block/mq-deadline: Fix the tag reservation code

The current tag reservation code is based on a misunderstanding of the
meaning of data->shallow_depth. Fix the tag reservation code as follows:
* By default, do not reserve any tags for synchronous requests because
  for certain use cases reserving tags reduces performance. See also
  Harshit Mogalapalli, [bug-report] Performance regression with fio
  sequential-write on a multipath setup, 2024-03-07
  (https://lore.kernel.org/linux-block/[email protected]/)
* Reduce min_shallow_depth to one because min_shallow_depth must be less
  than or equal any shallow_depth value.
* Scale dd->async_depth from the range [1, nr_requests] to [1,
  bits_per_sbitmap_word].

Cc: Christoph Hellwig <[email protected]>
Cc: Damien Le Moal <[email protected]>
Cc: Zhiguo Niu <[email protected]>
Fixes: 0775758 ("block/mq-deadline: Reserve 25% of scheduler tags for synchronous requests")
Signed-off-by: Bart Van Assche <[email protected]>
Reviewed-by: Christoph Hellwig <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jens Axboe <[email protected]>

Author: bvanassche

block/mq-deadline.c

@@ -487,6 +487,20 @@ static struct request *dd_dispatch_request(struct blk_mq_hw_ctx *hctx)
 	return rq;
 }
 
+/*
+ * 'depth' is a number in the range 1..INT_MAX representing a number of
+ * requests. Scale it with a factor (1 << bt->sb.shift) / q->nr_requests since
+ * 1..(1 << bt->sb.shift) is the range expected by sbitmap_get_shallow().
+ * Values larger than q->nr_requests have the same effect as q->nr_requests.
+ */
+static int dd_to_word_depth(struct blk_mq_hw_ctx *hctx, unsigned int qdepth)
+{
+	struct sbitmap_queue *bt = &hctx->sched_tags->bitmap_tags;
+	const unsigned int nrr = hctx->queue->nr_requests;
+
+	return ((qdepth << bt->sb.shift) + nrr - 1) / nrr;
+}
+
 /*
  * Called by __blk_mq_alloc_request(). The shallow_depth value set by this
  * function is used by __blk_mq_get_tag().
@@ -503,7 +517,7 @@ static void dd_limit_depth(blk_opf_t opf, struct blk_mq_alloc_data *data)
 	 * Throttle asynchronous requests and writes such that these requests
 	 * do not block the allocation of synchronous requests.
 	 */
-	data->shallow_depth = dd->async_depth;
+	data->shallow_depth = dd_to_word_depth(data->hctx, dd->async_depth);
 }
 
 /* Called by blk_mq_update_nr_requests(). */
@@ -513,9 +527,9 @@ static void dd_depth_updated(struct blk_mq_hw_ctx *hctx)
 	struct deadline_data *dd = q->elevator->elevator_data;
 	struct blk_mq_tags *tags = hctx->sched_tags;
 
-	dd->async_depth = max(1UL, 3 * q->nr_requests / 4);
+	dd->async_depth = q->nr_requests;
 
-	sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, dd->async_depth);
+	sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, 1);
 }
 
 /* Called by blk_mq_init_hctx() and blk_mq_init_sched(). */