summaryrefslogtreecommitdiff
path: root/tools/perf/util/session.c
diff options
context:
space:
mode:
authorAlexey Bayduraev <alexey.v.bayduraev@linux.intel.com>2022-01-17 21:34:35 +0300
committerArnaldo Carvalho de Melo <acme@redhat.com>2022-02-10 16:27:28 -0300
commitbb6be405c4a2a509d1d1008e1bed42e7cab5a326 (patch)
tree0da3bcd058ca6b3b3658501f552479ec0257cdc1 /tools/perf/util/session.c
parentb5f2511d4b3976e352b47b79c3c119addb7c2033 (diff)
perf session: Load data directory files for analysis
Load data directory files and provide basic raw dump and aggregated analysis support of data directories in report mode, still with no memory consumption optimizations. READER_MAX_SIZE is chosen based on the results of measurements on different machines on perf.data directory sizes >1GB. On machines with big core count (192 cores) the difference between 1MB and 2MB is about 4%. Other sizes (>2MB) are quite equal to 2MB. On machines with small core count (4-24) there is no differences between 1-16 MB sizes. So this constant is 2MB. Suggested-by: Jiri Olsa <jolsa@kernel.org> Reviewed-by: Riccardo Mancini <rickyman7@gmail.com> Signed-off-by: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com> Tested-by: Jiri Olsa <jolsa@kernel.org> Tested-by: Riccardo Mancini <rickyman7@gmail.com> Acked-by: Namhyung Kim <namhyung@gmail.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Antonov <alexander.antonov@linux.intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexei Budankov <abudankov@huawei.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/3f10c13a226c0ceb53e88a082f847b91c1ae2c25.1642440724.git.alexey.v.bayduraev@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Diffstat (limited to 'tools/perf/util/session.c')
-rw-r--r--tools/perf/util/session.c133
1 files changed, 133 insertions, 0 deletions
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 498b05708db5..70577cd33cef 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -2186,6 +2186,8 @@ struct reader {
u64 file_pos;
u64 file_offset;
u64 head;
+ u64 size;
+ bool done;
struct zstd_data zstd_data;
struct decomp_data decomp_data;
};
@@ -2303,6 +2305,7 @@ reader__read_event(struct reader *rd, struct perf_session *session,
if (skip)
size += skip;
+ rd->size += size;
rd->head += size;
rd->file_pos += size;
@@ -2411,6 +2414,133 @@ out_err:
return err;
}
+/*
+ * Processing 2 MB of data from each reader in sequence,
+ * because that's the way the ordered events sorting works
+ * most efficiently.
+ */
+#define READER_MAX_SIZE (2 * 1024 * 1024)
+
+/*
+ * This function reads, merge and process directory data.
+ * It assumens the version 1 of directory data, where each
+ * data file holds per-cpu data, already sorted by kernel.
+ */
+static int __perf_session__process_dir_events(struct perf_session *session)
+{
+ struct perf_data *data = session->data;
+ struct perf_tool *tool = session->tool;
+ int i, ret, readers, nr_readers;
+ struct ui_progress prog;
+ u64 total_size = perf_data__size(session->data);
+ struct reader *rd;
+
+ perf_tool__fill_defaults(tool);
+
+ ui_progress__init_size(&prog, total_size, "Sorting events...");
+
+ nr_readers = 1;
+ for (i = 0; i < data->dir.nr; i++) {
+ if (data->dir.files[i].size)
+ nr_readers++;
+ }
+
+ rd = zalloc(nr_readers * sizeof(struct reader));
+ if (!rd)
+ return -ENOMEM;
+
+ rd[0] = (struct reader) {
+ .fd = perf_data__fd(session->data),
+ .data_size = session->header.data_size,
+ .data_offset = session->header.data_offset,
+ .process = process_simple,
+ .in_place_update = session->data->in_place_update,
+ };
+ ret = reader__init(&rd[0], NULL);
+ if (ret)
+ goto out_err;
+ ret = reader__mmap(&rd[0], session);
+ if (ret)
+ goto out_err;
+ readers = 1;
+
+ for (i = 0; i < data->dir.nr; i++) {
+ if (!data->dir.files[i].size)
+ continue;
+ rd[readers] = (struct reader) {
+ .fd = data->dir.files[i].fd,
+ .data_size = data->dir.files[i].size,
+ .data_offset = 0,
+ .process = process_simple,
+ .in_place_update = session->data->in_place_update,
+ };
+ ret = reader__init(&rd[readers], NULL);
+ if (ret)
+ goto out_err;
+ ret = reader__mmap(&rd[readers], session);
+ if (ret)
+ goto out_err;
+ readers++;
+ }
+
+ i = 0;
+ while (readers) {
+ if (session_done())
+ break;
+
+ if (rd[i].done) {
+ i = (i + 1) % nr_readers;
+ continue;
+ }
+ if (reader__eof(&rd[i])) {
+ rd[i].done = true;
+ readers--;
+ continue;
+ }
+
+ session->active_decomp = &rd[i].decomp_data;
+ ret = reader__read_event(&rd[i], session, &prog);
+ if (ret < 0) {
+ goto out_err;
+ } else if (ret == READER_NODATA) {
+ ret = reader__mmap(&rd[i], session);
+ if (ret)
+ goto out_err;
+ }
+
+ if (rd[i].size >= READER_MAX_SIZE) {
+ rd[i].size = 0;
+ i = (i + 1) % nr_readers;
+ }
+ }
+
+ ret = ordered_events__flush(&session->ordered_events, OE_FLUSH__FINAL);
+ if (ret)
+ goto out_err;
+
+ ret = perf_session__flush_thread_stacks(session);
+out_err:
+ ui_progress__finish();
+
+ if (!tool->no_warn)
+ perf_session__warn_about_errors(session);
+
+ /*
+ * We may switching perf.data output, make ordered_events
+ * reusable.
+ */
+ ordered_events__reinit(&session->ordered_events);
+
+ session->one_mmap = false;
+
+ session->active_decomp = &session->decomp_data;
+ for (i = 0; i < nr_readers; i++)
+ reader__release_decomp(&rd[i]);
+ zfree(&rd);
+
+ return ret;
+}
+
int perf_session__process_events(struct perf_session *session)
{
if (perf_session__register_idle_thread(session) < 0)
@@ -2419,6 +2549,9 @@ int perf_session__process_events(struct perf_session *session)
if (perf_data__is_pipe(session->data))
return __perf_session__process_pipe_events(session);
+ if (perf_data__is_dir(session->data))
+ return __perf_session__process_dir_events(session);
+
return __perf_session__process_events(session);
}