Re: [PATCH v2 2/2] try to fix /proc/stat scalability of irq sum ofall cpu

[Andrew Morton]

On Thu, 21 Oct 2010 16:03:43 +0900
KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx> wrote:

> From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
> 
> In /proc/stat, the number of per-IRQ event is shown by making a sum
> each irq's events on all cpus. But we can make use of kstat_irqs().
> 
> kstat_irqs() do the same calculation, If !CONFIG_GENERIC_HARDIRQ,
> it's not a big cost. (Both of the number of cpus and irqs are small.)
> 
> If a system is very big and CONFIG_GENERIC_HARDIRQ, it does
> 
> 	for_each_irq()
> 		for_each_cpu()
> 			- look up a radix tree
> 			- read desc->irq_stat[cpu]
> This seems not efficient. This patch adds kstat_irqs() for
> CONFIG_GENRIC_HARDIRQ and change the calculation as
> 
> 	for_each_irq()
> 		look up radix tree
> 		for_each_cpu()
> 			- read desc->irq_stat[cpu]
> 
> This reduces cost.
> 
> A test on (4096cpusp, 256 nodes, 4592 irqs) host (by Jack Steiner)
> 
> %time cat /proc/stat > /dev/null
> 
> Before Patch:	 2.459 sec
> After Patch :	  .561 sec
> 
> Changelog:
>  - rebased onto mmotm-1020 (kernel/irq/handle.c is modified)
> 
> Tested-by: Jack Steiner <steiner@xxxxxxx>
> Acked-by: Jack Steiner <steiner@xxxxxxx>
> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
> ---
>  fs/proc/stat.c              |    9 ++-------
>  include/linux/kernel_stat.h |    4 ++++
>  kernel/irq/irqdesc.c        |   16 ++++++++++++++++
>  3 files changed, 22 insertions(+), 7 deletions(-)
> 
> Index: mmotm-1020/fs/proc/stat.c
> ===================================================================
> --- mmotm-1020.orig/fs/proc/stat.c
> +++ mmotm-1020/fs/proc/stat.c
> @@ -108,13 +108,8 @@ static int show_stat(struct seq_file *p,
>  	seq_printf(p, "intr %llu", (unsigned long long)sum);
>  
>  	/* sum again ? it could be updated? */
> -	for_each_irq_nr(j) {
> -		per_irq_sum = 0;
> -		for_each_possible_cpu(i)
> -			per_irq_sum += kstat_irqs_cpu(j, i);
> -
> -		seq_printf(p, " %u", per_irq_sum);
> -	}
> +	for_each_irq_nr(j)
> +		seq_printf(p, " %u", kstat_irqs(j));
>  
>  	seq_printf(p,
>  		"\nctxt %llu\n"
> Index: mmotm-1020/include/linux/kernel_stat.h
> ===================================================================
> --- mmotm-1020.orig/include/linux/kernel_stat.h
> +++ mmotm-1020/include/linux/kernel_stat.h
> @@ -86,6 +86,7 @@ static inline unsigned int kstat_softirq
>  /*
>   * Number of interrupts per specific IRQ source, since bootup
>   */
> +#ifndef CONFIG_GENERIC_HARDIRQS
>  static inline unsigned int kstat_irqs(unsigned int irq)
>  {
>  	unsigned int sum = 0;
> @@ -96,6 +97,9 @@ static inline unsigned int kstat_irqs(un
>  
>  	return sum;
>  }
> +#else
> +extern unsigned int kstat_irqs(unsigned int irq);
> +#endif

hrm, why on earth was that inlined.

>  /*
>   * Number of interrupts per cpu, since bootup
> Index: mmotm-1020/kernel/irq/irqdesc.c
> ===================================================================
> --- mmotm-1020.orig/kernel/irq/irqdesc.c
> +++ mmotm-1020/kernel/irq/irqdesc.c
> @@ -393,3 +393,19 @@ unsigned int kstat_irqs_cpu(unsigned int
>  	struct irq_desc *desc = irq_to_desc(irq);
>  	return desc ? desc->kstat_irqs[cpu] : 0;
>  }
> +
> +#ifdef CONFIG_GENERIC_HARDIRQS
> +unsigned int  kstat_irqs(unsigned int irq)
> +{
> +	struct irq_desc *desc = irq_to_desc(irq);
> +	int cpu;
> +	int sum = 0;
> +
> +	if (!desc)
> +		return 0;
> +	for_each_possible_cpu(cpu)
> +		sum += desc->kstat_irqs[cpu];
> +	return sum;
> +}
> +EXPORT_SYMBOL_GPL(kstat_irqs);

kstat_irqs() needs to be exported to modules because of some silliness
in drivers/isdn/hisax/config.c.  But in linux-next that silliness got
deleted and the kstat_irqs export was removed.

--- a/kernel/irq/irqdesc.c~proc-stat-fix-scalability-of-irq-sum-of-all-cpu-fix
+++ a/kernel/irq/irqdesc.c
@@ -395,7 +395,7 @@ unsigned int kstat_irqs_cpu(unsigned int
 }
 
 #ifdef CONFIG_GENERIC_HARDIRQS
-unsigned int  kstat_irqs(unsigned int irq)
+unsigned int kstat_irqs(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	int cpu;
@@ -407,5 +407,4 @@ unsigned int  kstat_irqs(unsigned int ir
 		sum += desc->kstat_irqs[cpu];
 	return sum;
 }
-EXPORT_SYMBOL_GPL(kstat_irqs);
-#endif /*CONFIG_GENERIC_HARDIRQS*/
+#endif /* CONFIG_GENERIC_HARDIRQS */
_

--
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/