Re: [PATCH v2 1/4] perf record: allocate affinity masks
Hi,
On 02.01.2019 0:39, Jiri Olsa wrote:
> On Mon, Dec 24, 2018 at 03:23:13PM +0300, Alexey Budankov wrote:
>
> SNIP
>
>> @@ -2143,6 +2152,8 @@ 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(, argc, argv);
>> out:
>> perf_evlist__delete(rec->evlist);
>> diff --git a/tools/perf/perf.h b/tools/perf/perf.h
>> index 388c6dd128b8..69f54529d81f 100644
>> --- a/tools/perf/perf.h
>> +++ b/tools/perf/perf.h
>> @@ -83,6 +83,14 @@ struct record_opts {
>> clockid_tclockid;
>> u64 clockid_res_ns;
>> int nr_cblocks;
>> +int affinity;
>> +};
>> +
>> +enum perf_affinity {
>> +PERF_AFFINITY_SYS = 0,
>> +PERF_AFFINITY_NODE,
>> +PERF_AFFINITY_CPU,
>> +PERF_AFFINITY_EOF
>
> PERF_AFFINITY_MAX might be better name
Corrected in v3.
Thanks,
Alexey
>
> jirka
>
Re: [PATCH v2 1/4] perf record: allocate affinity masks
On Mon, Dec 24, 2018 at 03:23:13PM +0300, Alexey Budankov wrote:
SNIP
> @@ -2143,6 +2152,8 @@ 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(, argc, argv);
> out:
> perf_evlist__delete(rec->evlist);
> diff --git a/tools/perf/perf.h b/tools/perf/perf.h
> index 388c6dd128b8..69f54529d81f 100644
> --- a/tools/perf/perf.h
> +++ b/tools/perf/perf.h
> @@ -83,6 +83,14 @@ struct record_opts {
> clockid_tclockid;
> u64 clockid_res_ns;
> int nr_cblocks;
> + int affinity;
> +};
> +
> +enum perf_affinity {
> + PERF_AFFINITY_SYS = 0,
> + PERF_AFFINITY_NODE,
> + PERF_AFFINITY_CPU,
> + PERF_AFFINITY_EOF
PERF_AFFINITY_MAX might be better name
jirka
[PATCH v2 1/4] perf record: allocate affinity masks
Allocate affinity option and masks for mmap data buffers and
record thread as well as initialize allocated objects.
Signed-off-by: Alexey Budankov
---
Changes in v2:
- made debug affinity mode message user friendly
- converted affinity mode defines to enum values
---
tools/perf/builtin-record.c | 13 -
tools/perf/perf.h | 8
tools/perf/util/evlist.c| 6 +++---
tools/perf/util/evlist.h| 2 +-
tools/perf/util/mmap.c | 2 ++
tools/perf/util/mmap.h | 3 ++-
6 files changed, 28 insertions(+), 6 deletions(-)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 882285fb9f64..b26febb54d01 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -81,12 +81,17 @@ struct record {
booltimestamp_boundary;
struct switch_outputswitch_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_EOF] = {
+ "SYS", "NODE", "CPU"
+};
+
static bool switch_output_signal(struct record *rec)
{
return rec->switch_output.signal &&
@@ -533,7 +538,8 @@ 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) < 0) {
+opts->auxtrace_snapshot_mode,
+opts->nr_cblocks, opts->affinity) < 0) {
if (errno == EPERM) {
pr_err("Permission error mapping pages.\n"
"Consider increasing "
@@ -1980,6 +1986,9 @@ int cmd_record(int argc, const char **argv)
# undef REASON
#endif
+ CPU_ZERO(>affinity_mask);
+ rec->opts.affinity = PERF_AFFINITY_SYS;
+
rec->evlist = perf_evlist__new();
if (rec->evlist == NULL)
return -ENOMEM;
@@ -2143,6 +2152,8 @@ 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(, argc, argv);
out:
perf_evlist__delete(rec->evlist);
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 388c6dd128b8..69f54529d81f 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -83,6 +83,14 @@ struct record_opts {
clockid_tclockid;
u64 clockid_res_ns;
int nr_cblocks;
+ int affinity;
+};
+
+enum perf_affinity {
+ PERF_AFFINITY_SYS = 0,
+ PERF_AFFINITY_NODE,
+ PERF_AFFINITY_CPU,
+ PERF_AFFINITY_EOF
};
struct option;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index e90575192209..60e825be944a 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1018,7 +1018,7 @@ 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;
@@ -1028,7 +1028,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist,
unsigned int pages,
* Its value is decided by evsel's write_backward.
* So 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 };
if (!evlist->mmap)
evlist->mmap = perf_evlist__alloc_mmap(evlist, false);
@@ -1060,7 +1060,7 @@ 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
[PATCH v2 1/4] perf record: allocate affinity masks
Allocate affinity option and masks for mmap data buffers and
record thread as well as initialize allocated objects.
Signed-off-by: Alexey Budankov
---
Changes in v2:
- made debug affinity mode message user friendly
- converted affinity mode defines to enum values
---
tools/perf/builtin-record.c | 13 -
tools/perf/perf.h | 8
tools/perf/util/evlist.c| 6 +++---
tools/perf/util/evlist.h| 2 +-
tools/perf/util/mmap.c | 2 ++
tools/perf/util/mmap.h | 3 ++-
6 files changed, 28 insertions(+), 6 deletions(-)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 882285fb9f64..b26febb54d01 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -81,12 +81,17 @@ struct record {
booltimestamp_boundary;
struct switch_outputswitch_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_EOF] = {
+ "SYS", "NODE", "CPU"
+};
+
static bool switch_output_signal(struct record *rec)
{
return rec->switch_output.signal &&
@@ -533,7 +538,8 @@ 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) < 0) {
+opts->auxtrace_snapshot_mode,
+opts->nr_cblocks, opts->affinity) < 0) {
if (errno == EPERM) {
pr_err("Permission error mapping pages.\n"
"Consider increasing "
@@ -1980,6 +1986,9 @@ int cmd_record(int argc, const char **argv)
# undef REASON
#endif
+ CPU_ZERO(>affinity_mask);
+ rec->opts.affinity = PERF_AFFINITY_SYS;
+
rec->evlist = perf_evlist__new();
if (rec->evlist == NULL)
return -ENOMEM;
@@ -2143,6 +2152,8 @@ 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(, argc, argv);
out:
perf_evlist__delete(rec->evlist);
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 388c6dd128b8..69f54529d81f 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -83,6 +83,14 @@ struct record_opts {
clockid_tclockid;
u64 clockid_res_ns;
int nr_cblocks;
+ int affinity;
+};
+
+enum perf_affinity {
+ PERF_AFFINITY_SYS = 0,
+ PERF_AFFINITY_NODE,
+ PERF_AFFINITY_CPU,
+ PERF_AFFINITY_EOF
};
struct option;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index e90575192209..60e825be944a 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1018,7 +1018,7 @@ 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;
@@ -1028,7 +1028,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist,
unsigned int pages,
* Its value is decided by evsel's write_backward.
* So 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 };
if (!evlist->mmap)
evlist->mmap = perf_evlist__alloc_mmap(evlist, false);
@@ -1060,7 +1060,7 @@ 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
