From 0e3dc019143104a6e676287b1e453cccd7add404 Mon Sep 17 00:00:00 2001 From: Andrei Vagin Date: Tue, 10 Apr 2018 16:30:44 -0700 Subject: procfs: add seq_put_hex_ll to speed up /proc/pid/maps seq_put_hex_ll() prints a number in hexadecimal notation and works faster than seq_printf(). == test.py num = 0 with open("/proc/1/maps") as f: while num < 10000 : data = f.read() f.seek(0, 0) num = num + 1 == == Before patch == $ time python test.py real 0m1.561s user 0m0.257s sys 0m1.302s == After patch == $ time python test.py real 0m0.986s user 0m0.279s sys 0m0.707s $ perf -g record python test.py: == Before patch == - 67.42% 2.82% python [kernel.kallsyms] [k] show_map_vma.isra.22 - 64.60% show_map_vma.isra.22 - 44.98% seq_printf - seq_vprintf - vsnprintf + 14.85% number + 12.22% format_decode 5.56% memcpy_erms + 15.06% seq_path + 4.42% seq_pad + 2.45% __GI___libc_read == After patch == - 47.35% 3.38% python [kernel.kallsyms] [k] show_map_vma.isra.23 - 43.97% show_map_vma.isra.23 + 20.84% seq_path - 15.73% show_vma_header_prefix 10.55% seq_put_hex_ll + 2.65% seq_put_decimal_ull 0.95% seq_putc + 6.96% seq_pad + 2.94% __GI___libc_read [avagin@openvz.org: use unsigned int instead of int where it is suitable] Link: http://lkml.kernel.org/r/20180214025619.4005-1-avagin@openvz.org [avagin@openvz.org: v2] Link: http://lkml.kernel.org/r/20180117082050.25406-1-avagin@openvz.org Link: http://lkml.kernel.org/r/20180112185812.7710-1-avagin@openvz.org Signed-off-by: Andrei Vagin Cc: Alexey Dobriyan Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/seq_file.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux/seq_file.h') diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index ab437dd2e3b9..599e145f4917 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -121,6 +121,9 @@ void seq_puts(struct seq_file *m, const char *s); void seq_put_decimal_ull(struct seq_file *m, const char *delimiter, unsigned long long num); void seq_put_decimal_ll(struct seq_file *m, const char *delimiter, long long num); +void seq_put_hex_ll(struct seq_file *m, const char *delimiter, + unsigned long long v, unsigned int width); + void seq_escape(struct seq_file *m, const char *s, const char *esc); void seq_hex_dump(struct seq_file *m, const char *prefix_str, int prefix_type, -- cgit v1.2.3 From d1be35cb6f96975d792a1535d3fe9b75239065ee Mon Sep 17 00:00:00 2001 From: Andrei Vagin Date: Tue, 10 Apr 2018 16:31:16 -0700 Subject: proc: add seq_put_decimal_ull_width to speed up /proc/pid/smaps seq_put_decimal_ull_w(m, str, val, width) prints a decimal number with a specified minimal field width. It is equivalent of seq_printf(m, "%s%*d", str, width, val), but it works much faster. == test_smaps.py num = 0 with open("/proc/1/smaps") as f: for x in xrange(10000): data = f.read() f.seek(0, 0) == == Before patch == $ time python test_smaps.py real 0m4.593s user 0m0.398s sys 0m4.158s == After patch == $ time python test_smaps.py real 0m3.828s user 0m0.413s sys 0m3.408s $ perf -g record python test_smaps.py == Before patch == - 79.01% 3.36% python [kernel.kallsyms] [k] show_smap.isra.33 - 75.65% show_smap.isra.33 + 48.85% seq_printf + 15.75% __walk_page_range + 9.70% show_map_vma.isra.23 0.61% seq_puts == After patch == - 75.51% 4.62% python [kernel.kallsyms] [k] show_smap.isra.33 - 70.88% show_smap.isra.33 + 24.82% seq_put_decimal_ull_w + 19.78% __walk_page_range + 12.74% seq_printf + 11.08% show_map_vma.isra.23 + 1.68% seq_puts [akpm@linux-foundation.org: fix drivers/of/unittest.c build] Link: http://lkml.kernel.org/r/20180212074931.7227-1-avagin@openvz.org Signed-off-by: Andrei Vagin Cc: Alexey Dobriyan Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/seq_file.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/seq_file.h') diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 599e145f4917..23d6a92cea9f 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -118,6 +118,8 @@ __printf(2, 3) void seq_printf(struct seq_file *m, const char *fmt, ...); void seq_putc(struct seq_file *m, char c); void seq_puts(struct seq_file *m, const char *s); +void seq_put_decimal_ull_width(struct seq_file *m, const char *delimiter, + unsigned long long num, unsigned int width); void seq_put_decimal_ull(struct seq_file *m, const char *delimiter, unsigned long long num); void seq_put_decimal_ll(struct seq_file *m, const char *delimiter, long long num); -- cgit v1.2.3 From 0965232035cfa59a64d197cf8a8ee0bc407bb3e4 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 10 Apr 2018 16:34:45 -0700 Subject: seq_file: allocate seq_file from kmem_cache For fine-grained debugging and usercopy protection. Link: http://lkml.kernel.org/r/20180310085027.GA17121@avx2 Signed-off-by: Alexey Dobriyan Reviewed-by: Andrew Morton Cc: Al Viro Cc: Glauber Costa Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/seq_file.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/seq_file.h') diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 23d6a92cea9f..a121982af0f5 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -240,4 +240,5 @@ extern struct hlist_node *seq_hlist_start_percpu(struct hlist_head __percpu *hea extern struct hlist_node *seq_hlist_next_percpu(void *v, struct hlist_head __percpu *head, int *cpu, loff_t *pos); +void seq_file_init(void); #endif -- cgit v1.2.3