Re: [PATCH v2 2/4] perf record: implement -z=<level> and --mmap-flush=<thres> options

[Jiri Olsa <jolsa@redhat.com>]

On Mon, Feb 11, 2019 at 11:22:38PM +0300, Alexey Budankov wrote:

SNIP

> +static int perf_mmap__aio_mmap_blocks(struct perf_mmap *map);
> +
>  static int perf_mmap__aio_mmap(struct perf_mmap *map, struct mmap_params *mp)
>  {
> -	int delta_max, i, prio, ret;
> +	int i, ret = 0, init_blocks = 1;
>  
>  	map->aio.nr_cblocks = mp->nr_cblocks;
> +	if (map->aio.nr_cblocks == -1) {
> +		map->aio.nr_cblocks = 1;
> +		init_blocks = 0;
> +	}
> +
>  	if (map->aio.nr_cblocks) {
> -		map->aio.aiocb = calloc(map->aio.nr_cblocks, sizeof(struct aiocb *));
> -		if (!map->aio.aiocb) {
> -			pr_debug2("failed to allocate aiocb for data buffer, error %m\n");
> -			return -1;
> -		}
> -		map->aio.cblocks = calloc(map->aio.nr_cblocks, sizeof(struct aiocb));
> -		if (!map->aio.cblocks) {
> -			pr_debug2("failed to allocate cblocks for data buffer, error %m\n");
> -			return -1;
> -		}
>  		map->aio.data = calloc(map->aio.nr_cblocks, sizeof(void *));
>  		if (!map->aio.data) {
>  			pr_debug2("failed to allocate data buffer, error %m\n");
>  			return -1;
>  		}
> -		delta_max = sysconf(_SC_AIO_PRIO_DELTA_MAX);
>  		for (i = 0; i < map->aio.nr_cblocks; ++i) {
>  			ret = perf_mmap__aio_alloc(map, i);
>  			if (ret == -1) {
> @@ -251,29 +245,16 @@ static int perf_mmap__aio_mmap(struct perf_mmap *map, struct mmap_params *mp)
>  			ret = perf_mmap__aio_bind(map, i, map->cpu, mp->affinity);
>  			if (ret == -1)
>  				return -1;
> -			/*
> -			 * Use cblock.aio_fildes value different from -1
> -			 * to denote started aio write operation on the
> -			 * cblock so it requires explicit record__aio_sync()
> -			 * call prior the cblock may be reused again.
> -			 */
> -			map->aio.cblocks[i].aio_fildes = -1;
> -			/*
> -			 * Allocate cblocks with priority delta to have
> -			 * faster aio write system calls because queued requests
> -			 * are kept in separate per-prio queues and adding
> -			 * a new request will iterate thru shorter per-prio
> -			 * list. Blocks with numbers higher than
> -			 *  _SC_AIO_PRIO_DELTA_MAX go with priority 0.
> -			 */
> -			prio = delta_max - i;
> -			map->aio.cblocks[i].aio_reqprio = prio >= 0 ? prio : 0;
>  		}
> +		if (init_blocks)
> +			ret = perf_mmap__aio_mmap_blocks(map);
>  	}
>  
> -	return 0;
> +	return ret;
>  }

SNIP

it seems like little refactoring happened in here (up and down) for
aio code, which is not explained and I'm unable to follow it.. please
separate this in simple change

SNIP

> +#ifdef HAVE_AIO_SUPPORT
> +static int perf_mmap__aio_mmap_blocks(struct perf_mmap *map)
> +{
> +	int delta_max, i, prio;
> +
> +	map->aio.aiocb = calloc(map->aio.nr_cblocks, sizeof(struct aiocb *));
> +	if (!map->aio.aiocb) {
> +		pr_debug2("failed to allocate aiocb for data buffer, error %m\n");
> +		return -1;
> +	}
> +	map->aio.cblocks = calloc(map->aio.nr_cblocks, sizeof(struct aiocb));
> +	if (!map->aio.cblocks) {
> +		pr_debug2("failed to allocate cblocks for data buffer, error %m\n");
> +		return -1;
> +	}
> +	delta_max = sysconf(_SC_AIO_PRIO_DELTA_MAX);
> +	for (i = 0; i < map->aio.nr_cblocks; ++i) {
> +		/*
> +		 * Use cblock.aio_fildes value different from -1
> +		 * to denote started aio write operation on the
> +		 * cblock so it requires explicit record__aio_sync()
> +		 * call prior the cblock may be reused again.
> +		 */
> +		map->aio.cblocks[i].aio_fildes = -1;
> +		/*
> +		 * Allocate cblocks with priority delta to have
> +		 * faster aio write system calls because queued requests
> +		 * are kept in separate per-prio queues and adding
> +		 * a new request will iterate thru shorter per-prio
> +		 * list. Blocks with numbers higher than
> +		 *  _SC_AIO_PRIO_DELTA_MAX go with priority 0.
> +		 */
> +		prio = delta_max - i;
> +		map->aio.cblocks[i].aio_reqprio = prio >= 0 ? prio : 0;
> +	}
> +
> +	return 0;
> +}
> +

SNIP