aboutsummaryrefslogtreecommitdiffstats
path: root/drivers
diff options
context:
space:
mode:
authorRobert Becker <Rob.Becker@riverbed.com>2009-12-13 20:49:57 -0500
committerNeilBrown <neilb@suse.de>2009-12-13 20:51:41 -0500
commit67b8dc4b06b0e97df55fd76e209f34f9a52e820e (patch)
treec205f668bbe9752af1c140009200aef2019fed39 /drivers
parentffa23322b1596bb1a115e767d4251b62842adc23 (diff)
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>
Diffstat (limited to 'drivers')
-rw-r--r--drivers/md/raid10.c32
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)
1488 /* write it back and re-read */ 1488 /* write it back and re-read */
1489 rcu_read_lock(); 1489 rcu_read_lock();
1490 while (sl != r10_bio->read_slot) { 1490 while (sl != r10_bio->read_slot) {
1491 char b[BDEVNAME_SIZE];
1491 int d; 1492 int d;
1492 if (sl==0) 1493 if (sl==0)
1493 sl = conf->copies; 1494 sl = conf->copies;
@@ -1503,9 +1504,21 @@ static void fix_read_error(conf_t *conf, mddev_t *mddev, r10bio_t *r10_bio)
1503 r10_bio->devs[sl].addr + 1504 r10_bio->devs[sl].addr +
1504 sect + rdev->data_offset, 1505 sect + rdev->data_offset,
1505 s<<9, conf->tmppage, WRITE) 1506 s<<9, conf->tmppage, WRITE)
1506 == 0) 1507 == 0) {
1507 /* Well, this device is dead */ 1508 /* Well, this device is dead */
1509 printk(KERN_NOTICE
1510 "raid10:%s: read correction "
1511 "write failed"
1512 " (%d sectors at %llu on %s)\n",
1513 mdname(mddev), s,
1514 (unsigned long long)(sect+
1515 rdev->data_offset),
1516 bdevname(rdev->bdev, b));
1517 printk(KERN_NOTICE "raid10:%s: failing "
1518 "drive\n",
1519 bdevname(rdev->bdev, b));
1508 md_error(mddev, rdev); 1520 md_error(mddev, rdev);
1521 }
1509 rdev_dec_pending(rdev, mddev); 1522 rdev_dec_pending(rdev, mddev);
1510 rcu_read_lock(); 1523 rcu_read_lock();
1511 } 1524 }
@@ -1526,10 +1539,22 @@ static void fix_read_error(conf_t *conf, mddev_t *mddev, r10bio_t *r10_bio)
1526 if (sync_page_io(rdev->bdev, 1539 if (sync_page_io(rdev->bdev,
1527 r10_bio->devs[sl].addr + 1540 r10_bio->devs[sl].addr +
1528 sect + rdev->data_offset, 1541 sect + rdev->data_offset,
1529 s<<9, conf->tmppage, READ) == 0) 1542 s<<9, conf->tmppage,
1543 READ) == 0) {
1530 /* Well, this device is dead */ 1544 /* Well, this device is dead */
1545 printk(KERN_NOTICE
1546 "raid10:%s: unable to read back "
1547 "corrected sectors"
1548 " (%d sectors at %llu on %s)\n",
1549 mdname(mddev), s,
1550 (unsigned long long)(sect+
1551 rdev->data_offset),
1552 bdevname(rdev->bdev, b));
1553 printk(KERN_NOTICE "raid10:%s: failing drive\n",
1554 bdevname(rdev->bdev, b));
1555
1531 md_error(mddev, rdev); 1556 md_error(mddev, rdev);
1532 else 1557 } else {
1533 printk(KERN_INFO 1558 printk(KERN_INFO
1534 "raid10:%s: read error corrected" 1559 "raid10:%s: read error corrected"
1535 " (%d sectors at %llu on %s)\n", 1560 " (%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)
1537 (unsigned long long)(sect+ 1562 (unsigned long long)(sect+
1538 rdev->data_offset), 1563 rdev->data_offset),
1539 bdevname(rdev->bdev, b)); 1564 bdevname(rdev->bdev, b));
1565 }
1540 1566
1541 rdev_dec_pending(rdev, mddev); 1567 rdev_dec_pending(rdev, mddev);
1542 rcu_read_lock(); 1568 rcu_read_lock();