>https://community.hpe.com/t5/disk-enclosures/eva6000-i-o-calculation/m-p/3705406#M19045</link>
      <description>Hello Everybody,&lt;BR /&gt;I want to calculate I/O bandwidth of my disk array. It is an EVA 6000 with 28 disks.&lt;BR /&gt;I found the following link in regards of my question. In the below link Uwe, offer a formula:  &lt;BR /&gt;I/O bandwidth / number of disk / chunk size =IOPS&lt;BR /&gt;They talked about an EVA 4000.&lt;BR /&gt;&lt;A href="http://forums1.itrc.hp.com/service/forums/questionanswer.do?threadId=977114" target="_blank"&gt;http://forums1.itrc.hp.com/service/forums/questionanswer.do?threadId=977114&lt;/A&gt;&lt;BR /&gt;Now, I want to calculate maximum I/O bandwidth of my EVA with that formula. However I do not know what chunk size is and how much IOPS each 15rpm disk has.&lt;BR /&gt;Please advice.&lt;BR /&gt;</description>
      <pubDate>Mon, 09 Jan 2006 13:20:39 GMT</pubDate>
      <guid>https://community.hpe.com/t5/disk-enclosures/eva6000-i-o-calculation/m-p/3705406#M19045</guid>
      <dc:creator>Hasan_9</dc:creator>
      <dc:date>2006-01-09T13:20:39Z</dc:date>
    </item>
    <item>
      <title>Re: EVA6000 I/O calculation</title>
      <link>https://community.hpe.com/t5/disk-enclosures/eva6000-i-o-calculation/m-p/3705407#M19046</link>
      <description>EVAs uses fixed 256k chunk size, but I don't know if that formula will give you the real IOPS that the EVA will perform. For the I/O bandwidth, check the eva quickspecs.</description>
      <pubDate>Mon, 09 Jan 2006 14:52:54 GMT</pubDate>
      <guid>https://community.hpe.com/t5/disk-enclosures/eva6000-i-o-calculation/m-p/3705407#M19046</guid>
      <dc:creator>Ivan Ferreira</dc:creator>
      <dc:date>2006-01-09T14:52:54Z</dc:date>
    </item>
    <item>
      <title>Re: EVA6000 I/O calculation</title>
      <link>https://community.hpe.com/t5/disk-enclosures/eva6000-i-o-calculation/m-p/3705408#M19047</link>
      <description>The EVA6000 uses the same controller (HSV200) like the EVA4000 - the controller does not know if it is working in an EVA4000 or 6000 ;-)&lt;BR /&gt;&lt;BR /&gt;The EVA3000/5000 use a chunk size of 128 KBytes - my guess is that the 4000/6000/8000 use the same size.&lt;BR /&gt;&lt;BR /&gt;The formular only makes sense for large sequential transfers - random I/Os with large seek distances will kill result in smaller MB/s throughput.</description>
      <pubDate>Mon, 09 Jan 2006 15:34:36 GMT</pubDate>
      <guid>https://community.hpe.com/t5/disk-enclosures/eva6000-i-o-calculation/m-p/3705408#M19047</guid>
      <dc:creator>Uwe Zessin</dc:creator>
      <dc:date>2006-01-09T15:34:36Z</dc:date>
    </item>
    <item>
      <title>Re: EVA6000 I/O calculation</title>
      <link>https://community.hpe.com/t5/disk-enclosures/eva6000-i-o-calculation/m-p/3705409#M19048</link>
      <description>Uwe is right, my mistake, The chunk size is 128KB (256 blocks), fixed.</description>
      <pubDate>Mon, 09 Jan 2006 15:47:17 GMT</pubDate>
      <guid>https://community.hpe.com/t5/disk-enclosures/eva6000-i-o-calculation/m-p/3705409#M19048</guid>
      <dc:creator>Ivan Ferreira</dc:creator>
      <dc:date>2006-01-09T15:47:17Z</dc:date>
    </item>
    <item>
      <title>Re: EVA6000 I/O calculation</title>
      <link>https://community.hpe.com/t5/disk-enclosures/eva6000-i-o-calculation/m-p/3705410#M19049</link>
      <description>Thank you all,&lt;BR /&gt;How much IOPS does a single 15K disk has? What about 10k disk?What can be the maximum IOPS of a disk?</description>
      <pubDate>Mon, 09 Jan 2006 23:43:40 GMT</pubDate>
      <guid>https://community.hpe.com/t5/disk-enclosures/eva6000-i-o-calculation/m-p/3705410#M19049</guid>
      <dc:creator>Hasan_9</dc:creator>
      <dc:date>2006-01-09T23:43:40Z</dc:date>
    </item>
    <item>
      <title>Re: EVA6000 I/O calculation</title>
      <link>https://community.hpe.com/t5/disk-enclosures/eva6000-i-o-calculation/m-p/3705411#M19050</link>
      <description>I have multiple EVA5K, and can consistently get 500MB/second on some of these.  It seems to be a never ending battle to break 520MB/s and to keep this level of performance from multiple EVA's consecutively.  Usually get 1 at 480 and another at 510, with a 3rd at 350, and others hardly reporting any.  relocate, rerun, and still get hot spots, though I can move from one to another.  Still working with dba to tune.</description>
      <pubDate>Wed, 11 Jan 2006 12:10:17 GMT</pubDate>
      <guid>https://community.hpe.com/t5/disk-enclosures/eva6000-i-o-calculation/m-p/3705411#M19050</guid>
      <dc:creator>Pat Obrien_1</dc:creator>
      <dc:date>2006-01-11T12:10:17Z</dc:date>
    </item>
  </channel>
</rss>

