Re: [PATCH v1 5/6] blk-mq: fix for trace_block_plug()

From: Ming Lei
Date: Mon Oct 19 2015 - 11:58:46 EST


On Mon, Oct 19, 2015 at 11:38 PM, Jeff Moyer <jmoyer@xxxxxxxxxx> wrote:
> Ming Lei <ming.lei@xxxxxxxxxxxxx> writes:
>
>> The trace point is for tracing plug event of each request
>> queue instead of each task, so we should check the request
>> count in the plug list from current queue instead of
>> current task.
>
> If blk_queue_nomerges returns true, request_count won't be updated, so
> you've essentially broken plugging for those queues.

Yes, you are right, and blk_queue_bio() has the same problem too,
and looks automatic flush plug can't work for nomerges queue at all.

Thanks,
Ming

>
> Cheers,
> Jeff
>
>>
>> Signed-off-by: Ming Lei <ming.lei@xxxxxxxxxxxxx>
>> ---
>> block/blk-mq.c | 2 +-
>> 1 file changed, 1 insertion(+), 1 deletion(-)
>>
>> diff --git a/block/blk-mq.c b/block/blk-mq.c
>> index d55d022..a5e33bc 100644
>> --- a/block/blk-mq.c
>> +++ b/block/blk-mq.c
>> @@ -1377,7 +1377,7 @@ static void blk_sq_make_request(struct request_queue *q, struct bio *bio)
>> plug = current->plug;
>> if (plug) {
>> blk_mq_bio_to_request(rq, bio);
>> - if (list_empty(&plug->mq_list))
>> + if (!request_count)
>> trace_block_plug(q);
>> else if (request_count >= BLK_MAX_REQUEST_COUNT) {
>> blk_flush_plug_list(plug, false);
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/