<?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: Is your backup server fast enough?</title>
	<atom:link href="http://nsrd.info/blog/2009/02/26/is-your-backup-server-fast-enough/feed/" rel="self" type="application/rss+xml" />
	<link>http://nsrd.info/blog/2009/02/26/is-your-backup-server-fast-enough/</link>
	<description>EMC NetWorker commentary from a long term backup consultant and theorist</description>
	<lastBuildDate>Mon, 14 May 2012 03:13:01 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.3.2</generator>
	<item>
		<title>By: Preston</title>
		<link>http://nsrd.info/blog/2009/02/26/is-your-backup-server-fast-enough/comment-page-1/#comment-129</link>
		<dc:creator>Preston</dc:creator>
		<pubDate>Thu, 26 Feb 2009 10:01:30 +0000</pubDate>
		<guid isPermaLink="false">http://nsrd.wordpress.com/?p=208#comment-129</guid>
		<description>I didn&#039;t mean to imply that I agree with putting index regions on the same SAN as is being protected – more that it&#039;s something very commonly seen in a lot of environments. Where possible of course the NetWorker index region should be reasonably well separated from the storage that it&#039;s protecting.

I agree that spreading the load over more disks is quite important - and particularly when we start moving into regions of say, 200+ GB this becomes very important. If examining NetWorker servers that work only from DAS though (and I&#039;d argue that at least 50%, if not more, of NetWorker servers fall into this category), the number of spindles available is often a limiting factor, and hence higher speed drives does become quite important.

The key lesson however is ensuring that the design of the NetWorker server suits the overall architecture and performance requirements of the environment at hand – regardless of whether that&#039;s by, say, high speed drives in smaller environments, or a higher numbers of spindles in larger environments, etc.</description>
		<content:encoded><![CDATA[<p>I didn&#8217;t mean to imply that I agree with putting index regions on the same SAN as is being protected – more that it&#8217;s something very commonly seen in a lot of environments. Where possible of course the NetWorker index region should be reasonably well separated from the storage that it&#8217;s protecting.</p>
<p>I agree that spreading the load over more disks is quite important &#8211; and particularly when we start moving into regions of say, 200+ GB this becomes very important. If examining NetWorker servers that work only from DAS though (and I&#8217;d argue that at least 50%, if not more, of NetWorker servers fall into this category), the number of spindles available is often a limiting factor, and hence higher speed drives does become quite important.</p>
<p>The key lesson however is ensuring that the design of the NetWorker server suits the overall architecture and performance requirements of the environment at hand – regardless of whether that&#8217;s by, say, high speed drives in smaller environments, or a higher numbers of spindles in larger environments, etc.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Roger</title>
		<link>http://nsrd.info/blog/2009/02/26/is-your-backup-server-fast-enough/comment-page-1/#comment-128</link>
		<dc:creator>Roger</dc:creator>
		<pubDate>Thu, 26 Feb 2009 09:53:09 +0000</pubDate>
		<guid isPermaLink="false">http://nsrd.wordpress.com/?p=208#comment-128</guid>
		<description>Wjile I agree that you need to put index and mediadb on fast disks, I do not agree that you should put them on the same SAN-system as the production data. Single point of failure sort of thing.

And also, since it is more an IOPS thing, spreading the load over more disks is more important than using the fastest disks. 16 5k disks should still give you more IOPS than 2 15k disks.</description>
		<content:encoded><![CDATA[<p>Wjile I agree that you need to put index and mediadb on fast disks, I do not agree that you should put them on the same SAN-system as the production data. Single point of failure sort of thing.</p>
<p>And also, since it is more an IOPS thing, spreading the load over more disks is more important than using the fastest disks. 16 5k disks should still give you more IOPS than 2 15k disks.</p>
]]></content:encoded>
	</item>
</channel>
</rss>

<!-- Performance optimized by W3 Total Cache. Learn more: http://www.w3-edge.com/wordpress-plugins/

Minified using disk: basic
Page Caching using disk: basic

Served from: nsrd.info @ 2012-05-22 12:56:37 -->
