[PATCH v6 02/10] perf record: implement -f,--mmap-flush=<threshold> option

From: Alexey Budankov
Date: Tue Mar 05 2019 - 04:24:32 EST



Implemented -f,--mmap-flush option that specifies minimal size of data
chunk that is extracted from mmaped kernel buffer to store into a trace.

$ tools/perf/perf record -f 1024 -e cycles -- matrix.gcc
$ tools/perf/perf record --aio -f 1024 -e cycles -- matrix.gcc

Option can serve two purposes the first one is to increase the compression
ratio of a trace data and the second one is to avoid live-lock-like self
monitoring in system wide (-a) profiling mode.

The default option value is 1 byte what means that every time trace
writing thread finds some new data in the mmaped buffer the data is
extracted, possibly compressed and written to a trace. Larger data chunks
are compressed more effectively in comparison to smaller chunks so
extraction of larger chunks from the kernel buffer is preferable from
perspective of trace size reduction. So the implemented option allows
specifying minimal data chunk size that is more than 1 byte to influence
data compression ratio. Also at some cases executing more write syscalls
with smaller data size can take longer than executing less write syscalls
with bigger data size due to syscall overhead so extracting bigger data
chunks specified by the option value could additionally decrease runtime
overhead.

Profiling in system wide mode with compression (-a -z) can additionally
induce data into the kernel buffers along with the data from monitored
processes. If performance data rate and volume from the monitored processes
is high then trace streaming and compression activity in the tool is also
high and it can lead to subtle live-lock effect of endless activity when
compression of single new byte from some of mmaped kernel buffer leads to
generation of the next single byte at some mmaped buffer so perf tool trace
writing thread never stops on polling event file descriptors.

Implemented sync parameter is the mean to force data move independently
from the threshold value. Despite the provided flush value from the command
line, the tool needs capability to unconditionally drain memory buffers,
at least in the end of the collection.

Signed-off-by: Alexey Budankov <alexey.budankov@xxxxxxxxxxxxxxx>
---
tools/perf/Documentation/perf-record.txt | 13 ++++++
tools/perf/builtin-record.c | 53 +++++++++++++++++++++---
tools/perf/perf.h | 1 +
tools/perf/util/evlist.c | 6 +--
tools/perf/util/evlist.h | 3 +-
tools/perf/util/mmap.c | 4 +-
tools/perf/util/mmap.h | 3 +-
7 files changed, 71 insertions(+), 12 deletions(-)

diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 8f0c2be34848..5f9b557afb28 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -459,6 +459,19 @@ Set affinity mask of trace reading thread according to the policy defined by 'mo
node - thread affinity mask is set to NUMA node cpu mask of the processed mmap buffer
cpu - thread affinity mask is set to cpu of the processed mmap buffer

+-f::
+--mmap-flush=n::
+Specify minimal number of bytes that is extracted from mmap data pages and stored
+into a trace. Maximal allowed value is a quarter of the size of mmaped data pages.
+The default option value is 1 what means that every time trace writing thread finds
+some new data in the mmaped buffer the data is extracted, possibly compressed (-z)
+and written to a trace. Larger data chunks are compressed more effectively in
+comparison to smaller chunks so extraction of larger chunks from the mmap data pages
+is preferable from perspective of trace size reduction. Also at some cases
+executing less trace write syscalls with bigger data size can take shorter than
+executing more trace write syscalls with smaller data size thus lowering runtime
+profiling overhead.
+
--all-kernel::
Configure all used events to run in kernel space.

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index f3f7f3100336..9b02a68e8c23 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -334,6 +334,29 @@ static int record__aio_enabled(struct record *rec)
return rec->opts.nr_cblocks > 0;
}

+#define MMAP_FLUSH_DEFAULT 1
+static int record__mmap_flush_parse(const struct option *opt,
+ const char *str,
+ int unset)
+{
+ int mmap_len;
+ struct record_opts *opts = (struct record_opts *)opt->value;
+
+ if (unset)
+ return 0;
+
+ if (str)
+ opts->mmap_flush = strtol(str, NULL, 0);
+ if (!opts->mmap_flush)
+ opts->mmap_flush = MMAP_FLUSH_DEFAULT;
+
+ mmap_len = perf_evlist__mmap_size(opts->mmap_pages);
+ if (opts->mmap_flush > mmap_len / 4)
+ opts->mmap_flush = mmap_len / 4;
+
+ return 0;
+}
+
static int process_synthesized_event(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample __maybe_unused,
@@ -543,7 +566,8 @@ static int record__mmap_evlist(struct record *rec,
if (perf_evlist__mmap_ex(evlist, opts->mmap_pages,
opts->auxtrace_mmap_pages,
opts->auxtrace_snapshot_mode,
- opts->nr_cblocks, opts->affinity) < 0) {
+ opts->nr_cblocks, opts->affinity,
+ opts->mmap_flush) < 0) {
if (errno == EPERM) {
pr_err("Permission error mapping pages.\n"
"Consider increasing "
@@ -733,7 +757,7 @@ static void record__adjust_affinity(struct record *rec, struct perf_mmap *map)
}

static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evlist,
- bool overwrite)
+ bool overwrite, bool sync)
{
u64 bytes_written = rec->bytes_written;
int i;
@@ -756,12 +780,19 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli
off = record__aio_get_pos(trace_fd);

for (i = 0; i < evlist->nr_mmaps; i++) {
+ u64 flush = MMAP_FLUSH_DEFAULT;
struct perf_mmap *map = &maps[i];

if (map->base) {
record__adjust_affinity(rec, map);
+ if (sync) {
+ flush = map->flush;
+ map->flush = MMAP_FLUSH_DEFAULT;
+ }
if (!record__aio_enabled(rec)) {
if (perf_mmap__push(map, rec, record__pushfn) != 0) {
+ if (sync)
+ map->flush = flush;
rc = -1;
goto out;
}
@@ -774,10 +805,14 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli
idx = record__aio_sync(map, false);
if (perf_mmap__aio_push(map, rec, idx, record__aio_pushfn, &off) != 0) {
record__aio_set_pos(trace_fd, off);
+ if (sync)
+ map->flush = flush;
rc = -1;
goto out;
}
}
+ if (sync)
+ map->flush = flush;
}

if (map->auxtrace_mmap.base && !rec->opts.auxtrace_snapshot_mode &&
@@ -803,15 +838,15 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli
return rc;
}

-static int record__mmap_read_all(struct record *rec)
+static int record__mmap_read_all(struct record *rec, bool sync)
{
int err;

- err = record__mmap_read_evlist(rec, rec->evlist, false);
+ err = record__mmap_read_evlist(rec, rec->evlist, false, sync);
if (err)
return err;

- return record__mmap_read_evlist(rec, rec->evlist, true);
+ return record__mmap_read_evlist(rec, rec->evlist, true, sync);
}

static void record__init_features(struct record *rec)
@@ -1310,7 +1345,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
if (trigger_is_hit(&switch_output_trigger) || done || draining)
perf_evlist__toggle_bkw_mmap(rec->evlist, BKW_MMAP_DATA_PENDING);

- if (record__mmap_read_all(rec) < 0) {
+ if (record__mmap_read_all(rec, false) < 0) {
trigger_error(&auxtrace_snapshot_trigger);
trigger_error(&switch_output_trigger);
err = -1;
@@ -1411,6 +1446,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
record__synthesize_workload(rec, true);

out_child:
+ record__mmap_read_all(rec, true);
record__aio_mmap_read_sync(rec);

if (forks) {
@@ -1813,6 +1849,7 @@ static struct record record = {
.uses_mmap = true,
.default_per_cpu = true,
},
+ .mmap_flush = MMAP_FLUSH_DEFAULT,
},
.tool = {
.sample = process_sample_event,
@@ -1879,6 +1916,9 @@ static struct option __record_options[] = {
OPT_CALLBACK('m', "mmap-pages", &record.opts, "pages[,pages]",
"number of mmap data pages and AUX area tracing mmap pages",
record__parse_mmap_pages),
+ OPT_CALLBACK('f', "mmap-flush", &record.opts, "bytes",
+ "Minimal number of bytes that is extracted from mmap data pages (default: 1)",
+ record__mmap_flush_parse),
OPT_BOOLEAN(0, "group", &record.opts.group,
"put the counters into a counter group"),
OPT_CALLBACK_NOOPT('g', NULL, &callchain_param,
@@ -2182,6 +2222,7 @@ int cmd_record(int argc, const char **argv)
pr_info("nr_cblocks: %d\n", rec->opts.nr_cblocks);

pr_debug("affinity: %s\n", affinity_tags[rec->opts.affinity]);
+ pr_debug("mmap flush: %d\n", rec->opts.mmap_flush);

err = __cmd_record(&record, argc, argv);
out:
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index b120e547ddc7..7886cc9771cf 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -85,6 +85,7 @@ struct record_opts {
u64 clockid_res_ns;
int nr_cblocks;
int affinity;
+ int mmap_flush;
};

enum perf_affinity {
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 08cedb643ea6..937039faac59 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1022,7 +1022,7 @@ int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
*/
int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
unsigned int auxtrace_pages,
- bool auxtrace_overwrite, int nr_cblocks, int affinity)
+ bool auxtrace_overwrite, int nr_cblocks, int affinity, int flush)
{
struct perf_evsel *evsel;
const struct cpu_map *cpus = evlist->cpus;
@@ -1032,7 +1032,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
* Its value is decided by evsel's write_backward.
* So &mp should not be passed through const pointer.
*/
- struct mmap_params mp = { .nr_cblocks = nr_cblocks, .affinity = affinity };
+ struct mmap_params mp = { .nr_cblocks = nr_cblocks, .affinity = affinity, .flush = flush };

if (!evlist->mmap)
evlist->mmap = perf_evlist__alloc_mmap(evlist, false);
@@ -1064,7 +1064,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,

int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages)
{
- return perf_evlist__mmap_ex(evlist, pages, 0, false, 0, PERF_AFFINITY_SYS);
+ return perf_evlist__mmap_ex(evlist, pages, 0, false, 0, PERF_AFFINITY_SYS, 1);
}

int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 744906dd4887..edf18811e39f 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -165,7 +165,8 @@ unsigned long perf_event_mlock_kb_in_pages(void);

int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
unsigned int auxtrace_pages,
- bool auxtrace_overwrite, int nr_cblocks, int affinity);
+ bool auxtrace_overwrite, int nr_cblocks,
+ int affinity, int flush);
int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages);
void perf_evlist__munmap(struct perf_evlist *evlist);

diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index cdc7740fc181..ef3d79b2c90b 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -440,6 +440,8 @@ int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd, int c

perf_mmap__setup_affinity_mask(map, mp);

+ map->flush = mp->flush;
+
if (auxtrace_mmap__mmap(&map->auxtrace_mmap,
&mp->auxtrace_mp, map->base, fd))
return -1;
@@ -492,7 +494,7 @@ static int __perf_mmap__read_init(struct perf_mmap *md)
md->start = md->overwrite ? head : old;
md->end = md->overwrite ? old : head;

- if (md->start == md->end)
+ if ((md->end - md->start) < md->flush)
return -EAGAIN;

size = md->end - md->start;
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index e566c19b242b..b82f8c2d55c4 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -39,6 +39,7 @@ struct perf_mmap {
} aio;
#endif
cpu_set_t affinity_mask;
+ u64 flush;
};

/*
@@ -70,7 +71,7 @@ enum bkw_mmap_state {
};

struct mmap_params {
- int prot, mask, nr_cblocks, affinity;
+ int prot, mask, nr_cblocks, affinity, flush;
struct auxtrace_mmap_params auxtrace_mp;
};

--
2.20.1