In order to prevent the degraded raid from becaming fail,we should first
set badsector instead of ejecting the rdev when read fail.
Signed-off-by: majianpeng <majianpeng@xxxxxxxxx>
---
drivers/md/raid5.c | 10 ++++++++--
1 files changed, 8 insertions(+), 2 deletions(-)
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index d267672..89cfd73 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1737,6 +1737,7 @@ static void raid5_end_read_request(struct bio * bi, int error)
} else {
const char *bdn = bdevname(rdev->bdev, b);
int retry = 0;
+ int set_bad = 0;
clear_bit(R5_UPTODATE, &sh->dev[i].flags);
atomic_inc(&rdev->read_errors);
@@ -1748,7 +1749,8 @@ static void raid5_end_read_request(struct bio * bi, int error)
mdname(conf->mddev),
(unsigned long long)s,
bdn);
- else if (conf->mddev->degraded >= conf->max_degraded)
+ else if (conf->mddev->degraded >= conf->max_degraded) {
+ set_bad = 1;
printk_ratelimited(
KERN_WARNING
"md/raid:%s: read error not correctable "
@@ -1756,6 +1758,7 @@ static void raid5_end_read_request(struct bio * bi, int error)
mdname(conf->mddev),
(unsigned long long)s,
bdn);
+ }
else if (test_bit(R5_ReWrite, &sh->dev[i].flags))
/* Oh, no!!! */
printk_ratelimited(
@@ -1777,7 +1780,10 @@ static void raid5_end_read_request(struct bio * bi, int error)
else {
clear_bit(R5_ReadError, &sh->dev[i].flags);
clear_bit(R5_ReWrite, &sh->dev[i].flags);
- md_error(conf->mddev, rdev);
+ if (!(set_bad && test_bit(In_sync, &rdev->flags)
+ && rdev_set_badblocks(rdev,
+ sh->sector, STRIPE_SECTORS, 0)))
+ md_error(conf->mddev, rdev);
}
}
rdev_dec_pending(rdev, conf->mddev);
--
1.7.5.4
--------------
majianpeng
2012-05-26
--
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
