<?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: When Memory Serves You: Using ramfs and tmpfs</title>
	<atom:link href="http://www.linux-mag.com/id/7689/feed/" rel="self" type="application/rss+xml" />
	<link>http://www.linux-mag.com/id/7689/</link>
	<description>Open Source, Open Standards</description>
	<lastBuildDate>Sat, 05 Oct 2013 13:48:18 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.1</generator>
	<item>
		<title>By: Linux Tutorials</title>
		<link>http://www.linux-mag.com/id/7689/#comment-71573</link>
		<dc:creator>Linux Tutorials</dc:creator>
		<pubDate>Tue, 06 Dec 2011 21:12:57 +0000</pubDate>
		<guid isPermaLink="false">http://www.linux-mag.com/id/7689/#comment-71573</guid>
		<description>I will immediately grasp your rss as I can&#039;t find your e-mail subscription link or e-newsletter service. Do you&#039;ve any? Kindly allow me understand in order that I could subscribe. Thanks.</description>
		<content:encoded><![CDATA[<p>I will immediately grasp your rss as I can&#8217;t find your e-mail subscription link or e-newsletter service. Do you&#8217;ve any? Kindly allow me understand in order that I could subscribe. Thanks.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: phred14</title>
		<link>http://www.linux-mag.com/id/7689/#comment-7780</link>
		<dc:creator>phred14</dc:creator>
		<pubDate>Wed, 30 Nov -0001 00:00:00 +0000</pubDate>
		<guid isPermaLink="false">http://www.linux-mag.com/id/7689/#comment-7780</guid>
		<description>&lt;p&gt;For the reasons mentioned in the article, ramfs sounds a bit scary and uncontrolled.  Why would one ever prefer ramfs over tmpfs.  I have in the past used tmpfs in this exact scenario - huge amounts of tmpfs backed by huge amounts of swap.  I quit when it turned out that some software I needed to use liked to know what fs it was running on top of, and it liked afs, nfs, and ext - only.
&lt;/p&gt;
</description>
		<content:encoded><![CDATA[<p>For the reasons mentioned in the article, ramfs sounds a bit scary and uncontrolled.  Why would one ever prefer ramfs over tmpfs.  I have in the past used tmpfs in this exact scenario &#8211; huge amounts of tmpfs backed by huge amounts of swap.  I quit when it turned out that some software I needed to use liked to know what fs it was running on top of, and it liked afs, nfs, and ext &#8211; only.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: johnh51</title>
		<link>http://www.linux-mag.com/id/7689/#comment-7781</link>
		<dc:creator>johnh51</dc:creator>
		<pubDate>Wed, 30 Nov -0001 00:00:00 +0000</pubDate>
		<guid isPermaLink="false">http://www.linux-mag.com/id/7689/#comment-7781</guid>
		<description>&lt;p&gt;This technique was useful on the IBM360 in the \&#039;70s, but you may want to benchmark it today.&lt;br /&gt;
I stopped doing this when The Man posted that&lt;br /&gt;
using memory for files was not necessary since Linux buffering was so effective...  The system flushes every 20 seconds, if the file lasts less than this, why would the FS write it to disk at all?...  The difference between memory swapping and buffer flushing - I leave the performance benchmark to the individual machine &amp; application mix to see if there is any improvement at all...
&lt;/p&gt;
</description>
		<content:encoded><![CDATA[<p>This technique was useful on the IBM360 in the \&#8217;70s, but you may want to benchmark it today.<br />
I stopped doing this when The Man posted that<br />
using memory for files was not necessary since Linux buffering was so effective&#8230;  The system flushes every 20 seconds, if the file lasts less than this, why would the FS write it to disk at all?&#8230;  The difference between memory swapping and buffer flushing &#8211; I leave the performance benchmark to the individual machine &#38; application mix to see if there is any improvement at all&#8230;</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: mrechenburg</title>
		<link>http://www.linux-mag.com/id/7689/#comment-7782</link>
		<dc:creator>mrechenburg</dc:creator>
		<pubDate>Wed, 30 Nov -0001 00:00:00 +0000</pubDate>
		<guid isPermaLink="false">http://www.linux-mag.com/id/7689/#comment-7782</guid>
		<description>&lt;p&gt;Cool article, Many thanks Ken !&lt;/p&gt;
&lt;p&gt;We have just added \&quot;in-Memory\&quot; deployment of physical systems and virtual machines to the openQRM Datacenter Management platform (&lt;a&gt;http://www.openqrm-enterprise.com/&lt;/a&gt;) using tmpfs.&lt;br /&gt;
More details at :&lt;/p&gt;
&lt;p&gt;&lt;a&gt;http://it.toolbox.com/blogs/openqrm-blog/new-feature-inmemory-deployment-runs-server-on-ramdisk-36651&lt;/a&gt;&lt;/p&gt;
&lt;p&gt;greetz + stay tuned,&lt;/p&gt;
&lt;p&gt;Matt
&lt;/p&gt;
</description>
		<content:encoded><![CDATA[<p>Cool article, Many thanks Ken !</p>
<p>We have just added \&#8221;in-Memory\&#8221; deployment of physical systems and virtual machines to the openQRM Datacenter Management platform (<a>http://www.openqrm-enterprise.com/</a>) using tmpfs.<br />
More details at :</p>
<p><a>http://it.toolbox.com/blogs/openqrm-blog/new-feature-inmemory-deployment-runs-server-on-ramdisk-36651</a></p>
<p>greetz + stay tuned,</p>
<p>Matt</p>
]]></content:encoded>
	</item>
</channel>
</rss>