The patch titled
Subject: procfs: add num_to_str() to speed up /proc/stat
has been added to the -mm tree. Its filename is
procfs-add-num_to_str-to-speed-up-proc-stat.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Subject: procfs: add num_to_str() to speed up /proc/stat
== stat_check.py
num = 0
with open("/proc/stat") as f:
while num < 1000 :
data = f.read()
f.seek(0, 0)
num = num + 1
==
perf shows
20.39% stat_check.py [kernel.kallsyms] [k] format_decode
13.41% stat_check.py [kernel.kallsyms] [k] number
12.61% stat_check.py [kernel.kallsyms] [k] vsnprintf
10.85% stat_check.py [kernel.kallsyms] [k] memcpy
4.85% stat_check.py [kernel.kallsyms] [k] radix_tree_lookup
4.43% stat_check.py [kernel.kallsyms] [k] seq_printf
This patch removes most of calls to vsnprintf() by adding
num_to_str() and seq_print_decimal_ull(), which prints decimal numbers
without rich functions provided by printf().
On my 8cpu box.
== Before patch ==
[root@bluextal test]# time ./stat_check.py
real 0m0.150s
user 0m0.026s
sys 0m0.121s
== After patch ==
[root@bluextal test]# time ./stat_check.py
real 0m0.055s
user 0m0.022s
sys 0m0.030s
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Cc: Eric Dumazet <eric.dumazet@xxxxxxxxx>
Cc: Glauber Costa <glommer@xxxxxxxxxxxxx>
Cc: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxx>
Cc: Paul Turner <pjt@xxxxxxxxxx>
Cc: Russell King <rmk@xxxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/proc/stat.c | 55 ++++++++++++++++++-------------------
fs/seq_file.c | 34 ++++++++++++++++++++++
include/linux/kernel.h | 8 +++++
include/linux/seq_file.h | 5 ++-
lib/vsprintf.c | 14 +++++++++
5 files changed, 87 insertions(+), 29 deletions(-)
diff -puN fs/proc/stat.c~procfs-add-num_to_str-to-speed-up-proc-stat fs/proc/stat.c
--- a/fs/proc/stat.c~procfs-add-num_to_str-to-speed-up-proc-stat
+++ a/fs/proc/stat.c
@@ -89,18 +89,19 @@ static int show_stat(struct seq_file *p,
}
sum += arch_irq_stat();
- seq_printf(p, "cpu %llu %llu %llu %llu %llu %llu %llu %llu %llu "
- "%llu\n",
- (unsigned long long)cputime64_to_clock_t(user),
- (unsigned long long)cputime64_to_clock_t(nice),
- (unsigned long long)cputime64_to_clock_t(system),
- (unsigned long long)cputime64_to_clock_t(idle),
- (unsigned long long)cputime64_to_clock_t(iowait),
- (unsigned long long)cputime64_to_clock_t(irq),
- (unsigned long long)cputime64_to_clock_t(softirq),
- (unsigned long long)cputime64_to_clock_t(steal),
- (unsigned long long)cputime64_to_clock_t(guest),
- (unsigned long long)cputime64_to_clock_t(guest_nice));
+ seq_puts(p, "cpu ");
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(user));
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(nice));
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(system));
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(idle));
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(iowait));
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(irq));
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(softirq));
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(steal));
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest));
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest_nice));
+ seq_putc(p, '\n');
+
for_each_online_cpu(i) {
/* Copy values here to work around gcc-2.95.3, gcc-2.96 */
user = kcpustat_cpu(i).cpustat[CPUTIME_USER];
@@ -113,26 +114,24 @@ static int show_stat(struct seq_file *p,
steal = kcpustat_cpu(i).cpustat[CPUTIME_STEAL];
guest = kcpustat_cpu(i).cpustat[CPUTIME_GUEST];
guest_nice = kcpustat_cpu(i).cpustat[CPUTIME_GUEST_NICE];
- seq_printf(p,
- "cpu%d %llu %llu %llu %llu %llu %llu %llu %llu %llu "
- "%llu\n",
- i,
- (unsigned long long)cputime64_to_clock_t(user),
- (unsigned long long)cputime64_to_clock_t(nice),
- (unsigned long long)cputime64_to_clock_t(system),
- (unsigned long long)cputime64_to_clock_t(idle),
- (unsigned long long)cputime64_to_clock_t(iowait),
- (unsigned long long)cputime64_to_clock_t(irq),
- (unsigned long long)cputime64_to_clock_t(softirq),
- (unsigned long long)cputime64_to_clock_t(steal),
- (unsigned long long)cputime64_to_clock_t(guest),
- (unsigned long long)cputime64_to_clock_t(guest_nice));
+ seq_printf(p, "cpu %d", i);
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(user));
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(nice));
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(system));
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(idle));
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(iowait));
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(irq));
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(softirq));
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(steal));
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest));
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest_nice));
+ seq_putc(p, '\n');
}
seq_printf(p, "intr %llu", (unsigned long long)sum);
/* sum again ? it could be updated? */
for_each_irq_nr(j)
- seq_printf(p, " %u", kstat_irqs(j));
+ seq_put_decimal_ull(p, ' ', kstat_irqs(j));
seq_printf(p,
"\nctxt %llu\n"
@@ -149,7 +148,7 @@ static int show_stat(struct seq_file *p,
seq_printf(p, "softirq %llu", (unsigned long long)sum_softirq);
for (i = 0; i < NR_SOFTIRQS; i++)
- seq_printf(p, " %u", per_softirq_sums[i]);
+ seq_put_decimal_ull(p, ' ', per_softirq_sums[i]);
seq_putc(p, '\n');
return 0;
diff -puN fs/seq_file.c~procfs-add-num_to_str-to-speed-up-proc-stat fs/seq_file.c
--- a/fs/seq_file.c~procfs-add-num_to_str-to-speed-up-proc-stat
+++ a/fs/seq_file.c
@@ -644,6 +644,40 @@ int seq_puts(struct seq_file *m, const c
}
EXPORT_SYMBOL(seq_puts);
+/*
+ * A helper routine for putting decimal numbers without rich format of printf().
+ * only 'unsigned long long' is supported.
+ * This routine will put one byte delimiter + number into seq_file.
+ * This routine is very quick when you show lots of numbers.
+ * In usual cases, it will be better to use seq_printf(). It's easier to read.
+ */
+int seq_put_decimal_ull(struct seq_file *m, char delimiter,
+ unsigned long long num)
+{
+ int len;
+
+ if (m->count + 2 >= m->size) /* we'll write 2 bytes at least */
+ goto overflow;
+
+ if (num < 10) {
+ m->buf[m->count++] = delimiter;
+ m->buf[m->count++] = num + '0';
+ return 0;
+ }
+
+ m->buf[m->count++] = delimiter;
+
+ len = num_to_str(m->buf + m->count, m->size - m->count, num);
+ if (!len)
+ goto overflow;
+ m->count += len;
+ return 0;
+overflow:
+ m->count = m->size;
+ return -1;
+}
+EXPORT_SYMBOL(seq_put_decimal_ull);
+
/**
* seq_write - write arbitrary data to buffer
* @seq: seq_file identifying the buffer to which data should be written
diff -puN include/linux/kernel.h~procfs-add-num_to_str-to-speed-up-proc-stat include/linux/kernel.h
--- a/include/linux/kernel.h~procfs-add-num_to_str-to-speed-up-proc-stat
+++ a/include/linux/kernel.h
@@ -299,6 +299,14 @@ extern long long simple_strtoll(const ch
#define strict_strtoull kstrtoull
#define strict_strtoll kstrtoll
+/*
+ * Convert passed number to decimal string.
+ * returns returns the length of string. at buffer overflow, returns 0.
+ *
+ * If speed is not important, use snprintf(). It's easy to read the code.
+ */
+extern int num_to_str(char *buf, int size, unsigned long long num);
+
/* lib/printf utilities */
extern __printf(2, 3) int sprintf(char *buf, const char * fmt, ...);
diff -puN include/linux/seq_file.h~procfs-add-num_to_str-to-speed-up-proc-stat include/linux/seq_file.h
--- a/include/linux/seq_file.h~procfs-add-num_to_str-to-speed-up-proc-stat
+++ a/include/linux/seq_file.h
@@ -122,8 +122,11 @@ void *__seq_open_private(struct file *,
int seq_open_private(struct file *, const struct seq_operations *, int);
int seq_release_private(struct inode *, struct file *);
-#define SEQ_START_TOKEN ((void *)1)
+/* defined in lib/vsprintf.c */
+int seq_put_decimal_ull(struct seq_file *m, char delimiter,
+ unsigned long long num);
+#define SEQ_START_TOKEN ((void *)1)
/*
* Helpers for iteration over list_head-s in seq_files
*/
diff -puN lib/vsprintf.c~procfs-add-num_to_str-to-speed-up-proc-stat lib/vsprintf.c
--- a/lib/vsprintf.c~procfs-add-num_to_str-to-speed-up-proc-stat
+++ a/lib/vsprintf.c
@@ -212,6 +212,20 @@ char *put_dec(char *buf, unsigned long l
}
}
+int num_to_str(char *buf, int size, unsigned long long num)
+{
+ char tmp[66];
+ int idx, len;
+
+ len = put_dec(tmp, num) - tmp;
+
+ if (len > size)
+ return 0;
+ for (idx = 0; idx < len; ++idx)
+ buf[idx] = tmp[len - idx - 1];
+ return len;
+}
+
#define ZEROPAD 1 /* pad with zero */
#define SIGN 2 /* unsigned/signed long */
#define PLUS 4 /* show plus */
_
Subject: Subject: procfs: add num_to_str() to speed up /proc/stat
Patches currently in -mm which might be from kamezawa.hiroyu@xxxxxxxxxxxxxx are
origin.patch
mm-postpone-migrated-page-mapping-reset.patch
linux-next.patch
mm-memcontrolc-fix-warning-with-config_numa=n.patch
mm-oom-avoid-looping-when-chosen-thread-detaches-its-mm.patch
mm-oom-fold-oom_kill_task-into-oom_kill_process.patch
mm-oom-do-not-emit-oom-killer-warning-if-chosen-thread-is-already-exiting.patch
mm-add-rss-counters-consistency-check.patch
mm-vmscanc-cleanup-with-s-reclaim_mode-isolate_mode.patch
mm-make-get_mm_counter-static-inline.patch
mm-vmscan-fix-misused-nr_reclaimed-in-shrink_mem_cgroup_zone.patch
memcg-replace-mem_cont-by-mem_res_ctlr.patch
memcg-replace-mem-and-mem_cont-stragglers.patch
memcg-lru_size-instead-of-mem_cgroup_zstat.patch
memcg-enum-lru_list-lru.patch
memcg-remove-redundant-returns.patch
memcg-remove-unnecessary-thp-check-in-page-stat-accounting.patch
idr-make-idr_get_next-good-for-rcu_read_lock.patch
cgroup-revert-ss_id_lock-to-spinlock.patch
memcg-let-css_get_next-rely-upon-rcu_read_lock.patch
memcg-remove-pcg_cache-page_cgroup-flag.patch
memcg-remove-pcg_cache-page_cgroup-flag-checkpatch-fixes.patch
proc-speedup-proc-stat-handling.patch
procfs-add-num_to_str-to-speed-up-proc-stat.patch
procfs-add-num_to_str-to-speed-up-proc-stat-fix.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
