sched: do not set softirqs to nice +19
authorIngo Molnar <mingo@elte.hu>
Mon, 9 Jul 2007 16:52:00 +0000 (18:52 +0200)
committerIngo Molnar <mingo@elte.hu>
Mon, 9 Jul 2007 16:52:00 +0000 (18:52 +0200)
do not set softirqs to nice +19. _If_ for whatever reason
we missed to process some high-prio softirq and woke up
ksoftirqd, we should give it a fair chance to actually
get some work done, even if the system is under load.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
kernel/softirq.c

index 0b9886a00e74ba33ed59cafb8b02bc9d01570575..73217a9e2875b27909cb4c9db09a6ec2d4284a7c 100644 (file)
@@ -488,7 +488,6 @@ void __init softirq_init(void)
 
 static int ksoftirqd(void * __bind_cpu)
 {
-       set_user_nice(current, 19);
        current->flags |= PF_NOFREEZE;
 
        set_current_state(TASK_INTERRUPTIBLE);