I have a apple G4 machine that is dual processor and running SMP kernel. On
the lines of a patch I ceated a module that I use to bind a process to a
processor.
My program creates multiple threads and there are multiple instances of
program running at same time. All the threads/processes are binded to a
single processor. If I boot my machine in non-SMP kernel and run all the
instances of my program, everything works fine. But if I boot my machine in
SMP kernel and run all the instances of my program, I get a timeout
condition from one of the threads regularly but at random intervals of
time. After adding a lot of debugging statements, most probably it scales
down to scheduling problem. I added 'sleep(1)' in all the threads that are
created and everything worked fine. Are there any other methods to debug?
How can I find out the time intervals during which a process was scheduled
out and on which processor it ran on during its lifetime?
Regards,
Daljeet.
-
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/