[patch] sched: accurate user accounting

[Ingo Molnar <mingo@elte.hu>]

* Con Kolivas <kernel@kolivas.org> wrote:

> For an rsdl 0.33 patched kernel. Comments? Overhead worth it?

we want to do this - and we should do this to the vanilla scheduler 
first and check the results. I've back-merged the patch to before RSDL 
and have tested it - find the patch below. Vale, could you try this 
patch against a 2.6.21-rc4-ish kernel and re-test your testcase?

	Ingo

--------------------->
Subject: [patch] sched: accurate user accounting
From: Con Kolivas <kernel@kolivas.org>

Currently we only do cpu accounting to userspace based on what is 
actually happening precisely on each tick. The accuracy of that 
accounting gets progressively worse the lower HZ is. As we already keep 
accounting of nanosecond resolution we can accurately track user cpu, 
nice cpu and idle cpu if we move the accounting to update_cpu_clock with 
a nanosecond cpu_usage_stat entry. This increases overhead slightly but 
avoids the problem of tick aliasing errors making accounting unreliable.

Signed-off-by: Con Kolivas <kernel@kolivas.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/kernel_stat.h |    3 ++
 include/linux/sched.h       |    2 -
 kernel/sched.c              |   52 +++++++++++++++++++++++++++++++++++++++++---
 kernel/timer.c              |    5 +---
 4 files changed, 55 insertions(+), 7 deletions(-)

Index: linux/include/linux/kernel_stat.h
===================================================================
--- linux.orig/include/linux/kernel_stat.h
+++ linux/include/linux/kernel_stat.h
@@ -16,11 +16,14 @@
 
 struct cpu_usage_stat {
 	cputime64_t user;
+	cputime64_t user_ns;
 	cputime64_t nice;
+	cputime64_t nice_ns;
 	cputime64_t system;
 	cputime64_t softirq;
 	cputime64_t irq;
 	cputime64_t idle;
+	cputime64_t idle_ns;
 	cputime64_t iowait;
 	cputime64_t steal;
 };
Index: linux/include/linux/sched.h
===================================================================
--- linux.orig/include/linux/sched.h
+++ linux/include/linux/sched.h
@@ -882,7 +882,7 @@ struct task_struct {
 	int __user *clear_child_tid;		/* CLONE_CHILD_CLEARTID */
 
 	unsigned long rt_priority;
-	cputime_t utime, stime;
+	cputime_t utime, utime_ns, stime;
 	unsigned long nvcsw, nivcsw; /* context switch counts */
 	struct timespec start_time;
 /* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */
Index: linux/kernel/sched.c
===================================================================
--- linux.orig/kernel/sched.c
+++ linux/kernel/sched.c
@@ -167,6 +167,12 @@ unsigned long long __attribute__((weak))
 	(JIFFIES_TO_NS(MAX_SLEEP_AVG * \
 		(MAX_BONUS / 2 + DELTA((p)) + 1) / MAX_BONUS - 1))
 
+/*
+ * Some helpers for converting nanosecond timing to jiffy resolution
+ */
+#define NS_TO_JIFFIES(TIME)   ((TIME) / (1000000000 / HZ))
+#define JIFFIES_TO_NS(TIME)   ((TIME) * (1000000000 / HZ))
+
 #define TASK_PREEMPTS_CURR(p, rq) \
 	((p)->prio < (rq)->curr->prio)
 
@@ -3017,8 +3023,50 @@ EXPORT_PER_CPU_SYMBOL(kstat);
 static inline void
 update_cpu_clock(struct task_struct *p, struct rq *rq, unsigned long long now)
 {
-	p->sched_time += now - p->last_ran;
+	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+	cputime64_t time_diff = now - p->last_ran;
+
+	p->sched_time += time_diff;
 	p->last_ran = rq->most_recent_timestamp = now;
+	if (p != rq->idle) {
+		cputime_t utime_diff = time_diff;
+
+		if (TASK_NICE(p) > 0) {
+			cpustat->nice_ns = cputime64_add(cpustat->nice_ns,
+							 time_diff);
+			if (NS_TO_JIFFIES(cpustat->nice_ns) > 1) {
+				cpustat->nice_ns =
+					cputime64_sub(cpustat->nice_ns,
+					JIFFIES_TO_NS(1));
+				cpustat->nice =
+					cputime64_add(cpustat->nice, 1);
+			}
+		} else {
+			cpustat->user_ns = cputime64_add(cpustat->user_ns,
+						time_diff);
+			if (NS_TO_JIFFIES(cpustat->user_ns) > 1) {
+				cpustat->user_ns =
+					cputime64_sub(cpustat->user_ns,
+					JIFFIES_TO_NS(1));
+				cpustat ->user =
+					cputime64_add(cpustat->user, 1);
+			}
+		}
+		p->utime_ns = cputime_add(p->utime_ns, utime_diff);
+		if (NS_TO_JIFFIES(p->utime_ns) > 1) {
+			p->utime_ns = cputime_sub(p->utime_ns,
+						  JIFFIES_TO_NS(1));
+			p->utime = cputime_add(p->utime,
+					       jiffies_to_cputime(1));
+		}
+	} else {
+		cpustat->idle_ns = cputime64_add(cpustat->idle_ns, time_diff);
+		if (NS_TO_JIFFIES(cpustat->idle_ns) > 1) {
+			cpustat->idle_ns = cputime64_sub(cpustat->idle_ns,
+							 JIFFIES_TO_NS(1));
+			cpustat->idle = cputime64_add(cpustat->idle, 1);
+		}
+	}
 }
 
 /*
@@ -3104,8 +3152,6 @@ void account_system_time(struct task_str
 		cpustat->system = cputime64_add(cpustat->system, tmp);
 	else if (atomic_read(&rq->nr_iowait) > 0)
 		cpustat->iowait = cputime64_add(cpustat->iowait, tmp);
-	else
-		cpustat->idle = cputime64_add(cpustat->idle, tmp);
 	/* Account for system time used */
 	acct_update_integrals(p);
 }
Index: linux/kernel/timer.c
===================================================================
--- linux.orig/kernel/timer.c
+++ linux/kernel/timer.c
@@ -1196,10 +1196,9 @@ void update_process_times(int user_tick)
 	int cpu = smp_processor_id();
 
 	/* Note: this timer irq context must be accounted for as well. */
-	if (user_tick)
-		account_user_time(p, jiffies_to_cputime(1));
-	else
+	if (!user_tick)
 		account_system_time(p, HARDIRQ_OFFSET, jiffies_to_cputime(1));
+	/* User time is accounted for in update_cpu_clock in sched.c */
 	run_local_timers();
 	if (rcu_pending(cpu))
 		rcu_check_callbacks(cpu, user_tick);