Re: [PATCH v12 09/16] perf record: Introduce bytes written stats

[Bayduraev, Alexey V]

On 05.12.2021 18:14, Jiri Olsa wrote:

<SNIP>

>>  static int record__write(struct record *rec, struct mmap *map __maybe_unused,
>> @@ -210,13 +223,15 @@ static int record__write(struct record *rec, struct mmap *map __maybe_unused,
>>  		return -1;
>>  	}
>>  
>> -	if (!(map && map->file))
>> +	if (map && map->file)
>> +		thread->bytes_written += size;
>> +	else
>>  		rec->bytes_written += size;
> 
> ok, that's why ;-) do we actually stil need rec->bytes_written?
> can't we count that under synthesizing main thread->bytes_written?

Hi Jiri,

No, we still need rec->bytes_written because it is used for 
the header in "perf.data/data", and it cannot be replaced by
threads[0].bytes_written because threads[0] is used for
"perf.data/data.0".

Regards,
Alexey

> 
> jirka
> 
>>  
>>  	if (record__output_max_size_exceeded(rec) && !done) {
>>  		fprintf(stderr, "[ perf record: perf size limit reached (%" PRIu64 " KB),"
>>  				" stopping session ]\n",
>> -				rec->bytes_written >> 10);
>> +				record__bytes_written(rec) >> 10);
>>  		done = 1;
>>  	}
>>  
>> -- 
>> 2.19.0
>>
>