diff mbox

[1/2] procfs: add seq_put_hex_ll to speed up /proc/pid/maps

Message ID 20180112185812.7710-1-avagin@openvz.org (mailing list archive)
State New, archived
Headers show

Commit Message

Andrey Vagin Jan. 12, 2018, 6:58 p.m. UTC
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

Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrei Vagin <avagin@openvz.org>
---
 fs/proc/task_mmu.c       | 21 ++++++++------
 fs/seq_file.c            | 74 ++++++++++++++++++++++++++++++++++++++++--------
 include/linux/seq_file.h |  3 ++
 3 files changed, 77 insertions(+), 21 deletions(-)

Comments

Andrew Morton Jan. 12, 2018, 11:33 p.m. UTC | #1
On Fri, 12 Jan 2018 10:58:11 -0800 Andrei Vagin <avagin@openvz.org> wrote:

> seq_put_hex_ll() prints a number in hexadecimal notation and works
> faster than seq_printf().
> 
> ...
>
> --- a/fs/seq_file.c
> +++ b/fs/seq_file.c
> @@ -670,6 +670,26 @@ void seq_puts(struct seq_file *m, const char *s)
>  }
>  EXPORT_SYMBOL(seq_puts);
>  
> +static inline void seq_put_delimeter(struct seq_file *m, const char *delimiter)
> +{
> +	int len;
> +
> +	if (!delimiter || !delimiter[0])
> +		return;
> +
> +	if (delimiter[1] == 0)
> +		return seq_putc(m, delimiter[0]);
> +
> +	len = strlen(delimiter);
> +	if (m->count + len >= m->size) {
> +		seq_set_overflow(m);
> +		return;
> +	}
> +
> +	memcpy(m->buf + m->count, delimiter, len);
> +	m->count += len;
> +}

Can we please have a nice comment describing this function's role and
behaviour?

I don't think the `inline' is needed or desirable - gcc can figure that
out, and with three callsites a `noinline' would be more justified!

That `return seq_putc(...)' will generate a warning in some situations
- seq_putc() returns void.  Let's split it into 'seq_putc(...);
return;' please.

> +/**
> + * seq_put_hex_ll - put a number in hexadecimal notation
> + * @m: seq_file identifying the buffer to which data should be written
> + * @delimiter: a string which is printed before the number
> + * @v: the number
> + * @width: a minimum field width
> + *
> + * seq_put_hex_ll(m, "", v, 8) is equal to seq_printf(m, "0x08llx", v)
> + *
> + * 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.
> + */
> +void seq_put_hex_ll(struct seq_file *m, const char *delimiter,
> +				unsigned long long v, int width)
> +{
> +	int i, len;
> +
> +	seq_put_delimeter(m, delimiter);
> +
> +	len = (sizeof(v) * 8 - __builtin_clzll(v) + 3) / 4;
> +
> +	if (unlikely(len == 0))
> +		len = 1;
> +
> +	if (len < width)
> +		len = width;
> +
> +	if (m->count + len > m->size)
> +		goto overflow;
> +
> +	for (i = len - 1; i >= 0; i--) {
> +		m->buf[m->count + i] = hex_asc[0xf & v];
> +		v = v >> 4;
> +	}
> +	m->count += len;
> +	return;
> +overflow:
> +	seq_set_overflow(m);
> +}

I don't think we need the goto.  Just do "seq_set_overflow(m); return;".
Andrey Vagin Jan. 15, 2018, 7:04 a.m. UTC | #2
On Fri, Jan 12, 2018 at 03:33:04PM -0800, Andrew Morton wrote:
> On Fri, 12 Jan 2018 10:58:11 -0800 Andrei Vagin <avagin@openvz.org> wrote:
> 
> > seq_put_hex_ll() prints a number in hexadecimal notation and works
> > faster than seq_printf().
> > 
> > ...
> >
> > --- a/fs/seq_file.c
> > +++ b/fs/seq_file.c
> > @@ -670,6 +670,26 @@ void seq_puts(struct seq_file *m, const char *s)
> >  }
> >  EXPORT_SYMBOL(seq_puts);
> >  
> > +static inline void seq_put_delimeter(struct seq_file *m, const char *delimiter)
> > +{
> > +	int len;
> > +
> > +	if (!delimiter || !delimiter[0])
> > +		return;
> > +
> > +	if (delimiter[1] == 0)
> > +		return seq_putc(m, delimiter[0]);
> > +
> > +	len = strlen(delimiter);
> > +	if (m->count + len >= m->size) {
> > +		seq_set_overflow(m);
> > +		return;
> > +	}
> > +
> > +	memcpy(m->buf + m->count, delimiter, len);
> > +	m->count += len;
> > +}
> 
> Can we please have a nice comment describing this function's role and
> behaviour?

seq_put_decimal_* and seq_put_hex_ll prints a string before printing a
number. Originaly it was just one symbol, it is probably a reason why it
is called delimeter.

I added an optimization for a case when delimiter is one symbol, and
found that it sinificantly affect perfomance (about 13% for
/proc/pid/maps):

Without this optimization:
[root@fc24 ~]# time python test.py 

real	0m9.105s
user	0m2.200s
sys	0m6.901s

With this optimization:
[root@fc24 ~]# time python test.py 

real	0m8.097s
user	0m1.994s
sys	0m6.102s


If inline is replaced by noinline
[root@fc24 ~]# time python test.py 

real	0m8.263s
user	0m2.058s
sys	0m6.200s

[root@fc24 ~]# cat test.py 
#!/usr/bin/env python2

num = 0
with open("/proc/1/maps") as f:
        for x in xrange(100000):
                data = f.read()
                f.seek(0, 0)

Andrew, thank you for the review, I will send a fixed patch soon.

> 
> I don't think the `inline' is needed or desirable - gcc can figure that
> out, and with three callsites a `noinline' would be more justified!
> 
> That `return seq_putc(...)' will generate a warning in some situations
> - seq_putc() returns void.  Let's split it into 'seq_putc(...);
> return;' please.
> 
> > +/**
> > + * seq_put_hex_ll - put a number in hexadecimal notation
> > + * @m: seq_file identifying the buffer to which data should be written
> > + * @delimiter: a string which is printed before the number
> > + * @v: the number
> > + * @width: a minimum field width
> > + *
> > + * seq_put_hex_ll(m, "", v, 8) is equal to seq_printf(m, "0x08llx", v)
> > + *
> > + * 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.
> > + */
> > +void seq_put_hex_ll(struct seq_file *m, const char *delimiter,
> > +				unsigned long long v, int width)
> > +{
> > +	int i, len;
> > +
> > +	seq_put_delimeter(m, delimiter);
> > +
> > +	len = (sizeof(v) * 8 - __builtin_clzll(v) + 3) / 4;
> > +
> > +	if (unlikely(len == 0))
> > +		len = 1;
> > +
> > +	if (len < width)
> > +		len = width;
> > +
> > +	if (m->count + len > m->size)
> > +		goto overflow;
> > +
> > +	for (i = len - 1; i >= 0; i--) {
> > +		m->buf[m->count + i] = hex_asc[0xf & v];
> > +		v = v >> 4;
> > +	}
> > +	m->count += len;
> > +	return;
> > +overflow:
> > +	seq_set_overflow(m);
> > +}
> 
> I don't think we need the goto.  Just do "seq_set_overflow(m); return;".
>
diff mbox

Patch

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 339e4c1c044d..3a08685ef27c 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -282,15 +282,18 @@  static void show_vma_header_prefix(struct seq_file *m,
 				   dev_t dev, unsigned long ino)
 {
 	seq_setwidth(m, 25 + sizeof(void *) * 6 - 1);
-	seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ",
-		   start,
-		   end,
-		   flags & VM_READ ? 'r' : '-',
-		   flags & VM_WRITE ? 'w' : '-',
-		   flags & VM_EXEC ? 'x' : '-',
-		   flags & VM_MAYSHARE ? 's' : 'p',
-		   pgoff,
-		   MAJOR(dev), MINOR(dev), ino);
+	seq_put_hex_ll(m, NULL, start, 8);
+	seq_put_hex_ll(m, "-", end, 8);
+	seq_putc(m, ' ');
+	seq_putc(m, flags & VM_READ ? 'r' : '-');
+	seq_putc(m, flags & VM_WRITE ? 'w' : '-');
+	seq_putc(m, flags & VM_EXEC ? 'x' : '-');
+	seq_putc(m, flags & VM_MAYSHARE ? 's' : 'p');
+	seq_put_hex_ll(m, " ", pgoff, 8);
+	seq_put_hex_ll(m, " ", MAJOR(dev), 2);
+	seq_put_hex_ll(m, ":", MINOR(dev), 2);
+	seq_put_decimal_ull(m, " ", ino);
+	seq_putc(m, ' ');
 }
 
 static void
diff --git a/fs/seq_file.c b/fs/seq_file.c
index 4be761c1a03d..fb37ec42fae2 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -670,6 +670,26 @@  void seq_puts(struct seq_file *m, const char *s)
 }
 EXPORT_SYMBOL(seq_puts);
 
+static inline void seq_put_delimeter(struct seq_file *m, const char *delimiter)
+{
+	int len;
+
+	if (!delimiter || !delimiter[0])
+		return;
+
+	if (delimiter[1] == 0)
+		return seq_putc(m, delimiter[0]);
+
+	len = strlen(delimiter);
+	if (m->count + len >= m->size) {
+		seq_set_overflow(m);
+		return;
+	}
+
+	memcpy(m->buf + m->count, delimiter, len);
+	m->count += len;
+}
+
 /*
  * A helper routine for putting decimal numbers without rich format of printf().
  * only 'unsigned long long' is supported.
@@ -685,12 +705,7 @@  void seq_put_decimal_ull(struct seq_file *m, const char *delimiter,
 	if (m->count + 2 >= m->size) /* we'll write 2 bytes at least */
 		goto overflow;
 
-	len = strlen(delimiter);
-	if (m->count + len >= m->size)
-		goto overflow;
-
-	memcpy(m->buf + m->count, delimiter, len);
-	m->count += len;
+	seq_put_delimeter(m, delimiter);
 
 	if (m->count + 1 >= m->size)
 		goto overflow;
@@ -712,6 +727,46 @@  void seq_put_decimal_ull(struct seq_file *m, const char *delimiter,
 }
 EXPORT_SYMBOL(seq_put_decimal_ull);
 
+/**
+ * seq_put_hex_ll - put a number in hexadecimal notation
+ * @m: seq_file identifying the buffer to which data should be written
+ * @delimiter: a string which is printed before the number
+ * @v: the number
+ * @width: a minimum field width
+ *
+ * seq_put_hex_ll(m, "", v, 8) is equal to seq_printf(m, "0x08llx", v)
+ *
+ * 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.
+ */
+void seq_put_hex_ll(struct seq_file *m, const char *delimiter,
+				unsigned long long v, int width)
+{
+	int i, len;
+
+	seq_put_delimeter(m, delimiter);
+
+	len = (sizeof(v) * 8 - __builtin_clzll(v) + 3) / 4;
+
+	if (unlikely(len == 0))
+		len = 1;
+
+	if (len < width)
+		len = width;
+
+	if (m->count + len > m->size)
+		goto overflow;
+
+	for (i = len - 1; i >= 0; i--) {
+		m->buf[m->count + i] = hex_asc[0xf & v];
+		v = v >> 4;
+	}
+	m->count += len;
+	return;
+overflow:
+	seq_set_overflow(m);
+}
+
 void seq_put_decimal_ll(struct seq_file *m, const char *delimiter, long long num)
 {
 	int len;
@@ -719,12 +774,7 @@  void seq_put_decimal_ll(struct seq_file *m, const char *delimiter, long long num
 	if (m->count + 3 >= m->size) /* we'll write 2 bytes at least */
 		goto overflow;
 
-	len = strlen(delimiter);
-	if (m->count + len >= m->size)
-		goto overflow;
-
-	memcpy(m->buf + m->count, delimiter, len);
-	m->count += len;
+	seq_put_delimeter(m, delimiter);
 
 	if (m->count + 2 >= m->size)
 		goto overflow;
diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h
index 09c6e28746f9..53f238934d7f 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, 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,