[PATCH] md: improvements to raid5 handling of read errors

Two refinements to the 'attempt-overwrite-on-read-error' mechanism.
1/ If the array is read-only, don't attempt an over-write.
2/ If there are more than max_nr_stripes read errors on a device with
   no success, fail the drive.  This will make sure a dead
   drive will be eventually kicked even when we aren't trying
   to rewrite (which would normally kick a dead drive more quickly.

Signed-off-by: Neil Brown <neilb@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This commit is contained in:
NeilBrown 2005-11-08 21:39:31 -08:00 committed by Linus Torvalds
parent 007583c925
commit ba22dcbf10
3 changed files with 21 additions and 8 deletions

View File

@ -1582,6 +1582,7 @@ static mdk_rdev_t *md_import_device(dev_t newdev, int super_format, int super_mi
rdev->in_sync = 0;
rdev->data_offset = 0;
atomic_set(&rdev->nr_pending, 0);
atomic_set(&rdev->read_errors, 0);
size = rdev->bdev->bd_inode->i_size >> BLOCK_SIZE_BITS;
if (!size) {

View File

@ -420,21 +420,29 @@ static int raid5_end_read_request(struct bio * bi, unsigned int bytes_done,
clear_bit(R5_ReadError, &sh->dev[i].flags);
clear_bit(R5_ReWrite, &sh->dev[i].flags);
}
if (atomic_read(&conf->disks[i].rdev->read_errors))
atomic_set(&conf->disks[i].rdev->read_errors, 0);
} else {
int retry = 0;
clear_bit(R5_UPTODATE, &sh->dev[i].flags);
if (conf->mddev->degraded) {
atomic_inc(&conf->disks[i].rdev->read_errors);
if (conf->mddev->degraded)
printk("R5: read error not correctable.\n");
clear_bit(R5_ReadError, &sh->dev[i].flags);
clear_bit(R5_ReWrite, &sh->dev[i].flags);
md_error(conf->mddev, conf->disks[i].rdev);
} else if (test_bit(R5_ReWrite, &sh->dev[i].flags)) {
else if (test_bit(R5_ReWrite, &sh->dev[i].flags))
/* Oh, no!!! */
printk("R5: read error NOT corrected!!\n");
else if (atomic_read(&conf->disks[i].rdev->read_errors)
> conf->max_nr_stripes)
printk("raid5: Too many read errors, failing device.\n");
else
retry = 1;
if (retry)
set_bit(R5_ReadError, &sh->dev[i].flags);
else {
clear_bit(R5_ReadError, &sh->dev[i].flags);
clear_bit(R5_ReWrite, &sh->dev[i].flags);
md_error(conf->mddev, conf->disks[i].rdev);
} else
set_bit(R5_ReadError, &sh->dev[i].flags);
}
}
rdev_dec_pending(conf->disks[i].rdev, conf->mddev);
#if 0
@ -1328,7 +1336,8 @@ static void handle_stripe(struct stripe_head *sh)
/* If the failed drive is just a ReadError, then we might need to progress
* the repair/check process
*/
if (failed == 1 && test_bit(R5_ReadError, &sh->dev[failed_num].flags)
if (failed == 1 && ! conf->mddev->ro &&
test_bit(R5_ReadError, &sh->dev[failed_num].flags)
&& !test_bit(R5_LOCKED, &sh->dev[failed_num].flags)
&& test_bit(R5_UPTODATE, &sh->dev[failed_num].flags)
) {

View File

@ -134,6 +134,9 @@ struct mdk_rdev_s
* only maintained for arrays that
* support hot removal
*/
atomic_t read_errors; /* number of consecutive read errors that
* we have tried to ignore.
*/
};
typedef struct mdk_personality_s mdk_personality_t;