[PATCH v1 14/15] perf record: start threads in the beginning of trace streaming
From: Alexey Budankov
Date: Mon Oct 12 2020 - 05:11:47 EST
Start threads in detached state because its management is possible
via messaging. Block signals prior the threads start so only main
tool thread would be notified on external async signals during data
collection. Streaming threads connect one-to-one to mapped data
buffers and write into per-CPU trace files located at data directory.
Data buffers and threads are affined to local NUMA nodes and monitored
CPUs according to system topology. --cpu option can be used to specify
exact CPUs to be monitored.
Signed-off-by: Alexey Budankov <alexey.budankov@xxxxxxxxxxxxxxx>
---
tools/perf/builtin-record.c | 128 +++++++++++++++++++++++++++++++++---
1 file changed, 120 insertions(+), 8 deletions(-)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index a15642656066..1d41e996a994 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -56,6 +56,7 @@
#include <poll.h>
#include <pthread.h>
#include <unistd.h>
+#include <sys/syscall.h>
#include <sched.h>
#include <signal.h>
#ifdef HAVE_EVENTFD_SUPPORT
@@ -1377,6 +1378,62 @@ static void record__thread_munmap_filtered(struct fdarray *fda, int fd,
perf_mmap__put(map);
}
+static void *record__thread(void *arg)
+{
+ enum thread_msg msg = THREAD_MSG__READY;
+ bool terminate = false;
+ struct fdarray *pollfd;
+ int err, ctlfd_pos;
+
+ thread = arg;
+ thread->tid = syscall(SYS_gettid);
+
+ err = write(thread->comm.ack[1], &msg, sizeof(msg));
+ if (err == -1)
+ pr_err("threads: %d failed to notify on start. Error %m", thread->tid);
+
+ pollfd = &(thread->pollfd);
+ ctlfd_pos = thread->ctlfd_pos;
+
+ for (;;) {
+ unsigned long long hits = thread->samples;
+
+ if (record__mmap_read_all(thread->rec, false) < 0 || terminate)
+ break;
+
+ if (hits == thread->samples) {
+
+ err = fdarray__poll(pollfd, -1);
+ /*
+ * Propagate error, only if there's any. Ignore positive
+ * number of returned events and interrupt error.
+ */
+ if (err > 0 || (err < 0 && errno == EINTR))
+ err = 0;
+ thread->waking++;
+
+ if (fdarray__filter(pollfd, POLLERR | POLLHUP,
+ record__thread_munmap_filtered, NULL) == 0)
+ break;
+ }
+
+ if (pollfd->entries[ctlfd_pos].revents & POLLHUP) {
+ terminate = true;
+ close(thread->comm.msg[0]);
+ pollfd->entries[ctlfd_pos].fd = -1;
+ pollfd->entries[ctlfd_pos].events = 0;
+ }
+
+ pollfd->entries[ctlfd_pos].revents = 0;
+ }
+
+ err = write(thread->comm.ack[1], &msg, sizeof(msg));
+ if (err == -1)
+ pr_err("threads: %d failed to notify on termination. Error %m", thread->tid);
+
+ return NULL;
+}
+
static void record__init_features(struct record *rec)
{
struct perf_session *session = rec->session;
@@ -1823,6 +1880,58 @@ static int record__terminate_thread(struct thread_data *thread_data)
return 0;
}
+static int record__start_threads(struct record *rec)
+{
+ int i, j, ret = 0;
+ sigset_t full, mask;
+ pthread_t handle;
+ pthread_attr_t attrs;
+ int nr_thread_data = rec->nr_thread_data;
+ struct thread_data *thread_data = rec->thread_data;
+
+ if (!record__threads_enabled(rec))
+ return 0;
+
+ sigfillset(&full);
+ if (sigprocmask(SIG_SETMASK, &full, &mask)) {
+ pr_err("Failed to block signals on threads start. Error: %m\n");
+ return -1;
+ }
+
+ pthread_attr_init(&attrs);
+ pthread_attr_setdetachstate(&attrs, PTHREAD_CREATE_DETACHED);
+
+ for (i = 1; i < nr_thread_data; i++) {
+ int res = 0;
+ enum thread_msg msg = THREAD_MSG__UNSUPPORTED;
+
+ if (pthread_create(&handle, &attrs, record__thread, &thread_data[i])) {
+ for (j = 1; j < i; j++)
+ record__terminate_thread(&thread_data[i]);
+ pr_err("Failed to start threads. Error: %m\n");
+ ret = -1;
+ goto out_err;
+ }
+
+ res = read(thread_data[i].comm.ack[0], &msg, sizeof(msg));
+ if (res > 0)
+ pr_debug("threads: %d -> %s\n", rec->thread_data[i].tid,
+ thread_msg_tags[msg]);
+ }
+
+ thread = &thread_data[0];
+ thread->tid = syscall(SYS_gettid);
+ pr_debug("threads: %d -> %s\n", thread->tid, thread_msg_tags[THREAD_MSG__READY]);
+
+out_err:
+ if (sigprocmask(SIG_SETMASK, &mask, NULL)) {
+ pr_err("Failed to unblock signals on threads start. Error: %m\n");
+ ret = -1;
+ }
+
+ return ret;
+}
+
static int record__stop_threads(struct record *rec, unsigned long *waking)
{
int i, j, nr_thread_data = rec->nr_thread_data;
@@ -1965,7 +2074,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
err = record__kcore_copy(&session->machines.host, data);
if (err) {
pr_err("ERROR: Failed to copy kcore\n");
- goto out_child;
+ goto out_free_threads;
}
}
@@ -1976,7 +2085,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
bpf__strerror_apply_obj_config(err, errbuf, sizeof(errbuf));
pr_err("ERROR: Apply config to BPF failed: %s\n",
errbuf);
- goto out_child;
+ goto out_free_threads;
}
/*
@@ -1994,11 +2103,11 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
if (data->is_pipe) {
err = perf_header__write_pipe(fd);
if (err < 0)
- goto out_child;
+ goto out_free_threads;
} else {
err = perf_session__write_header(session, rec->evlist, fd, false);
if (err < 0)
- goto out_child;
+ goto out_free_threads;
}
err = -1;
@@ -2006,16 +2115,16 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
&& !perf_header__has_feat(&session->header, HEADER_BUILD_ID)) {
pr_err("Couldn't generate buildids. "
"Use --no-buildid to profile anyway.\n");
- goto out_child;
+ goto out_free_threads;
}
err = record__setup_sb_evlist(rec);
if (err)
- goto out_child;
+ goto out_free_threads;
err = record__synthesize(rec, false);
if (err < 0)
- goto out_child;
+ goto out_free_threads;
if (rec->realtime_prio) {
struct sched_param param;
@@ -2024,10 +2133,13 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
if (sched_setscheduler(0, SCHED_FIFO, ¶m)) {
pr_err("Could not set realtime priority.\n");
err = -1;
- goto out_child;
+ goto out_free_threads;
}
}
+ if (record__start_threads(rec))
+ goto out_free_threads;
+
/*
* When perf is starting the traced process, all the events
* (apart from group members) have enable_on_exec=1 set,
--
2.24.1