<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
		>
<channel>
	<title>Comments on: Found an Ideal I/O Scheduler for my MySQL boxes</title>
	<atom:link href="http://kovyrin.net/2008/07/20/found-an-ideal-io-scheduler-for-my-mysql-boxes/feed/" rel="self" type="application/rss+xml" />
	<link>http://kovyrin.net/2008/07/20/found-an-ideal-io-scheduler-for-my-mysql-boxes/</link>
	<description>Yet Another Admin&#039;s blog</description>
	<lastBuildDate>Thu, 04 Feb 2010 07:58:50 +0000</lastBuildDate>
	<generator>http://wordpress.org/?v=2.9.1</generator>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
		<item>
		<title>By: pligg.com</title>
		<link>http://kovyrin.net/2008/07/20/found-an-ideal-io-scheduler-for-my-mysql-boxes/comment-page-1/#comment-231375</link>
		<dc:creator>pligg.com</dc:creator>
		<pubDate>Thu, 18 Mar 2010 12:18:00 +0000</pubDate>
		<guid isPermaLink="false">http://blog.kovyrin.net/?p=129#comment-231375</guid>
		<description>&lt;strong&gt;mysql :: Homo-Adminus Blog by Alexey Kovyrin...&lt;/strong&gt;

Disk IO performance...</description>
		<content:encoded><![CDATA[<p><strong>mysql :: Homo-Adminus Blog by Alexey Kovyrin&#8230;</strong></p>
<p>Disk IO performance&#8230;</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Илья</title>
		<link>http://kovyrin.net/2008/07/20/found-an-ideal-io-scheduler-for-my-mysql-boxes/comment-page-1/#comment-231090</link>
		<dc:creator>Илья</dc:creator>
		<pubDate>Thu, 18 Mar 2010 11:11:00 +0000</pubDate>
		<guid isPermaLink="false">http://blog.kovyrin.net/?p=129#comment-231090</guid>
		<description>Спасибо!очнь интересная статья!</description>
		<content:encoded><![CDATA[<p>Спасибо!очнь интересная статья!</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: 选择合适的IO Scheduler，获得更高性能Mysql环境 &#124; Coder,肖德时的个人BLOG</title>
		<link>http://kovyrin.net/2008/07/20/found-an-ideal-io-scheduler-for-my-mysql-boxes/comment-page-1/#comment-230993</link>
		<dc:creator>选择合适的IO Scheduler，获得更高性能Mysql环境 &#124; Coder,肖德时的个人BLOG</dc:creator>
		<pubDate>Thu, 18 Mar 2010 10:53:00 +0000</pubDate>
		<guid isPermaLink="false">http://blog.kovyrin.net/?p=129#comment-230993</guid>
		<description>[...] =&quot;http://coderchina.72pines.com/feed/&quot;; 刚读一Mysql DBA写的文章受到提示，知道了Linux下的IO [...]</description>
		<content:encoded><![CDATA[<p>[...] =&#8221;http://coderchina.72pines.com/feed/&#8221;; 刚读一Mysql DBA写的文章受到提示，知道了Linux下的IO [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Marcelb</title>
		<link>http://kovyrin.net/2008/07/20/found-an-ideal-io-scheduler-for-my-mysql-boxes/comment-page-1/#comment-230878</link>
		<dc:creator>Marcelb</dc:creator>
		<pubDate>Thu, 18 Mar 2010 13:28:00 +0000</pubDate>
		<guid isPermaLink="false">http://blog.kovyrin.net/?p=129#comment-230878</guid>
		<description>Link to the conference: 
http://video.google.com/videoplay?docid=-6304964351441328559</description>
		<content:encoded><![CDATA[<p>Link to the conference:<br />
<a href="http://video.google.com/videoplay?docid=-6304964351441328559" rel="nofollow">http://video.google.com/videoplay?docid=-6304964351441328559</a></p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Scoundrel</title>
		<link>http://kovyrin.net/2008/07/20/found-an-ideal-io-scheduler-for-my-mysql-boxes/comment-page-1/#comment-230800</link>
		<dc:creator>Scoundrel</dc:creator>
		<pubDate>Thu, 18 Mar 2010 23:19:00 +0000</pubDate>
		<guid isPermaLink="false">http://blog.kovyrin.net/?p=129#comment-230800</guid>
		<description>2Yordan: There were 8 separate threads in our &quot;database load generation tool&quot; (sphinx indexer) + some number of requests is being done from the site directly.</description>
		<content:encoded><![CDATA[<p>2Yordan: There were 8 separate threads in our &#8220;database load generation tool&#8221; (sphinx indexer) + some number of requests is being done from the site directly.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Yordan</title>
		<link>http://kovyrin.net/2008/07/20/found-an-ideal-io-scheduler-for-my-mysql-boxes/comment-page-1/#comment-230794</link>
		<dc:creator>Yordan</dc:creator>
		<pubDate>Thu, 18 Mar 2010 07:52:00 +0000</pubDate>
		<guid isPermaLink="false">http://blog.kovyrin.net/?p=129#comment-230794</guid>
		<description>what is the number of threads in mysqld?</description>
		<content:encoded><![CDATA[<p>what is the number of threads in mysqld?</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Scoundrel</title>
		<link>http://kovyrin.net/2008/07/20/found-an-ideal-io-scheduler-for-my-mysql-boxes/comment-page-1/#comment-230789</link>
		<dc:creator>Scoundrel</dc:creator>
		<pubDate>Thu, 18 Mar 2010 18:55:00 +0000</pubDate>
		<guid isPermaLink="false">http://blog.kovyrin.net/?p=129#comment-230789</guid>
		<description>2.6.18-53.el5</description>
		<content:encoded><![CDATA[<p>2.6.18-53.el5</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Kostas Georgiou</title>
		<link>http://kovyrin.net/2008/07/20/found-an-ideal-io-scheduler-for-my-mysql-boxes/comment-page-1/#comment-230785</link>
		<dc:creator>Kostas Georgiou</dc:creator>
		<pubDate>Thu, 18 Mar 2010 17:47:00 +0000</pubDate>
		<guid isPermaLink="false">http://blog.kovyrin.net/?p=129#comment-230785</guid>
		<description>Well there isn&#039;t much that the I/O schedulers can do if your access pattern is quite random beyond maybe giving you better average latencies . 

Running cfq with slice_idle=0 might be a good idea btw, keeping the disks idle for up to slice_idle (8ms by default) isn&#039;t probably the best option for a db workload.  

It would be interesting to get some plots/movies from seekwatcher also, I find that it gives you a nice insight on your workload and how each scheduler is affecting it.</description>
		<content:encoded><![CDATA[<p>Well there isn&#8217;t much that the I/O schedulers can do if your access pattern is quite random beyond maybe giving you better average latencies . </p>
<p>Running cfq with slice_idle=0 might be a good idea btw, keeping the disks idle for up to slice_idle (8ms by default) isn&#8217;t probably the best option for a db workload.  </p>
<p>It would be interesting to get some plots/movies from seekwatcher also, I find that it gives you a nice insight on your workload and how each scheduler is affecting it.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Yordan</title>
		<link>http://kovyrin.net/2008/07/20/found-an-ideal-io-scheduler-for-my-mysql-boxes/comment-page-1/#comment-230784</link>
		<dc:creator>Yordan</dc:creator>
		<pubDate>Thu, 18 Mar 2010 17:43:00 +0000</pubDate>
		<guid isPermaLink="false">http://blog.kovyrin.net/?p=129#comment-230784</guid>
		<description>Kernel version?</description>
		<content:encoded><![CDATA[<p>Kernel version?</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Me</title>
		<link>http://kovyrin.net/2008/07/20/found-an-ideal-io-scheduler-for-my-mysql-boxes/comment-page-1/#comment-230779</link>
		<dc:creator>Me</dc:creator>
		<pubDate>Thu, 18 Mar 2010 14:35:00 +0000</pubDate>
		<guid isPermaLink="false">http://blog.kovyrin.net/?p=129#comment-230779</guid>
		<description>echo 1 &gt; /proc/sys/vm/drop_caches</description>
		<content:encoded><![CDATA[<p>echo 1 &gt; /proc/sys/vm/drop_caches</p>
]]></content:encoded>
	</item>
</channel>
</rss>
