In function raid5_end_read_request(),when degraded raid read failed,it
will call md_error in order to remove this disk. If so,the degraded raid
will become failed raid and lost all data.
Then using badsector function to avoid.
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 f351422..337eb03 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1695,6 +1695,7 @@ 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);
@@ -1707,7 +1708,9 @@ static void raid5_end_read_request(struct bio * bi, int error)
(unsigned long long)(sh->sector
+ rdev->data_offset),
bdn);
- else if (conf->mddev->degraded >= conf->max_degraded)
+ else if (conf->mddev->degraded >= conf->max_degraded) {
+ /*Not remove disk,instead of set badblocks */
+ set_bad = 1;
printk_ratelimited(
KERN_WARNING
"md/raid:%s: read error not correctable "
@@ -1716,6 +1719,7 @@ static void raid5_end_read_request(struct bio * bi, int error)
(unsigned long long)(sh->sector
+ rdev->data_offset),
bdn);
+ }
else if (test_bit(R5_ReWrite, &sh->dev[i].flags))
/* Oh, no!!! */
printk_ratelimited(
@@ -1738,7 +1742,9 @@ 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 && 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
2012-05-22
--
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
