Re: [PATCH v13 3/3]: perf record: extend trace writing to multi AIO

[Alexey Budankov]

Hi,

On 12.10.2018 12:49, Namhyung Kim wrote:
> Hi,
> 
> On Thu, Oct 11, 2018 at 09:59:19PM +0300, Alexey Budankov wrote:
>>
<SNIP>
>> @@ -1882,8 +1913,8 @@ static struct option __record_options[] = {
>>  	OPT_BOOLEAN(0, "dry-run", &dry_run,
>>  		    "Parse options then exit"),
>>  #ifdef HAVE_AIO_SUPPORT
>> -	OPT_CALLBACK_NOOPT(0, "aio", &record.opts,
>> -		     NULL, "Enable asynchronous trace writing mode",
>> +	OPT_CALLBACK(0, "aio", &record.opts,
>> +		     "n", "Use <n> control blocks in asynchronous trace writing mode (default: 1, max: 4)",
> 
> One question.  It seems you used a very large N in your test result.
> Why did you limit it to 4 here?  Is it something different?  Maybe
> you'd better making it a macro constant for future changes..

Yes, it's less than values used during metrics measurements.
There is still no good rationale behind top border value 
because currently it is a kind of implementation detail. 
Defining as a macro makes sense for easier source code management.

Thanks,
Alexey

> 
> Otherwise looks good to me.  For the 3 patches
> 
> Acked-by: Namhyung Kim <namhyung@xxxxxxxxxx>
> 
> Thanks,
> Namhyung