Introduce affinity and mmap thread masks. Thread affinity mask
defines cpus that a thread is allowed to run on. Thread maps
mask defines mmap data buffers the thread serves to stream
profiling data from.
Acked-by: Andi Kleen <[email protected]>
Acked-by: Namhyung Kim <[email protected]>
Reviewed-by: Riccardo Mancini <[email protected]>
Tested-by: Riccardo Mancini <[email protected]>
Signed-off-by: Alexey Bayduraev <[email protected]>
---
tools/perf/builtin-record.c | 129 ++++++++++++++++++++++++++++++++++++
1 file changed, 129 insertions(+)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 0338b813585a..11537971ea3b 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -87,6 +87,11 @@ struct switch_output {
int cur_file;
};
+struct thread_mask {
+ struct mmap_cpu_mask maps;
+ struct mmap_cpu_mask affinity;
+};
+
struct record {
struct perf_tool tool;
struct record_opts opts;
@@ -111,6 +116,8 @@ struct record {
unsigned long long samples;
struct mmap_cpu_mask affinity_mask;
unsigned long output_max_size; /* = 0: unlimited */
+ int nr_threads;
+ struct thread_mask *thread_masks;
};
static volatile int done;
@@ -2197,6 +2204,54 @@ static int record__parse_affinity(const struct option *opt, const char *str, int
return 0;
}
+static int record__mmap_cpu_mask_alloc(struct mmap_cpu_mask *mask, int nr_bits)
+{
+ mask->nbits = nr_bits;
+ mask->bits = bitmap_zalloc(mask->nbits);
+ if (!mask->bits) {
+ pr_err("Failed to allocate mmap_cpu mask\n");
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+static void record__mmap_cpu_mask_free(struct mmap_cpu_mask *mask)
+{
+ bitmap_free(mask->bits);
+ mask->nbits = 0;
+}
+
+static void record__thread_mask_clear(struct thread_mask *mask)
+{
+ bitmap_zero(mask->maps.bits, mask->maps.nbits);
+ bitmap_zero(mask->affinity.bits, mask->affinity.nbits);
+}
+
+static int record__thread_mask_alloc(struct thread_mask *mask, int nr_bits)
+{
+ int ret = record__mmap_cpu_mask_alloc(&mask->maps, nr_bits);
+
+ if (ret) {
+ mask->affinity.bits = NULL;
+ return ret;
+ }
+
+ ret = record__mmap_cpu_mask_alloc(&mask->affinity, nr_bits);
+ if (ret) {
+ record__mmap_cpu_mask_free(&mask->maps);
+ mask->maps.bits = NULL;
+ }
+
+ return ret;
+}
+
+static void record__thread_mask_free(struct thread_mask *mask)
+{
+ record__mmap_cpu_mask_free(&mask->maps);
+ record__mmap_cpu_mask_free(&mask->affinity);
+}
+
static int parse_output_max_size(const struct option *opt,
const char *str, int unset)
{
@@ -2668,6 +2723,72 @@ static struct option __record_options[] = {
struct option *record_options = __record_options;
+static void record__mmap_cpu_mask_init(struct mmap_cpu_mask *mask, struct perf_cpu_map *cpus)
+{
+ int c;
+
+ for (c = 0; c < cpus->nr; c++)
+ set_bit(cpus->map[c], mask->bits);
+}
+
+static void record__free_thread_masks(struct record *rec, int nr_threads)
+{
+ int t;
+
+ if (rec->thread_masks)
+ for (t = 0; t < nr_threads; t++)
+ record__thread_mask_free(&rec->thread_masks[t]);
+
+ zfree(&rec->thread_masks);
+}
+
+static int record__alloc_thread_masks(struct record *rec, int nr_threads, int nr_bits)
+{
+ int t, ret;
+
+ rec->thread_masks = zalloc(nr_threads * sizeof(*(rec->thread_masks)));
+ if (!rec->thread_masks) {
+ pr_err("Failed to allocate thread masks\n");
+ return -ENOMEM;
+ }
+
+ for (t = 0; t < nr_threads; t++) {
+ ret = record__thread_mask_alloc(&rec->thread_masks[t], nr_bits);
+ if (ret)
+ goto out_free;
+ record__thread_mask_clear(&rec->thread_masks[t]);
+ }
+
+ return 0;
+
+out_free:
+ record__free_thread_masks(rec, nr_threads);
+
+ return ret;
+}
+
+static int record__init_thread_default_masks(struct record *rec, struct perf_cpu_map *cpus)
+{
+ int ret;
+
+ ret = record__alloc_thread_masks(rec, 1, cpu__max_cpu());
+ if (ret)
+ return ret;
+
+ record__mmap_cpu_mask_init(&rec->thread_masks->maps, cpus);
+
+ rec->nr_threads = 1;
+
+ return 0;
+}
+
+static int record__init_thread_masks(struct record *rec)
+{
+ struct perf_cpu_map *cpus = rec->evlist->core.cpus;
+
+ return record__init_thread_default_masks(rec, cpus);
+}
+
int cmd_record(int argc, const char **argv)
{
int err;
@@ -2927,6 +3048,12 @@ int cmd_record(int argc, const char **argv)
goto out;
}
+ err = record__init_thread_masks(rec);
+ if (err) {
+ pr_err("record__init_thread_masks failed, error %d\n", err);
+ goto out;
+ }
+
if (rec->opts.nr_cblocks > nr_cblocks_max)
rec->opts.nr_cblocks = nr_cblocks_max;
pr_debug("nr_cblocks: %d\n", rec->opts.nr_cblocks);
@@ -2945,6 +3072,8 @@ int cmd_record(int argc, const char **argv)
symbol__exit();
auxtrace_record__free(rec->itr);
out_opts:
+ record__free_thread_masks(rec, rec->nr_threads);
+ rec->nr_threads = 0;
evlist__close_control(rec->opts.ctl_fd, rec->opts.ctl_fd_ack, &rec->opts.ctl_fd_close);
return err;
}
--
2.19.0
On Tue, Nov 23, 2021 at 05:07:57PM +0300, Alexey Bayduraev wrote:
SNIP
> +static void record__mmap_cpu_mask_init(struct mmap_cpu_mask *mask, struct perf_cpu_map *cpus)
> +{
> + int c;
> +
> + for (c = 0; c < cpus->nr; c++)
> + set_bit(cpus->map[c], mask->bits);
> +}
> +
> +static void record__free_thread_masks(struct record *rec, int nr_threads)
> +{
> + int t;
> +
> + if (rec->thread_masks)
> + for (t = 0; t < nr_threads; t++)
> + record__thread_mask_free(&rec->thread_masks[t]);
> +
> + zfree(&rec->thread_masks);
> +}
> +
> +static int record__alloc_thread_masks(struct record *rec, int nr_threads, int nr_bits)
> +{
> + int t, ret;
> +
> + rec->thread_masks = zalloc(nr_threads * sizeof(*(rec->thread_masks)));
> + if (!rec->thread_masks) {
> + pr_err("Failed to allocate thread masks\n");
> + return -ENOMEM;
> + }
> +
> + for (t = 0; t < nr_threads; t++) {
> + ret = record__thread_mask_alloc(&rec->thread_masks[t], nr_bits);
> + if (ret)
> + goto out_free;
> + record__thread_mask_clear(&rec->thread_masks[t]);
nit, is this clear needed?
jirka
> + }
> +
> + return 0;
> +
> +out_free:
> + record__free_thread_masks(rec, nr_threads);
> +
> + return ret;
> +}
> +
SNIP
On 05.12.2021 18:13, Jiri Olsa wrote:
> On Tue, Nov 23, 2021 at 05:07:57PM +0300, Alexey Bayduraev wrote:
>
> SNIP
>
>> +static void record__mmap_cpu_mask_init(struct mmap_cpu_mask *mask, struct perf_cpu_map *cpus)
>> +{
>> + int c;
>> +
>> + for (c = 0; c < cpus->nr; c++)
>> + set_bit(cpus->map[c], mask->bits);
>> +}
>> +
>> +static void record__free_thread_masks(struct record *rec, int nr_threads)
>> +{
>> + int t;
>> +
>> + if (rec->thread_masks)
>> + for (t = 0; t < nr_threads; t++)
>> + record__thread_mask_free(&rec->thread_masks[t]);
>> +
>> + zfree(&rec->thread_masks);
>> +}
>> +
>> +static int record__alloc_thread_masks(struct record *rec, int nr_threads, int nr_bits)
>> +{
>> + int t, ret;
>> +
>> + rec->thread_masks = zalloc(nr_threads * sizeof(*(rec->thread_masks)));
>> + if (!rec->thread_masks) {
>> + pr_err("Failed to allocate thread masks\n");
>> + return -ENOMEM;
>> + }
>> +
>> + for (t = 0; t < nr_threads; t++) {
>> + ret = record__thread_mask_alloc(&rec->thread_masks[t], nr_bits);
>> + if (ret)
>> + goto out_free;
>> + record__thread_mask_clear(&rec->thread_masks[t]);
>
> nit, is this clear needed?
Hi,
You are right, since all elements of mask->bits is set to zero after
bitmap_zalloc in record__thread_mask_alloc, calling
record__thread_mask_clear after record__thread_mask_alloc
is redundant.
I will remove it here and in [PATCH v12 13/16].
Thanks,
Alexey
>
> jirka
>
>> + }
>> +
>> + return 0;
>> +
>> +out_free:
>> + record__free_thread_masks(rec, nr_threads);
>> +
>> + return ret;
>> +}
>> +
>
> SNIP
>