On 04/20/2017 02:07 PM, Omar Sandoval wrote:
> On Fri, Apr 07, 2017 at 06:24:03AM -0600, sbates@xxxxxxxxxxxx wrote:
>> From: Stephen Bates <sbates@xxxxxxxxxxxx>
>>
>> Rather than bucketing IO statisics based on direction only we also
>> bucket based on the IO size. This leads to improved polling
>> performance. Update the bucket callback function and use it in the
>> polling latency estimation.
>>
>> Signed-off-by: Stephen Bates <sbates@xxxxxxxxxxxx>
>
> Hey, Stephen, just taking a look at this now. Comments below.
>
>> ---
>> block/blk-mq.c | 45 +++++++++++++++++++++++++++++++++++----------
>> 1 file changed, 35 insertions(+), 10 deletions(-)
>>
>> diff --git a/block/blk-mq.c b/block/blk-mq.c
>> index 061fc2c..5fd376b 100644
>> --- a/block/blk-mq.c
>> +++ b/block/blk-mq.c
>> @@ -42,6 +42,25 @@ static LIST_HEAD(all_q_list);
>> static void blk_mq_poll_stats_start(struct request_queue *q);
>> static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb);
>>
>> +/* Must be consisitent with function below */
>> +#define BLK_MQ_POLL_STATS_BKTS 16
>> +static int blk_mq_poll_stats_bkt(const struct request *rq)
>> +{
>> + int ddir, bytes, bucket;
>> +
>> + ddir = blk_stat_rq_ddir(rq);
>
> No need to call the wrapper function here, we can use rq_data_dir()
> directly.
>
>> + bytes = blk_rq_bytes(rq);
>> +
>> + bucket = ddir + 2*(ilog2(bytes) - 9);
>> +
>> + if (bucket < 0)
>> + return -1;
>> + else if (bucket >= BLK_MQ_POLL_STATS_BKTS)
>> + return ddir + BLK_MQ_POLL_STATS_BKTS - 2;
>> +
>> + return bucket;
>> +}
>
> Nitpicking here, but defining things in terms of the number of size
> buckets seems more natural to me. How about something like this
> (untested)? Note that this obviates the need for patch 1.
>
> #define BLK_MQ_POLL_STATS_SIZE_BKTS 8
> static unsigned int blk_mq_poll_stats_bkt(const struct request *rq)
> {
> unsigned int size_bucket;
>
> size_bucket = clamp(ilog2(blk_rq_bytes(rq)) - 9, 0,
> BLK_MQ_POLL_STATS_SIZE_BKTS - 1);
> return 2 * size_bucket + rq_data_dir(rq);
> }
As I wrote in an earlier reply, it would be a lot cleaner to just have
the buckets be:
buckets[2][BUCKETS_PER_RW];
and not have to do weird math based on both size and data direction.
Just have it return the bucket index based on size, and have the caller
do:
bucket[rq_data_dir(rq)][bucket_index];
--
Jens Axboe
