login
Header Space

 
 

Re: MAX_RT_PRIO - 1 Highest prio?

Score:
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
To: Chris Rigg <cdrigg@...>
Cc: Ingo Molnar <mingo@...>, Willy Tarreau <w@...>, <linux-kernel@...>
Date: Thursday, September 20, 2007 - 11:46 pm

On Wed, Sep 19, 2007 at 05:20:27PM -0600, Chris Rigg wrote:

Hi Chris,


Actually it's probably best to use sched_get_priority_max for the max
prio.


The migrate task of a given CPU isn't the only one that will take
tasks off its CPU to push them to others (although it does do that).
But there's other load balancing work going on in the scheduler
(looking at the 2.6.20 sched.c).

Although it would be interesting to see what the result would be if you
had N+1 tasks running on N CPUs all doing busy loops, and make one of
the tasks with the prio of MAX_RT_PRIO-1, and see if we have one task
that is starved and never schedules. But I'm sure this should be fixed
(if it was ever broken) with the latest scheduling work that's being
done in the most recent kernels.

-- Steve

-
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]

Messages in current thread:
CFS patch (v6) -- dynamic RT priorities?, Chris Rigg, (Mon Sep 17, 4:33 pm)
Re: CFS patch (v6) -- dynamic RT priorities?, Willy Tarreau, (Tue Sep 18, 1:00 am)
Re: CFS patch (v6) -- dynamic RT priorities?, Ingo Molnar, (Tue Sep 18, 2:26 am)
MAX_RT_PRIO - 1 Highest prio?, Chris Rigg, (Wed Sep 19, 7:20 pm)
Re: MAX_RT_PRIO - 1 Highest prio?, Steven Rostedt, (Thu Sep 20, 11:46 pm)
speck-geostationary