#include <unistd.h>
#include <sched.h>
+#include <sys/mman.h>
enum write_mode_t {
WRITE_FORCE,
static int realtime_prio = 0;
static bool raw_samples = false;
static bool system_wide = false;
-static int profile_cpu = -1;
static pid_t target_pid = -1;
static pid_t target_tid = -1;
static pid_t *all_tids = NULL;
static bool inherit_stat = false;
static bool no_samples = false;
static bool sample_address = false;
-static bool multiplex = false;
-static int multiplex_fd = -1;
static long samples = 0;
-static struct timeval last_read;
-static struct timeval this_read;
-
static u64 bytes_written = 0;
static struct pollfd *event_array;
static off_t post_processing_offset;
static struct perf_session *session;
+static const char *cpu_list;
struct mmap_data {
int counter;
unsigned int prev;
};
-static struct mmap_data *mmap_array[MAX_NR_CPUS][MAX_COUNTERS];
+static struct mmap_data mmap_array[MAX_NR_CPUS];
static unsigned long mmap_read_head(struct mmap_data *md)
{
void *buf;
int diff;
- gettimeofday(&this_read, NULL);
-
/*
* If we're further behind than half the buffer, there's a chance
* the writer will bite our tail and mess up the samples under us.
*/
diff = head - old;
if (diff < 0) {
- struct timeval iv;
- unsigned long msecs;
-
- timersub(&this_read, &last_read, &iv);
- msecs = iv.tv_sec*1000 + iv.tv_usec/1000;
-
- fprintf(stderr, "WARNING: failed to keep up with mmap data."
- " Last read %lu msecs ago.\n", msecs);
-
+ fprintf(stderr, "WARNING: failed to keep up with mmap data\n");
/*
* head points to a known good entry, start there.
*/
old = head;
}
- last_read = this_read;
-
if (old != head)
samples++;
if (inherit_stat)
attr->inherit_stat = 1;
- if (sample_address)
+ if (sample_address) {
attr->sample_type |= PERF_SAMPLE_ADDR;
+ attr->mmap_data = track;
+ }
if (call_graph)
attr->sample_type |= PERF_SAMPLE_CALLCHAIN;
+ if (system_wide)
+ attr->sample_type |= PERF_SAMPLE_CPU;
+
if (raw_samples) {
attr->sample_type |= PERF_SAMPLE_TIME;
attr->sample_type |= PERF_SAMPLE_RAW;
die("Permission error - are you root?\n"
"\t Consider tweaking"
" /proc/sys/kernel/perf_event_paranoid.\n");
- else if (err == ENODEV && profile_cpu != -1) {
+ else if (err == ENODEV && cpu_list) {
die("No such device - did you specify"
" an out-of-range profile CPU?\n");
}
*/
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);
+ if (counter || thread_index) {
+ ret = ioctl(fd[nr_cpu][counter][thread_index],
+ PERF_EVENT_IOC_SET_OUTPUT,
+ fd[nr_cpu][0][0]);
+ if (ret) {
+ error("failed to set output: %d (%s)\n", errno,
+ strerror(errno));
+ exit(-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,
+ mmap_array[nr_cpu].counter = counter;
+ mmap_array[nr_cpu].prev = 0;
+ mmap_array[nr_cpu].mask = mmap_pages*page_size - 1;
+ mmap_array[nr_cpu].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) {
+ if (mmap_array[nr_cpu].base == MAP_FAILED) {
error("failed to mmap with %d (%s)\n", errno, strerror(errno));
exit(-1);
}
+
+ event_array[nr_poll].fd = fd[nr_cpu][counter][thread_index];
+ event_array[nr_poll].events = POLLIN;
+ nr_poll++;
}
if (filter != NULL) {
static void mmap_read_all(void)
{
- int i, counter, thread;
+ int i;
for (i = 0; i < nr_cpu; i++) {
- for (counter = 0; counter < nr_counters; counter++) {
- for (thread = 0; thread < thread_num; thread++) {
- if (mmap_array[i][counter][thread].base)
- mmap_read(&mmap_array[i][counter][thread]);
- }
-
- }
+ if (mmap_array[i].base)
+ mmap_read(&mmap_array[i]);
}
if (perf_header__has_feat(&session->header, HEADER_TRACE_INFO))
{
int i, counter;
struct stat st;
- pid_t pid = 0;
int flags;
int err;
unsigned long waking = 0;
if (forks) {
child_pid = fork();
- if (pid < 0) {
+ if (child_pid < 0) {
perror("failed to fork");
exit(-1);
}
close(child_ready_pipe[0]);
}
- if ((!system_wide && no_inherit) || profile_cpu != -1) {
- open_counters(profile_cpu);
+ nr_cpus = read_cpu_map(cpu_list);
+ if (nr_cpus < 1) {
+ perror("failed to collect number of CPUs\n");
+ return -1;
+ }
+
+ if (!system_wide && no_inherit && !cpu_list) {
+ open_counters(-1);
} else {
- nr_cpus = read_cpu_map();
for (i = 0; i < nr_cpus; i++)
open_counters(cpumap[i]);
}
if (perf_guest)
perf_session__process_machines(session, event__synthesize_guest_os);
- if (!system_wide && profile_cpu == -1)
+ if (!system_wide && cpu_list)
event__synthesize_thread(target_tid, process_synthesized_event,
session);
else
"system-wide collection from all CPUs"),
OPT_BOOLEAN('A', "append", &append_file,
"append to the output file to do incremental profiling"),
- OPT_INTEGER('C', "profile_cpu", &profile_cpu,
- "CPU to profile on"),
+ OPT_STRING('C', "cpu", &cpu_list, "cpu",
+ "list of cpus to monitor"),
OPT_BOOLEAN('f', "force", &force,
"overwrite existing data file (deprecated)"),
OPT_U64('c', "count", &user_interval, "event period to sample"),
"Sample addresses"),
OPT_BOOLEAN('n', "no-samples", &no_samples,
"don't sample"),
- OPT_BOOLEAN('M', "multiplex", &multiplex,
- "multiplex counter output in a single channel"),
OPT_END()
};
argc = parse_options(argc, argv, options, record_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
if (!argc && target_pid == -1 && target_tid == -1 &&
- !system_wide && profile_cpu == -1)
+ !system_wide && !cpu_list)
usage_with_options(record_usage, options);
if (force && append_file) {
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] = zalloc(
- sizeof(struct mmap_data)*thread_num);
- if (!fd[i][j] || !mmap_array[i][j])
+ if (!fd[i][j])
return -ENOMEM;
}
}