[PATCH v9 5/8] perf record: Toggle overwrite ring buffer for reading

From: Wang Nan
Date: Wed Jun 22 2016 - 05:11:57 EST


overwrite_evt_state is introduced to reflect the state of overwritable
ring buffers. It is a state machine with 3 states:

RUNNING --(1)--> DATA_PENDING --(2)--> EMPTY
^ ^ |
| |___(disallow)___/|
| |
\_________________(3)______________/

RUNNING : Overwritable ring buffers are recording
DATA_PENDING : We are required to collect overwritable ring buffers
EMPTY : We have collected data from those ring buffers.

(1): Pause ring buffers for reading
(2): Read from ring buffers
(3): Resume ring buffers for recording

We can't avoid this complexity. Since we deliberately drop records from
overwritable ring buffer, there's no mean for us to check remaining from
ring buffer itself (by checking head and old pointers). Therefore, we
need DATA_PENDING and EMPTY state to help us recording what we have done
to the ring buffer.

Signed-off-by: Wang Nan <wangnan0@xxxxxxxxxx>
Signed-off-by: He Kuang <hekuang@xxxxxxxxxx>
Cc: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Masami Hiramatsu <mhiramat@xxxxxxxxxx>
Cc: Namhyung Kim <namhyung@xxxxxxxxxx>
Cc: Zefan Li <lizefan@xxxxxxxxxx>
Cc: pi3orama@xxxxxxx
---
tools/perf/builtin-record.c | 146 +++++++++++++++++++++++++++++++++++++++++---
1 file changed, 136 insertions(+), 10 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 4a77bf3..019151a 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -42,6 +42,28 @@
#include <sys/mman.h>
#include <asm/bug.h>

+/*
+ * State machine of overwrite_evt_state:
+ *
+ * RUNNING --(1)--> DATA_PENDING --(2)--> EMPTY
+ * ^ ^ |
+ * | |___(disallow)___/|
+ * | |
+ * \_________________(3)______________/
+ *
+ * RUNNING : Overwritable ring buffers are recording
+ * DATA_PENDING : We are required to collect overwritable ring buffers
+ * EMPTY : We have collected data from those ring buffers.
+ *
+ * (1): Pause ring buffers for reading
+ * (2): Read from ring buffers
+ * (3): Resume ring buffers for recording
+ */
+enum overwrite_evt_state {
+ OVERWRITE_EVT_RUNNING,
+ OVERWRITE_EVT_DATA_PENDING,
+ OVERWRITE_EVT_EMPTY,
+};

struct record {
struct perf_tool tool;
@@ -61,6 +83,7 @@ struct record {
bool buildid_all;
bool timestamp_filename;
bool switch_output;
+ enum overwrite_evt_state overwrite_evt_state;
unsigned long long samples;
};

@@ -132,9 +155,9 @@ rb_find_range(struct perf_evlist *evlist,
return backward_rb_find_range(data, mask, head, start, end);
}

-static int record__mmap_read(struct record *rec, int idx)
+static int record__mmap_read(struct record *rec, struct perf_evlist *evlist, int idx)
{
- struct perf_mmap *md = &rec->evlist->mmap[idx];
+ struct perf_mmap *md = &evlist->mmap[idx];
u64 head = perf_mmap__read_head(md);
u64 old = md->prev;
u64 end = head, start = old;
@@ -143,7 +166,7 @@ static int record__mmap_read(struct record *rec, int idx)
void *buf;
int rc = 0;

- if (rb_find_range(rec->evlist, data, md->mask, head,
+ if (rb_find_range(evlist, data, md->mask, head,
old, &start, &end))
return -1;

@@ -157,7 +180,7 @@ static int record__mmap_read(struct record *rec, int idx)
WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n");

md->prev = head;
- perf_evlist__mmap_consume(rec->evlist, idx);
+ perf_evlist__mmap_consume(evlist, idx);
return 0;
}

@@ -182,7 +205,7 @@ static int record__mmap_read(struct record *rec, int idx)
}

md->prev = head;
- perf_evlist__mmap_consume(rec->evlist, idx);
+ perf_evlist__mmap_consume(evlist, idx);
out:
return rc;
}
@@ -469,6 +492,7 @@ try_again:

session->evlist = evlist;
perf_session__set_id_hdr_size(session);
+ rec->overwrite_evt_state = OVERWRITE_EVT_RUNNING;
out:
return rc;
}
@@ -549,17 +573,72 @@ static struct perf_event_header finished_round_event = {
.type = PERF_RECORD_FINISHED_ROUND,
};

-static int record__mmap_read_all(struct record *rec)
+static void
+record__toggle_overwrite_evsels(struct record *rec,
+ enum overwrite_evt_state state)
+{
+ struct perf_evlist *evlist = rec->overwrite_evlist;
+ enum overwrite_evt_state old_state = rec->overwrite_evt_state;
+ enum action {
+ NONE,
+ PAUSE,
+ RESUME,
+ } action = NONE;
+
+ switch (old_state) {
+ case OVERWRITE_EVT_RUNNING:
+ if (state != OVERWRITE_EVT_RUNNING)
+ action = PAUSE;
+ break;
+ case OVERWRITE_EVT_DATA_PENDING:
+ if (state == OVERWRITE_EVT_RUNNING)
+ action = RESUME;
+ break;
+ case OVERWRITE_EVT_EMPTY:
+ if (state == OVERWRITE_EVT_RUNNING)
+ action = RESUME;
+ if (state == OVERWRITE_EVT_DATA_PENDING)
+ state = OVERWRITE_EVT_EMPTY;
+ break;
+ default:
+ WARN_ONCE(1, "Shouldn't get there\n");
+ }
+
+ rec->overwrite_evt_state = state;
+
+ if (action == NONE)
+ return;
+
+ if (!evlist)
+ return;
+
+ switch (action) {
+ case PAUSE:
+ perf_evlist__pause(evlist);
+ break;
+ case RESUME:
+ perf_evlist__resume(evlist);
+ break;
+ case NONE:
+ default:
+ break;
+ }
+}
+
+static int __record__mmap_read_evlist(struct record *rec, struct perf_evlist *evlist)
{
u64 bytes_written = rec->bytes_written;
int i;
int rc = 0;

- for (i = 0; i < rec->evlist->nr_mmaps; i++) {
- struct auxtrace_mmap *mm = &rec->evlist->mmap[i].auxtrace_mmap;
+ if (!evlist)
+ return 0;
+
+ for (i = 0; i < evlist->nr_mmaps; i++) {
+ struct auxtrace_mmap *mm = &evlist->mmap[i].auxtrace_mmap;

- if (rec->evlist->mmap[i].base) {
- if (record__mmap_read(rec, i) != 0) {
+ if (evlist->mmap[i].base) {
+ if (record__mmap_read(rec, evlist, i) != 0) {
rc = -1;
goto out;
}
@@ -583,6 +662,23 @@ out:
return rc;
}

+static int record__mmap_read_all(struct record *rec)
+{
+ int err;
+
+ err = __record__mmap_read_evlist(rec, rec->evlist);
+ if (err)
+ return err;
+
+ if (rec->overwrite_evt_state == OVERWRITE_EVT_DATA_PENDING) {
+ err = __record__mmap_read_evlist(rec, rec->overwrite_evlist);
+ if (err)
+ return err;
+ record__toggle_overwrite_evsels(rec, OVERWRITE_EVT_EMPTY);
+ }
+ return 0;
+}
+
static void record__init_features(struct record *rec)
{
struct perf_session *session = rec->session;
@@ -979,6 +1075,17 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
for (;;) {
unsigned long long hits = rec->samples;

+ /*
+ * rec->overwrite_evt_state is possible to be
+ * OVERWRITE_EVT_EMPTY here: when done == true and
+ * hits != rec->samples after previous reading.
+ *
+ * record__toggle_overwrite_evsels ensure we never
+ * convert OVERWRITE_EVT_EMPTY to OVERWRITE_EVT_DATA_PENDING.
+ */
+ if (trigger_is_hit(&switch_output_trigger) || done || draining)
+ record__toggle_overwrite_evsels(rec, OVERWRITE_EVT_DATA_PENDING);
+
if (record__mmap_read_all(rec) < 0) {
trigger_error(&auxtrace_snapshot_trigger);
trigger_error(&switch_output_trigger);
@@ -998,8 +1105,27 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
}

if (trigger_is_hit(&switch_output_trigger)) {
+ /*
+ * If switch_output_trigger is hit, the data in
+ * overwritable ring buffer should have been collected,
+ * so overwrite_evt_state should be set to
+ * OVERWRITE_EVT_EMPTY.
+ *
+ * If SIGUSR2 raise after or during record__mmap_read_all(),
+ * record__mmap_read_all() didn't collect data from
+ * overwritable ring buffer. Read again.
+ */
+ if (rec->overwrite_evt_state == OVERWRITE_EVT_RUNNING)
+ continue;
trigger_ready(&switch_output_trigger);

+ /*
+ * Reenable events in overwrite ring buffer after
+ * record__mmap_read_all(): we should have collected
+ * data from it.
+ */
+ record__toggle_overwrite_evsels(rec, OVERWRITE_EVT_RUNNING);
+
if (!quiet)
fprintf(stderr, "[ perf record: dump data: Woken up %ld times ]\n",
waking);
--
1.8.3.4