<?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: Nifty Link Roundup</title>
	<atom:link href="http://blogs.n1zyy.com/n1zyy/2009/11/18/nifty-link-roundup/feed/" rel="self" type="application/rss+xml" />
	<link>http://blogs.n1zyy.com/n1zyy/2009/11/18/nifty-link-roundup/</link>
	<description>It&#039;s a blog.</description>
	<lastBuildDate>Mon, 30 Jan 2012 21:37:54 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.2.1</generator>
	<item>
		<title>By: Matt</title>
		<link>http://blogs.n1zyy.com/n1zyy/2009/11/18/nifty-link-roundup/comment-page-1/#comment-8618</link>
		<dc:creator>Matt</dc:creator>
		<pubDate>Wed, 18 Nov 2009 04:39:10 +0000</pubDate>
		<guid isPermaLink="false">http://blogs.n1zyy.com/n1zyy/?p=2523#comment-8618</guid>
		<description>Ooh, and Maatkit&#039;s mk-query-digest seems to do more than the name implies: besides doing stats on the MySQL protocol, it can analyze protocols like HTTP: http://www.xaprb.com/blog/2009/11/14/mk-query-digest-now-understands-http/

And, apparently, memcache: http://www.xaprb.com/blog/2009/07/25/analyze-and-optimize-memcached-usage-with-maatkit/

The Percona patches get really good reviews:
http://www.xaprb.com/blog/2008/11/20/an-alternative-to-the-mysql-query-analyzer/

I also found Schooner Info Tech, which makes some pretty nifty memcache appliances: http://www.schoonerinfotech.com/products/memcached-appliance.html

If you&#039;ve got a sufficiently large site, memory for memcache becomes an issue. RAM gets extremely expensive when you try to get it in very dense capacity -- 32GB in 1U is completely doable, but it means shelling out for 8x 4GB DIMMs... And the neat thing is that 64GB per appliance is just the beginning... That&#039;s just in front of their 512GB of SSDs. I infer that they keep the &quot;hottest&quot; data in RAM, and use lightning-fast SSDs as a fallback. Nifty. (I bet they would also be amazing for very, very large varnish installs.)</description>
		<content:encoded><![CDATA[<p>Ooh, and Maatkit&#8217;s mk-query-digest seems to do more than the name implies: besides doing stats on the MySQL protocol, it can analyze protocols like HTTP: <a href="http://www.xaprb.com/blog/2009/11/14/mk-query-digest-now-understands-http/" rel="nofollow">http://www.xaprb.com/blog/2009/11/14/mk-query-digest-now-understands-http/</a></p>
<p>And, apparently, memcache: <a href="http://www.xaprb.com/blog/2009/07/25/analyze-and-optimize-memcached-usage-with-maatkit/" rel="nofollow">http://www.xaprb.com/blog/2009/07/25/analyze-and-optimize-memcached-usage-with-maatkit/</a></p>
<p>The Percona patches get really good reviews:<br />
<a href="http://www.xaprb.com/blog/2008/11/20/an-alternative-to-the-mysql-query-analyzer/" rel="nofollow">http://www.xaprb.com/blog/2008/11/20/an-alternative-to-the-mysql-query-analyzer/</a></p>
<p>I also found Schooner Info Tech, which makes some pretty nifty memcache appliances: <a href="http://www.schoonerinfotech.com/products/memcached-appliance.html" rel="nofollow">http://www.schoonerinfotech.com/products/memcached-appliance.html</a></p>
<p>If you&#8217;ve got a sufficiently large site, memory for memcache becomes an issue. RAM gets extremely expensive when you try to get it in very dense capacity &#8212; 32GB in 1U is completely doable, but it means shelling out for 8x 4GB DIMMs&#8230; And the neat thing is that 64GB per appliance is just the beginning&#8230; That&#8217;s just in front of their 512GB of SSDs. I infer that they keep the &#8220;hottest&#8221; data in RAM, and use lightning-fast SSDs as a fallback. Nifty. (I bet they would also be amazing for very, very large varnish installs.)</p>
]]></content:encoded>
	</item>
</channel>
</rss>

