<?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: Storage QoS in HPE Nimble Storage Solution Specialists</title>
    <link>https://community.hpe.com/t5/hpe-nimble-storage-solution/storage-qos/m-p/7135427#M406</link>
    <description>&lt;P&gt;We are experiencing this issue with multiple MSSQL AlwaysOn servers. It is a lot of IOs for a second and then it is quiet again for the rest of the minute and so it repeats.&lt;BR /&gt;&lt;span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="spikes.PNG" style="width: 1173px;"&gt;&lt;img src="https://community.hpe.com/t5/image/serverpage/image-id/123453i0F04707E2103AF3C/image-size/large?v=v2&amp;amp;px=2000" role="button" title="spikes.PNG" alt="spikes.PNG" /&gt;&lt;/span&gt;We resolved it by doubling the QoS limit, but it is still not going above what was the original QoS limit.&lt;span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="spikes2.PNG" style="width: 1148px;"&gt;&lt;img src="https://community.hpe.com/t5/image/serverpage/image-id/123456i9CEA792F9C74688D/image-size/large?v=v2&amp;amp;px=2000" role="button" title="spikes2.PNG" alt="spikes2.PNG" /&gt;&lt;/span&gt;&lt;/P&gt;</description>
    <pubDate>Fri, 21 May 2021 10:25:36 GMT</pubDate>
    <dc:creator>k_erik</dc:creator>
    <dc:date>2021-05-21T10:25:36Z</dc:date>
    <item>
      <title>Storage QoS</title>
      <link>https://community.hpe.com/t5/hpe-nimble-storage-solution/storage-qos/m-p/7134936#M403</link>
      <description>&lt;P&gt;Hi,&lt;/P&gt;&lt;P&gt;We use storage QoS on our Nimble arrays together with VMware vVols. Does anyone know exactly how the QoS works? I'm wondering if a VM has a 5000 IOPS limit and tries to push those 5000 IOs through in a tenth of a second.&lt;BR /&gt;Will they all go through quickly and if it tries 5001 IOs the last IO will get a latency of 900ms since it spills over into the next second?&lt;BR /&gt;Or will the first 5000 IOs be spread out throughout the whole second and we will see a small latency increase for most of the 5000 IOs?&lt;/P&gt;</description>
      <pubDate>Wed, 19 May 2021 07:21:35 GMT</pubDate>
      <guid>https://community.hpe.com/t5/hpe-nimble-storage-solution/storage-qos/m-p/7134936#M403</guid>
      <dc:creator>k_erik</dc:creator>
      <dc:date>2021-05-19T07:21:35Z</dc:date>
    </item>
    <item>
      <title>Re: Storage QoS</title>
      <link>https://community.hpe.com/t5/hpe-nimble-storage-solution/storage-qos/m-p/7135410#M405</link>
      <description>&lt;P&gt;As per my understanding, For example: If the IOPS limit on a Volume is set to 5000 IOPS, the array will always enforce this limit and cap the IOPS to 5000. Nimble Array will always ensure that the number of IOPS is capped to whatever the user has specified during the volume creation.&lt;/P&gt;&lt;P&gt;When the IOPS limit is set on a volume (ex: 5000 IOPS), Host may not even send IOs more than the specified limit (&amp;gt;5000).&lt;/P&gt;&lt;P&gt;Could you please let us know how you are testing this IOPS limitation on your Nimble in your envirounment so that we can try to replicate this scenario in our lab and give you better explanation.&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Fri, 21 May 2021 09:55:57 GMT</pubDate>
      <guid>https://community.hpe.com/t5/hpe-nimble-storage-solution/storage-qos/m-p/7135410#M405</guid>
      <dc:creator>Candhade</dc:creator>
      <dc:date>2021-05-21T09:55:57Z</dc:date>
    </item>
    <item>
      <title>Re: Storage QoS</title>
      <link>https://community.hpe.com/t5/hpe-nimble-storage-solution/storage-qos/m-p/7135427#M406</link>
      <description>&lt;P&gt;We are experiencing this issue with multiple MSSQL AlwaysOn servers. It is a lot of IOs for a second and then it is quiet again for the rest of the minute and so it repeats.&lt;BR /&gt;&lt;span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="spikes.PNG" style="width: 1173px;"&gt;&lt;img src="https://community.hpe.com/t5/image/serverpage/image-id/123453i0F04707E2103AF3C/image-size/large?v=v2&amp;amp;px=2000" role="button" title="spikes.PNG" alt="spikes.PNG" /&gt;&lt;/span&gt;We resolved it by doubling the QoS limit, but it is still not going above what was the original QoS limit.&lt;span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="spikes2.PNG" style="width: 1148px;"&gt;&lt;img src="https://community.hpe.com/t5/image/serverpage/image-id/123456i9CEA792F9C74688D/image-size/large?v=v2&amp;amp;px=2000" role="button" title="spikes2.PNG" alt="spikes2.PNG" /&gt;&lt;/span&gt;&lt;/P&gt;</description>
      <pubDate>Fri, 21 May 2021 10:25:36 GMT</pubDate>
      <guid>https://community.hpe.com/t5/hpe-nimble-storage-solution/storage-qos/m-p/7135427#M406</guid>
      <dc:creator>k_erik</dc:creator>
      <dc:date>2021-05-21T10:25:36Z</dc:date>
    </item>
  </channel>
</rss>

