<?xml version="1.0" encoding="UTF-8"?><!-- generator="wordpress/2.0.11" -->
<rss version="2.0" 
	xmlns:content="http://purl.org/rss/1.0/modules/content/">
<channel>
	<title>Comments on: Linux Scalability in a NUMA World</title>
	<link>http://www.linux-mag.com/id/6868/</link>
	<description>Open Source, Open Standards</description>
	<pubDate>Sun, 21 Mar 2010 06:26:54 +0000</pubDate>
	<generator>http://wordpress.org/?v=2.0.11</generator>

	<item>
		<title>by: Unfilling my inbox: NetBSD news from the past few weeks &#8211; ACPI, NUMA, Xen, and more &#171; The Daily BSD</title>
		<link>http://www.linux-mag.com/id/6868/#comment-3159</link>
		<pubDate>Sun, 31 Jan 2010 19:01:56 +0000</pubDate>
		<guid>http://www.linux-mag.com/id/6868/#comment-3159</guid>
					<description>[...] Supporting NUMA in a contemporary (i.e.: Intel centric) SMP-enabled operating system requires following a bunch of standards, two of which are parsing of two tables, the System Resource Affinity Table (SRAT) and the System Locality Information Table (SLIT). Both tables are accessible via the Advanced Configuration and Power Interface (ACPI), and according to the German-language Wikipedia, the SRAT is used to assign local memory to local threads to boost their performance, and the SLIT defines the &#8220;distance&#8221; of the nodes among themselves, which is used to determine the &#8220;nearest&#8221; memory if local memory is not enough. [...]</description>
		<content:encoded><![CDATA[<p>[&#8230;] Supporting NUMA in a contemporary (i.e.: Intel centric) SMP-enabled operating system requires following a bunch of standards, two of which are parsing of two tables, the System Resource Affinity Table (SRAT) and the System Locality Information Table (SLIT). Both tables are accessible via the Advanced Configuration and Power Interface (ACPI), and according to the German-language Wikipedia, the SRAT is used to assign local memory to local threads to boost their performance, and the SLIT defines the &#8220;distance&#8221; of the nodes among themselves, which is used to determine the &#8220;nearest&#8221; memory if local memory is not enough. [&#8230;]
</p>
]]></content:encoded>
				</item>
	<item>
		<title>by: 肥佳洛的Linux學習網 &#187; Top 10 Software Development Articles of 2008</title>
		<link>http://www.linux-mag.com/id/6868/#comment-2566</link>
		<pubDate>Thu, 07 May 2009 16:46:30 +0000</pubDate>
		<guid>http://www.linux-mag.com/id/6868/#comment-2566</guid>
					<description>[...] #4 Linux Scalability in a NUMA World [...]</description>
		<content:encoded><![CDATA[<p>[&#8230;] #4 Linux Scalability in a NUMA World [&#8230;]
</p>
]]></content:encoded>
				</item>
	<item>
		<title>by: Top 10 Software Development Articles of 2008 &#124; &#124; 肥佳洛的 Linux 學習網</title>
		<link>http://www.linux-mag.com/id/6868/#comment-1822</link>
		<pubDate>Mon, 01 Dec 2008 15:46:12 +0000</pubDate>
		<guid>http://www.linux-mag.com/id/6868/#comment-1822</guid>
					<description>[...] #4 Linux Scalability in a NUMA World [...]</description>
		<content:encoded><![CDATA[<p>[&#8230;] #4 Linux Scalability in a NUMA World [&#8230;]
</p>
]]></content:encoded>
				</item>
	<item>
		<title>by: David Cymbala</title>
		<link>http://www.linux-mag.com/id/6868/#comment-1484</link>
		<pubDate>Tue, 16 Sep 2008 01:56:20 +0000</pubDate>
		<guid>http://www.linux-mag.com/id/6868/#comment-1484</guid>
					<description>I'm curious if there is any support in the Linux kernel for an application to be profiled so that the NUMA model it uses is based on some kind of empirical data. It seems that right now it is up to the application writer to have some understanding of the memory usage behavior the application has in advance. I suppose that each application could provide command-line parameters to select a model, but it would be really great for the application to "observe itself" use memory and adapt dynamically. Do such things exist right now?</description>
		<content:encoded><![CDATA[<p>I&#8217;m curious if there is any support in the Linux kernel for an application to be profiled so that the NUMA model it uses is based on some kind of empirical data. It seems that right now it is up to the application writer to have some understanding of the memory usage behavior the application has in advance. I suppose that each application could provide command-line parameters to select a model, but it would be really great for the application to &#8220;observe itself&#8221; use memory and adapt dynamically. Do such things exist right now?
</p>
]]></content:encoded>
				</item>
	<item>
		<title>by: Boycott Novell &#187; Links 15/09/2008: Google Phones Out Shortly, New GNU/Linux Software</title>
		<link>http://www.linux-mag.com/id/6868/#comment-1483</link>
		<pubDate>Tue, 16 Sep 2008 01:00:14 +0000</pubDate>
		<guid>http://www.linux-mag.com/id/6868/#comment-1483</guid>
					<description>[...] Linux Scalability in a NUMA World [...]</description>
		<content:encoded><![CDATA[<p>[&#8230;] Linux Scalability in a NUMA World [&#8230;]
</p>
]]></content:encoded>
				</item>
	<item>
		<title>by: Aaron Birenboim</title>
		<link>http://www.linux-mag.com/id/6868/#comment-1481</link>
		<pubDate>Mon, 15 Sep 2008 18:41:03 +0000</pubDate>
		<guid>http://www.linux-mag.com/id/6868/#comment-1481</guid>
					<description>Excellent introductory article.
I will be keeping this in mind while designing a new application.
I always wondered if there was a way to control aspects of NUMA.
I now have a starting point for researching these NUMA control techniques.</description>
		<content:encoded><![CDATA[<p>Excellent introductory article.<br />
I will be keeping this in mind while designing a new application.<br />
I always wondered if there was a way to control aspects of NUMA.<br />
I now have a starting point for researching these NUMA control techniques.
</p>
]]></content:encoded>
				</item>
	<item>
		<title>by: Linux Scalability in a NUMA World</title>
		<link>http://www.linux-mag.com/id/6868/#comment-1478</link>
		<pubDate>Mon, 15 Sep 2008 06:50:16 +0000</pubDate>
		<guid>http://www.linux-mag.com/id/6868/#comment-1478</guid>
					<description>[...] Go to the author&#8217;s original blog: Linux Scalability in a NUMA World [...]</description>
		<content:encoded><![CDATA[<p>[&#8230;] Go to the author&#8217;s original blog: Linux Scalability in a NUMA World [&#8230;]
</p>
]]></content:encoded>
				</item>
</channel>
</rss>
