Re: [PATCH v2 03/14] Move /proc/stat logic inside sched.c

From: Glauber Costa
Date: Sat Nov 12 2011 - 05:28:03 EST

On 11/11/2011 11:35 PM, Paul Turner wrote:
On 11/01/2011 02:19 PM, Glauber Costa wrote:
This patch moves all of the /proc/stat display code inside
sched.c. The goal is to later on, have a different version
of it per-cgroup. In containers environment, this is useful
to give each container a different and independent view of
the statistics displayed in this file.

Signed-off-by: Glauber Costa<glommer@xxxxxxxxxxxxx>
---
fs/proc/stat.c | 139 +-----------------------------------------------
include/linux/sched.h | 1 +
kernel/sched.c | 142 +++++++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 144 insertions(+), 138 deletions(-)


This feels a little contrived. sched.c isn't the right place for much of
this code. Why do you want to move it all instead of exporting the
functionality (e.g. remove static?).

Because later on in the series I start using task_group, which is a scheduler internal data structure (Since the very goal here is achieving
per cgroup data.

It seemed to me better to do this way - as much as I agree with you that a lot here may not belong in sched.c - than to use external functions. Since all we have outside sched.c is a task_struct,
we'd have to derive a task_group from it every time. Also,
as you can see in the followup patches, which task_group to use depends on the caller and possibly some runtime variables. So the computation is not as trivially fast as just getting a field in a structure.


diff --git a/kernel/sched.c b/kernel/sched.c
index e78e1aa..3f42916 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -71,6 +71,7 @@
#include<linux/ctype.h>
#include<linux/ftrace.h>
#include<linux/slab.h>
+#include<linux/tick.h>

#include<asm/tlb.h>
#include<asm/irq_regs.h>
@@ -9494,6 +9495,147 @@ struct cgroup_subsys cpu_cgroup_subsys = {

#endif /* CONFIG_CGROUP_SCHED */

+#ifndef fi
+#define arch_irq_stat_cpu(cpu) 0
+#endif
+#ifndef arch_irq_stat
+#define arch_irq_stat() 0
+#endif
+#ifndef arch_idle_time
+#define arch_idle_time(cpu) 0
+#endif
+
+static u64 get_idle_time(int cpu)
+{
+ u64 idle, idle_time = get_cpu_idle_time_us(cpu, NULL);
+
+ if (idle_time == -1ULL) {
+ /* !NO_HZ so we can rely on cpustat.idle */
+ idle = kstat_cpu(cpu).cpustat[IDLE];
+ idle += arch_idle_time(cpu);
+ } else
+ idle = usecs_to_cputime(idle_time);
+
+ return idle;
+}
+
+static u64 get_iowait_time(int cpu)
+{
+ u64 iowait, iowait_time = get_cpu_iowait_time_us(cpu, NULL);
+
+ if (iowait_time == -1ULL)
+ /* !NO_HZ so we can rely on cpustat.iowait */
+ iowait = kstat_cpu(cpu).cpustat[IOWAIT];
+ else
+ iowait = usecs_to_cputime(iowait_time);
+
+ return iowait;
+}
+
+int cpu_cgroup_proc_stat(struct seq_file *p)
+{
+ int i, j;
+ unsigned long jif;
+ u64 user, nice, system, idle, iowait, irq, softirq, steal;
+ u64 guest, guest_nice;
+ u64 sum = 0;
+ u64 sum_softirq = 0;
+ unsigned int per_softirq_sums[NR_SOFTIRQS] = {0};
+ struct timespec boottime;
+
+ user = nice = system = idle = iowait =
+ irq = softirq = steal = 0;
+ guest = guest_nice = 0;
+ getboottime(&boottime);
+ jif = boottime.tv_sec;
+
+ for_each_possible_cpu(i) {
+ user += kstat_cpu(i).cpustat[USER];
+ nice += kstat_cpu(i).cpustat[NICE];
+ system += kstat_cpu(i).cpustat[SYSTEM];
+ idle += get_idle_time(i);
+ iowait += get_iowait_time(i);
+ irq += kstat_cpu(i).cpustat[IRQ];
+ softirq += kstat_cpu(i).cpustat[SOFTIRQ];
+ steal += kstat_cpu(i).cpustat[STEAL];
+ guest += kstat_cpu(i).cpustat[GUEST];
+ guest_nice += kstat_cpu(i).cpustat[GUEST_NICE];
+
+ for (j = 0; j< NR_SOFTIRQS; j++) {
+ unsigned int softirq_stat = kstat_softirqs_cpu(j, i);
+
+ per_softirq_sums[j] += softirq_stat;
+ sum_softirq += softirq_stat;
+ }
+ }
+ sum += arch_irq_stat();
+
+ seq_printf(p, "cpu %llu %llu %llu %llu %llu %llu %llu %llu %llu "
+ "%llu\n",
+ (unsigned long long)cputime64_to_clock_t(user),
+ (unsigned long long)cputime64_to_clock_t(nice),
+ (unsigned long long)cputime64_to_clock_t(system),
+ (unsigned long long)cputime64_to_clock_t(idle),
+ (unsigned long long)cputime64_to_clock_t(iowait),
+ (unsigned long long)cputime64_to_clock_t(irq),
+ (unsigned long long)cputime64_to_clock_t(softirq),
+ (unsigned long long)cputime64_to_clock_t(steal),
+ (unsigned long long)cputime64_to_clock_t(guest),
+ (unsigned long long)cputime64_to_clock_t(guest_nice));
+ for_each_online_cpu(i) {
+ /* Copy values here to work around gcc-2.95.3, gcc-2.96 */

GCC 3.2 is the listed current minimum requirement. If this code is being
revisited this could be cleaned up.

+ user = kstat_cpu(i).cpustat[USER];
+ nice = kstat_cpu(i).cpustat[NICE];
+ system = kstat_cpu(i).cpustat[SYSTEM];
+ idle = get_idle_time(i);
+ iowait = get_iowait_time(i);
+ irq = kstat_cpu(i).cpustat[IRQ];
+ softirq = kstat_cpu(i).cpustat[SOFTIRQ];
+ steal = kstat_cpu(i).cpustat[STEAL];
+ guest = kstat_cpu(i).cpustat[GUEST];
+ guest_nice = kstat_cpu(i).cpustat[GUEST_NICE];
+ seq_printf(p,
+ "cpu%d %llu %llu %llu %llu %llu %llu %llu %llu %llu "
+ "%llu\n",
+ i,
+ (unsigned long long)cputime64_to_clock_t(user),
+ (unsigned long long)cputime64_to_clock_t(nice),
+ (unsigned long long)cputime64_to_clock_t(system),
+ (unsigned long long)cputime64_to_clock_t(idle),
+ (unsigned long long)cputime64_to_clock_t(iowait),
+ (unsigned long long)cputime64_to_clock_t(irq),
+ (unsigned long long)cputime64_to_clock_t(softirq),
+ (unsigned long long)cputime64_to_clock_t(steal),
+ (unsigned long long)cputime64_to_clock_t(guest),
+ (unsigned long long)cputime64_to_clock_t(guest_nice));
+ }
+ seq_printf(p, "intr %llu", (unsigned long long)sum);
+
+ /* sum again ? it could be updated? */
+ for_each_irq_nr(j)
+ seq_printf(p, " %u", kstat_irqs(j));
+
+ seq_printf(p,
+ "\nctxt %llu\n"
+ "btime %lu\n"
+ "processes %lu\n"
+ "procs_running %lu\n"
+ "procs_blocked %lu\n",
+ nr_context_switches(),
+ (unsigned long)jif,
+ total_forks,
+ nr_running(),
+ nr_iowait());
+
+ seq_printf(p, "softirq %llu", (unsigned long long)sum_softirq);
+
+ for (i = 0; i< NR_SOFTIRQS; i++)
+ seq_printf(p, " %u", per_softirq_sums[i]);
+ seq_putc(p, '\n');
+
+ return 0;
+}
+
#ifdef CONFIG_CGROUP_CPUACCT

/*


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/