Re: [PATCH v8 01/22] perf record: Introduce thread affinity and mmap masks

[Arnaldo Carvalho de Melo <acme@kernel.org>]

Em Wed, Jun 30, 2021 at 01:17:13PM -0300, Arnaldo Carvalho de Melo escreveu:
> 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;

Note, this patchset is already 22 patches long and is at v8, so we can
do this as a next step.

I'll continue with the review
 
> 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

-- 

- Arnaldo