summaryrefslogtreecommitdiffstats
path: root/block
diff options
context:
space:
mode:
authorOmar Sandoval <osandov@fb.com>2017-02-22 10:58:29 -0800
committerJens Axboe <axboe@fb.com>2017-02-23 11:55:46 -0700
commitda55f2cc78418dee88400aafbbaed19d7ac8188e (patch)
tree59e8fea4c15519bfd0cfed355f59bf30d5d8e03d /block
parent2d19020b085eaf61d24377db27e8630cd9cff7ce (diff)
downloadop-kernel-dev-da55f2cc78418dee88400aafbbaed19d7ac8188e.zip
op-kernel-dev-da55f2cc78418dee88400aafbbaed19d7ac8188e.tar.gz
blk-mq: use sbq wait queues instead of restart for driver tags
Commit 50e1dab86aa2 ("blk-mq-sched: fix starvation for multiple hardware queues and shared tags") fixed one starvation issue for shared tags. However, we can still get into a situation where we fail to allocate a tag because all tags are allocated but we don't have any pending requests on any hardware queue. One solution for this would be to restart all queues that share a tag map, but that really sucks. Ideally, we could just block and wait for a tag, but that isn't always possible from blk_mq_dispatch_rq_list(). However, we can still use the struct sbitmap_queue wait queues with a custom callback instead of blocking. This has a few benefits: 1. It avoids iterating over all hardware queues when completing an I/O, which the current restart code has to do. 2. It benefits from the existing rolling wakeup code. 3. It avoids punting to another thread just to have it block. Signed-off-by: Omar Sandoval <osandov@fb.com> Signed-off-by: Jens Axboe <axboe@fb.com>
Diffstat (limited to 'block')
-rw-r--r--block/blk-mq.c64
1 files changed, 55 insertions, 9 deletions
diff --git a/block/blk-mq.c b/block/blk-mq.c
index b29e7dc..9e6b064 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -904,6 +904,44 @@ static bool reorder_tags_to_front(struct list_head *list)
return first != NULL;
}
+static int blk_mq_dispatch_wake(wait_queue_t *wait, unsigned mode, int flags,
+ void *key)
+{
+ struct blk_mq_hw_ctx *hctx;
+
+ hctx = container_of(wait, struct blk_mq_hw_ctx, dispatch_wait);
+
+ list_del(&wait->task_list);
+ clear_bit_unlock(BLK_MQ_S_TAG_WAITING, &hctx->state);
+ blk_mq_run_hw_queue(hctx, true);
+ return 1;
+}
+
+static bool blk_mq_dispatch_wait_add(struct blk_mq_hw_ctx *hctx)
+{
+ struct sbq_wait_state *ws;
+
+ /*
+ * The TAG_WAITING bit serves as a lock protecting hctx->dispatch_wait.
+ * The thread which wins the race to grab this bit adds the hardware
+ * queue to the wait queue.
+ */
+ if (test_bit(BLK_MQ_S_TAG_WAITING, &hctx->state) ||
+ test_and_set_bit_lock(BLK_MQ_S_TAG_WAITING, &hctx->state))
+ return false;
+
+ init_waitqueue_func_entry(&hctx->dispatch_wait, blk_mq_dispatch_wake);
+ ws = bt_wait_ptr(&hctx->tags->bitmap_tags, hctx);
+
+ /*
+ * As soon as this returns, it's no longer safe to fiddle with
+ * hctx->dispatch_wait, since a completion can wake up the wait queue
+ * and unlock the bit.
+ */
+ add_wait_queue(&ws->wait, &hctx->dispatch_wait);
+ return true;
+}
+
bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
{
struct request_queue *q = hctx->queue;
@@ -931,15 +969,22 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
continue;
/*
- * We failed getting a driver tag. Mark the queue(s)
- * as needing a restart. Retry getting a tag again,
- * in case the needed IO completed right before we
- * marked the queue as needing a restart.
+ * The initial allocation attempt failed, so we need to
+ * rerun the hardware queue when a tag is freed.
*/
- blk_mq_sched_mark_restart(hctx);
- if (!blk_mq_get_driver_tag(rq, &hctx, false))
+ if (blk_mq_dispatch_wait_add(hctx)) {
+ /*
+ * It's possible that a tag was freed in the
+ * window between the allocation failure and
+ * adding the hardware queue to the wait queue.
+ */
+ if (!blk_mq_get_driver_tag(rq, &hctx, false))
+ break;
+ } else {
break;
+ }
}
+
list_del_init(&rq->queuelist);
bd.rq = rq;
@@ -995,10 +1040,11 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
*
* blk_mq_run_hw_queue() already checks the STOPPED bit
*
- * If RESTART is set, then let completion restart the queue
- * instead of potentially looping here.
+ * If RESTART or TAG_WAITING is set, then let completion restart
+ * the queue instead of potentially looping here.
*/
- if (!blk_mq_sched_needs_restart(hctx))
+ if (!blk_mq_sched_needs_restart(hctx) &&
+ !test_bit(BLK_MQ_S_TAG_WAITING, &hctx->state))
blk_mq_run_hw_queue(hctx, true);
}
OpenPOWER on IntegriCloud