| From knikanth@suse.de Mon Apr 19 11:23:07 2010 |
| From: Nikanth Karthikesan <knikanth@suse.de> |
| Date: Fri, 26 Mar 2010 12:03:13 +0530 |
| Subject: dm mpath: fix stall when requeueing io |
| To: stable@kernel.org |
| Cc: "Jun'ichi Nomura" <j-nomura@ce.jp.nec.com>, Kiyoshi Ueda <k-ueda@ct.jp.nec.com>, Alasdair G Kergon <agk@redhat.com> |
| Message-ID: <201003261203.13503.knikanth@suse.de> |
| |
| From: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> |
| |
| upstream commit 9eef87da2a8ea4920e0d913ff977cac064b68ee0 backported to |
| 2.6.32.10 by Nikanth Karthikesan <knikanth@suse.de> |
| |
| 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. |
| |
| 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 \ |
| > dmsetup message mp 0 "fail_path 8:144" \ |
| > dmsetup suspend --noflush mp \ |
| > dmsetup resume mp \ |
| > dmsetup message mp 0 "reinstate_path 8:144" \ |
| > 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(). |
| |
| Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> |
| Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> |
| Signed-off-by: Alasdair G Kergon <agk@redhat.com> |
| Signed-off-by: Nikanth Karthikesan <knikanth@suse.de> |
| Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de> |
| |
| --- |
| drivers/md/dm.c | 21 +++++++++++++++++---- |
| 1 file changed, 17 insertions(+), 4 deletions(-) |
| |
| --- a/drivers/md/dm.c |
| +++ b/drivers/md/dm.c |
| @@ -1487,10 +1487,15 @@ static int dm_prep_fn(struct request_que |
| return BLKPREP_OK; |
| } |
| |
| -static void map_request(struct dm_target *ti, struct request *rq, |
| - 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 *rq, |
| + struct mapped_device *md) |
| { |
| - int r; |
| + int r, requeued = 0; |
| struct request *clone = rq->special; |
| struct dm_rq_target_io *tio = clone->end_io_data; |
| |
| @@ -1516,6 +1521,7 @@ static void map_request(struct dm_target |
| case DM_MAPIO_REQUEUE: |
| /* The target wants to requeue the I/O */ |
| dm_requeue_unmapped_request(clone); |
| + requeued = 1; |
| break; |
| default: |
| if (r > 0) { |
| @@ -1527,6 +1533,8 @@ static void map_request(struct dm_target |
| dm_kill_unmapped_request(clone, r); |
| break; |
| } |
| + |
| + return requeued; |
| } |
| |
| /* |
| @@ -1568,12 +1576,17 @@ static void dm_request_fn(struct request |
| |
| blk_start_request(rq); |
| spin_unlock(q->queue_lock); |
| - map_request(ti, rq, md); |
| + if (map_request(ti, rq, 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 */ |