rqdm: fix stall when ->map_rq returns DM_MAPIO_REQUEUE
PATCH 1/1 rqdm: fix stall when ->map_rq returns DM_MAPIO_REQUEUE
Hi Alasdair,
This patch fixes the problem that system may stall if target's ->map_rq returns DM_MAPIO_REQUEUE in map_request().
E.g. stall happens on 1 CPU box when a dm-mpath device with queue_if_no_path
bounces between all-paths-down and paths-up on I/O load.
It is for 2.6.33-rc6, and no dependency on your editing patches. Please review and apply.
When target's ->map_rq returns DM_MAPIO_REQUEUE, map_request() requeues the request and returns to dm_request_fn(). Then, dm_request_fn() doesn't exit the I/O dispatching loop and continues processing the requeued request again.
This map and requeue loop can be done with interrupt disabled, so 1 CPU system can be stalled if this situation happens.
For example, commands below can stall my 1 CPU box within 1 minute or so:
# dmsetup table mp mp: 0 2097152 multipath 1 queue_if_no_path 0 1 1 service-time 0 1 2 8:144 1 1 # while true; do dd if=/dev/mapper/mp of=/dev/null bs=1M count=100; done & # while true; do \
Quoted 5 lines
dmsetup message mp 0 "
fail_path8:144" \
dmsetup suspend --noflush mp \
dmsetup resume mp \
dmsetup message mp 0 "reinstate_path8:144" \
done
To fix the problem above, this patch changes dm_request_fn() to exit the I/O dispatching loop once if a request is requeued in map_request().
--- drivers/md/dm.c | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-)
drivers/md/dm.c +17 -4
@@ -1595,10 +1595,15 @@ static int dm_prep_fn(struct request_quereturn BLKPREP_OK ; } -static void map_request (struct dm_target *ti,struct request *clone, -struct mapped_device *md) +/* +* Returns: +* 0 : the request has been processed (not requeued) +* !0 : the request has been requeued +*/ +static int map_request (struct dm_target *ti,struct request *clone, +struct mapped_device *md) { -int r; +int r, requeued =0 ;struct dm_rq_target_io *tio = clone->end_io_data;/*
@@ -1625,6 +1630,7 @@ static void map_request(struct dm_targetcase DM_MAPIO_REQUEUE :/* The target wants to requeue the I/O */ dm_requeue_unmapped_request (clone); + requeued =1 ;break ;default :if (r >0 ) {
@@ -1636,6 +1642,8 @@ static void map_request(struct dm_targetdm_kill_unmapped_request (clone, r);break ; } + +return requeued; }/*
@@ -1677,12 +1685,17 @@ static void dm_request_fn(struct requestatomic_inc (&md->pending[rq_data_dir (clone)]);spin_unlock (q->queue_lock); -map_request (ti, clone, md); +if (map_request (ti, clone, md)) + goto requeued; +spin_lock_irq (q->queue_lock); } goto out; +requeued: +spin_lock_irq (q->queue_lock); + plug_and_out:if (!elv_queue_empty (q))/* Some requests still remain, retry later */