From 7e782af57649f8a8e943d80104c946a5cd7af7cc Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Mon, 1 Jul 2013 15:16:26 +0200 Subject: [SCSI] Return ENODATA on medium error When a medium error is detected the SCSI stack should return ENODATA to the upper layers. [jejb: fix whitespace error] Signed-off-by: Hannes Reinecke Signed-off-by: James Bottomley --- drivers/md/dm-mpath.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'drivers/md/dm-mpath.c') diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 5adede17ddf6..b759a127f9c3 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -1261,6 +1261,20 @@ static void activate_path(struct work_struct *work) pg_init_done, pgpath); } +static int noretry_error(int error) +{ + switch (error) { + case -EOPNOTSUPP: + case -EREMOTEIO: + case -EILSEQ: + case -ENODATA: + return 1; + } + + /* Anything else could be a path failure, so should be retried */ + return 0; +} + /* * end_io handling */ @@ -1284,7 +1298,7 @@ static int do_end_io(struct multipath *m, struct request *clone, if (!error && !clone->errors) return 0; /* I/O complete */ - if (error == -EOPNOTSUPP || error == -EREMOTEIO || error == -EILSEQ) + if (noretry_error(error)) return error; if (mpio->pgpath) -- cgit v1.2.3 From cc9d3c382bc1674884c2e5e468d51230a9503dee Mon Sep 17 00:00:00 2001 From: Jun'ichi Nomura Date: Fri, 13 Sep 2013 14:54:30 +0900 Subject: dm mpath: do not fail path on -ENOSPC Since ENOSPC is a target-side error, dm-mpath should just pass the error information to upper layer instead of retrying itself with path failover. Otherwise it will end up failing all paths down while path checkers find all paths ok. ENOSPC can now be returned from SCSI device after commit a9d6ceb8 ("[SCSI] return ENOSPC on thin provisioning failure"). Signed-off-by: Jun'ichi Nomura Acked-by: Hannes Reinecke Signed-off-by: Mike Snitzer --- drivers/md/dm-mpath.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/md/dm-mpath.c') diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index b759a127f9c3..075747e25f77 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -1268,6 +1268,7 @@ static int noretry_error(int error) case -EREMOTEIO: case -EILSEQ: case -ENODATA: + case -ENOSPC: return 1; } -- cgit v1.2.3 From f84cb8a46a771f36a04a02c61ea635c968ed5f6a Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Thu, 19 Sep 2013 12:13:58 -0400 Subject: 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 Cc: Martin K. Petersen Cc: Hannes Reinecke Cc: stable@vger.kernel.org # 3.10+ --- drivers/md/dm-mpath.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'drivers/md/dm-mpath.c') 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); -- cgit v1.2.3 From f47908269fb53d522a956b78612a0037f5faf8e7 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Thu, 12 Sep 2013 18:06:12 -0400 Subject: dm: add reserved_rq_based_ios module parameter Allow user to change the number of IOs that are reserved by request-based DM's mempools by writing to this file: /sys/module/dm_mod/parameters/reserved_rq_based_ios The default value is RESERVED_REQUEST_BASED_IOS (256). The maximum allowed value is RESERVED_MAX_IOS (1024). Export dm_get_reserved_rq_based_ios() for use by DM targets and core code. Switch to sizing dm-mpath's mempool using DM core's configurable 'reserved_rq_based_ios'. Signed-off-by: Mike Snitzer Signed-off-by: Frank Mayhar Acked-by: Mikulas Patocka --- drivers/md/dm-mpath.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'drivers/md/dm-mpath.c') diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index e08be94959fd..de570a558764 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -7,6 +7,7 @@ #include +#include "dm.h" #include "dm-path-selector.h" #include "dm-uevent.h" @@ -116,8 +117,6 @@ struct dm_mpath_io { typedef int (*action_fn) (struct pgpath *pgpath); -#define MIN_IOS 256 /* Mempool size */ - static struct kmem_cache *_mpio_cache; static struct workqueue_struct *kmultipathd, *kmpath_handlerd; @@ -190,6 +189,7 @@ static void free_priority_group(struct priority_group *pg, static struct multipath *alloc_multipath(struct dm_target *ti) { struct multipath *m; + unsigned min_ios = dm_get_reserved_rq_based_ios(); m = kzalloc(sizeof(*m), GFP_KERNEL); if (m) { @@ -202,7 +202,7 @@ static struct multipath *alloc_multipath(struct dm_target *ti) INIT_WORK(&m->trigger_event, trigger_event); init_waitqueue_head(&m->pg_init_wait); mutex_init(&m->work_mutex); - m->mpio_pool = mempool_create_slab_pool(MIN_IOS, _mpio_cache); + m->mpio_pool = mempool_create_slab_pool(min_ios, _mpio_cache); if (!m->mpio_pool) { kfree(m); return NULL; -- cgit v1.2.3