<?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: Increasing Splunks Search performance on Linux in Deployment Architecture</title>
    <link>https://community.splunk.com/t5/Deployment-Architecture/Increasing-Splunks-Search-performance-on-Linux/m-p/89042#M3241</link>
    <description>&lt;P&gt;Personally, I would install multiple Splunk Indexers listening on different ports with the aim of saturating the CPU cores as well as Disk I/O. Given that you have 12 CPU cores, I would start with perhaps 2 to 3 Splunk instances, and monitor the health status via iostat, top etc. to make sure that I am not overloading the box, and subsequently validate the improved utilisation of the hardware resources.&lt;/P&gt;</description>
    <pubDate>Tue, 11 Oct 2011 10:11:28 GMT</pubDate>
    <dc:creator>twkan</dc:creator>
    <dc:date>2011-10-11T10:11:28Z</dc:date>
    <item>
      <title>Increasing Splunks Search performance on Linux</title>
      <link>https://community.splunk.com/t5/Deployment-Architecture/Increasing-Splunks-Search-performance-on-Linux/m-p/89040#M3239</link>
      <description>&lt;P&gt;Hi. We have several big Splunk installations and im working on trying to increase the search performance on them. Unfortunatly ive come to and end and i could really use some input/suggestions on where to fix this.&lt;/P&gt;

&lt;P&gt;Info:&lt;BR /&gt;
 1. Splunk 4.3.2 x64 REDHAT @ RHEL 5.7 X64&lt;BR /&gt;
 2. HOT/WARM IDX @ 2x120GB SSD in RAID1 mounted volume&lt;BR /&gt;
 3. COLD &amp;amp; Thawed @a 14x300GB RAID6-ADG mounted volume&lt;BR /&gt;
 4. 2x6CPU Cores and 48GB MEM (HP DL380g7)&lt;/P&gt;

&lt;P&gt;So when i do a search i often see almost all my cpu's ad idle, but the one im using for search..&lt;BR /&gt;
I got no IO-Waiting on my Disk-IO subsystem so i know this issue is CPU bound.&lt;/P&gt;

&lt;P&gt;So the BIG question is : Is there a way to enable a search to span over multiple cpu cores? Multithreaded/processed searches?&lt;/P&gt;

&lt;P&gt;procs -----------memory---------- ---swap-- -----io---- --system-- -----cpu------&lt;BR /&gt;
 r  b   swpd   free   buff  cache   si   so    bi    bo   in   cs us sy id wa st&lt;BR /&gt;
 1  0    196 812064 1117692 32270052    0    0     6    50    2    2  6  0 94  0  0&lt;BR /&gt;
 2  0    196 809468 1117708 32272140    0    0     0   257 1280 1743  9  0 90  0  0&lt;BR /&gt;
 7  0    196 660532 1117800 32270748    0    0    62  1726 1602 3894 25  2 72  0  0&lt;BR /&gt;
 7  0    196 556972 1117920 32274096    0    0     1  1690 1648 21236 50  1 48  0  0&lt;BR /&gt;
 3  0    196 687980 1117952 32258168    0    0     0   428 1424 10324 40  1 59  0  0&lt;/P&gt;

&lt;P&gt;br TE&lt;/P&gt;</description>
      <pubDate>Mon, 10 Oct 2011 10:10:11 GMT</pubDate>
      <guid>https://community.splunk.com/t5/Deployment-Architecture/Increasing-Splunks-Search-performance-on-Linux/m-p/89040#M3239</guid>
      <dc:creator>dragmore</dc:creator>
      <dc:date>2011-10-10T10:10:11Z</dc:date>
    </item>
    <item>
      <title>Re: Increasing Splunks Search performance on Linux</title>
      <link>https://community.splunk.com/t5/Deployment-Architecture/Increasing-Splunks-Search-performance-on-Linux/m-p/89041#M3240</link>
      <description>&lt;P&gt;Hi dragmore&lt;/P&gt;

&lt;P&gt;please read this &lt;A href="http://splunk-base.splunk.com/answers/1829/splunk-searches-to-be-multithreaded-in-a-single-box"&gt;answer&lt;/A&gt; to find out more about search performance.&lt;/P&gt;

&lt;P&gt;regards&lt;/P&gt;</description>
      <pubDate>Mon, 10 Oct 2011 11:51:59 GMT</pubDate>
      <guid>https://community.splunk.com/t5/Deployment-Architecture/Increasing-Splunks-Search-performance-on-Linux/m-p/89041#M3240</guid>
      <dc:creator>MuS</dc:creator>
      <dc:date>2011-10-10T11:51:59Z</dc:date>
    </item>
    <item>
      <title>Re: Increasing Splunks Search performance on Linux</title>
      <link>https://community.splunk.com/t5/Deployment-Architecture/Increasing-Splunks-Search-performance-on-Linux/m-p/89042#M3241</link>
      <description>&lt;P&gt;Personally, I would install multiple Splunk Indexers listening on different ports with the aim of saturating the CPU cores as well as Disk I/O. Given that you have 12 CPU cores, I would start with perhaps 2 to 3 Splunk instances, and monitor the health status via iostat, top etc. to make sure that I am not overloading the box, and subsequently validate the improved utilisation of the hardware resources.&lt;/P&gt;</description>
      <pubDate>Tue, 11 Oct 2011 10:11:28 GMT</pubDate>
      <guid>https://community.splunk.com/t5/Deployment-Architecture/Increasing-Splunks-Search-performance-on-Linux/m-p/89042#M3241</guid>
      <dc:creator>twkan</dc:creator>
      <dc:date>2011-10-11T10:11:28Z</dc:date>
    </item>
    <item>
      <title>Re: Increasing Splunks Search performance on Linux</title>
      <link>https://community.splunk.com/t5/Deployment-Architecture/Increasing-Splunks-Search-performance-on-Linux/m-p/89043#M3242</link>
      <description>&lt;P&gt;Hi twkan, then you would 'only' increase the index performance but not the search performance.&lt;/P&gt;</description>
      <pubDate>Tue, 11 Oct 2011 11:00:48 GMT</pubDate>
      <guid>https://community.splunk.com/t5/Deployment-Architecture/Increasing-Splunks-Search-performance-on-Linux/m-p/89043#M3242</guid>
      <dc:creator>MuS</dc:creator>
      <dc:date>2011-10-11T11:00:48Z</dc:date>
    </item>
    <item>
      <title>Re: Increasing Splunks Search performance on Linux</title>
      <link>https://community.splunk.com/t5/Deployment-Architecture/Increasing-Splunks-Search-performance-on-Linux/m-p/89044#M3243</link>
      <description>&lt;P&gt;Generally speaking, search performance will increase along with indexing performance. This is where the multiple indexers with MapReduce will come into play to increase the search performance.&lt;/P&gt;</description>
      <pubDate>Tue, 11 Oct 2011 11:10:06 GMT</pubDate>
      <guid>https://community.splunk.com/t5/Deployment-Architecture/Increasing-Splunks-Search-performance-on-Linux/m-p/89044#M3243</guid>
      <dc:creator>twkan</dc:creator>
      <dc:date>2011-10-11T11:10:06Z</dc:date>
    </item>
    <item>
      <title>Re: Increasing Splunks Search performance on Linux</title>
      <link>https://community.splunk.com/t5/Deployment-Architecture/Increasing-Splunks-Search-performance-on-Linux/m-p/89045#M3244</link>
      <description>&lt;P&gt;okay at first I disagreed on this but after reading &lt;A href="http://splunk-base.splunk.com/answers/5202/how-do-i-get-the-most-out-of-a-16-core-server"&gt;http://splunk-base.splunk.com/answers/5202/how-do-i-get-the-most-out-of-a-16-core-server&lt;/A&gt; I think you can improve search performance this way.&lt;/P&gt;</description>
      <pubDate>Tue, 11 Oct 2011 11:43:15 GMT</pubDate>
      <guid>https://community.splunk.com/t5/Deployment-Architecture/Increasing-Splunks-Search-performance-on-Linux/m-p/89045#M3244</guid>
      <dc:creator>MuS</dc:creator>
      <dc:date>2011-10-11T11:43:15Z</dc:date>
    </item>
  </channel>
</rss>

