<?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: fabric versus arbitrated loop in HPE EVA Storage</title>
    <link>https://community.hpe.com/t5/hpe-eva-storage/fabric-versus-arbitrated-loop/m-p/2805956#M1160</link>
    <description>Everyone is right but the biggest difference is that a 100 MB/sec loop hub can only do 100 MB/sec for all traffic on that hub.&lt;BR /&gt;&lt;BR /&gt;A 16 port switch should be able to do 100MB/sec per port (16 *100=total throughput).&lt;BR /&gt;&lt;BR /&gt;This is a very important difference. &lt;BR /&gt;&lt;BR /&gt;If you are using multiple computers which need to communicate at the same time to devices on the loop/fabric then go with fabric.&lt;BR /&gt;&lt;BR /&gt;If you need more throughput than 100MB/sec total then go fabric. &lt;BR /&gt;&lt;BR /&gt;Loops are good in active/passive cluster environments. Loop is much cheaper also.&lt;BR /&gt;&lt;BR /&gt;Quin</description>
    <pubDate>Mon, 07 Oct 2002 17:13:59 GMT</pubDate>
    <dc:creator>Quin Hammes</dc:creator>
    <dc:date>2002-10-07T17:13:59Z</dc:date>
    <item>
      <title>fabric versus arbitrated loop</title>
      <link>https://community.hpe.com/t5/hpe-eva-storage/fabric-versus-arbitrated-loop/m-p/2805951#M1155</link>
      <description>Hi! &lt;BR /&gt;I would like to get some information about fabric and arbitrated loop topology.&lt;BR /&gt;When do I have to choose one instead of the other one?&lt;BR /&gt;Could you give me some example?&lt;BR /&gt;Thank you.</description>
      <pubDate>Fri, 13 Sep 2002 12:35:38 GMT</pubDate>
      <guid>https://community.hpe.com/t5/hpe-eva-storage/fabric-versus-arbitrated-loop/m-p/2805951#M1155</guid>
      <dc:creator>HPADM</dc:creator>
      <dc:date>2002-09-13T12:35:38Z</dc:date>
    </item>
    <item>
      <title>Re: fabric versus arbitrated loop</title>
      <link>https://community.hpe.com/t5/hpe-eva-storage/fabric-versus-arbitrated-loop/m-p/2805952#M1156</link>
      <description>Hi,&lt;BR /&gt;&lt;BR /&gt;Try this link from ITRC cookbook,&lt;BR /&gt;&lt;BR /&gt;&lt;A href="http://us-support.external.hp.com/iv/data/documents/DE_SW_UX_swrec_EN_01_E/FibreChannel.pdf" target="_blank"&gt;http://us-support.external.hp.com/iv/data/documents/DE_SW_UX_swrec_EN_01_E/FibreChannel.pdf&lt;/A&gt;&lt;BR /&gt;&lt;BR /&gt;Hope this helps.&lt;BR /&gt;&lt;BR /&gt;Regds&lt;BR /&gt;</description>
      <pubDate>Fri, 13 Sep 2002 12:46:29 GMT</pubDate>
      <guid>https://community.hpe.com/t5/hpe-eva-storage/fabric-versus-arbitrated-loop/m-p/2805952#M1156</guid>
      <dc:creator>Sanjay_6</dc:creator>
      <dc:date>2002-09-13T12:46:29Z</dc:date>
    </item>
    <item>
      <title>Re: fabric versus arbitrated loop</title>
      <link>https://community.hpe.com/t5/hpe-eva-storage/fabric-versus-arbitrated-loop/m-p/2805953#M1157</link>
      <description>Hi&lt;BR /&gt;&lt;BR /&gt;Very short:&lt;BR /&gt;loop: HUB (loop) network,limited number of devices, workgroup and department solutions. &lt;BR /&gt;fabric: switched network, very large number of devices, enterprise solutions.&lt;BR /&gt;&lt;BR /&gt;Perhaps this link can give you a little help.&lt;BR /&gt;&lt;BR /&gt;&lt;A href="http://www.networkcomputing.com/1109/1109ws1.html" target="_blank"&gt;http://www.networkcomputing.com/1109/1109ws1.html&lt;/A&gt;&lt;BR /&gt;&lt;BR /&gt;There is plenty of information about this on Internet.&lt;BR /&gt;&lt;BR /&gt;</description>
      <pubDate>Fri, 13 Sep 2002 12:59:49 GMT</pubDate>
      <guid>https://community.hpe.com/t5/hpe-eva-storage/fabric-versus-arbitrated-loop/m-p/2805953#M1157</guid>
      <dc:creator>Leif Halvarsson_2</dc:creator>
      <dc:date>2002-09-13T12:59:49Z</dc:date>
    </item>
    <item>
      <title>Re: fabric versus arbitrated loop</title>
      <link>https://community.hpe.com/t5/hpe-eva-storage/fabric-versus-arbitrated-loop/m-p/2805954#M1158</link>
      <description>One thing to note about fabric vs loop...&lt;BR /&gt;&lt;BR /&gt;You can direct-attach from a host to a disk array or tape device via loop, but you cannot with fabric mode.&lt;BR /&gt;&lt;BR /&gt;As a general rule, I like to use loop only in direct-attach situations; if I've got a switch in the config, it's in Fabric mode.&lt;BR /&gt;&lt;BR /&gt;There are exceptions, however.  When working with older equipment ("older" here meaning about 2-3 years or older), often the older devices do not support Fabric mode, and you are therefore forced to use loop mode.  There are modes you can set in the switches to help in mixed-mode configurations.  Mixed-mode configs are something to be avoided, if possible.&lt;BR /&gt;&lt;BR /&gt;Good luck!&lt;BR /&gt;</description>
      <pubDate>Fri, 13 Sep 2002 13:43:22 GMT</pubDate>
      <guid>https://community.hpe.com/t5/hpe-eva-storage/fabric-versus-arbitrated-loop/m-p/2805954#M1158</guid>
      <dc:creator>Vincent Fleming</dc:creator>
      <dc:date>2002-09-13T13:43:22Z</dc:date>
    </item>
    <item>
      <title>Re: fabric versus arbitrated loop</title>
      <link>https://community.hpe.com/t5/hpe-eva-storage/fabric-versus-arbitrated-loop/m-p/2805955#M1159</link>
      <description>When using fabric, constant traffic will be able to stream from many devices and hosts, whereas using loop, only one device in the loop can actually transmit data. Others wishing to transmit data wait their turn. Direct connecting is okay using loop, but in a switch definitely use fabric.</description>
      <pubDate>Sat, 14 Sep 2002 06:55:37 GMT</pubDate>
      <guid>https://community.hpe.com/t5/hpe-eva-storage/fabric-versus-arbitrated-loop/m-p/2805955#M1159</guid>
      <dc:creator>Michael Tully</dc:creator>
      <dc:date>2002-09-14T06:55:37Z</dc:date>
    </item>
    <item>
      <title>Re: fabric versus arbitrated loop</title>
      <link>https://community.hpe.com/t5/hpe-eva-storage/fabric-versus-arbitrated-loop/m-p/2805956#M1160</link>
      <description>Everyone is right but the biggest difference is that a 100 MB/sec loop hub can only do 100 MB/sec for all traffic on that hub.&lt;BR /&gt;&lt;BR /&gt;A 16 port switch should be able to do 100MB/sec per port (16 *100=total throughput).&lt;BR /&gt;&lt;BR /&gt;This is a very important difference. &lt;BR /&gt;&lt;BR /&gt;If you are using multiple computers which need to communicate at the same time to devices on the loop/fabric then go with fabric.&lt;BR /&gt;&lt;BR /&gt;If you need more throughput than 100MB/sec total then go fabric. &lt;BR /&gt;&lt;BR /&gt;Loops are good in active/passive cluster environments. Loop is much cheaper also.&lt;BR /&gt;&lt;BR /&gt;Quin</description>
      <pubDate>Mon, 07 Oct 2002 17:13:59 GMT</pubDate>
      <guid>https://community.hpe.com/t5/hpe-eva-storage/fabric-versus-arbitrated-loop/m-p/2805956#M1160</guid>
      <dc:creator>Quin Hammes</dc:creator>
      <dc:date>2002-10-07T17:13:59Z</dc:date>
    </item>
    <item>
      <title>Re: fabric versus arbitrated loop</title>
      <link>https://community.hpe.com/t5/hpe-eva-storage/fabric-versus-arbitrated-loop/m-p/2805957#M1161</link>
      <description>From performance perspective,&lt;BR /&gt;Arbitrated loop is like Token Ring which means bandwidth is shared across all the devices in a loop whileas Fabric is switched network so that it guarantees non-blocking throughput across all the ports in the switch.&lt;BR /&gt; &lt;BR /&gt;</description>
      <pubDate>Wed, 09 Oct 2002 03:48:15 GMT</pubDate>
      <guid>https://community.hpe.com/t5/hpe-eva-storage/fabric-versus-arbitrated-loop/m-p/2805957#M1161</guid>
      <dc:creator>Insu Kim</dc:creator>
      <dc:date>2002-10-09T03:48:15Z</dc:date>
    </item>
    <item>
      <title>Re: fabric versus arbitrated loop</title>
      <link>https://community.hpe.com/t5/hpe-eva-storage/fabric-versus-arbitrated-loop/m-p/2805958#M1162</link>
      <description>I quoted the statement below in the book titled "Building SANs with Brocade Fabric switches".&lt;BR /&gt;&lt;BR /&gt;Hubs can be used on small SANs to interconnect devices in an arbitrated loop topology or connect two devices directly. Hubs should not be used when there is more than one active host, since there will be more competion for the limited bandwidth of the loop. The more hosts that are added to the loop, the less efficient it is, because a larger percentage of time is spent arbitrating for control of the loop than actually transmitting data.&lt;BR /&gt;Remember that a switch creates circuits to maximize bandwidth, while all devices plugged into a hub share the bandwitdh of one line.&lt;BR /&gt;&lt;BR /&gt;Hope this helps,</description>
      <pubDate>Sun, 13 Oct 2002 14:23:46 GMT</pubDate>
      <guid>https://community.hpe.com/t5/hpe-eva-storage/fabric-versus-arbitrated-loop/m-p/2805958#M1162</guid>
      <dc:creator>Insu Kim</dc:creator>
      <dc:date>2002-10-13T14:23:46Z</dc:date>
    </item>
  </channel>
</rss>

