summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorJack Steiner <steiner@sgi.com>2006-03-31 02:31:21 -0800
committerLinus Torvalds <torvalds@g5.osdl.org>2006-03-31 12:18:58 -0800
commitdb1b1fefc2cecbff2e4214062fa8c680cb6e7b7d (patch)
treead8e68882f7c36216e16ab264101c5da96ccd5c9
parent3055addadbe9bfb2365006a1c13fd342a8d30d52 (diff)
downloadop-kernel-dev-db1b1fefc2cecbff2e4214062fa8c680cb6e7b7d.zip
op-kernel-dev-db1b1fefc2cecbff2e4214062fa8c680cb6e7b7d.tar.gz
[PATCH] sched: reduce overhead of calc_load
Currently, count_active_tasks() calls both nr_running() & nr_interruptible(). Each of these functions does a "for_each_cpu" & reads values from the runqueue of each cpu. Although this is not a lot of instructions, each runqueue may be located on different node. Depending on the architecture, a unique TLB entry may be required to access each runqueue. Since there may be more runqueues than cpu TLB entries, a scan of all runqueues can trash the TLB. Each memory reference incurs a TLB miss & refill. In addition, the runqueue cacheline that contains nr_running & nr_uninterruptible may be evicted from the cache between the two passes. This causes unnecessary cache misses. Combining nr_running() & nr_interruptible() into a single function substantially reduces the TLB & cache misses on large systems. This should have no measureable effect on smaller systems. On a 128p IA64 system running a memory stress workload, the new function reduced the overhead of calc_load() from 605 usec/call to 324 usec/call. Signed-off-by: Jack Steiner <steiner@sgi.com> Acked-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
-rw-r--r--include/linux/sched.h1
-rw-r--r--kernel/sched.c15
-rw-r--r--kernel/timer.c2
3 files changed, 17 insertions, 1 deletions
diff --git a/include/linux/sched.h b/include/linux/sched.h
index d04186d..ab84adf 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -100,6 +100,7 @@ DECLARE_PER_CPU(unsigned long, process_counts);
extern int nr_processes(void);
extern unsigned long nr_running(void);
extern unsigned long nr_uninterruptible(void);
+extern unsigned long nr_active(void);
extern unsigned long nr_iowait(void);
#include <linux/time.h>
diff --git a/kernel/sched.c b/kernel/sched.c
index a9ecac3..6e52e0a 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1658,6 +1658,21 @@ unsigned long nr_iowait(void)
return sum;
}
+unsigned long nr_active(void)
+{
+ unsigned long i, running = 0, uninterruptible = 0;
+
+ for_each_online_cpu(i) {
+ running += cpu_rq(i)->nr_running;
+ uninterruptible += cpu_rq(i)->nr_uninterruptible;
+ }
+
+ if (unlikely((long)uninterruptible < 0))
+ uninterruptible = 0;
+
+ return running + uninterruptible;
+}
+
#ifdef CONFIG_SMP
/*
diff --git a/kernel/timer.c b/kernel/timer.c
index 9062a82..6b812c0 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -825,7 +825,7 @@ void update_process_times(int user_tick)
*/
static unsigned long count_active_tasks(void)
{
- return (nr_running() + nr_uninterruptible()) * FIXED_1;
+ return nr_active() * FIXED_1;
}
/*
OpenPOWER on IntegriCloud