Avoid too many remote cpu references due to /proc/stat
Optimize show_stat to collect per-irq information just once.
On x86_64, with newer kernel versions, kstat_irqs is a bit of a problem.
On every call to kstat_irqs, the process brings in per-cpu data from all
online cpus. Doing this for NR_IRQS, which is now 256 + 32 * NR_CPUS
results in (256+32*63) * 63 remote cpu references on a 64 cpu config.
Considering the fact that we already compute this value per-cpu, we can
save on the remote references as below.
Signed-off-by: Alok N Kataria <alok.kataria@calsoftinc.com>
Signed-off-by: Ravikiran Thirumalai <kiran@scalex86.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index d24b8d4..f133afe 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -445,6 +445,11 @@
cputime64_t user, nice, system, idle, iowait, irq, softirq, steal;
u64 sum = 0;
struct timespec boottime;
+ unsigned int *per_irq_sum;
+
+ per_irq_sum = kzalloc(sizeof(unsigned int)*NR_IRQS, GFP_KERNEL);
+ if (!per_irq_sum)
+ return -ENOMEM;
user = nice = system = idle = iowait =
irq = softirq = steal = cputime64_zero;
@@ -462,8 +467,11 @@
irq = cputime64_add(irq, kstat_cpu(i).cpustat.irq);
softirq = cputime64_add(softirq, kstat_cpu(i).cpustat.softirq);
steal = cputime64_add(steal, kstat_cpu(i).cpustat.steal);
- for (j = 0 ; j < NR_IRQS ; j++)
- sum += kstat_cpu(i).irqs[j];
+ for (j = 0; j < NR_IRQS; j++) {
+ unsigned int temp = kstat_cpu(i).irqs[j];
+ sum += temp;
+ per_irq_sum[j] += temp;
+ }
}
seq_printf(p, "cpu %llu %llu %llu %llu %llu %llu %llu %llu\n",
@@ -501,7 +509,7 @@
#if !defined(CONFIG_PPC64) && !defined(CONFIG_ALPHA) && !defined(CONFIG_IA64)
for (i = 0; i < NR_IRQS; i++)
- seq_printf(p, " %u", kstat_irqs(i));
+ seq_printf(p, " %u", per_irq_sum[i]);
#endif
seq_printf(p,
@@ -516,6 +524,7 @@
nr_running(),
nr_iowait());
+ kfree(per_irq_sum);
return 0;
}
