From: Arnaldo Carvalho de Melo <acme@kernel.org>
To: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>, Namhyung Kim <namhyung@kernel.org>,
Alexander Shishkin <alexander.shishkin@linux.intel.com>,
Peter Zijlstra <peterz@infradead.org>,
Ingo Molnar <mingo@redhat.com>,
linux-kernel <linux-kernel@vger.kernel.org>,
Andi Kleen <ak@linux.intel.com>,
Adrian Hunter <adrian.hunter@intel.com>,
Alexander Antonov <alexander.antonov@linux.intel.com>,
Alexei Budankov <abudankov@huawei.com>,
Riccardo Mancini <rickyman7@gmail.com>
Subject: Re: [PATCH v8 01/22] perf record: Introduce thread affinity and mmap masks
Date: Wed, 30 Jun 2021 13:17:13 -0300 [thread overview]
Message-ID: <YNyZCZ92W39inSD2@kernel.org> (raw)
In-Reply-To: <ab1e7917845cc175a9e1d7f149e07b000d24c881.1625065643.git.alexey.v.bayduraev@linux.intel.com>
Em Wed, Jun 30, 2021 at 06:54:40PM +0300, Alexey Bayduraev escreveu:
> 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.
At this point we probably be better off renaming 'struct mmap_cpu_mask'
to 'struct cpumask' since it is not only for 'mmap's, right?
In fact probably would be better to adopt linux/cpumask.h from the
kernel sources, i.e.:
typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t;
some more comments below
> Acked-by: Andi Kleen <ak@linux.intel.com>
> Acked-by: Namhyung Kim <namhyung@gmail.com>
> Signed-off-by: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com>
> ---
> tools/perf/builtin-record.c | 127 ++++++++++++++++++++++++++++++++++++
> 1 file changed, 127 insertions(+)
>
> diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
> index 71efe6573ee7..31b3a515abc1 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 */
> + struct thread_mask *thread_masks;
> + int nr_threads;
can you move 'nr_threads' to before 'thread_masks'?
> };
>
> static volatile int done;
> @@ -2216,6 +2223,55 @@ 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_alloc(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;
Plese use NULL, as 'mask->nbits' is a pointer.
> +}
> +
> +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;
> +
> + ret = record__mmap_cpu_mask_alloc(&mask->maps, nr_bits);
please combine such decl + assign into one line, i.e.:
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)
> {
> @@ -2664,6 +2720,70 @@ 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 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);
Usually when we don't manage to allocate all that we need we go on and
free the partially allocated resources.
> + if (ret)
> + return ret;
> + record__thread_mask_clear(&rec->thread_masks[t]);
> + }
> +
> + return 0;
> +}
> +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());
ditto
> + 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);
> +}
> +
> +static int record__fini_thread_masks(struct record *rec)
> +{
> + int t;
> +
> + if (rec->thread_masks)
> + for (t = 0; t < rec->nr_threads; t++)
> + record__thread_mask_free(&rec->thread_masks[t]);
> +
> + zfree(&rec->thread_masks);
> +
> + rec->nr_threads = 0;
> +
> + return 0;
> +}
> +
> int cmd_record(int argc, const char **argv)
> {
> int err;
> @@ -2912,6 +3032,12 @@ 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);
> @@ -2930,6 +3056,7 @@ int cmd_record(int argc, const char **argv)
> symbol__exit();
> auxtrace_record__free(rec->itr);
> out_opts:
> + record__fini_thread_masks(rec);
> evlist__close_control(rec->opts.ctl_fd, rec->opts.ctl_fd_ack, &rec->opts.ctl_fd_close);
> return err;
> }
> --
> 2.19.0
>
--
- Arnaldo
next prev parent reply other threads:[~2021-06-30 16:17 UTC|newest]
Thread overview: 49+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-06-30 15:54 [PATCH v8 00/22] Introduce threaded trace streaming for basic perf record operation Alexey Bayduraev
2021-06-30 15:54 ` [PATCH v8 01/22] perf record: Introduce thread affinity and mmap masks Alexey Bayduraev
2021-06-30 16:17 ` Arnaldo Carvalho de Melo [this message]
2021-06-30 16:28 ` Arnaldo Carvalho de Melo
2021-07-01 13:05 ` Bayduraev, Alexey V
2021-07-01 14:23 ` Arnaldo Carvalho de Melo
2021-06-30 15:54 ` [PATCH v8 02/22] perf record: Introduce thread specific data array Alexey Bayduraev
2021-06-30 16:26 ` Arnaldo Carvalho de Melo
2021-06-30 17:18 ` Arnaldo Carvalho de Melo
2021-06-30 15:54 ` [PATCH v8 03/22] perf record: Introduce thread local variable Alexey Bayduraev
2021-06-30 17:16 ` Arnaldo Carvalho de Melo
2021-07-01 17:22 ` Bayduraev, Alexey V
2021-06-30 15:54 ` [PATCH v8 04/22] perf record: Stop threads in the end of trace streaming Alexey Bayduraev
2021-06-30 15:54 ` [PATCH v8 05/22] perf record: Start threads in the beginning " Alexey Bayduraev
2021-06-30 17:21 ` Arnaldo Carvalho de Melo
2021-06-30 15:54 ` [PATCH v8 06/22] perf record: Introduce data file at mmap buffer object Alexey Bayduraev
2021-06-30 17:23 ` Arnaldo Carvalho de Melo
2021-07-01 16:41 ` Bayduraev, Alexey V
2021-07-01 17:28 ` Arnaldo Carvalho de Melo
2021-06-30 15:54 ` [PATCH v8 07/22] perf record: Introduce data transferred and compressed stats Alexey Bayduraev
2021-06-30 15:54 ` [PATCH v8 08/22] perf record: Init data file at mmap buffer object Alexey Bayduraev
2021-06-30 15:54 ` [PATCH v8 09/22] tools lib: Introduce bitmap_intersects() operation Alexey Bayduraev
2021-06-30 17:24 ` Arnaldo Carvalho de Melo
2021-06-30 17:33 ` Bayduraev, Alexey V
2021-06-30 17:42 ` Arnaldo Carvalho de Melo
2021-06-30 15:54 ` [PATCH v8 10/22] perf record: Introduce --threads=<spec> command line option Alexey Bayduraev
2021-06-30 17:28 ` Arnaldo Carvalho de Melo
2021-06-30 18:54 ` Bayduraev, Alexey V
2021-07-01 11:50 ` Bayduraev, Alexey V
2021-07-01 14:26 ` Arnaldo Carvalho de Melo
2021-07-01 18:14 ` Bayduraev, Alexey V
2021-06-30 15:54 ` [PATCH v8 11/22] perf record: Document parallel data streaming mode Alexey Bayduraev
2021-06-30 17:28 ` Arnaldo Carvalho de Melo
2021-06-30 15:54 ` [PATCH v8 12/22] perf report: Output data file name in raw trace dump Alexey Bayduraev
2021-06-30 18:36 ` Arnaldo Carvalho de Melo
2021-07-01 22:46 ` Bayduraev, Alexey V
2021-06-30 15:54 ` [PATCH v8 13/22] perf session: Move reader structure to the top Alexey Bayduraev
2021-06-30 15:54 ` [PATCH v8 14/22] perf session: Introduce reader_state in reader object Alexey Bayduraev
2021-06-30 15:54 ` [PATCH v8 15/22] perf session: Introduce reader objects in session object Alexey Bayduraev
2021-06-30 15:54 ` [PATCH v8 16/22] perf session: Introduce decompressor into trace reader object Alexey Bayduraev
2021-06-30 15:54 ` [PATCH v8 17/22] perf session: Move init into reader__init function Alexey Bayduraev
2021-06-30 15:54 ` [PATCH v8 18/22] perf session: Move map/unmap into reader__mmap function Alexey Bayduraev
2021-06-30 15:54 ` [PATCH v8 19/22] perf session: Load single file for analysis Alexey Bayduraev
2021-06-30 15:54 ` [PATCH v8 20/22] perf session: Load data directory files " Alexey Bayduraev
2021-07-02 10:30 ` Jiri Olsa
2021-07-02 12:04 ` Bayduraev, Alexey V
2021-06-30 15:55 ` [PATCH v8 21/22] perf session: Introduce READER_NODATA state Alexey Bayduraev
2021-07-01 10:08 ` Bayduraev, Alexey V
2021-06-30 15:55 ` [PATCH v8 22/22] perf record: Introduce record__bytes_written and fix --max-size option Alexey Bayduraev
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=YNyZCZ92W39inSD2@kernel.org \
--to=acme@kernel.org \
--cc=abudankov@huawei.com \
--cc=adrian.hunter@intel.com \
--cc=ak@linux.intel.com \
--cc=alexander.antonov@linux.intel.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=alexey.v.bayduraev@linux.intel.com \
--cc=jolsa@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=namhyung@kernel.org \
--cc=peterz@infradead.org \
--cc=rickyman7@gmail.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).