<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:wfw="http://wellformedweb.org/CommentAPI/"
	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/"
	xmlns:slash="http://purl.org/rss/1.0/modules/slash/"
	>

<channel>
	<title>E2E Networks &#187; tuning</title>
	<atom:link href="http://e2enetworks.com/tag/tuning/feed/" rel="self" type="application/rss+xml" />
	<link>http://e2enetworks.com</link>
	<description>Low Latency hosting in India</description>
	<lastBuildDate>Mon, 23 Aug 2010 19:10:45 +0000</lastBuildDate>
	<language>en</language>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.0.1</generator>
		<item>
		<title>Improving linux IO performance</title>
		<link>http://e2enetworks.com/2008/10/28/improving-linux-io-performance/</link>
		<comments>http://e2enetworks.com/2008/10/28/improving-linux-io-performance/#comments</comments>
		<pubDate>Tue, 28 Oct 2008 15:17:08 +0000</pubDate>
		<dc:creator>tarun</dc:creator>
				<category><![CDATA[performance]]></category>
		<category><![CDATA[linux]]></category>
		<category><![CDATA[tuning]]></category>

		<guid isPermaLink="false">http://e2enetworks.com/?p=29</guid>
		<description><![CDATA[1. Mount options: use noatime Most Linux server machines can do without last access time modified for every file and each directory which is being read. So I&#8217;ll just go ahead and re-quote for the nth time what Linux Kernel developer Ingor Molar has to say to emphasize the point. &#60;Quote&#62; i cannot over-emphasise how [...]]]></description>
			<content:encoded><![CDATA[<div class="content clear-block">
<p><strong>1. Mount options: use noatime</strong></p>
<p>Most Linux server machines can do without last access time modified for every file and each directory which is being read. So I&#8217;ll just go ahead and re-quote for the nth time what Linux Kernel developer Ingor Molar has to say to emphasize the point.<br />
&lt;Quote&gt;<br />
i cannot over-emphasise how much of a deal it is in practice. Atime<br />
updates are by far the biggest IO performance deficiency that Linux has<br />
today. Getting rid of atime updates would give us more everyday Linux<br />
performance than all the pagecache speedups of the past 10 years,<br />
_combined_.<br />
&lt;Quote/&gt;</p>
<p>You can simply remount your filesystems without rebooting your machine using remount option.<br />
As an example:-<br />
/bin/mount -t ext3 -o noatime ext3 /dev/sda5 /<br />
for remounting<br />
/bin/mount -t ext3 -o noatime,remount ext3 /dev/sda5 /</p>
<p>And don&#8217;t forget to modify corresponding lines in your /etc/fstab<br />
/dev/sda5            /                    ext3 noatime     1 1</p>
<p><strong>2. Use tmpfs</strong><br />
Speedup heavy read-write IO for temporary data stores by by <a href="/2008/10/25/linux-in-memory-filesystems-tmpfs-vs-ramdisk/">using memory</a> instead of disk.</p>
<p>3.  On systems not constrained for memory <strong>reduce swappiness of the Linux machine</strong><br />
/bin/echo &#8220;10&#8243; &gt; /proc/sys/vm/swappiness</p>
<p><strong>4. Set blockdev readahead</strong> to a reasonable value to improve read performance<br />
/sbin/blockdev &#8211;setra 131072 /dev/sda</p>
<p>The default readahead value is too small.</p></div>
]]></content:encoded>
			<wfw:commentRss>http://e2enetworks.com/2008/10/28/improving-linux-io-performance/feed/</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
	</channel>
</rss>
