md/raid10: print more useful messages on device failure.

When we get a read error on a device in a RAID10, and attempting to
repair the error fails, print more useful messages about why it
failed.

Signed-off-by: Robert Becker <Rob.Becker@riverbed.com>
Signed-off-by: NeilBrown <neilb@suse.de>

1 files changed, 29 insertions, 3 deletions

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index d9e28a65af58..670449f7411f 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1488,6 +1488,7 @@ static void fix_read_error(conf_t *conf, mddev_t *mddev, r10bio_t *r10_bio)
                 /* write it back and re-read */
                 rcu_read_lock();
                 while (sl != r10_bio->read_slot) {
+                        char b[BDEVNAME_SIZE];
                         int d;
                         if (sl==0)
                                 sl = conf->copies;
@@ -1503,9 +1504,21 @@ static void fix_read_error(conf_t *conf, mddev_t *mddev, r10bio_t *r10_bio)
                                                  r10_bio->devs[sl].addr +
                                                  sect + rdev->data_offset,
                                                  s<<9, conf->tmppage, WRITE)
-                                    == 0)
+                                    == 0) {
                                         /* Well, this device is dead */
+                                        printk(KERN_NOTICE
+                                               "raid10:%s: read correction "
+                                               "write failed"
+                                               " (%d sectors at %llu on %s)\n",
+                                               mdname(mddev), s,
+                                               (unsigned long long)(sect+
+                                               rdev->data_offset),
+                                               bdevname(rdev->bdev, b));
+                                        printk(KERN_NOTICE "raid10:%s: failing "
+                                               "drive\n",
+                                               bdevname(rdev->bdev, b));
                                         md_error(mddev, rdev);
+                                }
                                 rdev_dec_pending(rdev, mddev);
                                 rcu_read_lock();
                         }
@@ -1526,10 +1539,22 @@ static void fix_read_error(conf_t *conf, mddev_t *mddev, r10bio_t *r10_bio)
                                 if (sync_page_io(rdev->bdev,
                                                  r10_bio->devs[sl].addr +
                                                  sect + rdev->data_offset,
-                                                 s<<9, conf->tmppage, READ) == 0)
+                                                 s<<9, conf->tmppage,
+                                                 READ) == 0) {
                                         /* Well, this device is dead */
+                                        printk(KERN_NOTICE
+                                               "raid10:%s: unable to read back "
+                                               "corrected sectors"
+                                               " (%d sectors at %llu on %s)\n",
+                                               mdname(mddev), s,
+                                               (unsigned long long)(sect+
+                                                    rdev->data_offset),
+                                               bdevname(rdev->bdev, b));
+                                        printk(KERN_NOTICE "raid10:%s: failing drive\n",
+                                               bdevname(rdev->bdev, b));
+
                                         md_error(mddev, rdev);
-                                else
+                                } else {
                                         printk(KERN_INFO
                                                "raid10:%s: read error corrected"
                                                " (%d sectors at %llu on %s)\n",
@@ -1537,6 +1562,7 @@ static void fix_read_error(conf_t *conf, mddev_t *mddev, r10bio_t *r10_bio)
                                                (unsigned long long)(sect+
                                                     rdev->data_offset),
                                                bdevname(rdev->bdev, b));
+                                }
 
                                 rdev_dec_pending(rdev, mddev);
                                 rcu_read_lock();