summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorMike Snitzer <snitzer@redhat.com>2013-09-19 12:13:58 -0400
committerMike Snitzer <snitzer@redhat.com>2013-09-20 10:36:34 -0400
commitf84cb8a46a771f36a04a02c61ea635c968ed5f6a (patch)
treeaf75fbffdf13f3765f4d8ddc13494585533351f8
parent60e356f381954d79088d0455e357db48cfdd6857 (diff)
downloadlinux-f84cb8a46a771f36a04a02c61ea635c968ed5f6a.tar.gz
linux-f84cb8a46a771f36a04a02c61ea635c968ed5f6a.tar.bz2
linux-f84cb8a46a771f36a04a02c61ea635c968ed5f6a.zip
dm mpath: disable WRITE SAME if it fails
Workaround the SCSI layer's problematic WRITE SAME heuristics by disabling WRITE SAME in the DM multipath device's queue_limits if an underlying device disabled it. The WRITE SAME heuristics, with both the original commit 5db44863b6eb ("[SCSI] sd: Implement support for WRITE SAME") and the updated commit 66c28f971 ("[SCSI] sd: Update WRITE SAME heuristics"), default to enabling WRITE SAME(10) even without successfully determining it is supported. After the first failed WRITE SAME the SCSI layer will disable WRITE SAME for the device (by setting sdkp->device->no_write_same which results in 'max_write_same_sectors' in device's queue_limits to be set to 0). When a device is stacked ontop of such a SCSI device any changes to that SCSI device's queue_limits do not automatically propagate up the stack. As such, a DM multipath device will not have its WRITE SAME support disabled. This causes the block layer to continue to issue WRITE SAME requests to the mpath device which causes paths to fail and (if mpath IO isn't configured to queue when no paths are available) it will result in actual IO errors to the upper layers. This fix doesn't help configurations that have additional devices stacked ontop of the mpath device (e.g. LVM created linear DM devices ontop). A proper fix that restacks all the queue_limits from the bottom of the device stack up will need to be explored if SCSI will continue to use this model of optimistically allowing op codes and then disabling them after they fail for the first time. Before this patch: EXT4-fs (dm-6): mounted filesystem with ordered data mode. Opts: (null) device-mapper: multipath: XXX snitm debugging: got -EREMOTEIO (-121) device-mapper: multipath: XXX snitm debugging: failing WRITE SAME IO with error=-121 end_request: critical target error, dev dm-6, sector 528 dm-6: WRITE SAME failed. Manually zeroing. device-mapper: multipath: Failing path 8:112. end_request: I/O error, dev dm-6, sector 4616 dm-6: WRITE SAME failed. Manually zeroing. end_request: I/O error, dev dm-6, sector 4616 end_request: I/O error, dev dm-6, sector 5640 end_request: I/O error, dev dm-6, sector 6664 end_request: I/O error, dev dm-6, sector 7688 end_request: I/O error, dev dm-6, sector 524288 Buffer I/O error on device dm-6, logical block 65536 lost page write due to I/O error on dm-6 JBD2: Error -5 detected when updating journal superblock for dm-6-8. end_request: I/O error, dev dm-6, sector 524296 Aborting journal on device dm-6-8. end_request: I/O error, dev dm-6, sector 524288 Buffer I/O error on device dm-6, logical block 65536 lost page write due to I/O error on dm-6 JBD2: Error -5 detected when updating journal superblock for dm-6-8. # cat /sys/block/sdh/queue/write_same_max_bytes 0 # cat /sys/block/dm-6/queue/write_same_max_bytes 33553920 After this patch: EXT4-fs (dm-6): mounted filesystem with ordered data mode. Opts: (null) device-mapper: multipath: XXX snitm debugging: got -EREMOTEIO (-121) device-mapper: multipath: XXX snitm debugging: WRITE SAME I/O failed with error=-121 end_request: critical target error, dev dm-6, sector 528 dm-6: WRITE SAME failed. Manually zeroing. # cat /sys/block/sdh/queue/write_same_max_bytes 0 # cat /sys/block/dm-6/queue/write_same_max_bytes 0 It should be noted that WRITE SAME support wasn't enabled in DM multipath until v3.10. Signed-off-by: Mike Snitzer <snitzer@redhat.com> Cc: Martin K. Petersen <martin.petersen@oracle.com> Cc: Hannes Reinecke <hare@suse.de> Cc: stable@vger.kernel.org # 3.10+
-rw-r--r--drivers/md/dm-mpath.c11
-rw-r--r--drivers/md/dm.c11
-rw-r--r--include/linux/device-mapper.h3
3 files changed, 23 insertions, 2 deletions
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 075747e25f77..e08be94959fd 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -1299,8 +1299,17 @@ static int do_end_io(struct multipath *m, struct request *clone,
if (!error && !clone->errors)
return 0; /* I/O complete */
- if (noretry_error(error))
+ if (noretry_error(error)) {
+ if ((clone->cmd_flags & REQ_WRITE_SAME) &&
+ !clone->q->limits.max_write_same_sectors) {
+ struct queue_limits *limits;
+
+ /* device doesn't really support WRITE SAME, disable it */
+ limits = dm_get_queue_limits(dm_table_get_md(m->ti->table));
+ limits->max_write_same_sectors = 0;
+ }
return error;
+ }
if (mpio->pgpath)
fail_path(mpio->pgpath);
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 6a5e9ed2fcc3..7b0ccdc5d65c 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -2278,6 +2278,17 @@ struct target_type *dm_get_immutable_target_type(struct mapped_device *md)
}
/*
+ * The queue_limits are only valid as long as you have a reference
+ * count on 'md'.
+ */
+struct queue_limits *dm_get_queue_limits(struct mapped_device *md)
+{
+ BUG_ON(!atomic_read(&md->holders));
+ return &md->queue->limits;
+}
+EXPORT_SYMBOL_GPL(dm_get_queue_limits);
+
+/*
* Fully initialize a request-based queue (->elevator, ->request_fn, etc).
*/
static int dm_init_request_based_queue(struct mapped_device *md)
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 653073de09e3..ed419c62dde1 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -406,13 +406,14 @@ int dm_noflush_suspending(struct dm_target *ti);
union map_info *dm_get_mapinfo(struct bio *bio);
union map_info *dm_get_rq_mapinfo(struct request *rq);
+struct queue_limits *dm_get_queue_limits(struct mapped_device *md);
+
/*
* Geometry functions.
*/
int dm_get_geometry(struct mapped_device *md, struct hd_geometry *geo);
int dm_set_geometry(struct mapped_device *md, struct hd_geometry *geo);
-
/*-----------------------------------------------------------------
* Functions for manipulating device-mapper tables.
*---------------------------------------------------------------*/