'perf record' will call kallsyms__parse 4 times during startup and
process megabytes of data. This changes kallsyms__parse to use the io
library rather than fgets to improve performance of the user code by
over 8%.
Before:
Running 'internals/kallsyms-parse' benchmark:
Average kallsyms__parse took: 103.988 ms (+- 0.203 ms)
After:
Running 'internals/kallsyms-parse' benchmark:
Average kallsyms__parse took: 95.571 ms (+- 0.006 ms)
For a workload like:
$ perf record /bin/true
Run under 'perf record -e cycles:u -g' the time goes from:
Before
30.10% 1.67% perf perf [.] kallsyms__parse
After
25.55% 20.04% perf perf [.] kallsyms__parse
So a little under 5% of the start-up time is removed. A lot of what
remains is on the kernel side, but caching kallsyms within perf would at
least impact memory footprint.
Committer notes:
The internal/kallsyms-parse bench is run using:
[root@five ~]# perf bench internals kallsyms-parse
# Running 'internals/kallsyms-parse' benchmark:
Average kallsyms__parse took: 80.381 ms (+- 0.115 ms)
[root@five ~]#
And this pre-existing test uses these routines to parse kallsyms and
then compare with the info obtained from the matching ELF symtab:
[root@five ~]# perf test vmlinux
1: vmlinux symtab matches kallsyms : Ok
[root@five ~]#
Also we can't remove hex2u64() in this patch as this breaks the build:
/usr/bin/ld: /tmp/build/perf/perf-in.o: in function `modules__parse':
/home/acme/git/perf/tools/perf/util/symbol.c:607: undefined reference to `hex2u64'
/usr/bin/ld: /home/acme/git/perf/tools/perf/util/symbol.c:607: undefined reference to `hex2u64'
/usr/bin/ld: /tmp/build/perf/perf-in.o: in function `dso__load_perf_map':
/home/acme/git/perf/tools/perf/util/symbol.c:1477: undefined reference to `hex2u64'
/usr/bin/ld: /home/acme/git/perf/tools/perf/util/symbol.c:1483: undefined reference to `hex2u64'
collect2: error: ld returned 1 exit status
Leave it there, move it in the next patch.
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lore.kernel.org/lkml/20200501221315.54715-3-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
116 lines
2.5 KiB
C
116 lines
2.5 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/*
|
|
* Lightweight buffered reading library.
|
|
*
|
|
* Copyright 2019 Google LLC.
|
|
*/
|
|
#ifndef __API_IO__
|
|
#define __API_IO__
|
|
|
|
#include <stdlib.h>
|
|
#include <unistd.h>
|
|
|
|
struct io {
|
|
/* File descriptor being read/ */
|
|
int fd;
|
|
/* Size of the read buffer. */
|
|
unsigned int buf_len;
|
|
/* Pointer to storage for buffering read. */
|
|
char *buf;
|
|
/* End of the storage. */
|
|
char *end;
|
|
/* Currently accessed data pointer. */
|
|
char *data;
|
|
/* Set true on when the end of file on read error. */
|
|
bool eof;
|
|
};
|
|
|
|
static inline void io__init(struct io *io, int fd,
|
|
char *buf, unsigned int buf_len)
|
|
{
|
|
io->fd = fd;
|
|
io->buf_len = buf_len;
|
|
io->buf = buf;
|
|
io->end = buf;
|
|
io->data = buf;
|
|
io->eof = false;
|
|
}
|
|
|
|
/* Reads one character from the "io" file with similar semantics to fgetc. */
|
|
static inline int io__get_char(struct io *io)
|
|
{
|
|
char *ptr = io->data;
|
|
|
|
if (io->eof)
|
|
return -1;
|
|
|
|
if (ptr == io->end) {
|
|
ssize_t n = read(io->fd, io->buf, io->buf_len);
|
|
|
|
if (n <= 0) {
|
|
io->eof = true;
|
|
return -1;
|
|
}
|
|
ptr = &io->buf[0];
|
|
io->end = &io->buf[n];
|
|
}
|
|
io->data = ptr + 1;
|
|
return *ptr;
|
|
}
|
|
|
|
/* Read a hexadecimal value with no 0x prefix into the out argument hex. If the
|
|
* first character isn't hexadecimal returns -2, io->eof returns -1, otherwise
|
|
* returns the character after the hexadecimal value which may be -1 for eof.
|
|
* If the read value is larger than a u64 the high-order bits will be dropped.
|
|
*/
|
|
static inline int io__get_hex(struct io *io, __u64 *hex)
|
|
{
|
|
bool first_read = true;
|
|
|
|
*hex = 0;
|
|
while (true) {
|
|
int ch = io__get_char(io);
|
|
|
|
if (ch < 0)
|
|
return ch;
|
|
if (ch >= '0' && ch <= '9')
|
|
*hex = (*hex << 4) | (ch - '0');
|
|
else if (ch >= 'a' && ch <= 'f')
|
|
*hex = (*hex << 4) | (ch - 'a' + 10);
|
|
else if (ch >= 'A' && ch <= 'F')
|
|
*hex = (*hex << 4) | (ch - 'A' + 10);
|
|
else if (first_read)
|
|
return -2;
|
|
else
|
|
return ch;
|
|
first_read = false;
|
|
}
|
|
}
|
|
|
|
/* Read a positive decimal value with out argument dec. If the first character
|
|
* isn't a decimal returns -2, io->eof returns -1, otherwise returns the
|
|
* character after the decimal value which may be -1 for eof. If the read value
|
|
* is larger than a u64 the high-order bits will be dropped.
|
|
*/
|
|
static inline int io__get_dec(struct io *io, __u64 *dec)
|
|
{
|
|
bool first_read = true;
|
|
|
|
*dec = 0;
|
|
while (true) {
|
|
int ch = io__get_char(io);
|
|
|
|
if (ch < 0)
|
|
return ch;
|
|
if (ch >= '0' && ch <= '9')
|
|
*dec = (*dec * 10) + ch - '0';
|
|
else if (first_read)
|
|
return -2;
|
|
else
|
|
return ch;
|
|
first_read = false;
|
|
}
|
|
}
|
|
|
|
#endif /* __API_IO__ */
|