On 6/18/23 18:07, Yu Kuai wrote:
From: Yu Kuai <yukuai3@xxxxxxxxxx>
Start tag fair sharing when a device start to issue io will waste
resources, same number of tags will be assigned to each disk/hctx,
and such tags can't be used for other disk/hctx, which means a disk/hctx
can't use more than assinged tags even if there are still lots of tags
that is assinged to other disks are unused.
Add a new api blk_mq_driver_tag_busy(), it will be called when get
driver tag failed, and move tag sharing from blk_mq_tag_busy() to
blk_mq_driver_tag_busy().
This approch will work well if total tags are not exhausted, and follow
up patches will try to refactor how tag is shared to handle this case.
Signed-off-by: Yu Kuai <yukuai3@xxxxxxxxxx>
---
block/blk-mq-debugfs.c | 4 ++-
block/blk-mq-tag.c | 60 ++++++++++++++++++++++++++++++++++--------
block/blk-mq.c | 4 ++-
block/blk-mq.h | 13 ++++++---
include/linux/blk-mq.h | 6 +++--
include/linux/blkdev.h | 1 +
6 files changed, 70 insertions(+), 18 deletions(-)
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 431aaa3eb181..de5a911b07c2 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -400,8 +400,10 @@ static void blk_mq_debugfs_tags_show(struct seq_file *m,
{
seq_printf(m, "nr_tags=%u\n", tags->nr_tags);
seq_printf(m, "nr_reserved_tags=%u\n", tags->nr_reserved_tags);
- seq_printf(m, "active_queues=%d\n",
+ seq_printf(m, "active_queues=%u\n",
READ_ONCE(tags->ctl.active_queues));
+ seq_printf(m, "share_queues=%u\n",
+ READ_ONCE(tags->ctl.share_queues));
seq_puts(m, "\nbitmap_tags:\n");
sbitmap_queue_show(&tags->bitmap_tags, m);
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index fe41a0d34fc0..1c2bde917195 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -29,6 +29,32 @@ static void blk_mq_update_wake_batch(struct blk_mq_tags *tags,
users);
}
+void __blk_mq_driver_tag_busy(struct blk_mq_hw_ctx *hctx)
+{
+ struct blk_mq_tags *tags = hctx->tags;
+
+ /*
+ * calling test_bit() prior to test_and_set_bit() is intentional,
+ * it avoids dirtying the cacheline if the queue is already active.
+ */
+ if (blk_mq_is_shared_tags(hctx->flags)) {
+ struct request_queue *q = hctx->queue;
+
+ if (test_bit(QUEUE_FLAG_HCTX_BUSY, &q->queue_flags) ||
+ test_and_set_bit(QUEUE_FLAG_HCTX_BUSY, &q->queue_flags))
+ return;
+ } else {
+ if (test_bit(BLK_MQ_S_DTAG_BUSY, &hctx->state) ||
+ test_and_set_bit(BLK_MQ_S_DTAG_BUSY, &hctx->state))
+ return;
+ }
+
+ spin_lock_irq(&tags->lock);
+ WRITE_ONCE(tags->ctl.share_queues, tags->ctl.active_queues);
+ blk_mq_update_wake_batch(tags, tags->ctl.share_queues);
+ spin_unlock_irq(&tags->lock);
+}
+
/*
* If a previously inactive queue goes active, bump the active user count.
* We need to do this before try to allocate driver tag, then even if fail
@@ -37,7 +63,6 @@ static void blk_mq_update_wake_batch(struct blk_mq_tags *tags,
*/
void __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
{
- unsigned int users;
struct blk_mq_tags *tags = hctx->tags;
/*
@@ -57,9 +82,7 @@ void __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
}
spin_lock_irq(&tags->lock);
- users = tags->ctl.active_queues + 1;
- WRITE_ONCE(tags->ctl.active_queues, users);
- blk_mq_update_wake_batch(tags, users);
+ WRITE_ONCE(tags->ctl.active_queues, tags->ctl.active_queues + 1);
Why did you remove the call to blk_mq_update_wake_batch() here?
Cheers,
Hannes
--
Dr. Hannes Reinecke Kernel Storage Architect
hare@xxxxxxx +49 911 74053 688
SUSE Software Solutions GmbH, Maxfeldstr. 5, 90409 Nürnberg
HRB 36809 (AG Nürnberg), Geschäftsführer: Ivo Totev, Andrew
Myers, Andrew McDonald, Martje Boudien Moerman
