From c2da3f1b711173b72378258496b49f74db7479de Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 8 Feb 2019 14:48:04 +0100 Subject: proc/stat: Make the interrupt statistics more efficient Waiman reported that on large systems with a large amount of interrupts the readout of /proc/stat takes a long time to sum up the interrupt statistics. In principle this is not a problem. but for unknown reasons some enterprise quality software reads /proc/stat with a high frequency. The reason for this is that interrupt statistics are accounted per cpu. So the /proc/stat logic has to sum up the interrupt stats for each interrupt. The interrupt core provides now a per interrupt summary counter which can be used to avoid the summation loops completely except for interrupts marked PER_CPU which are only a small fraction of the interrupt space if at all. Another simplification is to iterate only over the active interrupts and skip the potentially large gaps in the interrupt number space and just print zeros for the gaps without going into the interrupt core in the first place. Waiman provided test results from a 4-socket IvyBridge-EX system (60-core 120-thread, 3016 irqs) excuting a test program which reads /proc/stat 50,000 times: Before: 18.436s (sys 18.380s) After: 3.769s (sys 3.742s) Reported-by: Waiman Long Signed-off-by: Thomas Gleixner Reviewed-by: Alexey Dobriyan Reviewed-by: Waiman Long Reviewed-by: Marc Zyngier Reviewed-by: Davidlohr Bueso Cc: Matthew Wilcox Cc: Andrew Morton Cc: Kees Cook Cc: linux-fsdevel@vger.kernel.org Cc: Davidlohr Bueso Cc: Miklos Szeredi Cc: Daniel Colascione Cc: Dave Chinner Cc: Randy Dunlap Link: https://lkml.kernel.org/r/20190208135021.013828701@linutronix.de --- fs/proc/stat.c | 29 ++++++++++++++++++++++++++--- 1 file changed, 26 insertions(+), 3 deletions(-) (limited to 'fs/proc') diff --git a/fs/proc/stat.c b/fs/proc/stat.c index 535eda7857cf..76175211b304 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -79,6 +79,31 @@ static u64 get_iowait_time(int cpu) #endif +static void show_irq_gap(struct seq_file *p, unsigned int gap) +{ + static const char zeros[] = " 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0"; + + while (gap > 0) { + unsigned int inc; + + inc = min_t(unsigned int, gap, ARRAY_SIZE(zeros) / 2); + seq_write(p, zeros, 2 * inc); + gap -= inc; + } +} + +static void show_all_irqs(struct seq_file *p) +{ + unsigned int i, next = 0; + + for_each_active_irq(i) { + show_irq_gap(p, i - next); + seq_put_decimal_ull(p, " ", kstat_irqs_usr(i)); + next = i + 1; + } + show_irq_gap(p, nr_irqs - next); +} + static int show_stat(struct seq_file *p, void *v) { int i, j; @@ -156,9 +181,7 @@ static int show_stat(struct seq_file *p, void *v) } seq_put_decimal_ull(p, "intr ", (unsigned long long)sum); - /* sum again ? it could be updated? */ - for_each_irq_nr(j) - seq_put_decimal_ull(p, " ", kstat_irqs_usr(j)); + show_all_irqs(p); seq_printf(p, "\nctxt %llu\n" -- cgit