Home Messages Index
[Date Prev][Date Next][Thread Prev][Thread Next]
Author IndexDate IndexThread Index

[News] Performance of Completely Fair Linux Scheduler Improves Further

  • Subject: [News] Performance of Completely Fair Linux Scheduler Improves Further
  • From: Roy Schestowitz <newsgroups@xxxxxxxxxxxxxxx>
  • Date: Fri, 14 Sep 2007 05:56:00 +0100
  • Newsgroups: comp.os.linux.advocacy
  • Organization: Netscape / schestowitz.com
  • User-agent: KNode/0.10.4
CFS, Focusing on Simplification and Performance

,----[ Quote ]
| He added, "we are now a bit faster than the O(1) scheduler was under 
| v2.6.22 - even on 32-bit. The main speedup comes from the avoidance of 
| divisions (or shifts) in the wakeup and context-switch fastpaths."  


Vista's scheduler, on the other hand, is very notorious at this stage. Linux is
miles ahead.


Defining Scheduler Task Groups

,----[ Quote ]
| Srivatsa requested that his patch be merged into Andrew Morton's -mm tree to 
| receive more testing...


Linux: Discussing the Really Fair Scheduler

,----[ Quote ]
| Ingo Molnar reviewed Roman Zippel's Really Fair Scheduler code, suggesting 
| that much of the work was similar to that which was being done by Peter 
| Zijlstra  


Linux: The Really Fair Scheduler

,----[ Quote ]
| He offered a mathematical overview of how his new scheduler works, included 
| some benchmarks, and reflected back to earlier discussions on the lkml...


[Vista scheduler is broken]

,----[ Quote ]
| Critical optimizations such as zero-copy aside, there is no excusable reason 
| why processing IP packets should so damagingly affect the system.  
| [...]
| Putting aside the larger problem for the moment, there are several issues 
| with this solution. It prioritizes multimedia playback over networking 
| performance, which, as the resulting clamor has shown, is not everyone's 
| personal policy preference. It is almost assuredly a layering violation. It 
| picks a fixed and hard-coded packet limit (ten per millisecond), which won't 
| scale across different hardware—think significantly faster processors or 
| substantially slower networking drivers. It ignores the commonality of GigE. 
| And, finally, the solution is complicated, as the convoluted description and 
| resulting bugs in the implementation demonstrate.        


Syllable Server Video Demonstration

,----[ Quote ]
| Turning our attention to the future, there's a demonstration video of 
| Syllable Server, the server companion to Syllable Desktop that is under 
| development and is being built on the Linux kernel [torrent, 91 MB AVI 
| video].   


Linux: The Original Process Scheduler

,----[ Quote ]
| In a June of 1992 posting to the linux-activists mailing list, Linus Torvalds 
| described the original Linux scheduler noting, "the scheduler in linux is 
| pretty simple, but does a reasonably good job at giving good IO response 
| while not being too unfair against cpu-bound processes."   
| [...]
|  *  1996-12-23  Modified by Dave Grothe to fix bugs in semaphores and
|  *              make semaphores SMP safe
|  *  1998-11-19  Implemented schedule_timeout() and related stuff
|  *              by Andrea Arcangeli
|  *  2002-01-04  New ultra-scalable O(1) scheduler by Ingo Molnar:
|  *              hybrid priority-list and round-robin design with
|  *              an array-switch method of distributing timeslices
|  *              and per-CPU runqueues.  Cleanups and useful suggestions
|  *              by Davide Libenzi, preemptible kernel bits by Robert Love.
|  *  2003-09-03  Interactivity tuning by Con Kolivas.
|  *  2004-04-02  Scheduler domains code by Nick Piggin
|  *  2007-04-15  Work begun on replacing all interactivity tuning with a
|  *              fair scheduling design by Con Kolivas.
|  *  2007-05-05  Load balancing (smp-nice) and other improvements
|  *              by Peter Williams
|  *  2007-05-06  Interactivity improvements to CFS by Mike Galbraith
|  *  2007-07-01  Group scheduling enhancements by Srivatsa Vaddagiri


New Syllable Build System for Linux

,----[ Quote ] 
| The Syllable project has released a new package of Builder, the system that 
| builds Syllable, its native applications, and ported applications. Builder 
| can also be installed on Linux.  


Five Questions: Kristian 'Vanders' van der Vliet, Syllable

,----[ Quote ]
| Getting hardware support to a point that is even as good as Linux will take 
| time.  
| [...]
|  Kaj has been planning 
| it for a long time and it's exciting that it's really happening now. We 
| have already been noticing that it opens doors for us. On the other hand, 
| it's just a side project to help Syllable Desktop out. Using the Linux 
| kernel for Syllable Server gives us several things: stability, REBOL/Core, 
| and ReiserFS 3. 


Linux: Tuning CFS

,----[ Quote ]
| Nick Piggin used 'git bisect' to track a lmbench regression to the main CFS 
| commit, leading to an interesting discussion between Nick and Ingo Molnar.  


Linux: CFS and 3D Gaming

,----[ Quote ]
| Some of the concerns expressed about the Completely Fair Scheduler were 
| reports that it might not handle 3D games as well as the SD scheduler. 


CFS scheduler to appear in Linux kernel 2.6.23

,----[ Quote ]
| And also credit where credit's due, Con Kolivas was the first one to 
| prove via RSDL/SD that 'fair scheduling' is possible and that it 
| results in better desktop scheduling.


Linux: Linus On CFS vs SD

,----[ Quote ]
| "People who think SD was 'perfect' were simply ignoring reality," Linus 
| Torvalds began in a succinct explanation as to why he chose the CFS scheduler 
| written by Ingo Molnar instead of the SD scheduler written by Con Kolivas.  


[Date Prev][Date Next][Thread Prev][Thread Next]
Author IndexDate IndexThread Index