<?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: Raid 5 performance in Disk</title>
    <link>https://community.hpe.com/t5/disk/raid-5-performance/m-p/3679696#M5881</link>
    <description>Lee it will depend on the intended use. Is your application write heavy.  How frequently will you be accessing your data.&lt;BR /&gt;Perhaps if you describe your intentions for the LUN we can tell you if it will help.&lt;BR /&gt;&lt;BR /&gt;Read performance from all RAID levels is about the same, with exception of RAID 1 or RAID 1+0. Here you will see a slight increase due to load balancing. &lt;BR /&gt;&lt;BR /&gt;</description>
    <pubDate>Thu, 01 Dec 2005 09:17:51 GMT</pubDate>
    <dc:creator>John Kufrovich</dc:creator>
    <dc:date>2005-12-01T09:17:51Z</dc:date>
    <item>
      <title>Raid 5 performance</title>
      <link>https://community.hpe.com/t5/disk/raid-5-performance/m-p/3679690#M5875</link>
      <description>It was mentioned to me by a fellow tech that when using Raid 5, you should use a minimum of 4 drives. Using only 3 causes poor performance, and going to 4 makes a large difference. Can anyone support this?</description>
      <pubDate>Sun, 27 Nov 2005 22:37:26 GMT</pubDate>
      <guid>https://community.hpe.com/t5/disk/raid-5-performance/m-p/3679690#M5875</guid>
      <dc:creator>Lee J milam</dc:creator>
      <dc:date>2005-11-27T22:37:26Z</dc:date>
    </item>
    <item>
      <title>Re: Raid 5 performance</title>
      <link>https://community.hpe.com/t5/disk/raid-5-performance/m-p/3679691#M5876</link>
      <description>Hi Lee!&lt;BR /&gt;&lt;BR /&gt;Note, that RAID5 level have the poorest write perfomance in comparsion RAID 1,10,0.&lt;BR /&gt;Increasing the number of disks in RAID5  array we can improve read perfomance.</description>
      <pubDate>Mon, 28 Nov 2005 03:17:25 GMT</pubDate>
      <guid>https://community.hpe.com/t5/disk/raid-5-performance/m-p/3679691#M5876</guid>
      <dc:creator>Ruslan</dc:creator>
      <dc:date>2005-11-28T03:17:25Z</dc:date>
    </item>
    <item>
      <title>Re: Raid 5 performance</title>
      <link>https://community.hpe.com/t5/disk/raid-5-performance/m-p/3679692#M5877</link>
      <description>As more drives in the array, the better the performance, but you still can use 3 disks in the array. If you will use 3 disks, ensure that the disks are the fastest, like 15k rpm scsi.&lt;BR /&gt;&lt;BR /&gt;Also, as said above, you will improve read performance, write performance is reduced by the parity calculation.</description>
      <pubDate>Mon, 28 Nov 2005 07:08:51 GMT</pubDate>
      <guid>https://community.hpe.com/t5/disk/raid-5-performance/m-p/3679692#M5877</guid>
      <dc:creator>Ivan Ferreira</dc:creator>
      <dc:date>2005-11-28T07:08:51Z</dc:date>
    </item>
    <item>
      <title>Re: Raid 5 performance</title>
      <link>https://community.hpe.com/t5/disk/raid-5-performance/m-p/3679693#M5878</link>
      <description>What also wil help is a lot of cache esspecialy for the writes.&lt;BR /&gt;&lt;BR /&gt;Writes wil be writen driectly to cache and will be destaged later, like a XP storage system. &lt;BR /&gt;&lt;BR /&gt;Other systems like the EVA's works differtly. They need a lot of disks to create performance.</description>
      <pubDate>Mon, 28 Nov 2005 08:38:08 GMT</pubDate>
      <guid>https://community.hpe.com/t5/disk/raid-5-performance/m-p/3679693#M5878</guid>
      <dc:creator>Fabian_Nowee</dc:creator>
      <dc:date>2005-11-28T08:38:08Z</dc:date>
    </item>
    <item>
      <title>Re: Raid 5 performance</title>
      <link>https://community.hpe.com/t5/disk/raid-5-performance/m-p/3679694#M5879</link>
      <description>These are all good points, but I know about these. My core question is weather there is a big improvement with 4 or more drives over 3 drives in a raid 5.</description>
      <pubDate>Wed, 30 Nov 2005 23:56:28 GMT</pubDate>
      <guid>https://community.hpe.com/t5/disk/raid-5-performance/m-p/3679694#M5879</guid>
      <dc:creator>Lee J milam</dc:creator>
      <dc:date>2005-11-30T23:56:28Z</dc:date>
    </item>
    <item>
      <title>Re: Raid 5 performance</title>
      <link>https://community.hpe.com/t5/disk/raid-5-performance/m-p/3679695#M5880</link>
      <description>I think that you won't see an amazing change, but the performance should increase. The theory implies that, but only with real tests you will measure the performance increase.</description>
      <pubDate>Thu, 01 Dec 2005 01:23:26 GMT</pubDate>
      <guid>https://community.hpe.com/t5/disk/raid-5-performance/m-p/3679695#M5880</guid>
      <dc:creator>Ivan Ferreira</dc:creator>
      <dc:date>2005-12-01T01:23:26Z</dc:date>
    </item>
    <item>
      <title>Re: Raid 5 performance</title>
      <link>https://community.hpe.com/t5/disk/raid-5-performance/m-p/3679696#M5881</link>
      <description>Lee it will depend on the intended use. Is your application write heavy.  How frequently will you be accessing your data.&lt;BR /&gt;Perhaps if you describe your intentions for the LUN we can tell you if it will help.&lt;BR /&gt;&lt;BR /&gt;Read performance from all RAID levels is about the same, with exception of RAID 1 or RAID 1+0. Here you will see a slight increase due to load balancing. &lt;BR /&gt;&lt;BR /&gt;</description>
      <pubDate>Thu, 01 Dec 2005 09:17:51 GMT</pubDate>
      <guid>https://community.hpe.com/t5/disk/raid-5-performance/m-p/3679696#M5881</guid>
      <dc:creator>John Kufrovich</dc:creator>
      <dc:date>2005-12-01T09:17:51Z</dc:date>
    </item>
  </channel>
</rss>

