linux_dsm_epyc7002/tools/perf/perf.c

509 lines
12 KiB
C
Raw Normal View History

/*
* perf.c
*
* Performance analysis utility.
*
* This is the main hub from which the sub-commands (perf stat,
* perf top, perf record, perf report, etc.) are started.
*/
#include "builtin.h"
#include "util/exec_cmd.h"
#include "util/cache.h"
#include "util/quote.h"
#include "util/run-command.h"
#include "util/parse-events.h"
#include "util/debugfs.h"
const char perf_usage_string[] =
"perf [--version] [--help] COMMAND [ARGS]";
const char perf_more_info_string[] =
"See 'perf help COMMAND' for more information on a specific command.";
int use_browser = -1;
static int use_pager = -1;
struct pager_config {
const char *cmd;
int val;
};
static int pager_command_config(const char *var, const char *value, void *data)
{
struct pager_config *c = data;
if (!prefixcmp(var, "pager.") && !strcmp(var + 6, c->cmd))
c->val = perf_config_bool(var, value);
return 0;
}
/* returns 0 for "no pager", 1 for "use pager", and -1 for "not specified" */
int check_pager_config(const char *cmd)
{
struct pager_config c;
c.cmd = cmd;
c.val = -1;
perf_config(pager_command_config, &c);
return c.val;
}
static int tui_command_config(const char *var, const char *value, void *data)
{
struct pager_config *c = data;
if (!prefixcmp(var, "tui.") && !strcmp(var + 4, c->cmd))
c->val = perf_config_bool(var, value);
return 0;
}
/* returns 0 for "no tui", 1 for "use tui", and -1 for "not specified" */
static int check_tui_config(const char *cmd)
{
struct pager_config c;
c.cmd = cmd;
c.val = -1;
perf_config(tui_command_config, &c);
return c.val;
}
static void commit_pager_choice(void)
{
switch (use_pager) {
case 0:
setenv("PERF_PAGER", "cat", 1);
break;
case 1:
/* setup_pager(); */
break;
default:
break;
}
}
static int handle_options(const char ***argv, int *argc, int *envchanged)
{
int handled = 0;
while (*argc > 0) {
const char *cmd = (*argv)[0];
if (cmd[0] != '-')
break;
/*
* For legacy reasons, the "version" and "help"
* commands can be written with "--" prepended
* to make them look like flags.
*/
if (!strcmp(cmd, "--help") || !strcmp(cmd, "--version"))
break;
/*
* Check remaining flags.
*/
if (!prefixcmp(cmd, CMD_EXEC_PATH)) {
cmd += strlen(CMD_EXEC_PATH);
if (*cmd == '=')
perf_set_argv_exec_path(cmd + 1);
else {
puts(perf_exec_path());
exit(0);
}
} else if (!strcmp(cmd, "--html-path")) {
puts(system_path(PERF_HTML_PATH));
exit(0);
} else if (!strcmp(cmd, "-p") || !strcmp(cmd, "--paginate")) {
use_pager = 1;
} else if (!strcmp(cmd, "--no-pager")) {
use_pager = 0;
if (envchanged)
*envchanged = 1;
} else if (!strcmp(cmd, "--perf-dir")) {
if (*argc < 2) {
fprintf(stderr, "No directory given for --perf-dir.\n");
usage(perf_usage_string);
}
setenv(PERF_DIR_ENVIRONMENT, (*argv)[1], 1);
if (envchanged)
*envchanged = 1;
(*argv)++;
(*argc)--;
handled++;
} else if (!prefixcmp(cmd, CMD_PERF_DIR)) {
setenv(PERF_DIR_ENVIRONMENT, cmd + strlen(CMD_PERF_DIR), 1);
if (envchanged)
*envchanged = 1;
} else if (!strcmp(cmd, "--work-tree")) {
if (*argc < 2) {
fprintf(stderr, "No directory given for --work-tree.\n");
usage(perf_usage_string);
}
setenv(PERF_WORK_TREE_ENVIRONMENT, (*argv)[1], 1);
if (envchanged)
*envchanged = 1;
(*argv)++;
(*argc)--;
} else if (!prefixcmp(cmd, CMD_WORK_TREE)) {
setenv(PERF_WORK_TREE_ENVIRONMENT, cmd + strlen(CMD_WORK_TREE), 1);
if (envchanged)
*envchanged = 1;
} else if (!strcmp(cmd, "--debugfs-dir")) {
if (*argc < 2) {
fprintf(stderr, "No directory given for --debugfs-dir.\n");
usage(perf_usage_string);
}
debugfs_set_path((*argv)[1]);
if (envchanged)
*envchanged = 1;
(*argv)++;
(*argc)--;
} else if (!prefixcmp(cmd, CMD_DEBUGFS_DIR)) {
debugfs_set_path(cmd + strlen(CMD_DEBUGFS_DIR));
fprintf(stderr, "dir: %s\n", debugfs_mountpoint);
if (envchanged)
*envchanged = 1;
} else {
fprintf(stderr, "Unknown option: %s\n", cmd);
usage(perf_usage_string);
}
(*argv)++;
(*argc)--;
handled++;
}
return handled;
}
static int handle_alias(int *argcp, const char ***argv)
{
int envchanged = 0, ret = 0, saved_errno = errno;
int count, option_count;
const char **new_argv;
const char *alias_command;
char *alias_string;
alias_command = (*argv)[0];
alias_string = alias_lookup(alias_command);
if (alias_string) {
if (alias_string[0] == '!') {
if (*argcp > 1) {
struct strbuf buf;
strbuf_init(&buf, PATH_MAX);
strbuf_addstr(&buf, alias_string);
sq_quote_argv(&buf, (*argv) + 1, PATH_MAX);
free(alias_string);
alias_string = buf.buf;
}
ret = system(alias_string + 1);
if (ret >= 0 && WIFEXITED(ret) &&
WEXITSTATUS(ret) != 127)
exit(WEXITSTATUS(ret));
die("Failed to run '%s' when expanding alias '%s'",
alias_string + 1, alias_command);
}
count = split_cmdline(alias_string, &new_argv);
if (count < 0)
die("Bad alias.%s string", alias_command);
option_count = handle_options(&new_argv, &count, &envchanged);
if (envchanged)
die("alias '%s' changes environment variables\n"
"You can use '!perf' in the alias to do this.",
alias_command);
memmove(new_argv - option_count, new_argv,
count * sizeof(char *));
new_argv -= option_count;
if (count < 1)
die("empty alias for %s", alias_command);
if (!strcmp(alias_command, new_argv[0]))
die("recursive alias: %s", alias_command);
new_argv = realloc(new_argv, sizeof(char *) *
(count + *argcp + 1));
/* insert after command name */
memcpy(new_argv + count, *argv + 1, sizeof(char *) * *argcp);
new_argv[count + *argcp] = NULL;
*argv = new_argv;
*argcp += count - 1;
ret = 1;
}
errno = saved_errno;
return ret;
}
const char perf_version_string[] = PERF_VERSION;
#define RUN_SETUP (1<<0)
#define USE_PAGER (1<<1)
/*
* require working tree to be present -- anything uses this needs
* RUN_SETUP for reading from the configuration file.
*/
#define NEED_WORK_TREE (1<<2)
struct cmd_struct {
const char *cmd;
int (*fn)(int, const char **, const char *);
int option;
};
static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
{
int status;
struct stat st;
const char *prefix;
prefix = NULL;
if (p->option & RUN_SETUP)
prefix = NULL; /* setup_perf_directory(); */
if (use_browser == -1)
use_browser = check_tui_config(p->cmd);
if (use_pager == -1 && p->option & RUN_SETUP)
use_pager = check_pager_config(p->cmd);
if (use_pager == -1 && p->option & USE_PAGER)
use_pager = 1;
commit_pager_choice();
status = p->fn(argc, argv, prefix);
exit_browser(status);
if (status)
return status & 0xff;
/* Somebody closed stdout? */
if (fstat(fileno(stdout), &st))
return 0;
/* Ignore write errors for pipes and sockets.. */
if (S_ISFIFO(st.st_mode) || S_ISSOCK(st.st_mode))
return 0;
/* Check for ENOSPC and EIO errors.. */
if (fflush(stdout))
die("write failure on standard output: %s", strerror(errno));
if (ferror(stdout))
die("unknown write failure on standard output");
if (fclose(stdout))
die("close failed on standard output: %s", strerror(errno));
return 0;
}
static void handle_internal_command(int argc, const char **argv)
{
const char *cmd = argv[0];
static struct cmd_struct commands[] = {
{ "buildid-cache", cmd_buildid_cache, 0 },
{ "buildid-list", cmd_buildid_list, 0 },
perf diff: Introduce tool to show performance difference I guess it is enough to show some examples: [root@doppio linux-2.6-tip]# rm -f perf.data* [root@doppio linux-2.6-tip]# ls -la perf.data* ls: cannot access perf.data*: No such file or directory [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74440 2009-12-14 20:03 perf.data [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2692 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74280 2009-12-14 20:03 perf.data -rw------- 1 root root 74440 2009-12-14 20:03 perf.data.old [root@doppio linux-2.6-tip]# perf diff | head -5 1 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 -15307806 [kernel.kallsyms] __kmalloc 3 +1 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -p | head -5 1 +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 [kernel.kallsyms] __kmalloc 3 +1 /lib64/libc-2.10.1.so __GI_memmove 4 +4 /lib64/libc-2.10.1.so _int_malloc 5 +7 -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -v | head -5 1 361449551 326454971 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 151009241 135701435 -15307806 [kernel.kallsyms] __kmalloc 3 +1 101805328 105471269 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 78041440 101550435 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 59536172 98074985 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -vp | head -5 1 9.00% 8.00% +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 3.00% 3.00% [kernel.kallsyms] __kmalloc 3 +1 2.00% 2.00% /lib64/libc-2.10.1.so __GI_memmove 4 +4 2.00% 2.00% /lib64/libc-2.10.1.so _int_malloc 5 +7 1.00% 2.00% -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# This should be enough for diffs where the system is non volatile, i.e. when one doesn't updates binaries. For volatile environments, stay tuned for the next perf tool feature: a buildid cache populated by 'perf record', managed by 'perf buildid-cache' a-la ccache, and used by all the report tools. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> LKML-Reference: <1260828571-3613-3-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-15 05:09:31 +07:00
{ "diff", cmd_diff, 0 },
{ "evlist", cmd_evlist, 0 },
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 14:53:25 +07:00
{ "help", cmd_help, 0 },
{ "list", cmd_list, 0 },
{ "record", cmd_record, 0 },
{ "report", cmd_report, 0 },
{ "bench", cmd_bench, 0 },
{ "stat", cmd_stat, 0 },
{ "timechart", cmd_timechart, 0 },
{ "top", cmd_top, 0 },
{ "annotate", cmd_annotate, 0 },
{ "version", cmd_version, 0 },
{ "script", cmd_script, 0 },
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 14:53:25 +07:00
{ "sched", cmd_sched, 0 },
{ "probe", cmd_probe, 0 },
{ "kmem", cmd_kmem, 0 },
{ "lock", cmd_lock, 0 },
{ "kvm", cmd_kvm, 0 },
perf test: Initial regression testing command First an example with the first internal test: [acme@doppio linux-2.6-tip]$ perf test 1: vmlinux symtab matches kallsyms: Ok So it run just one test, that is "vmlinux symtab matches kallsyms", and it was successful. If we run it in verbose mode, we'll see details about errors and extra warnings for non-fatal problems: [acme@doppio linux-2.6-tip]$ perf test -v 1: vmlinux symtab matches kallsyms: --- start --- Looking at the vmlinux_path (5 entries long) No build_id in vmlinux, ignoring it No build_id in /boot/vmlinux, ignoring it No build_id in /boot/vmlinux-2.6.34-rc4-tip+, ignoring it Using /lib/modules/2.6.34-rc4-tip+/build/vmlinux for symbols Maps only in vmlinux: ffffffff81cb81b1-ffffffff81e1149b 0 [kernel].init.text ffffffff81e1149c-ffffffff9fffffff 0 [kernel].exit.text ffffffffff600000-ffffffffff6000ff 0 [kernel].vsyscall_0 ffffffffff600100-ffffffffff6003ff 0 [kernel].vsyscall_fn ffffffffff600400-ffffffffff6007ff 0 [kernel].vsyscall_1 ffffffffff600800-ffffffffffffffff 0 [kernel].vsyscall_2 Maps in vmlinux with a different name in kallsyms: ffffffffff600000-ffffffffff6000ff 0 [kernel].vsyscall_0 in kallsyms as [kernel].0 ffffffffff600100-ffffffffff6003ff 0 [kernel].vsyscall_fn in kallsyms as: *ffffffffff600100-ffffffffff60012f 0 [kernel].2 ffffffffff600400-ffffffffff6007ff 0 [kernel].vsyscall_1 in kallsyms as [kernel].6 ffffffffff600800-ffffffffffffffff 0 [kernel].vsyscall_2 in kallsyms as [kernel].8 Maps only in kallsyms: ffffffffff600130-ffffffffff6003ff 0 [kernel].4 ---- end ---- vmlinux symtab matches kallsyms: Ok [acme@doppio linux-2.6-tip]$ In the above case we only know the name of the non contiguous kernel ranges in the address space when reading the symbol information from the ELF symtab in vmlinux. The /proc/kallsyms file lack this, we only notice they are separate because there are modules after the kernel and after that more kernel functions, so we need to have a module rbtree backed by the module .ko path to get symtabs in the vmlinux case. The tool uses it to match by address to emit appropriate warning, but don't considers this fatal. The .init.text and .exit.text ines, of course, aren't in kallsyms, so I left these cases just as extra info in verbose mode. The end of the sections also aren't in kallsyms, so we the symbols layer does another pass and sets the end addresses as the next map start minus one, which sometimes pads, causing harmless mismatches. But at least the symbols match, tested it by copying /proc/kallsyms to /tmp/kallsyms and doing changes to see if they were detected. This first test also should serve as a first stab at documenting the symbol library by providing a self contained example that exercises it together with comments about what is being done. More tests to check if actions done on a monitored app, like doing mmaps, etc, makes the kernel generate the expected events should be added next. Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <new-submission> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-04-30 04:58:32 +07:00
{ "test", cmd_test, 0 },
perf: add perf-inject builtin Currently, perf 'live mode' writes build-ids at the end of the session, which isn't actually useful for processing live mode events. What would be better would be to have the build-ids sent before any of the samples that reference them, which can be done by processing the event stream and retrieving the build-ids on the first hit. Doing that in perf-record itself, however, is off-limits. This patch introduces perf-inject, which does the same job while leaving perf-record untouched. Normal mode perf still records the build-ids at the end of the session as it should, but for live mode, perf-inject can be injected in between the record and report steps e.g.: perf record -o - ./hackbench 10 | perf inject -v -b | perf report -v -i - perf-inject reads a perf-record event stream and repipes it to stdout. At any point the processing code can inject other events into the event stream - in this case build-ids (-b option) are read and injected as needed into the event stream. Build-ids are just the first user of perf-inject - potentially anything that needs userspace processing to augment the trace stream with additional information could make use of this facility. Cc: Ingo Molnar <mingo@elte.hu> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frédéric Weisbecker <fweisbec@gmail.com> LKML-Reference: <1272696080-16435-3-git-send-email-tzanussi@gmail.com> Signed-off-by: Tom Zanussi <tzanussi@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-05-01 13:41:20 +07:00
{ "inject", cmd_inject, 0 },
};
unsigned int i;
static const char ext[] = STRIP_EXTENSION;
if (sizeof(ext) > 1) {
i = strlen(argv[0]) - strlen(ext);
if (i > 0 && !strcmp(argv[0] + i, ext)) {
char *argv0 = strdup(argv[0]);
argv[0] = cmd = argv0;
argv0[i] = '\0';
}
}
/* Turn "perf cmd --help" into "perf help cmd" */
if (argc > 1 && !strcmp(argv[1], "--help")) {
argv[1] = argv[0];
argv[0] = cmd = "help";
}
for (i = 0; i < ARRAY_SIZE(commands); i++) {
struct cmd_struct *p = commands+i;
if (strcmp(p->cmd, cmd))
continue;
exit(run_builtin(p, argc, argv));
}
}
static void execv_dashed_external(const char **argv)
{
struct strbuf cmd = STRBUF_INIT;
const char *tmp;
int status;
strbuf_addf(&cmd, "perf-%s", argv[0]);
/*
* argv[0] must be the perf command, but the argv array
* belongs to the caller, and may be reused in
* subsequent loop iterations. Save argv[0] and
* restore it on error.
*/
tmp = argv[0];
argv[0] = cmd.buf;
/*
* if we fail because the command is not found, it is
* OK to return. Otherwise, we just pass along the status code.
*/
status = run_command_v_opt(argv, 0);
if (status != -ERR_RUN_COMMAND_EXEC) {
if (IS_RUN_COMMAND_ERR(status))
die("unable to run '%s'", argv[0]);
exit(-status);
}
errno = ENOENT; /* as if we called execvp */
argv[0] = tmp;
strbuf_release(&cmd);
}
static int run_argv(int *argcp, const char ***argv)
{
int done_alias = 0;
while (1) {
/* See if it's an internal command */
handle_internal_command(*argcp, *argv);
/* .. then try the external ones */
execv_dashed_external(*argv);
/* It could be an alias -- this works around the insanity
* of overriding "perf log" with "perf show" by having
* alias.log = show
*/
if (done_alias || !handle_alias(argcp, argv))
break;
done_alias = 1;
}
return done_alias;
}
static void pthread__block_sigwinch(void)
{
sigset_t set;
sigemptyset(&set);
sigaddset(&set, SIGWINCH);
pthread_sigmask(SIG_BLOCK, &set, NULL);
}
void pthread__unblock_sigwinch(void)
{
sigset_t set;
sigemptyset(&set);
sigaddset(&set, SIGWINCH);
pthread_sigmask(SIG_UNBLOCK, &set, NULL);
}
int main(int argc, const char **argv)
{
const char *cmd;
cmd = perf_extract_argv0_path(argv[0]);
if (!cmd)
cmd = "perf-help";
/* get debugfs mount point from /proc/mounts */
debugfs_mount(NULL);
/*
* "perf-xxxx" is the same as "perf xxxx", but we obviously:
*
* - cannot take flags in between the "perf" and the "xxxx".
* - cannot execute it externally (since it would just do
* the same thing over again)
*
* So we just directly call the internal command handler, and
* die if that one cannot handle it.
*/
if (!prefixcmp(cmd, "perf-")) {
cmd += 5;
argv[0] = cmd;
handle_internal_command(argc, argv);
die("cannot handle %s internally", cmd);
}
/* Look for flags.. */
argv++;
argc--;
handle_options(&argv, &argc, NULL);
commit_pager_choice();
perf buildid: add perfconfig option to specify buildid cache dir This patch adds the ability to specify an alternate directory to store the buildid cache (buildids, copy of binaries). By default, it is hardcoded to $HOME/.debug. This directory contains immutable data. The layout of the directory is such that no conflicts in filenames are possible. A modification in a file, yields a different buildid and thus a different location in the subdir hierarchy. You may want to put the buildid cache elsewhere because of disk space limitation or simply to share the cache between users. It is also useful for remote collect vs. local analysis of profiles. This patch adds a new config option to the perfconfig file. Under the tag 'buildid', there is a dir option. For instance, if you have: $ cat /etc/perfconfig [buildid] dir = /var/cache/perf-buildid All buildids and binaries are be saved in the directory specified. The perf record, buildid-list, buildid-cache, report, annotate, and archive commands will it to pull information out. The option can be set in the system-wide perfconfig file or in the $HOME/.perfconfig file. Cc: David S. Miller <davem@davemloft.net> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Tom Zanussi <tzanussi@gmail.com> LKML-Reference: <4c055fb7.df0ce30a.5f0d.ffffae52@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-06-02 02:25:01 +07:00
set_buildid_dir();
if (argc > 0) {
if (!prefixcmp(argv[0], "--"))
argv[0] += 2;
} else {
/* The user didn't specify a command; give them help */
printf("\n usage: %s\n\n", perf_usage_string);
list_common_cmds_help();
printf("\n %s\n\n", perf_more_info_string);
exit(1);
}
cmd = argv[0];
/*
* We use PATH to find perf commands, but we prepend some higher
* precedence paths: the "--exec-path" option, the PERF_EXEC_PATH
* environment, and the $(perfexecdir) from the Makefile at build
* time.
*/
setup_path();
/*
* Block SIGWINCH notifications so that the thread that wants it can
* unblock and get syscalls like select interrupted instead of waiting
* forever while the signal goes to some other non interested thread.
*/
pthread__block_sigwinch();
while (1) {
static int done_help;
static int was_alias;
was_alias = run_argv(&argc, &argv);
if (errno != ENOENT)
break;
if (was_alias) {
fprintf(stderr, "Expansion of alias '%s' failed; "
"'%s' is not a perf-command\n",
cmd, argv[0]);
exit(1);
}
if (!done_help) {
cmd = argv[0] = help_unknown_cmd(cmd);
done_help = 1;
} else
break;
}
fprintf(stderr, "Failed to run command '%s': %s\n",
cmd, strerror(errno));
return 1;
}