V-3.0 Single Priority Array O(1) CPU Scheduler Evaluation

Version 3.1 of the various single priority array scheduler patches for 
2.6.7, 2.6.8-rc2 and 2.6.8-rc3 kernels are now available for evaluation.

This is a bug fix release to fix a problem caused by sched_clock() not 
being monotonic.  This meant that when measuring small time intervals by 
taking the difference between successive calls to sched_clock() there is 
a possibility of obtaining a negative value (or, as unsigned long longs 
are being used, a very big one).  One unfortunate consequence of this is 
that adding to non zero intervals together could lead to a zero result 
and possible divide by zero problems.


1. [ZAPHOD] Runtime selectable choice between a priority based or 
entitlement based O(1) scheduler with active/expired arrays replaced by 
a single array and an O(1) promotion mechanism plus scheduling 
statistics with new interactive bonus mechanism and throughput bonus 
mechanism:

2.6.7 
<http://prdownloads.sourceforge.net/cpuse/patch-2.6.7-sp[...]>
2.6.8-rc2 
<http://prdownloads.sourceforge.net/cpuse/patch-2.6.8-rc[...]>
2.6.8-rc3 
<http://prdownloads.sourceforge.net/cpuse/patch-2.6.8-rc[...]>

2. Slightly modified version of Con Kolivas's staircase O(1) scheduler 
with active/expired arrays replaced by a single array and an O(1) 
promotion mechanism:

2.6.7 
<http://prdownloads.sourceforge.net/cpuse/patch-2.6.7-sp[...]>
2.6.8-rc2 
<http://prdownloads.sourceforge.net/cpuse/patch-2.6.8-rc[...]>
2.6.8-rc3 
<http://prdownloads.sourceforge.net/cpuse/patch-2.6.8-rc[...]>

3. [HYDRA] Runtime selection between staircase, priority based and 
entitlement based O(1) schedulers:

2.6.7 
<http://prdownloads.sourceforge.net/cpuse/patch-2.6.7-sp[...]>
2.6.8-rc2 
<http://prdownloads.sourceforge.net/cpuse/patch-2.6.8-rc[...]>
2.6.8-rc3 
<http://prdownloads.sourceforge.net/cpuse/patch-2.6.8-rc[...]>

Other schedulers are also available from 
<https://sourceforge.net/projects/cpuse/>>

So as not to interfere with the staircase scheduler's evaluation I do 
not propose to release patches for rc3-mm kernels unless requested.

I'm in the process of simplifying my schedulers (I got carried away with 
the theory) in order to reduce their overhead and hope to release a new 
slimmer version early next week.  Also on the "to do" list are CPU rate 
caps.

Peter
-- 
Peter Williams                                   pwil3058@bigpond.net.au

"Learning, n. The kind of ignorance distinguishing the studious."
  -- Ambrose Bierce

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/