From 187f1882b5b0748b3c4c22274663fdb372ac0452 Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Wed, 23 Nov 2011 20:12:59 -0500 Subject: BUG: headers with BUG/BUG_ON etc. need linux/bug.h If a header file is making use of BUG, BUG_ON, BUILD_BUG_ON, or any other BUG variant in a static inline (i.e. not in a #define) then that header really should be including and not just expecting it to be implicitly present. We can make this change risk-free, since if the files using these headers didn't have exposure to linux/bug.h already, they would have been causing compile failures/warnings. Signed-off-by: Paul Gortmaker --- 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 44f1514b00b..5ff2df6c821 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -3,6 +3,7 @@ #include #include +#include #include #include #include -- cgit v1.2.3-70-g09d2 From 1ac101a5d675aca2426c5cd460c73fb95acb8391 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Fri, 23 Mar 2012 15:02:54 -0700 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 [akpm@linux-foundation.org: remove incorrect comment, use less statck in num_to_str(), move comment from .h to .c, simplify seq_put_decimal_ull()] [andrea@betterlinux.com: avoid breaking the ABI in /proc/stat] Signed-off-by: KAMEZAWA Hiroyuki Signed-off-by: Andrea Righi Cc: Eric Dumazet Cc: Glauber Costa Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Paul Turner Cc: Russell King Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/stat.c | 55 ++++++++++++++++++++++++------------------------ fs/seq_file.c | 33 +++++++++++++++++++++++++++++ include/linux/kernel.h | 2 ++ include/linux/seq_file.h | 3 ++- lib/vsprintf.c | 20 ++++++++++++++++++ 5 files changed, 84 insertions(+), 29 deletions(-) (limited to 'include/linux/seq_file.h') diff --git a/fs/proc/stat.c b/fs/proc/stat.c index ac446114cd4..6a0c62d6e44 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -89,18 +89,19 @@ static int show_stat(struct seq_file *p, void *v) } 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, void *v) 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, void *v) 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 --git a/fs/seq_file.c b/fs/seq_file.c index aa242dc9937..7d19816c4cc 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -644,6 +644,39 @@ int seq_puts(struct seq_file *m, const char *s) } 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; + + m->buf[m->count++] = delimiter; + + if (num < 10) { + m->buf[m->count++] = num + '0'; + return 0; + } + + 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 --git a/include/linux/kernel.h b/include/linux/kernel.h index f2085b541a2..3e140add536 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -312,6 +312,8 @@ extern long long simple_strtoll(const char *,char **,unsigned int); #define strict_strtoull kstrtoull #define strict_strtoll kstrtoll +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 --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 44f1514b00b..5bba42c9944 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -121,9 +121,10 @@ int single_release(struct inode *, struct file *); void *__seq_open_private(struct file *, const struct seq_operations *, int); int seq_open_private(struct file *, const struct seq_operations *, int); int seq_release_private(struct inode *, struct file *); +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 --git a/lib/vsprintf.c b/lib/vsprintf.c index 38e612e66da..385c40291cd 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -212,6 +212,26 @@ char *put_dec(char *buf, unsigned long long num) } } +/* + * Convert passed number to decimal string. + * Returns the length of string. On buffer overflow, returns 0. + * + * If speed is not important, use snprintf(). It's easy to read the code. + */ +int num_to_str(char *buf, int size, unsigned long long num) +{ + char tmp[21]; /* Enough for 2^64 in decimal */ + 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 */ -- cgit v1.2.3-70-g09d2 From bda7bad62bc4c4e0783348e8db51abe094153c56 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Fri, 23 Mar 2012 15:02:54 -0700 Subject: procfs: speed up /proc/pid/stat, statm Process accounting applications as top, ps visit some files under /proc/. With seq_put_decimal_ull(), we can optimize /proc//stat and /proc//statm files. This patch adds - seq_put_decimal_ll() for signed values. - allow delimiter == 0. - convert seq_printf() to seq_put_decimal_ull/ll in /proc/stat, statm. Test result on a system with 2000+ procs. Before patch: [kamezawa@bluextal test]$ top -b -n 1 | wc -l 2223 [kamezawa@bluextal test]$ time top -b -n 1 > /dev/null real 0m0.675s user 0m0.044s sys 0m0.121s [kamezawa@bluextal test]$ time ps -elf > /dev/null real 0m0.236s user 0m0.056s sys 0m0.176s After patch: kamezawa@bluextal ~]$ time top -b -n 1 > /dev/null real 0m0.657s user 0m0.052s sys 0m0.100s [kamezawa@bluextal ~]$ time ps -elf > /dev/null real 0m0.198s user 0m0.050s sys 0m0.145s Considering top, ps tend to scan /proc periodically, this will reduce cpu consumption by top/ps to some extent. [akpm@linux-foundation.org: checkpatch fixes] Signed-off-by: KAMEZAWA Hiroyuki Cc: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/array.c | 119 +++++++++++++++++++++++++---------------------- fs/seq_file.c | 21 ++++++++- include/linux/seq_file.h | 2 + 3 files changed, 86 insertions(+), 56 deletions(-) (limited to 'include/linux/seq_file.h') diff --git a/fs/proc/array.c b/fs/proc/array.c index c602b8d20f0..fbb53c24908 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -462,59 +462,56 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, /* convert nsec -> ticks */ start_time = nsec_to_clock_t(start_time); - seq_printf(m, "%d (%s) %c %d %d %d %d %d %u %lu \ -%lu %lu %lu %lu %lu %ld %ld %ld %ld %d 0 %llu %lu %ld %lu %lu %lu %lu %lu \ -%lu %lu %lu %lu %lu %lu %lu %lu %d %d %u %u %llu %lu %ld %lu %lu %lu\n", - pid_nr_ns(pid, ns), - tcomm, - state, - ppid, - pgid, - sid, - tty_nr, - tty_pgrp, - task->flags, - min_flt, - cmin_flt, - maj_flt, - cmaj_flt, - cputime_to_clock_t(utime), - cputime_to_clock_t(stime), - cputime_to_clock_t(cutime), - cputime_to_clock_t(cstime), - priority, - nice, - num_threads, - start_time, - vsize, - mm ? get_mm_rss(mm) : 0, - rsslim, - mm ? (permitted ? mm->start_code : 1) : 0, - mm ? (permitted ? mm->end_code : 1) : 0, - (permitted && mm) ? mm->start_stack : 0, - esp, - eip, - /* The signal information here is obsolete. - * It must be decimal for Linux 2.0 compatibility. - * Use /proc/#/status for real-time signals. - */ - task->pending.signal.sig[0] & 0x7fffffffUL, - task->blocked.sig[0] & 0x7fffffffUL, - sigign .sig[0] & 0x7fffffffUL, - sigcatch .sig[0] & 0x7fffffffUL, - wchan, - 0UL, - 0UL, - task->exit_signal, - task_cpu(task), - task->rt_priority, - task->policy, - (unsigned long long)delayacct_blkio_ticks(task), - cputime_to_clock_t(gtime), - cputime_to_clock_t(cgtime), - (mm && permitted) ? mm->start_data : 0, - (mm && permitted) ? mm->end_data : 0, - (mm && permitted) ? mm->start_brk : 0); + seq_printf(m, "%d (%s) %c", pid_nr_ns(pid, ns), tcomm, state); + seq_put_decimal_ll(m, ' ', ppid); + seq_put_decimal_ll(m, ' ', pgid); + seq_put_decimal_ll(m, ' ', sid); + seq_put_decimal_ll(m, ' ', tty_nr); + seq_put_decimal_ll(m, ' ', tty_pgrp); + seq_put_decimal_ull(m, ' ', task->flags); + seq_put_decimal_ull(m, ' ', min_flt); + seq_put_decimal_ull(m, ' ', cmin_flt); + seq_put_decimal_ull(m, ' ', maj_flt); + seq_put_decimal_ull(m, ' ', cmaj_flt); + seq_put_decimal_ull(m, ' ', cputime_to_clock_t(utime)); + seq_put_decimal_ull(m, ' ', cputime_to_clock_t(stime)); + seq_put_decimal_ll(m, ' ', cputime_to_clock_t(cutime)); + seq_put_decimal_ll(m, ' ', cputime_to_clock_t(cstime)); + seq_put_decimal_ll(m, ' ', priority); + seq_put_decimal_ll(m, ' ', nice); + seq_put_decimal_ll(m, ' ', num_threads); + seq_put_decimal_ull(m, ' ', 0); + seq_put_decimal_ull(m, ' ', start_time); + seq_put_decimal_ull(m, ' ', vsize); + seq_put_decimal_ll(m, ' ', mm ? get_mm_rss(mm) : 0); + seq_put_decimal_ull(m, ' ', rsslim); + seq_put_decimal_ull(m, ' ', mm ? (permitted ? mm->start_code : 1) : 0); + seq_put_decimal_ull(m, ' ', mm ? (permitted ? mm->end_code : 1) : 0); + seq_put_decimal_ull(m, ' ', (permitted && mm) ? mm->start_stack : 0); + seq_put_decimal_ull(m, ' ', esp); + seq_put_decimal_ull(m, ' ', eip); + /* The signal information here is obsolete. + * It must be decimal for Linux 2.0 compatibility. + * Use /proc/#/status for real-time signals. + */ + seq_put_decimal_ull(m, ' ', task->pending.signal.sig[0] & 0x7fffffffUL); + seq_put_decimal_ull(m, ' ', task->blocked.sig[0] & 0x7fffffffUL); + seq_put_decimal_ull(m, ' ', sigign.sig[0] & 0x7fffffffUL); + seq_put_decimal_ull(m, ' ', sigcatch.sig[0] & 0x7fffffffUL); + seq_put_decimal_ull(m, ' ', wchan); + seq_put_decimal_ull(m, ' ', 0); + seq_put_decimal_ull(m, ' ', 0); + seq_put_decimal_ll(m, ' ', task->exit_signal); + seq_put_decimal_ll(m, ' ', task_cpu(task)); + seq_put_decimal_ull(m, ' ', task->rt_priority); + seq_put_decimal_ull(m, ' ', task->policy); + seq_put_decimal_ull(m, ' ', delayacct_blkio_ticks(task)); + seq_put_decimal_ull(m, ' ', cputime_to_clock_t(gtime)); + seq_put_decimal_ll(m, ' ', cputime_to_clock_t(cgtime)); + seq_put_decimal_ull(m, ' ', (mm && permitted) ? mm->start_data : 0); + seq_put_decimal_ull(m, ' ', (mm && permitted) ? mm->end_data : 0); + seq_put_decimal_ull(m, ' ', (mm && permitted) ? mm->start_brk : 0); + seq_putc(m, '\n'); if (mm) mmput(mm); return 0; @@ -542,8 +539,20 @@ int proc_pid_statm(struct seq_file *m, struct pid_namespace *ns, size = task_statm(mm, &shared, &text, &data, &resident); mmput(mm); } - seq_printf(m, "%lu %lu %lu %lu 0 %lu 0\n", - size, resident, shared, text, data); + /* + * For quick read, open code by putting numbers directly + * expected format is + * seq_printf(m, "%lu %lu %lu %lu 0 %lu 0\n", + * size, resident, shared, text, data); + */ + seq_put_decimal_ull(m, 0, size); + seq_put_decimal_ull(m, ' ', resident); + seq_put_decimal_ull(m, ' ', shared); + seq_put_decimal_ull(m, ' ', text); + seq_put_decimal_ull(m, ' ', 0); + seq_put_decimal_ull(m, ' ', text); + seq_put_decimal_ull(m, ' ', 0); + seq_putc(m, '\n'); return 0; } diff --git a/fs/seq_file.c b/fs/seq_file.c index 7d19816c4cc..55c293f7024 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -659,7 +659,8 @@ int seq_put_decimal_ull(struct seq_file *m, char delimiter, if (m->count + 2 >= m->size) /* we'll write 2 bytes at least */ goto overflow; - m->buf[m->count++] = delimiter; + if (delimiter) + m->buf[m->count++] = delimiter; if (num < 10) { m->buf[m->count++] = num + '0'; @@ -677,6 +678,24 @@ overflow: } EXPORT_SYMBOL(seq_put_decimal_ull); +int seq_put_decimal_ll(struct seq_file *m, char delimiter, + long long num) +{ + if (num < 0) { + if (m->count + 3 >= m->size) { + m->count = m->size; + return -1; + } + if (delimiter) + m->buf[m->count++] = delimiter; + num = -num; + delimiter = '-'; + } + return seq_put_decimal_ull(m, delimiter, num); + +} +EXPORT_SYMBOL(seq_put_decimal_ll); + /** * seq_write - write arbitrary data to buffer * @seq: seq_file identifying the buffer to which data should be written diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 5bba42c9944..54e5ae7f8ad 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -123,6 +123,8 @@ int seq_open_private(struct file *, const struct seq_operations *, int); int seq_release_private(struct inode *, struct file *); int seq_put_decimal_ull(struct seq_file *m, char delimiter, unsigned long long num); +int seq_put_decimal_ll(struct seq_file *m, char delimiter, + long long num); #define SEQ_START_TOKEN ((void *)1) /* -- cgit v1.2.3-70-g09d2