From: KAMEZAWA Hiroyuki Date: Wed, 27 Oct 2010 22:34:13 +0000 (-0700) Subject: /proc/stat: scalability of irq num per cpu X-Git-Url: https://git.stricted.de/?a=commitdiff_plain;h=f2c66cd8eeddedb440f33bc0f5cec1ed7ae376cb;p=GitHub%2FLineageOS%2FG12%2Fandroid_kernel_amlogic_linux-4.9.git /proc/stat: scalability of irq num per cpu /proc/stat shows the total number of all interrupts to each cpu. But when the number of IRQs are very large, it take very long time and 'cat /proc/stat' takes more than 10 secs. This is because sum of all irq events are counted when /proc/stat is read. This patch adds "sum of all irq" counter percpu and reduce read costs. The cost of reading /proc/stat is important because it's used by major applications as 'top', 'ps', 'w', etc.... A test on a mechin (4096cpu, 256 nodes, 4592 irqs) shows %time cat /proc/stat > /dev/null Before Patch: 12.627 sec After Patch: 2.459 sec Signed-off-by: KAMEZAWA Hiroyuki Tested-by: Jack Steiner Acked-by: Jack Steiner Cc: Yinghai Lu Cc: Ingo Molnar Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- diff --git a/fs/proc/stat.c b/fs/proc/stat.c index bf31b03fc275..b80c620565bf 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -52,9 +52,7 @@ static int show_stat(struct seq_file *p, void *v) guest = cputime64_add(guest, kstat_cpu(i).cpustat.guest); guest_nice = cputime64_add(guest_nice, kstat_cpu(i).cpustat.guest_nice); - for_each_irq_nr(j) { - sum += kstat_irqs_cpu(j, i); - } + sum += kstat_cpu_irqs_sum(i); sum += arch_irq_stat_cpu(i); for (j = 0; j < NR_SOFTIRQS; j++) { diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index c059044bc6dc..8b9b89085530 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -33,6 +33,7 @@ struct kernel_stat { #ifndef CONFIG_GENERIC_HARDIRQS unsigned int irqs[NR_IRQS]; #endif + unsigned long irqs_sum; unsigned int softirqs[NR_SOFTIRQS]; }; @@ -54,6 +55,7 @@ static inline void kstat_incr_irqs_this_cpu(unsigned int irq, struct irq_desc *desc) { kstat_this_cpu.irqs[irq]++; + kstat_this_cpu.irqs_sum++; } static inline unsigned int kstat_irqs_cpu(unsigned int irq, int cpu) @@ -65,8 +67,9 @@ static inline unsigned int kstat_irqs_cpu(unsigned int irq, int cpu) extern unsigned int kstat_irqs_cpu(unsigned int irq, int cpu); #define kstat_irqs_this_cpu(DESC) \ ((DESC)->kstat_irqs[smp_processor_id()]) -#define kstat_incr_irqs_this_cpu(irqno, DESC) \ - ((DESC)->kstat_irqs[smp_processor_id()]++) +#define kstat_incr_irqs_this_cpu(irqno, DESC) do {\ + ((DESC)->kstat_irqs[smp_processor_id()]++);\ + kstat_this_cpu.irqs_sum++; } while (0) #endif @@ -94,6 +97,13 @@ static inline unsigned int kstat_irqs(unsigned int irq) return sum; } +/* + * Number of interrupts per cpu, since bootup + */ +static inline unsigned int kstat_cpu_irqs_sum(unsigned int cpu) +{ + return kstat_cpu(cpu).irqs_sum; +} /* * Lock/unlock the current runqueue - to extract task statistics: