<?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: Does Raid level decides the Host read/write performace to storage disk in HPE EVA Storage</title>
    <link>https://community.hpe.com/t5/hpe-eva-storage/does-raid-level-decides-the-host-read-write-performace-to/m-p/4582003#M42804</link>
    <description>It really depends, but in general yes.&lt;BR /&gt;&lt;BR /&gt;Rule of thumb - RAID 5 slow writes, reads fast.</description>
    <pubDate>Thu, 11 Feb 2010 06:53:20 GMT</pubDate>
    <dc:creator>Torsten.</dc:creator>
    <dc:date>2010-02-11T06:53:20Z</dc:date>
    <item>
      <title>Does Raid level decides the Host read/write performace to storage disk</title>
      <link>https://community.hpe.com/t5/hpe-eva-storage/does-raid-level-decides-the-host-read-write-performace-to/m-p/4582002#M42803</link>
      <description>&lt;!--!*#--&gt;Hi Experts,&lt;BR /&gt;&lt;BR /&gt;Greetings for the day&lt;BR /&gt;&lt;BR /&gt;Does Raid level decides the host read/write performance to storage disk. Considering that on high end storages which has huge number of redundant cache and acknowledgment is given back to host as soon as the data is written to cache, choice of raid level should not play a significant role ?&lt;BR /&gt;&lt;BR /&gt;Appreciate any thoughts in this regard.&lt;BR /&gt;&lt;BR /&gt;Thanks&lt;BR /&gt;&lt;BR /&gt;Ranjith</description>
      <pubDate>Thu, 11 Feb 2010 06:49:04 GMT</pubDate>
      <guid>https://community.hpe.com/t5/hpe-eva-storage/does-raid-level-decides-the-host-read-write-performace-to/m-p/4582002#M42803</guid>
      <dc:creator>Ranjith M</dc:creator>
      <dc:date>2010-02-11T06:49:04Z</dc:date>
    </item>
    <item>
      <title>Re: Does Raid level decides the Host read/write performace to storage disk</title>
      <link>https://community.hpe.com/t5/hpe-eva-storage/does-raid-level-decides-the-host-read-write-performace-to/m-p/4582003#M42804</link>
      <description>It really depends, but in general yes.&lt;BR /&gt;&lt;BR /&gt;Rule of thumb - RAID 5 slow writes, reads fast.</description>
      <pubDate>Thu, 11 Feb 2010 06:53:20 GMT</pubDate>
      <guid>https://community.hpe.com/t5/hpe-eva-storage/does-raid-level-decides-the-host-read-write-performace-to/m-p/4582003#M42804</guid>
      <dc:creator>Torsten.</dc:creator>
      <dc:date>2010-02-11T06:53:20Z</dc:date>
    </item>
    <item>
      <title>Re: Does Raid level decides the Host read/write performace to storage disk</title>
      <link>https://community.hpe.com/t5/hpe-eva-storage/does-raid-level-decides-the-host-read-write-performace-to/m-p/4582004#M42805</link>
      <description>Yes it does to a point.&lt;BR /&gt;&lt;BR /&gt;If you have RAID 1 (mirroring on the controller) then a write needs to be sent to both disks.  Controllers should be able to send these to both disks at the same time unless the disks are on the same SCSI bus.&lt;BR /&gt;&lt;BR /&gt;On RAID 5 a write to a disk really could cause 4 disk I/Os worst case.  When you write a block you need to update the parity block as well.  To update the parity you need to read the old parity and the old data.  So worse case is 2 reads and 2 writes for every write.  There are a lot of optimizations that controllers do to reduce this but you need to realize that if you are driving the disk subsystem hard with a high amount of writes you could end up swamping it.</description>
      <pubDate>Fri, 19 Feb 2010 07:19:31 GMT</pubDate>
      <guid>https://community.hpe.com/t5/hpe-eva-storage/does-raid-level-decides-the-host-read-write-performace-to/m-p/4582004#M42805</guid>
      <dc:creator>Cass Witkowski</dc:creator>
      <dc:date>2010-02-19T07:19:31Z</dc:date>
    </item>
  </channel>
</rss>

