Re: [PATCH v3 0/4] Reduce NUMA related overhead in perf record profiling on large server systems

From: Alexey Budankov
Date: Wed Jan 09 2019 - 11:11:28 EST

Hi,

On 09.01.2019 17:41, Jiri Olsa wrote:
> On Wed, Jan 09, 2019 at 12:19:20PM +0300, Alexey Budankov wrote:
>>
<SNIP>
>> It has been observed that trace reading thread run>> The patch set is generated for acme perf/core repository.
>>
>> ---
>> Alexey Budankov (4):
>> perf record: allocate affinity masks
>> perf record: bind the AIO user space buffers to nodes
>> perf record: apply affinity masks when reading mmap buffers
>> perf record: implement --affinity=node|cpu option
>
>
> hi,
> can't apply your code on latest Arnaldo's perf/core:
>
> Applying: perf record: allocate affinity masks
> Applying: perf record: bind the AIO user space buffers to nodes
> Applying: perf record: apply affinity masks when reading mmap buffers
> Applying: perf record: implement --affinity=node|cpu option
> error: corrupt patch at line 62
> Patch failed at 0004 perf record: implement --affinity=node|cpu option
> Use 'git am --show-current-patch' to see the failed patch
> When you have resolved this problem, run "git am --continue".
> If you prefer to skip this patch, run "git am --skip" instead.
> To restore the original branch and stop patching, run "git am --abort".

Sorry about that.
Patch set update and resend is in progress.
The whole change on top of Arnaldo's perf/core tip follows for your convenience.

Thanks!
Alexey

---
tools/perf/Documentation/perf-record.txt | 5 ++
tools/perf/builtin-record.c | 47 ++++++++++++++++-
tools/perf/perf.h | 8 +++
tools/perf/util/evlist.c | 10 ++--
tools/perf/util/evlist.h | 2 +-
tools/perf/util/mmap.c | 91 ++++++++++++++++++++++++++++++--
tools/perf/util/mmap.h | 4 +-
7 files changed, 157 insertions(+), 10 deletions(-)

diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index d232b13ea713..efb839784f32 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -440,6 +440,11 @@ Use <n> control blocks in asynchronous (Posix AIO) trace writing mode (default:
Asynchronous mode is supported only when linking Perf tool with libc library
providing implementation for Posix AIO API.

+--affinity=mode::
+Set affinity mask of trace reading thread according to the policy defined by 'mode' value:
+ 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
+
--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 882285fb9f64..94a966ba9a6f 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -81,12 +81,17 @@ struct record {
bool timestamp_boundary;
struct switch_output switch_output;
unsigned long long samples;
+ cpu_set_t affinity_mask;
};

static volatile int auxtrace_record__snapshot_started;
static DEFINE_TRIGGER(auxtrace_snapshot_trigger);
static DEFINE_TRIGGER(switch_output_trigger);

+static const char *affinity_tags[PERF_AFFINITY_MAX] = {
+ "SYS", "NODE", "CPU"
+};
+
static bool switch_output_signal(struct record *rec)
{
return rec->switch_output.signal &&
@@ -531,9 +536,13 @@ static int record__mmap_evlist(struct record *rec,
struct record_opts *opts = &rec->opts;
char msg[512];

+ if (opts->affinity != PERF_AFFINITY_SYS)
+ cpu__setup_cpunode_map();
+
if (perf_evlist__mmap_ex(evlist, opts->mmap_pages,
opts->auxtrace_mmap_pages,
- opts->auxtrace_snapshot_mode, opts->nr_cblocks) < 0) {
+ opts->auxtrace_snapshot_mode,
+ opts->nr_cblocks, opts->affinity) < 0) {
if (errno == EPERM) {
pr_err("Permission error mapping pages.\n"
"Consider increasing "
@@ -722,6 +731,16 @@ static struct perf_event_header finished_round_event = {
.type = PERF_RECORD_FINISHED_ROUND,
};

+static void record__adjust_affinity(struct record *rec, struct perf_mmap *map)
+{
+ if (rec->opts.affinity != PERF_AFFINITY_SYS &&
+ !CPU_EQUAL(&rec->affinity_mask, &map->affinity_mask)) {
+ CPU_ZERO(&rec->affinity_mask);
+ CPU_OR(&rec->affinity_mask, &rec->affinity_mask, &map->affinity_mask);
+ sched_setaffinity(0, sizeof(rec->affinity_mask), &rec->affinity_mask);
+ }
+}
+
static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evlist,
bool overwrite)
{
@@ -749,6 +768,7 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli
struct perf_mmap *map = &maps[i];

if (map->base) {
+ record__adjust_affinity(rec, map);
if (!record__aio_enabled(rec)) {
if (perf_mmap__push(map, rec, record__pushfn) != 0) {
rc = -1;
@@ -1639,6 +1659,23 @@ static int parse_clockid(const struct option *opt, const char *str, int unset)
return -1;
}

+static int record__parse_affinity(const struct option *opt, const char *str, int unset)
+{
+ struct record_opts *opts = (struct record_opts *)opt->value;
+
+ if (unset)
+ return 0;
+
+ if (str) {
+ if (!strcasecmp(str, "node"))
+ opts->affinity = PERF_AFFINITY_NODE;
+ else if (!strcasecmp(str, "cpu"))
+ opts->affinity = PERF_AFFINITY_CPU;
+ }
+
+ return 0;
+}
+
static int record__parse_mmap_pages(const struct option *opt,
const char *str,
int unset __maybe_unused)
@@ -1946,6 +1983,9 @@ static struct option __record_options[] = {
&nr_cblocks_default, "n", "Use <n> control blocks in asynchronous trace writing mode (default: 1, max: 4)",
record__aio_parse),
#endif
+ OPT_CALLBACK(0, "affinity", &record.opts, "node|cpu",
+ "Set affinity mask of trace reading thread to NUMA node cpu mask or cpu of processed mmap buffer",
+ record__parse_affinity),
OPT_END()
};

@@ -1980,6 +2020,9 @@ int cmd_record(int argc, const char **argv)
# undef REASON
#endif

+ CPU_ZERO(&rec->affinity_mask);
+ rec->opts.affinity = PERF_AFFINITY_SYS;
+
rec->evlist = perf_evlist__new();
if (rec->evlist == NULL)
return -ENOMEM;
@@ -2143,6 +2186,8 @@ int cmd_record(int argc, const char **argv)
if (verbose > 0)
pr_info("nr_cblocks: %d\n", rec->opts.nr_cblocks);

+ pr_debug("affinity: %s\n", affinity_tags[rec->opts.affinity]);
+
err = __cmd_record(&record, argc, argv);
out:
perf_evlist__delete(rec->evlist);
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 388c6dd128b8..36d5cfe6362f 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -83,6 +83,14 @@ struct record_opts {
clockid_t clockid;
u64 clockid_res_ns;
int nr_cblocks;
+ int affinity;
+};
+
+enum perf_affinity {
+ PERF_AFFINITY_SYS = 0,
+ PERF_AFFINITY_NODE,
+ PERF_AFFINITY_CPU,
+ PERF_AFFINITY_MAX
};

struct option;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 8c902276d4b4..b6680f65ccc4 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)
+ bool auxtrace_overwrite, int nr_cblocks, int affinity)
{
struct perf_evsel *evsel;
const struct cpu_map *cpus = evlist->cpus;
@@ -1032,7 +1032,11 @@ 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 };
+ struct mmap_params mp = {
+ .nr_cblocks = nr_cblocks,
+ .affinity = affinity,
+ .cpu_map = cpus
+ };

if (!evlist->mmap)
evlist->mmap = perf_evlist__alloc_mmap(evlist, false);
@@ -1064,7 +1068,7 @@ 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);
+ return perf_evlist__mmap_ex(evlist, pages, 0, false, 0, PERF_AFFINITY_SYS);
}

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 868294491194..72728d7f4432 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -162,7 +162,7 @@ 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);
+ bool auxtrace_overwrite, int nr_cblocks, int affinity);
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 8fc39311a30d..ee0230eed635 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -10,6 +10,9 @@
#include <sys/mman.h>
#include <inttypes.h>
#include <asm/bug.h>
+#ifdef HAVE_LIBNUMA_SUPPORT
+#include <numaif.h>
+#endif
#include "debug.h"
#include "event.h"
#include "mmap.h"
@@ -154,9 +157,68 @@ void __weak auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp __mayb
}

#ifdef HAVE_AIO_SUPPORT
+
+#ifdef HAVE_LIBNUMA_SUPPORT
+static int perf_mmap__aio_alloc(struct perf_mmap *map, int index)
+{
+ map->aio.data[index] = mmap(NULL, perf_mmap__mmap_len(map), PROT_READ|PROT_WRITE,
+ MAP_PRIVATE|MAP_ANONYMOUS, 0, 0);
+ if (map->aio.data[index] == MAP_FAILED) {
+ map->aio.data[index] = NULL;
+ return -1;
+ }
+
+ return 0;
+}
+
+static void perf_mmap__aio_free(struct perf_mmap *map, int index)
+{
+ if (map->aio.data[index]) {
+ munmap(map->aio.data[index], perf_mmap__mmap_len(map));
+ map->aio.data[index] = NULL;
+ }
+}
+
+static void perf_mmap__aio_bind(struct perf_mmap *map, int index, int cpu, int affinity)
+{
+ void *data;
+ size_t mmap_len;
+ unsigned long node_mask;
+
+ if (affinity != PERF_AFFINITY_SYS && cpu__max_node() > 1) {
+ data = map->aio.data[index];
+ mmap_len = perf_mmap__mmap_len(map);
+ node_mask = 1UL << cpu__get_node(cpu);
+ if (mbind(data, mmap_len, MPOL_BIND, &node_mask, 1, 0)) {
+ pr_warn("failed to bind [%p-%p] to node %d\n",
+ data, data + mmap_len, cpu__get_node(cpu));
+ }
+ }
+}
+#else
+static int perf_mmap__aio_alloc(struct perf_mmap *map, int index)
+{
+ map->aio.data[index] = malloc(perf_mmap__mmap_len(map));
+ if (map->aio.data[index] == NULL)
+ return -1;
+
+ return 0;
+}
+
+static void perf_mmap__aio_free(struct perf_mmap *map, int index)
+{
+ zfree(&(map->aio.data[index]));
+}
+
+static void perf_mmap__aio_bind(struct perf_mmap *map __maybe_unused, int index __maybe_unused,
+ int cpu __maybe_unused, int affinity __maybe_unused)
+{
+}
+#endif
+
static int perf_mmap__aio_mmap(struct perf_mmap *map, struct mmap_params *mp)
{
- int delta_max, i, prio;
+ int delta_max, i, prio, ret;

map->aio.nr_cblocks = mp->nr_cblocks;
if (map->aio.nr_cblocks) {
@@ -177,11 +239,12 @@ static int perf_mmap__aio_mmap(struct perf_mmap *map, struct mmap_params *mp)
}
delta_max = sysconf(_SC_AIO_PRIO_DELTA_MAX);
for (i = 0; i < map->aio.nr_cblocks; ++i) {
- map->aio.data[i] = malloc(perf_mmap__mmap_len(map));
- if (!map->aio.data[i]) {
+ ret = perf_mmap__aio_alloc(map, i);
+ if (ret == -1) {
pr_debug2("failed to allocate data buffer area, error %m");
return -1;
}
+ perf_mmap__aio_bind(map, i, map->cpu, mp->affinity);
/*
* Use cblock.aio_fildes value different from -1
* to denote started aio write operation on the
@@ -210,7 +273,7 @@ static void perf_mmap__aio_munmap(struct perf_mmap *map)
int i;

for (i = 0; i < map->aio.nr_cblocks; ++i)
- zfree(&map->aio.data[i]);
+ perf_mmap__aio_free(map, i);
if (map->aio.data)
zfree(&map->aio.data);
zfree(&map->aio.cblocks);
@@ -314,6 +377,24 @@ void perf_mmap__munmap(struct perf_mmap *map)
auxtrace_mmap__munmap(&map->auxtrace_mmap);
}

+static void perf_mmap__setup_affinity_mask(struct perf_mmap *map, struct mmap_params *mp)
+{
+ int c, cpu, nr_cpus, node;
+
+ CPU_ZERO(&map->affinity_mask);
+ if (mp->affinity == PERF_AFFINITY_NODE && cpu__max_node() > 1) {
+ nr_cpus = cpu_map__nr(mp->cpu_map);
+ node = cpu__get_node(map->cpu);
+ for (c = 0; c < nr_cpus; c++) {
+ cpu = mp->cpu_map->map[c]; /* map c index to online cpu index */
+ if (cpu__get_node(cpu) == node)
+ CPU_SET(cpu, &map->affinity_mask);
+ }
+ } else if (mp->affinity == PERF_AFFINITY_CPU) {
+ CPU_SET(map->cpu, &map->affinity_mask);
+ }
+}
+
int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd, int cpu)
{
/*
@@ -343,6 +424,8 @@ int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd, int c
map->fd = fd;
map->cpu = cpu;

+ perf_mmap__setup_affinity_mask(map, mp);
+
if (auxtrace_mmap__mmap(&map->auxtrace_mmap,
&mp->auxtrace_mp, map->base, fd))
return -1;
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index aeb6942fdb00..b3f724fad22e 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -38,6 +38,7 @@ struct perf_mmap {
int nr_cblocks;
} aio;
#endif
+ cpu_set_t affinity_mask;
};

/*
@@ -69,8 +70,9 @@ enum bkw_mmap_state {
};

struct mmap_params {
- int prot, mask, nr_cblocks;
+ int prot, mask, nr_cblocks, affinity;
struct auxtrace_mmap_params auxtrace_mp;
+ const struct cpu_map *cpu_map;
};

int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd, int cpu);

>
> jirka
>