diff -purN -X /home/mbligh/.diff.exclude 501-ppc64-pci/fs/proc/array.c 520-queuestat/fs/proc/array.c
--- 501-ppc64-pci/fs/proc/array.c 2003-06-05 14:38:39.000000000 -0700
+++ 520-queuestat/fs/proc/array.c 2003-07-28 19:01:30.000000000 -0700
@@ -336,7 +336,7 @@ int proc_pid_stat(struct task_struct *ta
read_unlock(&tasklist_lock);
res = sprintf(buffer,"%d (%s) %c %d %d %d %d %d %lu %lu \
%lu %lu %lu %lu %lu %ld %ld %ld %ld %ld %ld %llu %lu %ld %lu %lu %lu %lu %lu \
-%lu %lu %lu %lu %lu %lu %lu %lu %d %d %lu %lu\n",
+%lu %lu %lu %lu %lu %lu %lu %lu %d %d %lu %lu %lu %lu %lu\n",
task->pid,
task->comm,
state,
@@ -382,7 +382,10 @@ int proc_pid_stat(struct task_struct *ta
task->exit_signal,
task_cpu(task),
task->rt_priority,
- task->policy);
+ task->policy,
+ jiffies_to_clock_t(task->sched_info.inter_arrival_time),
+ jiffies_to_clock_t(task->sched_info.service_time),
+ jiffies_to_clock_t(task->sched_info.response_time));
if(mm)
mmput(mm);
return res;
diff -purN -X /home/mbligh/.diff.exclude 501-ppc64-pci/fs/proc/proc_misc.c 520-queuestat/fs/proc/proc_misc.c
--- 501-ppc64-pci/fs/proc/proc_misc.c 2003-07-28 18:58:37.000000000 -0700
+++ 520-queuestat/fs/proc/proc_misc.c 2003-07-28 19:01:30.000000000 -0700
@@ -464,14 +464,20 @@ static int kstat_read_proc(char *page, c
jiffies_to_clock_t(idle),
jiffies_to_clock_t(iowait));
for (i = 0 ; i < NR_CPUS; i++){
- if (!cpu_online(i)) continue;
- len += sprintf(page + len, "cpu%d %u %u %u %u %u\n",
+ struct sched_info info;
+ if (!cpu_online(i))
+ continue;
+ cpu_sched_info(&info, i);
+ len += sprintf(page + len, "cpu%d %u %u %u %u %u %u %u %u\n",
i,
jiffies_to_clock_t(kstat_cpu(i).cpustat.user),
jiffies_to_clock_t(kstat_cpu(i).cpustat.nice),
jiffies_to_clock_t(kstat_cpu(i).cpustat.system),
jiffies_to_clock_t(kstat_cpu(i).cpustat.idle),
- jiffies_to_clock_t(kstat_cpu(i).cpustat.iowait));
+ jiffies_to_clock_t(kstat_cpu(i).cpustat.iowait),
+ (uint) jiffies_to_clock_t(info.inter_arrival_time),
+ (uint) jiffies_to_clock_t(info.service_time),
+ (uint) jiffies_to_clock_t(info.response_time));
}
len += sprintf(page + len, "intr %u", sum);
diff -purN -X /home/mbligh/.diff.exclude 501-ppc64-pci/include/linux/sched.h 520-queuestat/include/linux/sched.h
--- 501-ppc64-pci/include/linux/sched.h 2003-07-28 18:58:44.000000000 -0700
+++ 520-queuestat/include/linux/sched.h 2003-07-28 19:01:30.000000000 -0700
@@ -95,6 +95,9 @@ extern unsigned long nr_running(void);
extern unsigned long nr_uninterruptible(void);
extern unsigned long nr_iowait(void);
+struct sched_info;
+extern void cpu_sched_info(struct sched_info *, int);
+
#include <linux/time.h>
#include <linux/param.h>
#include <linux/resource.h>
@@ -327,6 +330,13 @@ struct k_itimer {
struct sigqueue *sigq; /* signal queue entry. */
};
+struct sched_info {
+ /* running averages */
+ unsigned long response_time, inter_arrival_time, service_time;
+
+ /* timestamps */
+ unsigned long last_arrival, began_service;
+};
struct io_context; /* See blkdev.h */
void exit_io_context(void);
@@ -351,6 +361,8 @@ struct task_struct {
unsigned long cpus_allowed;
unsigned int time_slice, first_time_slice;
+ struct sched_info sched_info;
+
struct list_head tasks;
struct list_head ptrace_children;
struct list_head ptrace_list;
diff -purN -X /home/mbligh/.diff.exclude 501-ppc64-pci/kernel/sched.c 520-queuestat/kernel/sched.c
--- 501-ppc64-pci/kernel/sched.c 2003-07-28 18:58:52.000000000 -0700
+++ 520-queuestat/kernel/sched.c 2003-07-28 19:01:30.000000000 -0700
@@ -59,6 +59,11 @@
#define TASK_USER_PRIO(p) USER_PRIO((p)->static_prio)
#define MAX_USER_PRIO (USER_PRIO(MAX_PRIO))
+/* the FIXED_1 gunk is so running averages don't vanish prematurely */
+#define RAVG_WEIGHT 128
+#define RAVG_FACTOR (RAVG_WEIGHT*FIXED_1)
+#define RUNNING_AVG(x,y) (((RAVG_WEIGHT-1)*(x)+RAVG_FACTOR*(y))/RAVG_WEIGHT)
+
/*
* These are the 'tuning knobs' of the scheduler:
*
@@ -184,6 +189,8 @@ struct runqueue {
struct list_head migration_queue;
atomic_t nr_iowait;
+
+ struct sched_info info;
};
static DEFINE_PER_CPU(struct runqueue, runqueues);
@@ -273,6 +280,74 @@ static inline void task_rq_unlock(runque
spin_unlock_irqrestore(&rq->lock, *flags);
}
+static inline void sched_info_arrive(task_t *t)
+{
+ unsigned long now = jiffies;
+ unsigned long diff = now - t->sched_info.last_arrival;
+ struct runqueue *rq = task_rq(t);
+
+ t->sched_info.inter_arrival_time =
+ RUNNING_AVG(t->sched_info.inter_arrival_time, diff);
+ t->sched_info.last_arrival = now;
+
+ if (!rq)
+ return;
+ diff = now - rq->info.last_arrival;
+ rq->info.inter_arrival_time =
+ RUNNING_AVG(rq->info.inter_arrival_time, diff);
+ rq->info.last_arrival = now;
+}
+
+/* is this ever used? */
+static inline void sched_info_depart(task_t *t)
+{
+ struct runqueue *rq = task_rq(t);
+ unsigned long diff, now = jiffies;
+
+ diff = now - t->sched_info.began_service;
+ t->sched_info.service_time =
+ RUNNING_AVG(t->sched_info.service_time, diff);
+
+ if (!rq)
+ return;
+ diff = now - rq->info.began_service;
+ rq->info.service_time =
+ RUNNING_AVG(rq->info.service_time, diff);
+}
+
+static inline void sched_info_switch(task_t *prev, task_t *next)
+{
+ struct runqueue *rq = task_rq(prev);
+ unsigned long diff, now = jiffies;
+
+ /* prev now departs the cpu */
+ sched_info_depart(prev);
+
+ /* only for involuntary context switches */
+ if (prev->state == TASK_RUNNING)
+ sched_info_arrive(prev);
+
+ diff = now - next->sched_info.last_arrival;
+ next->sched_info.response_time =
+ RUNNING_AVG(next->sched_info.response_time, diff);
+ next->sched_info.began_service = now;
+
+ if (!rq)
+ return;
+ /* yes, reusing next's service time is valid */
+ rq->info.response_time =
+ RUNNING_AVG(rq->info.response_time, diff);
+ rq->info.began_service = now;
+
+ if (prev->state != TASK_RUNNING)
+ return;
+ /* if prev arrived subtract rq's last arrival from its arrival */
+ diff = now - rq->info.last_arrival;
+ rq->info.inter_arrival_time =
+ RUNNING_AVG(rq->info.inter_arrival_time, diff);
+ rq->info.last_arrival = now;
+}
+
/*
* rq_lock - lock a given runqueue and disable interrupts.
*/
@@ -505,15 +580,18 @@ repeat_lock_task:
(p->cpus_allowed & (1UL << smp_processor_id())))) {
set_task_cpu(p, smp_processor_id());
+ sched_info_arrive(p);
task_rq_unlock(rq, &flags);
goto repeat_lock_task;
}
if (old_state == TASK_UNINTERRUPTIBLE)
rq->nr_uninterruptible--;
- if (sync)
+ if (sync) {
+ sched_info_arrive(p);
__activate_task(p, rq);
- else {
+ } else {
activate_task(p, rq);
+ sched_info_arrive(p);
if (p->prio < rq->curr->prio)
resched_task(rq->curr);
}
@@ -567,6 +645,7 @@ void wake_up_forked_process(task_t * p)
p->sleep_avg = p->sleep_avg * CHILD_PENALTY / 100;
p->prio = effective_prio(p);
set_task_cpu(p, smp_processor_id());
+ sched_info_arrive(p);
if (unlikely(!current->array))
__activate_task(p, rq);
@@ -728,6 +807,11 @@ unsigned long nr_iowait(void)
return sum;
}
+void cpu_sched_info(struct sched_info *info, int cpu)
+{
+ memcpy(info, &cpu_rq(cpu)->info, sizeof(struct sched_info));
+}
+
/*
* double_rq_lock - safely lock two runqueues
*
@@ -1417,6 +1501,7 @@ switch_tasks:
if (likely(prev != next)) {
rq->nr_switches++;
+ sched_info_switch(prev, next);
rq->curr = next;
prepare_arch_switch(rq, next);