blk-mq: count the hctx as active before allocating tag

Currently, we count the hctx as active after allocate driver tag
successfully. If a previously inactive hctx try to get tag first
time, it may fails and need to wait. However, due to the stale tag
->active_queues, the other shared-tags users are still able to
occupy all driver tags while there is someone waiting for tag.
Consequently, even if the previously inactive hctx is waked up, it
still may not be able to get a tag and could be starved.

To fix it, we count the hctx as active before try to allocate driver
tag, then when it is waiting the tag, the other shared-tag users
will reserve budget for it.

Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jianchao Wang <jianchao.w.wang@oracle.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index c43b3398d7b417f9a6890410a948b7079b5caeba..c0c4e63583ae032195e11f95b169c7b4669358e3 100644 (file)
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -23,6 +23,9 @@ bool blk_mq_has_free_tags(struct blk_mq_tags *tags)
 
 /*
  * 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
+ * to get tag when first time, the other shared-tag users could reserve
+ * budget for it.
  */
 bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
 {

diff --git a/block/blk-mq.c b/block/blk-mq.c
index e13bdc2707ce255b32dbf423fb731071b4178494..5efd789910e25c1c187c8b36c8686bfb5a47a555 100644 (file)
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -285,7 +285,7 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
                rq->tag = -1;
                rq->internal_tag = tag;
        } else {
-               if (blk_mq_tag_busy(data->hctx)) {
+               if (data->hctx->flags & BLK_MQ_F_TAG_SHARED) {
                        rq_flags = RQF_MQ_INFLIGHT;
                        atomic_inc(&data->hctx->nr_active);
                }
@@ -367,6 +367,8 @@ static struct request *blk_mq_get_request(struct request_queue *q,
                if (!op_is_flush(op) && e->type->ops.mq.limit_depth &&
                    !(data->flags & BLK_MQ_REQ_RESERVED))
                        e->type->ops.mq.limit_depth(op, data);
+       } else {
+               blk_mq_tag_busy(data->hctx);
        }
 
        tag = blk_mq_get_tag(data);
@@ -971,6 +973,7 @@ bool blk_mq_get_driver_tag(struct request *rq)
                .hctx = blk_mq_map_queue(rq->q, rq->mq_ctx->cpu),
                .flags = BLK_MQ_REQ_NOWAIT,
        };
+       bool shared;
 
        if (rq->tag != -1)
                goto done;
@@ -978,9 +981,10 @@ bool blk_mq_get_driver_tag(struct request *rq)
        if (blk_mq_tag_is_reserved(data.hctx->sched_tags, rq->internal_tag))
                data.flags |= BLK_MQ_REQ_RESERVED;
 
+       shared = blk_mq_tag_busy(data.hctx);
        rq->tag = blk_mq_get_tag(&data);
        if (rq->tag >= 0) {
-               if (blk_mq_tag_busy(data.hctx)) {
+               if (shared) {
                        rq->rq_flags |= RQF_MQ_INFLIGHT;
                        atomic_inc(&data.hctx->nr_active);
                }