aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorChen, Kenneth W <kenneth.w.chen@intel.com>2006-02-14 13:53:10 -0800
committerLinus Torvalds <torvalds@g5.osdl.org>2006-02-14 16:09:34 -0800
commitd6077cb80cde4506720f9165eba99ee07438513f (patch)
treef4462e51cf0a14a113c0c524711636c8429424bb
parentf822566165dd46ff5de9bf895cfa6c51f53bb0c4 (diff)
[PATCH] sched: revert "filter affine wakeups"
Revert commit d7102e95b7b9c00277562c29aad421d2d521c5f6: [PATCH] sched: filter affine wakeups Apparently caused more than 10% performance regression for aim7 benchmark. The setup in use is 16-cpu HP rx8620, 64Gb of memory and 12 MSA1000s with 144 disks. Each disk is 72Gb with a single ext3 filesystem (courtesy of HP, who supplied benchmark results). The problem is, for aim7, the wake-up pattern is random, but it still needs load balancing action in the wake-up path to achieve best performance. With the above commit, lack of load balancing hurts that workload. However, for workloads like database transaction processing, the requirement is exactly opposite. In the wake up path, best performance is achieved with absolutely zero load balancing. We simply wake up the process on the CPU that it was previously run. Worst performance is obtained when we do load balancing at wake up. There isn't an easy way to auto detect the workload characteristics. Ingo's earlier patch that detects idle CPU and decide whether to load balance or not doesn't perform with aim7 either since all CPUs are busy (it causes even bigger perf. regression). Revert commit d7102e95b7b9c00277562c29aad421d2d521c5f6, which causes more than 10% performance regression with aim7. Signed-off-by: Ken Chen <kenneth.w.chen@intel.com> Acked-by: Ingo Molnar <mingo@elte.hu> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
-rw-r--r--include/linux/sched.h5
-rw-r--r--kernel/sched.c10
2 files changed, 2 insertions, 13 deletions
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9c1da0269a1..b6f51e3a38e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -697,12 +697,9 @@ struct task_struct {
int lock_depth; /* BKL lock depth */
-#if defined(CONFIG_SMP)
- int last_waker_cpu; /* CPU that last woke this task up */
-#if defined(__ARCH_WANT_UNLOCKED_CTXSW)
+#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
int oncpu;
#endif
-#endif
int prio, static_prio;
struct list_head run_list;
prio_array_t *array;
diff --git a/kernel/sched.c b/kernel/sched.c
index 87d93be336a..66d957227de 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1204,9 +1204,6 @@ static int try_to_wake_up(task_t *p, unsigned int state, int sync)
}
}
- if (p->last_waker_cpu != this_cpu)
- goto out_set_cpu;
-
if (unlikely(!cpu_isset(this_cpu, p->cpus_allowed)))
goto out_set_cpu;
@@ -1277,8 +1274,6 @@ out_set_cpu:
cpu = task_cpu(p);
}
- p->last_waker_cpu = this_cpu;
-
out_activate:
#endif /* CONFIG_SMP */
if (old_state == TASK_UNINTERRUPTIBLE) {
@@ -1360,12 +1355,9 @@ void fastcall sched_fork(task_t *p, int clone_flags)
#ifdef CONFIG_SCHEDSTATS
memset(&p->sched_info, 0, sizeof(p->sched_info));
#endif
-#if defined(CONFIG_SMP)
- p->last_waker_cpu = cpu;
-#if defined(__ARCH_WANT_UNLOCKED_CTXSW)
+#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
p->oncpu = 0;
#endif
-#endif
#ifdef CONFIG_PREEMPT
/* Want to start with kernel preemption disabled. */
task_thread_info(p)->preempt_count = 1;