Re: [RFC][PATCH 1/2] sched: Move idle_balance() to post_schedule

2013-01-05 Thread Frederic Weisbecker
2012/12/22 Steven Rostedt : > The idle_balance() code is called to do task load balancing just before > going to idle. This makes sense as the CPU is about to sleep anyway. > But currently it's called in the middle of the scheduler and in a place > that must have interrupts disabled. That means,

Re: [RFC][PATCH 1/2] sched: Move idle_balance() to post_schedule

2013-01-05 Thread Frederic Weisbecker
2012/12/22 Steven Rostedt rost...@goodmis.org: The idle_balance() code is called to do task load balancing just before going to idle. This makes sense as the CPU is about to sleep anyway. But currently it's called in the middle of the scheduler and in a place that must have interrupts

Re: [RFC][PATCH 1/2] sched: Move idle_balance() to post_schedule

2012-12-21 Thread Steven Rostedt
--- So much for saying it was well tested. As my email box is separate from the development boxes, I didn't copy the write set of patches over. This patch was tested thoroughly on 40 core and 4 core, but not UP. The UP had some bugs that were fixed (but not sent :-p) Here's the correct patch with

[RFC][PATCH 1/2] sched: Move idle_balance() to post_schedule

2012-12-21 Thread Steven Rostedt
The idle_balance() code is called to do task load balancing just before going to idle. This makes sense as the CPU is about to sleep anyway. But currently it's called in the middle of the scheduler and in a place that must have interrupts disabled. That means, while the load balancing is going on,

[RFC][PATCH 1/2] sched: Move idle_balance() to post_schedule

2012-12-21 Thread Steven Rostedt
The idle_balance() code is called to do task load balancing just before going to idle. This makes sense as the CPU is about to sleep anyway. But currently it's called in the middle of the scheduler and in a place that must have interrupts disabled. That means, while the load balancing is going on,

Re: [RFC][PATCH 1/2] sched: Move idle_balance() to post_schedule

2012-12-21 Thread Steven Rostedt
--- So much for saying it was well tested. As my email box is separate from the development boxes, I didn't copy the write set of patches over. This patch was tested thoroughly on 40 core and 4 core, but not UP. The UP had some bugs that were fixed (but not sent :-p) Here's the correct patch with