dm rq: add DM_MAPIO_DELAY_REQUEUE to delay requeue of blk-mq requests

Otherwise blk-mq will immediately dispatch requests that are requeued
via a BLK_MQ_RQ_QUEUE_BUSY return from blk_mq_ops .queue_rq.

Delayed requeue is implemented using blk_mq_delay_kick_requeue_list()
with a delay of 5 secs.  In the context of DM multipath (all paths down)
it doesn't make any sense to requeue more quickly.

Signed-off-by: Mike Snitzer <snitzer@redhat.com>

diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index 0d301d5a4d0bda3a3c0be028e32a65c1c21947c2..dbced7b159317a4b6701418d94dc1e09cd9f44b2 100644 (file)
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -336,20 +336,21 @@ static void dm_old_requeue_request(struct request *rq)
        spin_unlock_irqrestore(q->queue_lock, flags);
 }
 
-static void dm_mq_requeue_request(struct request *rq)
+static void dm_mq_delay_requeue_request(struct request *rq, unsigned long msecs)
 {
        struct request_queue *q = rq->q;
        unsigned long flags;
 
        blk_mq_requeue_request(rq);
+
        spin_lock_irqsave(q->queue_lock, flags);
        if (!blk_queue_stopped(q))
-               blk_mq_kick_requeue_list(q);
+               blk_mq_delay_kick_requeue_list(q, msecs);
        spin_unlock_irqrestore(q->queue_lock, flags);
 }
 
 static void dm_requeue_original_request(struct mapped_device *md,
-                                       struct request *rq)
+                                       struct request *rq, bool delay_requeue)
 {
        int rw = rq_data_dir(rq);
 
@@ -359,7 +360,7 @@ static void dm_requeue_original_request(struct mapped_device *md,
        if (!rq->q->mq_ops)
                dm_old_requeue_request(rq);
        else
-               dm_mq_requeue_request(rq);
+               dm_mq_delay_requeue_request(rq, delay_requeue ? 5000 : 0);
 
        rq_completed(md, rw, false);
 }
@@ -389,7 +390,7 @@ static void dm_done(struct request *clone, int error, bool mapped)
                return;
        else if (r == DM_ENDIO_REQUEUE)
                /* The target wants to requeue the I/O */
-               dm_requeue_original_request(tio->md, tio->orig);
+               dm_requeue_original_request(tio->md, tio->orig, false);
        else {
                DMWARN("unimplemented target endio return value: %d", r);
                BUG();
@@ -629,8 +630,8 @@ static int dm_old_prep_fn(struct request_queue *q, struct request *rq)
 
 /*
  * Returns:
- * 0                : the request has been processed
- * DM_MAPIO_REQUEUE : the original request needs to be requeued
+ * DM_MAPIO_*       : the request has been processed as indicated
+ * DM_MAPIO_REQUEUE : the original request needs to be immediately requeued
  * < 0              : the request was completed due to failure
  */
 static int map_request(struct dm_rq_target_io *tio, struct request *rq,
@@ -643,6 +644,8 @@ static int map_request(struct dm_rq_target_io *tio, struct request *rq,
        if (tio->clone) {
                clone = tio->clone;
                r = ti->type->map_rq(ti, clone, &tio->info);
+               if (r == DM_MAPIO_DELAY_REQUEUE)
+                       return DM_MAPIO_REQUEUE; /* .request_fn requeue is always immediate */
        } else {
                r = ti->type->clone_and_map_rq(ti, rq, &tio->info, &clone);
                if (r < 0) {
@@ -650,9 +653,8 @@ static int map_request(struct dm_rq_target_io *tio, struct request *rq,
                        dm_kill_unmapped_request(rq, r);
                        return r;
                }
-               if (r != DM_MAPIO_REMAPPED)
-                       return r;
-               if (setup_clone(clone, rq, tio, GFP_ATOMIC)) {
+               if (r == DM_MAPIO_REMAPPED &&
+                   setup_clone(clone, rq, tio, GFP_ATOMIC)) {
                        /* -ENOMEM */
                        ti->type->release_clone_rq(clone);
                        return DM_MAPIO_REQUEUE;
@@ -671,7 +673,10 @@ static int map_request(struct dm_rq_target_io *tio, struct request *rq,
                break;
        case DM_MAPIO_REQUEUE:
                /* The target wants to requeue the I/O */
-               dm_requeue_original_request(md, tio->orig);
+               break;
+       case DM_MAPIO_DELAY_REQUEUE:
+               /* The target wants to requeue the I/O after a delay */
+               dm_requeue_original_request(md, tio->orig, true);
                break;
        default:
                if (r > 0) {
@@ -681,10 +686,9 @@ static int map_request(struct dm_rq_target_io *tio, struct request *rq,
 
                /* The target wants to complete the I/O */
                dm_kill_unmapped_request(rq, r);
-               return r;
        }
 
-       return 0;
+       return r;
 }
 
 static void dm_start_request(struct mapped_device *md, struct request *orig)
@@ -727,7 +731,7 @@ static void map_tio_request(struct kthread_work *work)
        struct mapped_device *md = tio->md;
 
        if (map_request(tio, rq, md) == DM_MAPIO_REQUEUE)
-               dm_requeue_original_request(md, rq);
+               dm_requeue_original_request(md, rq, false);
 }
 
 ssize_t dm_attr_rq_based_seq_io_merge_deadline_show(struct mapped_device *md, char *buf)

diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 91acfce74a220010549536edde925ef9e3ec81c0..ef7962e84444d90429afbb0d5e53fd7eaf7d7668 100644 (file)
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -590,6 +590,7 @@ extern struct ratelimit_state dm_ratelimit_state;
 #define DM_MAPIO_SUBMITTED     0
 #define DM_MAPIO_REMAPPED      1
 #define DM_MAPIO_REQUEUE       DM_ENDIO_REQUEUE
+#define DM_MAPIO_DELAY_REQUEUE 3
 
 #define dm_sector_div64(x, y)( \
 { \