<?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 for SQLWorkshops.com Blog</title>
	<atom:link href="http://blog.sqlworkshops.com/comments/feed" rel="self" type="application/rss+xml" />
	<link>http://blog.sqlworkshops.com</link>
	<description>Microsoft SQL Server Performance Monitoring &#38; Tuning</description>
	<lastBuildDate>Thu, 19 Jul 2012 11:24:59 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.5.1</generator>
	<item>
		<title>Comment on Plan Caching and Query Memory Part 2: When not to use stored procedure or other plan caching mechanisms like sp_executesql or prepared statement by Basit Farooq</title>
		<link>http://blog.sqlworkshops.com/plan-caching-and-query-memory-part-2-when-not-to-use-stored-procedure-or-other-plan-caching-mechanisms-like-sp_executesql-or-prepared-statement/#comment-4</link>
		<dc:creator>Basit Farooq</dc:creator>
		<pubDate>Thu, 19 Jul 2012 11:24:59 +0000</pubDate>
		<guid isPermaLink="false">http://blog.sqlworkshops.com/?p=94#comment-4</guid>
		<description><![CDATA[Thanks for this excellient post.]]></description>
		<content:encoded><![CDATA[<p>Thanks for this excellient post.</p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on SQL Server IO handling mechanism can be severely affected by high CPU usage by R Meyyappan</title>
		<link>http://blog.sqlworkshops.com/sql-server-io-handling-mechanism-can-be-severely-affected-by-high-cpu-usage/#comment-3</link>
		<dc:creator>R Meyyappan</dc:creator>
		<pubDate>Wed, 18 Jul 2012 15:59:54 +0000</pubDate>
		<guid isPermaLink="false">http://blog.sqlworkshops.com/?p=73#comment-3</guid>
		<description><![CDATA[Hello Kennie, thanks for your suggestion. Unfortunately, dedicating a single CPU only for IO using an affinity mask like you mention will not help solve this problem. Did you test it?

See comments from Randy Rabin and Marco Carozzi to the connect item: https://connect.microsoft.com/SQLServer/feedback/details/744650/sql-server-io-handling-mechanism-can-be-severely-affected-by-high-cpu-usage. Randy’s feedback: Setting CPU and I/O affinity masks to separate the different workloads onto different CPUs had no effect (I was hoping it would). Even with one CPU allocated to processing and 3 CPUs to I/O, there was still a big difference in query performance.

Regards
-ramesh-]]></description>
		<content:encoded><![CDATA[<p>Hello Kennie, thanks for your suggestion. Unfortunately, dedicating a single CPU only for IO using an affinity mask like you mention will not help solve this problem. Did you test it?</p>
<p>See comments from Randy Rabin and Marco Carozzi to the connect item: <a href="https://connect.microsoft.com/SQLServer/feedback/details/744650/sql-server-io-handling-mechanism-can-be-severely-affected-by-high-cpu-usage" rel="nofollow">https://connect.microsoft.com/SQLServer/feedback/details/744650/sql-server-io-handling-mechanism-can-be-severely-affected-by-high-cpu-usage</a>. Randy’s feedback: Setting CPU and I/O affinity masks to separate the different workloads onto different CPUs had no effect (I was hoping it would). Even with one CPU allocated to processing and 3 CPUs to I/O, there was still a big difference in query performance.</p>
<p>Regards<br />
-ramesh-</p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on SQL Server IO handling mechanism can be severely affected by high CPU usage by Kennie Nybo Pontoppidan</title>
		<link>http://blog.sqlworkshops.com/sql-server-io-handling-mechanism-can-be-severely-affected-by-high-cpu-usage/#comment-2</link>
		<dc:creator>Kennie Nybo Pontoppidan</dc:creator>
		<pubDate>Mon, 04 Jun 2012 09:11:19 +0000</pubDate>
		<guid isPermaLink="false">http://blog.sqlworkshops.com/?p=73#comment-2</guid>
		<description><![CDATA[you could consider dedicating a single cpu only for IO using an affinity mask. I sat in a workshop in MOW2012 where Thomas Kejser described this very problem. You might want to consult him for the details

Best wishes,
Kennie]]></description>
		<content:encoded><![CDATA[<p>you could consider dedicating a single cpu only for IO using an affinity mask. I sat in a workshop in MOW2012 where Thomas Kejser described this very problem. You might want to consult him for the details</p>
<p>Best wishes,<br />
Kennie</p>
]]></content:encoded>
	</item>
</channel>
</rss>
