From: John Garry <john.garry@huawei.com>
To: Ming Lei <ming.lei@redhat.com>
Cc: <axboe@kernel.dk>, <linux-block@vger.kernel.org>,
<linux-kernel@vger.kernel.org>, <linux-scsi@vger.kernel.org>,
<hare@suse.de>
Subject: Re: [PATCH v4 12/13] blk-mq: Use shared tags for shared sbitmap support
Date: Mon, 27 Sep 2021 10:13:29 +0100 [thread overview]
Message-ID: <6f52adfd-6904-6efb-adfc-f5f20eb5c1cf@huawei.com> (raw)
In-Reply-To: <YU/oIu2uQ420ol8F@T590>
On 26/09/2021 04:25, Ming Lei wrote:
>> c
>> @@ -27,10 +27,11 @@ bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
>> if (blk_mq_is_sbitmap_shared(hctx->flags)) {
>> struct request_queue *q = hctx->queue;
>> struct blk_mq_tag_set *set = q->tag_set;
>> + struct blk_mq_tags *tags = set->shared_sbitmap_tags;
> The local variable of 'set' can be removed and just retrieve 'tags' from
> hctx->tags.
>
>>
>> if (!test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags) &&
>> !test_and_set_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags))
>> - atomic_inc(&set->active_queues_shared_sbitmap);
>> + atomic_inc(&tags->active_queues);
>> } else {
>> if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state) &&
>> !test_and_set_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
>> @@ -61,10 +62,12 @@ void __blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx)
>> struct blk_mq_tag_set *set = q->tag_set;
>>
>> if (blk_mq_is_sbitmap_shared(hctx->flags)) {
>> + struct blk_mq_tags *tags = set->shared_sbitmap_tags;
>> +
> Same with above.
ok
>
>> if (!test_and_clear_bit(QUEUE_FLAG_HCTX_ACTIVE,
>> &q->queue_flags))
>> return;
>> - atomic_dec(&set->active_queues_shared_sbitmap);
>> + atomic_dec(&tags->active_queues);
>> } else {
>> if (!test_and_clear_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
>> return;
>> @@ -510,38 +513,10 @@ static int blk_mq_init_bitmap_tags(struct blk_mq_tags *tags,
>> return 0;
>> }
...
>> - struct sbitmap_queue __bitmap_tags;
>> - struct sbitmap_queue __breserved_tags;
>> struct blk_mq_tags **tags;
>>
>> + struct blk_mq_tags *shared_sbitmap_tags;
>> +
>> struct mutex tag_list_lock;
>> struct list_head tag_list;
>> };
>> @@ -432,6 +429,8 @@ enum {
>> ((policy & ((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1)) \
>> << BLK_MQ_F_ALLOC_POLICY_START_BIT)
>>
>> +#define BLK_MQ_NO_HCTX_IDX (-1U)
>> +
>> struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, void *queuedata,
>> struct lock_class_key *lkclass);
>> #define blk_mq_alloc_disk(set, queuedata) \
>> diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
>> index 4baf9435232d..17e50e5ef47b 100644
>> --- a/include/linux/blkdev.h
>> +++ b/include/linux/blkdev.h
>> @@ -459,8 +459,7 @@ struct request_queue {
>>
>> atomic_t nr_active_requests_shared_sbitmap;
>>
>> - struct sbitmap_queue sched_bitmap_tags;
>> - struct sbitmap_queue sched_breserved_tags;
>> + struct blk_mq_tags *shared_sbitmap_tags;
> Maybe better with shared_sched_sbitmap_tags or sched_sbitmap_tags?
Yeah, I suppose I should add "sched" to the name, as before.
BTW, Do you think that I should just change shared_sbitmap ->
shared_tags naming now globally? I'm thinking now that I should...
Thanks,
John
next prev parent reply other threads:[~2021-09-27 9:10 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-09-24 8:28 [PATCH v4 00/13] blk-mq: Reduce static requests memory footprint for shared sbitmap John Garry
2021-09-24 8:28 ` [PATCH v4 01/13] blk-mq: Change rqs check in blk_mq_free_rqs() John Garry
2021-09-24 8:28 ` [PATCH v4 02/13] block: Rename BLKDEV_MAX_RQ -> BLKDEV_DEFAULT_RQ John Garry
2021-09-24 8:28 ` [PATCH v4 03/13] blk-mq: Relocate shared sbitmap resize in blk_mq_update_nr_requests() John Garry
2021-09-24 8:28 ` [PATCH v4 04/13] blk-mq: Invert check " John Garry
2021-09-24 8:28 ` [PATCH v4 05/13] blk-mq-sched: Rename blk_mq_sched_alloc_{tags -> map_and_rqs}() John Garry
2021-09-24 10:08 ` Hannes Reinecke
2021-09-24 8:28 ` [PATCH v4 06/13] blk-mq-sched: Rename blk_mq_sched_free_{requests -> rqs}() John Garry
2021-09-26 1:15 ` Ming Lei
2021-09-24 8:28 ` [PATCH v4 07/13] blk-mq: Pass driver tags to blk_mq_clear_rq_mapping() John Garry
2021-09-26 1:42 ` Ming Lei
2021-09-24 8:28 ` [PATCH v4 08/13] blk-mq: Don't clear driver tags own mapping John Garry
2021-09-26 1:43 ` Ming Lei
2021-09-24 8:28 ` [PATCH v4 09/13] blk-mq: Add blk_mq_tag_update_sched_shared_sbitmap() John Garry
2021-09-24 8:28 ` [PATCH v4 10/13] blk-mq: Add blk_mq_alloc_map_and_rqs() John Garry
2021-09-26 2:00 ` Ming Lei
2021-09-24 8:28 ` [PATCH v4 11/13] blk-mq: Refactor and rename blk_mq_free_map_and_{requests->rqs}() John Garry
2021-09-26 2:05 ` Ming Lei
2021-09-27 9:02 ` John Garry
2021-09-27 9:19 ` Ming Lei
2021-09-27 9:40 ` John Garry
2021-09-24 8:28 ` [PATCH v4 12/13] blk-mq: Use shared tags for shared sbitmap support John Garry
2021-09-24 10:23 ` Hannes Reinecke
2021-09-24 10:39 ` John Garry
2021-09-29 13:36 ` John Garry
2021-09-26 3:25 ` Ming Lei
2021-09-27 9:13 ` John Garry [this message]
2021-09-27 9:26 ` Ming Lei
2021-09-27 9:41 ` John Garry
2021-09-24 8:28 ` [PATCH v4 13/13] blk-mq: Stop using pointers for blk_mq_tags bitmap tags John Garry
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=6f52adfd-6904-6efb-adfc-f5f20eb5c1cf@huawei.com \
--to=john.garry@huawei.com \
--cc=axboe@kernel.dk \
--cc=hare@suse.de \
--cc=linux-block@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-scsi@vger.kernel.org \
--cc=ming.lei@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).