diff options
author | KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> | 2010-10-27 18:34:15 -0400 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2010-10-27 21:03:13 -0400 |
commit | 478735e38887077ac77a9756121b6ce0cb956e2f (patch) | |
tree | 7b42110f71b1711f56cbbc0a01f00894b221337d /kernel | |
parent | f2c66cd8eeddedb440f33bc0f5cec1ed7ae376cb (diff) |
/proc/stat: fix scalability of irq sum of all cpu
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
[akpm@linux-foundation.org: unexport kstat_irqs, coding-style tweaks]
[akpm@linux-foundation.org: fix unused variable 'per_irq_sum']
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Tested-by: Jack Steiner <steiner@sgi.com>
Acked-by: Jack Steiner <steiner@sgi.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/irq/irqdesc.c | 15 |
1 files changed, 15 insertions, 0 deletions
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 9d917ff72675..9988d03797f5 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c | |||
@@ -393,3 +393,18 @@ unsigned int kstat_irqs_cpu(unsigned int irq, int cpu) | |||
393 | struct irq_desc *desc = irq_to_desc(irq); | 393 | struct irq_desc *desc = irq_to_desc(irq); |
394 | return desc ? desc->kstat_irqs[cpu] : 0; | 394 | return desc ? desc->kstat_irqs[cpu] : 0; |
395 | } | 395 | } |
396 | |||
397 | #ifdef CONFIG_GENERIC_HARDIRQS | ||
398 | unsigned int kstat_irqs(unsigned int irq) | ||
399 | { | ||
400 | struct irq_desc *desc = irq_to_desc(irq); | ||
401 | int cpu; | ||
402 | int sum = 0; | ||
403 | |||
404 | if (!desc) | ||
405 | return 0; | ||
406 | for_each_possible_cpu(cpu) | ||
407 | sum += desc->kstat_irqs[cpu]; | ||
408 | return sum; | ||
409 | } | ||
410 | #endif /* CONFIG_GENERIC_HARDIRQS */ | ||