hollalinux
/
linux-sg2042
mirror of https://github.com/sophgo/linux-riscv.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

perf events: Change perf parameter --pid to process-wide collection instead of thread-wide 

Parameter --pid (or -p) of perf currently means a thread-wide
collection. For exmaple, if a process whose id is 8888 has 10
threads, 'perf top -p 8888' just collects the main thread
statistics. That's misleading. Users are used to attach a whole
process when debugging a process by gdb. To follow normal usage
style, the patch change --pid to process-wide collection and add
--tid (-t) to mean a thread-wide collection.

Usage example is:

 # perf top -p 8888
 # perf record -p 8888 -f sleep 10
 # perf stat -p 8888 -f sleep 10

Above commands collect the statistics of all threads of process
8888.

Signed-off-by: Zhang Yanmin <yanmin_zhang@linux.intel.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Sheng Yang <sheng@linux.intel.com>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Jes Sorensen <Jes.Sorensen@redhat.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Gleb Natapov <gleb@redhat.com>
Cc: zhiteng.huang@intel.com
Cc: Zachary Amsden <zamsden@redhat.com>
LKML-Reference: <1268922965-14774-3-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This commit is contained in:
Zhang, Yanmin 2010-03-18 11:36:05 -03:00 committed by Ingo Molnar
parent 46be604b5b
commit d6d901c23a
5 changed files with 366 additions and 187 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

258
tools/perf/builtin-record.c
View File

@ -27,7 +27,7 @@
#include <unistd.h>
#include <sched.h>
static int fd[MAX_NR_CPUS][MAX_COUNTERS];
static int *fd[MAX_NR_CPUS][MAX_COUNTERS];
static long default_interval = 0;
@ -43,6 +43,9 @@ static int raw_samples = 0;
static int system_wide = 0;
static int profile_cpu = -1;
static pid_t target_pid = -1;
static pid_t target_tid = -1;
static pid_t *all_tids = NULL;
static int thread_num = 0;
static pid_t child_pid = -1;
static int inherit = 1;
static int force = 0;
@ -60,7 +63,7 @@ static struct timeval this_read;
static u64 bytes_written = 0;
static struct pollfd event_array[MAX_NR_CPUS * MAX_COUNTERS];
static struct pollfd *event_array;
static int nr_poll = 0;
static int nr_cpu = 0;
@ -77,7 +80,7 @@ struct mmap_data {
unsigned int prev;
};
static struct mmap_data mmap_array[MAX_NR_CPUS][MAX_COUNTERS];
static struct mmap_data *mmap_array[MAX_NR_CPUS][MAX_COUNTERS];
static unsigned long mmap_read_head(struct mmap_data *md)
{
@ -225,12 +228,13 @@ static struct perf_header_attr *get_header_attr(struct perf_event_attr *a, int n
return h_attr;
}
static void create_counter(int counter, int cpu, pid_t pid)
static void create_counter(int counter, int cpu)
{
char *filter = filters[counter];
struct perf_event_attr *attr = attrs + counter;
struct perf_header_attr *h_attr;
int track = !counter; /* only the first counter needs these */
int thread_index;
int ret;
struct {
u64 count;
@ -280,115 +284,124 @@ static void create_counter(int counter, int cpu, pid_t pid)
attr->enable_on_exec = 1;
}
for (thread_index = 0; thread_index < thread_num; thread_index++) {
try_again:
fd[nr_cpu][counter] = sys_perf_event_open(attr, pid, cpu, group_fd, 0);
fd[nr_cpu][counter][thread_index] = sys_perf_event_open(attr,
all_tids[thread_index], cpu, group_fd, 0);
if (fd[nr_cpu][counter] < 0) {
int err = errno;
if (fd[nr_cpu][counter][thread_index] < 0) {
int err = errno;
if (err == EPERM || err == EACCES)
die("Permission error - are you root?\n"
"\t Consider tweaking /proc/sys/kernel/perf_event_paranoid.\n");
else if (err == ENODEV && profile_cpu != -1)
die("No such device - did you specify an out-of-range profile CPU?\n");
if (err == EPERM || err == EACCES)
die("Permission error - are you root?\n"
"\t Consider tweaking"
" /proc/sys/kernel/perf_event_paranoid.\n");
else if (err == ENODEV && profile_cpu != -1) {
die("No such device - did you specify"
" an out-of-range profile CPU?\n");
}
/*
* If it's cycles then fall back to hrtimer
* based cpu-clock-tick sw counter, which
* is always available even if no PMU support:
*/
if (attr->type == PERF_TYPE_HARDWARE
&& attr->config == PERF_COUNT_HW_CPU_CYCLES) {
/*
* If it's cycles then fall back to hrtimer
* based cpu-clock-tick sw counter, which
* is always available even if no PMU support:
*/
if (attr->type == PERF_TYPE_HARDWARE
&& attr->config == PERF_COUNT_HW_CPU_CYCLES) {
if (verbose)
warning(" ... trying to fall back to cpu-clock-ticks\n");
attr->type = PERF_TYPE_SOFTWARE;
attr->config = PERF_COUNT_SW_CPU_CLOCK;
goto try_again;
}
printf("\n");
error("perfcounter syscall returned with %d (%s)\n",
fd[nr_cpu][counter], strerror(err));
if (verbose)
warning(" ... trying to fall back to cpu-clock-ticks\n");
attr->type = PERF_TYPE_SOFTWARE;
attr->config = PERF_COUNT_SW_CPU_CLOCK;
goto try_again;
}
printf("\n");
error("perfcounter syscall returned with %d (%s)\n",
fd[nr_cpu][counter][thread_index], strerror(err));
#if defined(__i386__) || defined(__x86_64__)
if (attr->type == PERF_TYPE_HARDWARE && err == EOPNOTSUPP)
die("No hardware sampling interrupt available. No APIC? If so then you can boot the kernel with the \"lapic\" boot parameter to force-enable it.\n");
if (attr->type == PERF_TYPE_HARDWARE && err == EOPNOTSUPP)
die("No hardware sampling interrupt available."
" No APIC? If so then you can boot the kernel"
" with the \"lapic\" boot parameter to"
" force-enable it.\n");
#endif
die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
exit(-1);
}
h_attr = get_header_attr(attr, counter);
if (h_attr == NULL)
die("nomem\n");
if (!file_new) {
if (memcmp(&h_attr->attr, attr, sizeof(*attr))) {
fprintf(stderr, "incompatible append\n");
die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
exit(-1);
}
}
if (read(fd[nr_cpu][counter], &read_data, sizeof(read_data)) == -1) {
perror("Unable to read perf file descriptor\n");
exit(-1);
}
h_attr = get_header_attr(attr, counter);
if (h_attr == NULL)
die("nomem\n");
if (perf_header_attr__add_id(h_attr, read_data.id) < 0) {
pr_warning("Not enough memory to add id\n");
exit(-1);
}
if (!file_new) {
if (memcmp(&h_attr->attr, attr, sizeof(*attr))) {
fprintf(stderr, "incompatible append\n");
exit(-1);
}
}
assert(fd[nr_cpu][counter] >= 0);
fcntl(fd[nr_cpu][counter], F_SETFL, O_NONBLOCK);
/*
* First counter acts as the group leader:
*/
if (group && group_fd == -1)
group_fd = fd[nr_cpu][counter];
if (multiplex && multiplex_fd == -1)
multiplex_fd = fd[nr_cpu][counter];
if (multiplex && fd[nr_cpu][counter] != multiplex_fd) {
ret = ioctl(fd[nr_cpu][counter], PERF_EVENT_IOC_SET_OUTPUT, multiplex_fd);
assert(ret != -1);
} else {
event_array[nr_poll].fd = fd[nr_cpu][counter];
event_array[nr_poll].events = POLLIN;
nr_poll++;
mmap_array[nr_cpu][counter].counter = counter;
mmap_array[nr_cpu][counter].prev = 0;
mmap_array[nr_cpu][counter].mask = mmap_pages*page_size - 1;
mmap_array[nr_cpu][counter].base = mmap(NULL, (mmap_pages+1)*page_size,
PROT_READ|PROT_WRITE, MAP_SHARED, fd[nr_cpu][counter], 0);
if (mmap_array[nr_cpu][counter].base == MAP_FAILED) {
error("failed to mmap with %d (%s)\n", errno, strerror(errno));
if (read(fd[nr_cpu][counter][thread_index], &read_data, sizeof(read_data)) == -1) {
perror("Unable to read perf file descriptor\n");
exit(-1);
}
}
if (filter != NULL) {
ret = ioctl(fd[nr_cpu][counter],
PERF_EVENT_IOC_SET_FILTER, filter);
if (ret) {
error("failed to set filter with %d (%s)\n", errno,
strerror(errno));
if (perf_header_attr__add_id(h_attr, read_data.id) < 0) {
pr_warning("Not enough memory to add id\n");
exit(-1);
}
assert(fd[nr_cpu][counter][thread_index] >= 0);
fcntl(fd[nr_cpu][counter][thread_index], F_SETFL, O_NONBLOCK);
/*
* First counter acts as the group leader:
*/
if (group && group_fd == -1)
group_fd = fd[nr_cpu][counter][thread_index];
if (multiplex && multiplex_fd == -1)
multiplex_fd = fd[nr_cpu][counter][thread_index];
if (multiplex && fd[nr_cpu][counter][thread_index] != multiplex_fd) {
ret = ioctl(fd[nr_cpu][counter][thread_index], PERF_EVENT_IOC_SET_OUTPUT, multiplex_fd);
assert(ret != -1);
} else {
event_array[nr_poll].fd = fd[nr_cpu][counter][thread_index];
event_array[nr_poll].events = POLLIN;
nr_poll++;
mmap_array[nr_cpu][counter][thread_index].counter = counter;
mmap_array[nr_cpu][counter][thread_index].prev = 0;
mmap_array[nr_cpu][counter][thread_index].mask = mmap_pages*page_size - 1;
mmap_array[nr_cpu][counter][thread_index].base = mmap(NULL, (mmap_pages+1)*page_size,
PROT_READ|PROT_WRITE, MAP_SHARED, fd[nr_cpu][counter][thread_index], 0);
if (mmap_array[nr_cpu][counter][thread_index].base == MAP_FAILED) {
error("failed to mmap with %d (%s)\n", errno, strerror(errno));
exit(-1);
}
}
if (filter != NULL) {
ret = ioctl(fd[nr_cpu][counter][thread_index],
PERF_EVENT_IOC_SET_FILTER, filter);
if (ret) {
error("failed to set filter with %d (%s)\n", errno,
strerror(errno));
exit(-1);
}
}
}
}
static void open_counters(int cpu, pid_t pid)
static void open_counters(int cpu)
{
int counter;
group_fd = -1;
for (counter = 0; counter < nr_counters; counter++)
create_counter(counter, cpu, pid);
create_counter(counter, cpu);
nr_cpu++;
}
@ -529,6 +542,9 @@ static int __cmd_record(int argc, const char **argv)
exit(-1);
}
if (!system_wide && target_tid == -1 && target_pid == -1)
all_tids[0] = child_pid;
close(child_ready_pipe[1]);
close(go_pipe[0]);
/*
@ -541,17 +557,12 @@ static int __cmd_record(int argc, const char **argv)
close(child_ready_pipe[0]);
}
if (forks && target_pid == -1 && !system_wide)
pid = child_pid;
else
pid = target_pid;
if ((!system_wide && !inherit) || profile_cpu != -1) {
open_counters(profile_cpu, pid);
open_counters(profile_cpu);
} else {
nr_cpus = read_cpu_map();
for (i = 0; i < nr_cpus; i++)
open_counters(cpumap[i], pid);
open_counters(cpumap[i]);
}
if (file_new) {
@ -576,7 +587,7 @@ static int __cmd_record(int argc, const char **argv)
}
if (!system_wide && profile_cpu == -1)
event__synthesize_thread(target_pid, process_synthesized_event,
event__synthesize_thread(target_tid, process_synthesized_event,
session);
else
event__synthesize_threads(process_synthesized_event, session);
@ -599,11 +610,16 @@ static int __cmd_record(int argc, const char **argv)
for (;;) {
int hits = samples;
int thread;
for (i = 0; i < nr_cpu; i++) {
for (counter = 0; counter < nr_counters; counter++) {
if (mmap_array[i][counter].base)
mmap_read(&mmap_array[i][counter]);
for (thread = 0;
thread < thread_num; thread++) {
if (mmap_array[i][counter][thread].base)
mmap_read(&mmap_array[i][counter][thread]);
}
}
}
@ -616,8 +632,15 @@ static int __cmd_record(int argc, const char **argv)
if (done) {
for (i = 0; i < nr_cpu; i++) {
for (counter = 0; counter < nr_counters; counter++)
ioctl(fd[i][counter], PERF_EVENT_IOC_DISABLE);
for (counter = 0;
counter < nr_counters;
counter++) {
for (thread = 0;
thread < thread_num;
thread++)
ioctl(fd[i][counter][thread],
PERF_EVENT_IOC_DISABLE);
}
}
}
}
@ -649,7 +672,9 @@ static const struct option options[] = {
OPT_CALLBACK(0, "filter", NULL, "filter",
"event filter", parse_filter),
OPT_INTEGER('p', "pid", &target_pid,
"record events on existing pid"),
"record events on existing process id"),
OPT_INTEGER('t', "tid", &target_tid,
"record events on existing thread id"),
OPT_INTEGER('r', "realtime", &realtime_prio,
"collect data with this RT SCHED_FIFO priority"),
OPT_BOOLEAN('R', "raw-samples", &raw_samples,
@ -690,10 +715,12 @@ static const struct option options[] = {
int cmd_record(int argc, const char **argv, const char *prefix __used)
{
int counter;
int i,j;
argc = parse_options(argc, argv, options, record_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
if (!argc && target_pid == -1 && !system_wide && profile_cpu == -1)
if (!argc && target_pid == -1 && target_tid == -1 &&
!system_wide && profile_cpu == -1)
usage_with_options(record_usage, options);
symbol__init();
@ -704,6 +731,37 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
attrs[0].config = PERF_COUNT_HW_CPU_CYCLES;
}
if (target_pid != -1) {
target_tid = target_pid;
thread_num = find_all_tid(target_pid, &all_tids);
if (thread_num <= 0) {
fprintf(stderr, "Can't find all threads of pid %d\n",
target_pid);
usage_with_options(record_usage, options);
}
} else {
all_tids=malloc(sizeof(pid_t));
if (!all_tids)
return -ENOMEM;
all_tids[0] = target_tid;
thread_num = 1;
}
for (i = 0; i < MAX_NR_CPUS; i++) {
for (j = 0; j < MAX_COUNTERS; j++) {
fd[i][j] = malloc(sizeof(int)*thread_num);
mmap_array[i][j] = malloc(
sizeof(struct mmap_data)*thread_num);
if (!fd[i][j] || !mmap_array[i][j])
return -ENOMEM;
}
}
event_array = malloc(
sizeof(struct pollfd)*MAX_NR_CPUS*MAX_COUNTERS*thread_num);
if (!event_array)
return -ENOMEM;
/*
* User specified count overrides default frequency.
*/

104
tools/perf/builtin-stat.c
View File

@ -46,6 +46,7 @@
#include "util/debug.h"
#include "util/header.h"
#include "util/cpumap.h"
#include "util/thread.h"
#include <sys/prctl.h>
#include <math.h>
@ -74,10 +75,13 @@ static int run_count = 1;
static int inherit = 1;
static int scale = 1;
static pid_t target_pid = -1;
static pid_t target_tid = -1;
static pid_t *all_tids = NULL;
static int thread_num = 0;
static pid_t child_pid = -1;
static int null_run = 0;
static int fd[MAX_NR_CPUS][MAX_COUNTERS];
static int *fd[MAX_NR_CPUS][MAX_COUNTERS];
static int event_scaled[MAX_COUNTERS];
@ -140,9 +144,10 @@ struct stats runtime_branches_stats;
#define ERR_PERF_OPEN \
"Error: counter %d, sys_perf_event_open() syscall returned with %d (%s)\n"
static void create_perf_stat_counter(int counter, int pid)
static void create_perf_stat_counter(int counter)
{
struct perf_event_attr *attr = attrs + counter;
int thread;
if (scale)
attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
@ -152,10 +157,11 @@ static void create_perf_stat_counter(int counter, int pid)
unsigned int cpu;
for (cpu = 0; cpu < nr_cpus; cpu++) {
fd[cpu][counter] = sys_perf_event_open(attr, -1, cpumap[cpu], -1, 0);
if (fd[cpu][counter] < 0 && verbose)
fd[cpu][counter][0] = sys_perf_event_open(attr,
-1, cpumap[cpu], -1, 0);
if (fd[cpu][counter][0] < 0 && verbose)
fprintf(stderr, ERR_PERF_OPEN, counter,
fd[cpu][counter], strerror(errno));
fd[cpu][counter][0], strerror(errno));
}
} else {
attr->inherit = inherit;
@ -163,11 +169,14 @@ static void create_perf_stat_counter(int counter, int pid)
attr->disabled = 1;
attr->enable_on_exec = 1;
}
fd[0][counter] = sys_perf_event_open(attr, pid, -1, -1, 0);
if (fd[0][counter] < 0 && verbose)
fprintf(stderr, ERR_PERF_OPEN, counter,
fd[0][counter], strerror(errno));
for (thread = 0; thread < thread_num; thread++) {
fd[0][counter][thread] = sys_perf_event_open(attr,
all_tids[thread], -1, -1, 0);
if (fd[0][counter][thread] < 0 && verbose)
fprintf(stderr, ERR_PERF_OPEN, counter,
fd[0][counter][thread],
strerror(errno));
}
}
}
@ -192,25 +201,28 @@ static void read_counter(int counter)
unsigned int cpu;
size_t res, nv;
int scaled;
int i;
int i, thread;
count[0] = count[1] = count[2] = 0;
nv = scale ? 3 : 1;
for (cpu = 0; cpu < nr_cpus; cpu++) {
if (fd[cpu][counter] < 0)
continue;
for (thread = 0; thread < thread_num; thread++) {
if (fd[cpu][counter][thread] < 0)
continue;
res = read(fd[cpu][counter], single_count, nv * sizeof(u64));
assert(res == nv * sizeof(u64));
res = read(fd[cpu][counter][thread],
single_count, nv * sizeof(u64));
assert(res == nv * sizeof(u64));
close(fd[cpu][counter]);
fd[cpu][counter] = -1;
close(fd[cpu][counter][thread]);
fd[cpu][counter][thread] = -1;
count[0] += single_count[0];
if (scale) {
count[1] += single_count[1];
count[2] += single_count[2];
count[0] += single_count[0];
if (scale) {
count[1] += single_count[1];
count[2] += single_count[2];
}
}
}
@ -253,7 +265,6 @@ static int run_perf_stat(int argc __used, const char **argv)
unsigned long long t0, t1;
int status = 0;
int counter;
int pid;
int child_ready_pipe[2], go_pipe[2];
const bool forks = (argc > 0);
char buf;
@ -299,6 +310,9 @@ static int run_perf_stat(int argc __used, const char **argv)
exit(-1);
}
if (target_tid == -1 && target_pid == -1 && !system_wide)
all_tids[0] = child_pid;
/*
* Wait for the child to be ready to exec.
*/
@ -309,12 +323,8 @@ static int run_perf_stat(int argc __used, const char **argv)
close(child_ready_pipe[0]);
}
if (target_pid == -1)
pid = child_pid;
else
pid = target_pid;
for (counter = 0; counter < nr_counters; counter++)
create_perf_stat_counter(counter, pid);
create_perf_stat_counter(counter);
/*
* Enable counters and exec the command:
@ -433,12 +443,14 @@ static void print_stat(int argc, const char **argv)
fprintf(stderr, "\n");
fprintf(stderr, " Performance counter stats for ");
if(target_pid == -1) {
if(target_pid == -1 && target_tid == -1) {
fprintf(stderr, "\'%s", argv[0]);
for (i = 1; i < argc; i++)
fprintf(stderr, " %s", argv[i]);
}else
fprintf(stderr, "task pid \'%d", target_pid);
} else if (target_pid != -1)
fprintf(stderr, "process id \'%d", target_pid);
else
fprintf(stderr, "thread id \'%d", target_tid);
fprintf(stderr, "\'");
if (run_count > 1)
@ -493,7 +505,9 @@ static const struct option options[] = {
OPT_BOOLEAN('i', "inherit", &inherit,
"child tasks inherit counters"),
OPT_INTEGER('p', "pid", &target_pid,
"stat events on existing pid"),
"stat events on existing process id"),
OPT_INTEGER('t', "tid", &target_tid,
"stat events on existing thread id"),
OPT_BOOLEAN('a', "all-cpus", &system_wide,
"system-wide collection from all CPUs"),
OPT_BOOLEAN('c', "scale", &scale,
@ -510,10 +524,11 @@ static const struct option options[] = {
int cmd_stat(int argc, const char **argv, const char *prefix __used)
{
int status;
int i,j;
argc = parse_options(argc, argv, options, stat_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
if (!argc && target_pid == -1)
if (!argc && target_pid == -1 && target_tid == -1)
usage_with_options(stat_usage, options);
if (run_count <= 0)
usage_with_options(stat_usage, options);
@ -529,6 +544,31 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
else
nr_cpus = 1;
if (target_pid != -1) {
target_tid = target_pid;
thread_num = find_all_tid(target_pid, &all_tids);
if (thread_num <= 0) {
fprintf(stderr, "Can't find all threads of pid %d\n",
target_pid);
usage_with_options(stat_usage, options);
}
} else {
all_tids=malloc(sizeof(pid_t));
if (!all_tids)
return -ENOMEM;
all_tids[0] = target_tid;
thread_num = 1;
}
for (i = 0; i < MAX_NR_CPUS; i++) {
for (j = 0; j < MAX_COUNTERS; j++) {
fd[i][j] = malloc(sizeof(int)*thread_num);
if (!fd[i][j])
return -ENOMEM;
}
}
/*
* We dont want to block the signals - that would cause
* child tasks to inherit that and Ctrl-C would not work.

158
tools/perf/builtin-top.c
View File

@ -55,7 +55,7 @@
#include <linux/unistd.h>
#include <linux/types.h>
static int fd[MAX_NR_CPUS][MAX_COUNTERS];
static int *fd[MAX_NR_CPUS][MAX_COUNTERS];
static int system_wide = 0;
@ -65,6 +65,9 @@ static int count_filter = 5;
static int print_entries;
static int target_pid = -1;
static int target_tid = -1;
static pid_t *all_tids = NULL;
static int thread_num = 0;
static int inherit = 0;
static int profile_cpu = -1;
static int nr_cpus = 0;
@ -524,13 +527,15 @@ static void print_sym_table(void)
if (target_pid != -1)
printf(" (target_pid: %d", target_pid);
else if (target_tid != -1)
printf(" (target_tid: %d", target_tid);
else
printf(" (all");
if (profile_cpu != -1)
printf(", cpu: %d)\n", profile_cpu);
else {
if (target_pid != -1)
if (target_tid != -1)
printf(")\n");
else
printf(", %d CPUs)\n", nr_cpus);
@ -1129,16 +1134,21 @@ static void perf_session__mmap_read_counter(struct perf_session *self,
md->prev = old;
}
static struct pollfd event_array[MAX_NR_CPUS * MAX_COUNTERS];
static struct mmap_data mmap_array[MAX_NR_CPUS][MAX_COUNTERS];
static struct pollfd *event_array;
static struct mmap_data *mmap_array[MAX_NR_CPUS][MAX_COUNTERS];
static void perf_session__mmap_read(struct perf_session *self)
{
int i, counter;
int i, counter, thread_index;
for (i = 0; i < nr_cpus; i++) {
for (counter = 0; counter < nr_counters; counter++)
perf_session__mmap_read_counter(self, &mmap_array[i][counter]);
for (thread_index = 0;
thread_index < thread_num;
thread_index++) {
perf_session__mmap_read_counter(self,
&mmap_array[i][counter][thread_index]);
}
}
}
@ -1149,9 +1159,10 @@ static void start_counter(int i, int counter)
{
struct perf_event_attr *attr;
int cpu;
int thread_index;
cpu = profile_cpu;
if (target_pid == -1 && profile_cpu == -1)
if (target_tid == -1 && profile_cpu == -1)
cpu = cpumap[i];
attr = attrs + counter;
@ -1167,55 +1178,58 @@ static void start_counter(int i, int counter)
attr->inherit = (cpu < 0) && inherit;
attr->mmap = 1;
for (thread_index = 0; thread_index < thread_num; thread_index++) {
try_again:
fd[i][counter] = sys_perf_event_open(attr, target_pid, cpu, group_fd, 0);
fd[i][counter][thread_index] = sys_perf_event_open(attr,
all_tids[thread_index], cpu, group_fd, 0);
if (fd[i][counter] < 0) {
int err = errno;
if (fd[i][counter][thread_index] < 0) {
int err = errno;
if (err == EPERM || err == EACCES)
die("No permission - are you root?\n");
/*
* If it's cycles then fall back to hrtimer
* based cpu-clock-tick sw counter, which
* is always available even if no PMU support:
*/
if (attr->type == PERF_TYPE_HARDWARE
&& attr->config == PERF_COUNT_HW_CPU_CYCLES) {
if (err == EPERM || err == EACCES)
die("No permission - are you root?\n");
/*
* If it's cycles then fall back to hrtimer
* based cpu-clock-tick sw counter, which
* is always available even if no PMU support:
*/
if (attr->type == PERF_TYPE_HARDWARE
&& attr->config == PERF_COUNT_HW_CPU_CYCLES) {
if (verbose)
warning(" ... trying to fall back to cpu-clock-ticks\n");
if (verbose)
warning(" ... trying to fall back to cpu-clock-ticks\n");
attr->type = PERF_TYPE_SOFTWARE;
attr->config = PERF_COUNT_SW_CPU_CLOCK;
goto try_again;
attr->type = PERF_TYPE_SOFTWARE;
attr->config = PERF_COUNT_SW_CPU_CLOCK;
goto try_again;
}
printf("\n");
error("perfcounter syscall returned with %d (%s)\n",
fd[i][counter][thread_index], strerror(err));
die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
exit(-1);
}
printf("\n");
error("perfcounter syscall returned with %d (%s)\n",
fd[i][counter], strerror(err));
die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
exit(-1);
assert(fd[i][counter][thread_index] >= 0);
fcntl(fd[i][counter][thread_index], F_SETFL, O_NONBLOCK);
/*
* First counter acts as the group leader:
*/
if (group && group_fd == -1)
group_fd = fd[i][counter][thread_index];
event_array[nr_poll].fd = fd[i][counter][thread_index];
event_array[nr_poll].events = POLLIN;
nr_poll++;
mmap_array[i][counter][thread_index].counter = counter;
mmap_array[i][counter][thread_index].prev = 0;
mmap_array[i][counter][thread_index].mask = mmap_pages*page_size - 1;
mmap_array[i][counter][thread_index].base = mmap(NULL, (mmap_pages+1)*page_size,
PROT_READ, MAP_SHARED, fd[i][counter][thread_index], 0);
if (mmap_array[i][counter][thread_index].base == MAP_FAILED)
die("failed to mmap with %d (%s)\n", errno, strerror(errno));
}
assert(fd[i][counter] >= 0);
fcntl(fd[i][counter], F_SETFL, O_NONBLOCK);
/*
* First counter acts as the group leader:
*/
if (group && group_fd == -1)
group_fd = fd[i][counter];
event_array[nr_poll].fd = fd[i][counter];
event_array[nr_poll].events = POLLIN;
nr_poll++;
mmap_array[i][counter].counter = counter;
mmap_array[i][counter].prev = 0;
mmap_array[i][counter].mask = mmap_pages*page_size - 1;
mmap_array[i][counter].base = mmap(NULL, (mmap_pages+1)*page_size,
PROT_READ, MAP_SHARED, fd[i][counter], 0);
if (mmap_array[i][counter].base == MAP_FAILED)
die("failed to mmap with %d (%s)\n", errno, strerror(errno));
}
static int __cmd_top(void)
@ -1231,8 +1245,8 @@ static int __cmd_top(void)
if (session == NULL)
return -ENOMEM;
if (target_pid != -1)
event__synthesize_thread(target_pid, event__process, session);
if (target_tid != -1)
event__synthesize_thread(target_tid, event__process, session);
else
event__synthesize_threads(event__process, session);
@ -1243,7 +1257,7 @@ static int __cmd_top(void)
}
/* Wait for a minimal set of events before starting the snapshot */
poll(event_array, nr_poll, 100);
poll(&event_array[0], nr_poll, 100);
perf_session__mmap_read(session);
@ -1286,7 +1300,9 @@ static const struct option options[] = {
OPT_INTEGER('c', "count", &default_interval,
"event period to sample"),
OPT_INTEGER('p', "pid", &target_pid,
"profile events on existing pid"),
"profile events on existing process id"),
OPT_INTEGER('t', "tid", &target_tid,
"profile events on existing thread id"),
OPT_BOOLEAN('a', "all-cpus", &system_wide,
"system-wide collection from all CPUs"),
OPT_INTEGER('C', "CPU", &profile_cpu,
@ -1327,6 +1343,7 @@ static const struct option options[] = {
int cmd_top(int argc, const char **argv, const char *prefix __used)
{
int counter;
int i,j;
page_size = sysconf(_SC_PAGE_SIZE);
@ -1334,8 +1351,39 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
if (argc)
usage_with_options(top_usage, options);
if (target_pid != -1) {
target_tid = target_pid;
thread_num = find_all_tid(target_pid, &all_tids);
if (thread_num <= 0) {
fprintf(stderr, "Can't find all threads of pid %d\n",
target_pid);
usage_with_options(top_usage, options);
}
} else {
all_tids=malloc(sizeof(pid_t));
if (!all_tids)
return -ENOMEM;
all_tids[0] = target_tid;
thread_num = 1;
}
for (i = 0; i < MAX_NR_CPUS; i++) {
for (j = 0; j < MAX_COUNTERS; j++) {
fd[i][j] = malloc(sizeof(int)*thread_num);
mmap_array[i][j] = malloc(
sizeof(struct mmap_data)*thread_num);
if (!fd[i][j] || !mmap_array[i][j])
return -ENOMEM;
}
}
event_array = malloc(
sizeof(struct pollfd)*MAX_NR_CPUS*MAX_COUNTERS*thread_num);
if (!event_array)
return -ENOMEM;
/* CPU and PID are mutually exclusive */
if (target_pid != -1 && profile_cpu != -1) {
if (target_tid > 0 && profile_cpu != -1) {
printf("WARNING: PID switch overriding CPU\n");
sleep(1);
profile_cpu = -1;
@ -1376,7 +1424,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
attrs[counter].sample_period = default_interval;
}
if (target_pid != -1 || profile_cpu != -1)
if (target_tid != -1 || profile_cpu != -1)
nr_cpus = 1;
else
nr_cpus = read_cpu_map();

32
tools/perf/util/thread.c
View File

@ -7,6 +7,37 @@
#include "util.h"
#include "debug.h"
int find_all_tid(int pid, pid_t ** all_tid)
{
char name[256];
int items;
struct dirent **namelist = NULL;
int ret = 0;
int i;
sprintf(name, "/proc/%d/task", pid);
items = scandir(name, &namelist, NULL, NULL);
if (items <= 0)
return -ENOENT;
*all_tid = malloc(sizeof(pid_t) * items);
if (!*all_tid) {
ret = -ENOMEM;
goto failure;
}
for (i = 0; i < items; i++)
(*all_tid)[i] = atoi(namelist[i]->d_name);
ret = items;
failure:
for (i=0; i<items; i++)
free(namelist[i]);
free(namelist);
return ret;
}
void map_groups__init(struct map_groups *self)
{
int i;
@ -348,3 +379,4 @@ struct symbol *map_groups__find_symbol(struct map_groups *self,
return NULL;
}

1
tools/perf/util/thread.h
View File

@ -23,6 +23,7 @@ struct thread {
int comm_len;
};
int find_all_tid(int pid, pid_t ** all_tid);
void map_groups__init(struct map_groups *self);
int thread__set_comm(struct thread *self, const char *comm);
int thread__comm_len(struct thread *self);