<?xml version="1.0" encoding="utf-8"?>
<rss version="2.0" xml:base="http://kerneltrap.org"  xmlns:dc="http://purl.org/dc/elements/1.1/">
<channel>
 <title>KernelTrap - -rt</title>
 <link>http://kerneltrap.org/taxonomy/term/581/0</link>
 <description></description>
 <language>en-local</language>
<item>
 <title>Quote: Sacrificing Performance To Achieve Determinism</title>
 <link>http://kerneltrap.org/Quote/Sacrificing_Performance_To_Achieve_Determinism</link>
 <description>&lt;!-- google_ad_section_start --&gt;&lt;p&gt;&quot;An RTOS (Real-time Operating System) will sacrifice performance to achieve determinism (low latencies). Several key features to an RT system usually come with a performance cost.  A non RT system will perform 99% of the time faster than an RTOS. But all it takes is that one time to miss a deadline to make an RT system crash.&lt;/p&gt;
&lt;!-- google_ad_section_end --&gt;&lt;p&gt;&lt;a href=&quot;http://kerneltrap.org/Quote/Sacrificing_Performance_To_Achieve_Determinism&quot; target=&quot;_blank&quot;&gt;read more&lt;/a&gt;&lt;/p&gt;</description>
 <comments>http://kerneltrap.org/Quote/Sacrificing_Performance_To_Achieve_Determinism#comments</comments>
 <category domain="http://kerneltrap.org/taxonomy/term/581">-rt</category>
 <category domain="http://kerneltrap.org/Linux">Linux</category>
 <category domain="http://kerneltrap.org/quote">quote</category>
 <category domain="http://kerneltrap.org/taxonomy/term/874">Steven Rostedt</category>
 <category domain="http://kerneltrap.org/taxonomy/term/1094">linux-kernel</category>
 <category domain="http://kerneltrap.org/taxonomy/term/1174">Steven Rostedt</category>
 <pubDate>Wed, 21 May 2008 21:38:01 +0000</pubDate>
 <dc:creator>Jeremy</dc:creator>
 <guid isPermaLink="false">16182 at http://kerneltrap.org</guid>
</item>
<item>
 <title>Quote: Largest Performance Improvement To Hit The RT Patch</title>
 <link>http://kerneltrap.org/Quote/Largest_Performance_Improvement_To_Hit_The_RT_Patch</link>
 <description>&lt;!-- google_ad_section_start --&gt;&lt;p&gt;&quot;This is the largest performance improvement to hit the RT patch since the removal of the global PI lock. On my 4way box running &#039;hackbench 50&#039; went from 18 seconds down to just under 5 seconds (4.8). Vanilla 2.6.24.7 on this same box runs at 3.9 secs. This is the first time that the RT patched kernel is less than a magnitude away from mainline running this hackbench test.&quot;&lt;/p&gt;
&lt;!-- google_ad_section_end --&gt;</description>
 <comments>http://kerneltrap.org/Quote/Largest_Performance_Improvement_To_Hit_The_RT_Patch#comments</comments>
 <category domain="http://kerneltrap.org/taxonomy/term/581">-rt</category>
 <category domain="http://kerneltrap.org/Linux">Linux</category>
 <category domain="http://kerneltrap.org/quote">quote</category>
 <category domain="http://kerneltrap.org/taxonomy/term/874">Steven Rostedt</category>
 <category domain="http://kerneltrap.org/taxonomy/term/1094">linux-kernel</category>
 <category domain="http://kerneltrap.org/taxonomy/term/1174">Steven Rostedt</category>
 <pubDate>Tue, 20 May 2008 13:16:44 +0000</pubDate>
 <dc:creator>Jeremy</dc:creator>
 <guid isPermaLink="false">16176 at http://kerneltrap.org</guid>
</item>
<item>
 <title>Preemptible RCU</title>
 <link>http://kerneltrap.org/Linux/Preemptible_RCU</link>
 <description>&lt;div class=&quot;taxonomy-images&quot;&gt;&lt;a href=&quot;/news/linux&quot; class=&quot;taxonomy-image-links&quot;&gt;&lt;img src=&quot;http://kerneltrap.org/files/category_pictures/K-Linux.gif&quot; alt=&quot;Linux news&quot; title=&quot;Linux news&quot;  width=&quot;75&quot; height=&quot;75&quot; /&gt;&lt;/a&gt;&lt;/div&gt;&lt;!-- google_ad_section_start --&gt;&lt;p&gt;&quot;&lt;i&gt;This patch implements a new version of RCU which allows its read-side critical sections to be preempted,&lt;/i&gt;&quot; &lt;a href=&quot;http://kerneltrap.org/mailarchive/linux-kernel/2007/9/10/192214&quot;&gt;Paul McKenney said in a posting&lt;/a&gt; to the Linux Kernel mailing list.  He described the &lt;a href=&quot;http://en.wikipedia.org/wiki/Read-copy-update&quot;&gt;RCU&lt;/a&gt; code contained in his 9 part patchset, &quot;&lt;i&gt;it uses a set of counter pairs to keep track of the read-side critical sections and flips them when all tasks exit [the] read-side critical section.&lt;/i&gt;&quot;  He continued:&lt;/p&gt;
&lt;blockquote&gt;&lt;p&gt;&quot;This patch was developed as a part of the -rt kernel development and meant to provide better latencies when read-side critical sections of RCU don&#039;t disable preemption.  As a consequence of keeping track of RCU readers, the readers have a slight overhead (optimizations in the paper). This implementation co-exists with the &#039;classic&#039; RCU implementations and can be switched to at compiler.&quot;&lt;/p&gt;&lt;/blockquote&gt;
&lt;p&gt;Ingo Molnar responded very favorably to the patch, &quot;&lt;i&gt;cool! Now after 2 years of development and testing I think this is one of the most mature patchsets on lkml - so i&#039;d like to see this designated for potential upstream inclusion. I.e. everyone who can see some bug, please holler now.&lt;/i&gt;&quot;&lt;/p&gt;
&lt;!-- google_ad_section_end --&gt;&lt;p&gt;&lt;a href=&quot;http://kerneltrap.org/Linux/Preemptible_RCU&quot; target=&quot;_blank&quot;&gt;read more&lt;/a&gt;&lt;/p&gt;</description>
 <comments>http://kerneltrap.org/Linux/Preemptible_RCU#comments</comments>
 <category domain="http://kerneltrap.org/taxonomy/term/581">-rt</category>
 <category domain="http://kerneltrap.org/Ingo_Molnar">Ingo Molnar</category>
 <category domain="http://kerneltrap.org/low-latency">low-latency</category>
 <category domain="http://kerneltrap.org/taxonomy/term/583">patch</category>
 <category domain="http://kerneltrap.org/taxonomy/term/908">Paul McKenney</category>
 <category domain="http://kerneltrap.org/taxonomy/term/907">RCU</category>
 <category domain="http://kerneltrap.org/news/linux">Linux news</category>
 <pubDate>Tue, 11 Sep 2007 16:45:33 +0000</pubDate>
 <dc:creator>Jeremy</dc:creator>
 <guid isPermaLink="false">14341 at http://kerneltrap.org</guid>
</item>
<item>
 <title>Linux:  Real Time Kernel Patch Queue</title>
 <link>http://kerneltrap.org/node/11752</link>
 <description>&lt;div class=&quot;taxonomy-images&quot;&gt;&lt;a href=&quot;/news/linux&quot; class=&quot;taxonomy-image-links&quot;&gt;&lt;img src=&quot;http://kerneltrap.org/files/category_pictures/K-Linux.gif&quot; alt=&quot;Linux news&quot; title=&quot;Linux news&quot;  width=&quot;75&quot; height=&quot;75&quot; /&gt;&lt;/a&gt;&lt;/div&gt;&lt;!-- google_ad_section_start --&gt;&lt;p&gt;Ingo Molnar announced that the &lt;a href=&quot;http://rt.wiki.kernel.org&quot;&gt;real time patchset&lt;/a&gt; [&lt;a href=&quot;http://kerneltrap.org/node/3995&quot;&gt;story&lt;/a&gt;] that he and Thomas Gleixner maintain is now available as a series of 374 broken out patches, &quot;&lt;i&gt;from now on (as of 2.6.22.1-rt2) it will be part of every upstream -rt release and it is available from the &lt;a href=&quot;http://redhat.com/~mingo/realtime-preempt/&quot;&gt;-rt download site&lt;/a&gt;&lt;/i&gt;&quot;.  Regarding the patches, he notes that it&#039;s responsible for, &quot;&lt;i&gt;698 files changed, 27920 insertions(+), 9603 deletions(-)&lt;/i&gt;&quot;, going on to note, &quot;&lt;i&gt;which is impressive as we moved a huge chunk of -rt into mainline already ;-) The series file is attached below.&lt;/i&gt;&quot;.  Ingo explains:&lt;/p&gt;
&lt;blockquote&gt;&lt;p&gt;&quot;the purpose of this finegrained splitup is to foster (even ;-) quicker upstream integration of various -rt features, and to see the full -rt tree integrated upstream. We also hope that this split-up queue helps various vendors standardize their (currently quite splintered) real-time implementations to the upstream -rt patchset.  The queue is not (yet) bisectable at every point, and many of the splits are thematic, to allow the simpler future handling of updates.&quot;&lt;/p&gt;&lt;/blockquote&gt;
&lt;!-- google_ad_section_end --&gt;&lt;p&gt;&lt;a href=&quot;http://kerneltrap.org/node/11752&quot; target=&quot;_blank&quot;&gt;read more&lt;/a&gt;