[PATCH 13/13] dm, dm-mpath: Make it easier to detect unintended I/O request flushes

[Bart Van Assche <bart.vanassche@xxxxxxxxxxx>]

I/O errors triggered by multipathd incorrectly not enabling the
no-flush flag for DM_DEVICE_SUSPEND or DM_DEVICE_RESUME are hard to
debug. Add more logging to make it easier to debug this.

Signed-off-by: Bart Van Assche <bart.vanassche@xxxxxxxxxxx>
Cc: Hannes Reinecke <hare@xxxxxxxx>
---
 drivers/md/dm-mpath.c | 25 +++++++++++++++++++++----
 drivers/md/dm.c       |  3 +++
 2 files changed, 24 insertions(+), 4 deletions(-)

diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 57b467207741..7aebbf4ae7d5 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -442,6 +442,23 @@ static struct pgpath *choose_pgpath(struct multipath *m, size_t nr_bytes)
 }
 
 /*
+ * Note: dm_report_eio() is a macro instead of a function to make pr_debug()
+ * report the function name and line number of the function from which it has
+ * been invoked.
+ */
+#define dm_report_eio(m)						\
+({									\
+	struct mapped_device *md = dm_table_get_md((m)->ti->table);	\
+									\
+	pr_debug("%s: returning EIO; QIFNP = %d; SQIFNP = %d; DNFS = %d\n", \
+		 dm_device_name(md),					\
+		 test_bit(MPATHF_QUEUE_IF_NO_PATH, &(m)->flags),	\
+		 test_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &(m)->flags),	\
+		 dm_noflush_suspending((m)->ti));			\
+	-EIO;								\
+})
+
+/*
  * Map cloned requests (request-based multipath)
  */
 static int multipath_clone_and_map(struct dm_target *ti, struct request *rq,
@@ -466,7 +483,7 @@ static int multipath_clone_and_map(struct dm_target *ti, struct request *rq,
 			pr_debug("no path - requeueing\n");
 			return DM_MAPIO_DELAY_REQUEUE;
 		}
-		return -EIO;	/* Failed */
+		return dm_report_eio(m);	/* Failed */
 	} else if (test_bit(MPATHF_QUEUE_IO, &m->flags) ||
 		   test_bit(MPATHF_PG_INIT_REQUIRED, &m->flags)) {
 		return pg_init_all_paths(m) == 0 ? DM_MAPIO_REQUEUE :
@@ -542,7 +559,7 @@ static int __multipath_map_bio(struct multipath *m, struct bio *bio, struct dm_m
 	if (!pgpath) {
 		if (test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags))
 			return DM_MAPIO_REQUEUE;
-		return -EIO;
+		return dm_report_eio(m);
 	}
 
 	mpio->pgpath = pgpath;
@@ -1481,7 +1498,7 @@ static int do_end_io(struct multipath *m, struct request *clone,
 
 	if (atomic_read(&m->nr_valid_paths) == 0 &&
 	    !test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags))
-		r = -EIO;
+		r = dm_report_eio(m);
 
 	return r;
 }
@@ -1524,7 +1541,7 @@ static int do_end_io_bio(struct multipath *m, struct bio *clone,
 
 	if (atomic_read(&m->nr_valid_paths) == 0 &&
 	    !test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags))
-		return -EIO;
+		return dm_report_eio(m);
 
 	/* Queue for the daemon to resubmit */
 	dm_bio_restore(get_bio_details_from_bio(clone), clone);
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 7161c7804363..9f0aed0e1bf0 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -2158,6 +2158,9 @@ static int __dm_suspend(struct mapped_device *md, struct dm_table *map,
 	 */
 	if (noflush)
 		set_bit(DMF_NOFLUSH_SUSPENDING, &md->flags);
+	else
+		pr_debug("%s: suspending without no-flush flag\n",
+			 dm_device_name(md));
 
 	/*
 	 * This gets reverted if there's an error later and the targets
-- 
2.12.2

--
dm-devel mailing list
dm-devel@xxxxxxxxxx
https://www.redhat.com/mailman/listinfo/dm-devel