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

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <d3b3ccaf-c8d2-03f7-580e-f3318b1650d2@linux.intel.com>
Date:   Wed, 20 Feb 2019 18:24:30 +0300
From:   Alexey Budankov <alexey.budankov@...ux.intel.com>
To:     Jiri Olsa <jolsa@...hat.com>
Cc:     Arnaldo Carvalho de Melo <acme@...nel.org>,
        Ingo Molnar <mingo@...hat.com>,
        Peter Zijlstra <peterz@...radead.org>,
        Namhyung Kim <namhyung@...nel.org>,
        Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
        Andi Kleen <ak@...ux.intel.com>,
        linux-kernel <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH v2 2/4] perf record: implement -z=<level> and
 --mmap-flush=<thres> options


On 12.02.2019 16:08, Jiri Olsa wrote:
> 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

AIO buffers management has been taken out of HAVE_AIO_SUPPORT define
to be used for compression in case of serial streaming. It will be 
revisited after other issues are addressed.

Thanks,
Alexey

> 
> 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
>