Re: [PATCH v2 3/4] perf record: apply affinity masks when reading mmap buffers

[Alexey Budankov <alexey.budankov@linux.intel.com>]

Hi,

On 02.01.2019 0:39, Jiri Olsa wrote:
> On Mon, Dec 24, 2018 at 03:27:17PM +0300, Alexey Budankov wrote:
> 
> SNIP
> 
>> diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
>> index 742fa9a8e498..a2095e4eda4b 100644
>> --- a/tools/perf/util/mmap.c
>> +++ b/tools/perf/util/mmap.c
>> @@ -361,6 +361,7 @@ void perf_mmap__munmap(struct perf_mmap *map)
>>  
>>  int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd, int cpu)
>>  {
>> +	int c, nr_cpus, node;
>>  	/*
>>  	 * The last one will be done at perf_mmap__consume(), so that we
>>  	 * make sure we don't prevent tools from consuming every last event in
>> @@ -389,6 +390,17 @@ int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd, int c
>>  	map->cpu = cpu;
>>  
>>  	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++) {
>> +			if (cpu__get_node(c) == node) {
> 
> the 'c' is just an index here, I think you need to
> use the real cpu value from the mp->cpu_map->map[c]

Well, yes, mapping c index to online cpu index is more generic. 
Corrected in v3. Thanks!

Alexey

> 
> jirka
> 
>> +				CPU_SET(c, &map->affinity_mask);
>> +			}
>> +		}
>> +	} else if (mp->affinity == PERF_AFFINITY_CPU) {
>> +		CPU_SET(map->cpu, &map->affinity_mask);
>> +	}
>>  
>>  	if (auxtrace_mmap__mmap(&map->auxtrace_mmap,
>>  				&mp->auxtrace_mp, map->base, fd))
>> diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
>> index e566c19b242b..b3f724fad22e 100644
>> --- a/tools/perf/util/mmap.h
>> +++ b/tools/perf/util/mmap.h
>> @@ -72,6 +72,7 @@ enum bkw_mmap_state {
>>  struct mmap_params {
>>  	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);
>