linux-kernel - Re: blk-mq: takes hours for scsi scanning finish when thousands of LUNs

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] [day] [month] [year] [list]

Message-ID: <562A0285.4050109@oracle.com>
Date:	Fri, 23 Oct 2015 17:48:53 +0800
From:	jason <zhangqing.luo@...cle.com>
To:	Jeff Moyer <jmoyer@...hat.com>, Jens Axboe <axboe@...nel.dk>
CC:	Tejun Heo <tj@...nel.org>,
	Guru Anbalagane <guru.anbalagane@...cle.com>,
	Feng Jin <joe.jin@...cle.com>, linux-kernel@...r.kernel.org
Subject: Re: blk-mq: takes hours for scsi scanning finish when thousands of
 LUNs

Hi,Jeff

On Friday, October 23, 2015 03:04 AM, Jeff Moyer wrote:
> Jens Axboe <axboe@...nel.dk> writes:
>
>> On 10/22/2015 09:53 AM, Jeff Moyer wrote:
>>> I think that percolating BLK_MQ_F_TAG_SHARED up to the tag set would
>>> allow newly created hctxs to simply inherit the shared state (in
>>> blk_mq_init_hctx), and you won't need to freeze every queue in order to
>>> guarantee that.
>>>
>>> I was writing a patch to that effect.  I've now stopped as I want to
>>> make sure I'm not off in the weeds.  :)
>>
>> If that is where the delay is done, then yes, that should fix it and
>> be a trivial patch.
>
> It's not quite as trivial as I had hoped.  Jason, can you give the
> attached patch a try?  All I've done is boot tested it so far.
>
> Thanks!
> Jeff
>
> diff --git a/block/blk-mq.c b/block/blk-mq.c
> index 7785ae9..8b4c484 100644
> --- a/block/blk-mq.c
> +++ b/block/blk-mq.c
> @@ -1860,27 +1860,26 @@ static void blk_mq_map_swqueue(struct request_queue *q,
>   	}
>   }
>
> -static void blk_mq_update_tag_set_depth(struct blk_mq_tag_set *set)
> +static void queue_set_hctx_shared(struct request_queue *q, bool shared)
>   {
>   	struct blk_mq_hw_ctx *hctx;
> -	struct request_queue *q;
> -	bool shared;
>   	int i;
>
> -	if (set->tag_list.next == set->tag_list.prev)
> -		shared = false;
> -	else
> -		shared = true;
> +	queue_for_each_hw_ctx(q, hctx, i) {
> +		if (shared)
> +			hctx->flags |= BLK_MQ_F_TAG_SHARED;
> +		else
> +			hctx->flags &= ~BLK_MQ_F_TAG_SHARED;
> +	}
> +}
> +
> +static void blk_mq_update_tag_set_depth(struct blk_mq_tag_set *set, bool shared)
> +{
> +	struct request_queue *q;
>
>   	list_for_each_entry(q, &set->tag_list, tag_set_list) {
>   		blk_mq_freeze_queue(q);
> -
> -		queue_for_each_hw_ctx(q, hctx, i) {
> -			if (shared)
> -				hctx->flags |= BLK_MQ_F_TAG_SHARED;
> -			else
> -				hctx->flags &= ~BLK_MQ_F_TAG_SHARED;
> -		}
> +		queue_set_hctx_shared(q, shared);
>   		blk_mq_unfreeze_queue(q);
>   	}
>   }
> @@ -1891,7 +1890,13 @@ static void blk_mq_del_queue_tag_set(struct request_queue *q)
>
>   	mutex_lock(&set->tag_list_lock);
>   	list_del_init(&q->tag_set_list);
> -	blk_mq_update_tag_set_depth(set);
> +
> +	if (set->tag_list.next == set->tag_list.prev) {
> +		/* just transitioned to unshared */
> +		set->flags &= ~BLK_MQ_F_TAG_SHARED;
> +		/* update existing queue */
> +		blk_mq_update_tag_set_depth(set, false);
> +	}
>   	mutex_unlock(&set->tag_list_lock);
>   }
>
> @@ -1902,7 +1907,24 @@ static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set,
>
>   	mutex_lock(&set->tag_list_lock);
>   	list_add_tail(&q->tag_set_list, &set->tag_list);
> -	blk_mq_update_tag_set_depth(set);
> +
> +	if (set->tag_list.next != set->tag_list.prev) {
> +		/*
> +		 * Only update the tag set state if the state has
> +		 * actually changed.
> +		 */
> +		if (!(set->flags & BLK_MQ_F_TAG_SHARED)) {
> +			/* just transitioned to shared tags */
> +			set->flags |= BLK_MQ_F_TAG_SHARED;
> +			blk_mq_update_tag_set_depth(set, true);
> +		} else {
> +			/* ensure we didn't race with another addition */
> +			struct blk_mq_hw_ctx *hctx = queue_first_hw_ctx(q);
> +			if ((hctx->flags & BLK_MQ_F_TAG_SHARED) !=
> +							BLK_MQ_F_TAG_SHARED)
> +				queue_set_hctx_shared(q, true);
> +		}
> +	}
>   	mutex_unlock(&set->tag_list_lock);
>   }
>
> diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
> index 5e7d43a..12ffc40 100644
> --- a/include/linux/blk-mq.h
> +++ b/include/linux/blk-mq.h
> @@ -254,6 +254,9 @@ static inline void *blk_mq_rq_to_pdu(struct request *rq)
>   	for ((i) = 0; (i) < (hctx)->nr_ctx &&				\
>   	     ({ ctx = (hctx)->ctxs[(i)]; 1; }); (i)++)
>
> +#define queue_first_hw_ctx(q)						\
> +	(q)->queue_hw_ctx[0]
> +
>   #define blk_ctx_sum(q, sum)						\
>   ({									\
>   	struct blk_mq_ctx *__x;						\
>

I tested with your patch which avoids looping all queues in set by 
checking flag BLK_MQ_F_TAG_SHARED.
it works!
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/