Re: migration thread and active_load_balance

Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
From: Andi Kleen
Date: Sunday, April 20, 2008 - 2:35 pm

"Dan Upton" <upton.dan.linux@gmail.com> writes:

[not a scheduler expert; just some general comments]


Other CPUs can access it yes subject to the lock. You can test that
theory by running with only one CPU.


That might be obvious, but are you aware that printks inside
the scheduler can lead to deadlocks? printk when the buffer
is full calls wake_up and that calls the scheduler. So for
debugging the scheduler you need some other way to get
the information out.

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

Messages in current thread:
migration thread and active_load_balance, Dan Upton, (Sun Apr 20, 11:21 am)
Re: migration thread and active_load_balance, Dmitry Adamushko, (Sun Apr 20, 2:26 pm)
Re: migration thread and active_load_balance, Andi Kleen, (Sun Apr 20, 2:35 pm)
Re: migration thread and active_load_balance, Dan Upton, (Sun Apr 20, 5:44 pm)
Re: migration thread and active_load_balance, Dan Upton, (Sun Apr 20, 5:46 pm)
Re: migration thread and active_load_balance, Dmitry Adamushko, (Mon Apr 21, 4:03 am)
Re: migration thread and active_load_balance, Dan Upton, (Mon Apr 21, 12:38 pm)
Re: migration thread and active_load_balance, Dmitry Adamushko, (Mon Apr 21, 1:39 pm)
Re: migration thread and active_load_balance, Dan Upton, (Tue Apr 22, 12:19 pm)