<?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: Witch Replication Protocol has better performance? in Disk Enclosures</title>
    <link>https://community.hpe.com/t5/disk-enclosures/witch-replication-protocol-has-better-performance/m-p/4759474#M37161</link>
    <description>Thanks for your answer.&lt;BR /&gt;This protocol option is only available from 09534000 and our EVAs have that version.&lt;BR /&gt;With Async mode, perhaps it is the better option, but we have Sync mode and so, every I/O has two round trips to acknowledgement operation.&lt;BR /&gt;So, I don't know if this time lost, having two round trips, is bigger than the time gained travelling for two ISL ports instead of only for one ISL port per fabric.&lt;BR /&gt;That is the question.</description>
    <pubDate>Tue, 01 Mar 2011 17:23:10 GMT</pubDate>
    <dc:creator>Luis J. Fernández</dc:creator>
    <dc:date>2011-03-01T17:23:10Z</dc:date>
    <item>
      <title>Witch Replication Protocol has better performance?</title>
      <link>https://community.hpe.com/t5/disk-enclosures/witch-replication-protocol-has-better-performance/m-p/4759472#M37159</link>
      <description>Two EVA8400 with FC SAN Switches with Port Channel configured with two ISL ports per switch.&lt;BR /&gt;With Protocol HP-FC (in order delivery) only one of the ISL ports in every port channel is used (active-pasive), but it is one round trip.&lt;BR /&gt;With Protocol HP-SCSI FCP (exchange delivery) both ISL ports in every Port channel are used (active-active), but is is two round trip.&lt;BR /&gt;Remote site is about 10KM far.&lt;BR /&gt;Wich protocol can have better performance?</description>
      <pubDate>Tue, 01 Mar 2011 10:15:32 GMT</pubDate>
      <guid>https://community.hpe.com/t5/disk-enclosures/witch-replication-protocol-has-better-performance/m-p/4759472#M37159</guid>
      <dc:creator>Luis J. Fernández</dc:creator>
      <dc:date>2011-03-01T10:15:32Z</dc:date>
    </item>
    <item>
      <title>Re: Witch Replication Protocol has better performance?</title>
      <link>https://community.hpe.com/t5/disk-enclosures/witch-replication-protocol-has-better-performance/m-p/4759473#M37160</link>
      <description>Make sure that EVA with Latest XCS - 9534 and select HP-SCSI (Exchnage based routing) which is the better performace method.&lt;BR /&gt;&lt;BR /&gt;I have confiured at one customer place with Async replicaiton and found good.&lt;BR /&gt;&lt;BR /&gt;</description>
      <pubDate>Tue, 01 Mar 2011 16:47:38 GMT</pubDate>
      <guid>https://community.hpe.com/t5/disk-enclosures/witch-replication-protocol-has-better-performance/m-p/4759473#M37160</guid>
      <dc:creator>Sivaramakrishna_1</dc:creator>
      <dc:date>2011-03-01T16:47:38Z</dc:date>
    </item>
    <item>
      <title>Re: Witch Replication Protocol has better performance?</title>
      <link>https://community.hpe.com/t5/disk-enclosures/witch-replication-protocol-has-better-performance/m-p/4759474#M37161</link>
      <description>Thanks for your answer.&lt;BR /&gt;This protocol option is only available from 09534000 and our EVAs have that version.&lt;BR /&gt;With Async mode, perhaps it is the better option, but we have Sync mode and so, every I/O has two round trips to acknowledgement operation.&lt;BR /&gt;So, I don't know if this time lost, having two round trips, is bigger than the time gained travelling for two ISL ports instead of only for one ISL port per fabric.&lt;BR /&gt;That is the question.</description>
      <pubDate>Tue, 01 Mar 2011 17:23:10 GMT</pubDate>
      <guid>https://community.hpe.com/t5/disk-enclosures/witch-replication-protocol-has-better-performance/m-p/4759474#M37161</guid>
      <dc:creator>Luis J. Fernández</dc:creator>
      <dc:date>2011-03-01T17:23:10Z</dc:date>
    </item>
  </channel>
</rss>

