summaryrefslogtreecommitdiffstats
path: root/drivers/md
diff options
context:
space:
mode:
authorNeilBrown <neilb@suse.de>2006-01-06 00:20:18 -0800
committerLinus Torvalds <torvalds@g5.osdl.org>2006-01-06 08:34:03 -0800
commitd69762e98456b71167865db9e33e732a28dd36ab (patch)
treea93c3872d23db70e7e6089328cafd3eebba6aadb /drivers/md
parentca65b73bd9c301d243df93780f7b26579e6c9204 (diff)
[PATCH] md: improve handing of read errors with raid6
This is a simple port of match functionality across from raid5. If we get a read error, we don't kick the drive straight away, but try to over-write with good data first. Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Diffstat (limited to 'drivers/md')
-rw-r--r--drivers/md/raid6main.c70
1 files changed, 66 insertions, 4 deletions
diff --git a/drivers/md/raid6main.c b/drivers/md/raid6main.c
index 52e8796bb8a..7a51553d8be 100644
--- a/drivers/md/raid6main.c
+++ b/drivers/md/raid6main.c
@@ -367,8 +367,8 @@ static void shrink_stripes(raid6_conf_t *conf)
conf->slab_cache = NULL;
}
-static int raid6_end_read_request (struct bio * bi, unsigned int bytes_done,
- int error)
+static int raid6_end_read_request(struct bio * bi, unsigned int bytes_done,
+ int error)
{
struct stripe_head *sh = bi->bi_private;
raid6_conf_t *conf = sh->raid_conf;
@@ -420,9 +420,35 @@ static int raid6_end_read_request (struct bio * bi, unsigned int bytes_done,
#else
set_bit(R5_UPTODATE, &sh->dev[i].flags);
#endif
+ if (test_bit(R5_ReadError, &sh->dev[i].flags)) {
+ printk(KERN_INFO "raid6: read error corrected!!\n");
+ 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 {
- md_error(conf->mddev, conf->disks[i].rdev);
+ int retry = 0;
clear_bit(R5_UPTODATE, &sh->dev[i].flags);
+ atomic_inc(&conf->disks[i].rdev->read_errors);
+ if (conf->mddev->degraded)
+ printk(KERN_WARNING "raid6: read error not correctable.\n");
+ else if (test_bit(R5_ReWrite, &sh->dev[i].flags))
+ /* Oh, no!!! */
+ printk(KERN_WARNING "raid6: read error NOT corrected!!\n");
+ else if (atomic_read(&conf->disks[i].rdev->read_errors)
+ > conf->max_nr_stripes)
+ printk(KERN_WARNING
+ "raid6: 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);
+ }
}
rdev_dec_pending(conf->disks[i].rdev, conf->mddev);
#if 0
@@ -1079,6 +1105,12 @@ static void handle_stripe(struct stripe_head *sh, struct page *tmp_page)
if (dev->written) written++;
rdev = conf->disks[i].rdev; /* FIXME, should I be looking rdev */
if (!rdev || !test_bit(In_sync, &rdev->flags)) {
+ /* The ReadError flag will just be confusing now */
+ clear_bit(R5_ReadError, &dev->flags);
+ clear_bit(R5_ReWrite, &dev->flags);
+ }
+ if (!rdev || !test_bit(In_sync, &rdev->flags)
+ || test_bit(R5_ReadError, &dev->flags)) {
if ( failed < 2 )
failed_num[failed] = i;
failed++;
@@ -1095,6 +1127,14 @@ static void handle_stripe(struct stripe_head *sh, struct page *tmp_page)
if (failed > 2 && to_read+to_write+written) {
for (i=disks; i--; ) {
int bitmap_end = 0;
+
+ if (test_bit(R5_ReadError, &sh->dev[i].flags)) {
+ mdk_rdev_t *rdev = conf->disks[i].rdev;
+ if (rdev && test_bit(In_sync, &rdev->flags))
+ /* multiple read failures in one stripe */
+ md_error(conf->mddev, rdev);
+ }
+
spin_lock_irq(&conf->device_lock);
/* fail all writes first */
bi = sh->dev[i].towrite;
@@ -1130,7 +1170,8 @@ static void handle_stripe(struct stripe_head *sh, struct page *tmp_page)
}
/* fail any reads if this device is non-operational */
- if (!test_bit(R5_Insync, &sh->dev[i].flags)) {
+ if (!test_bit(R5_Insync, &sh->dev[i].flags) ||
+ test_bit(R5_ReadError, &sh->dev[i].flags)) {
bi = sh->dev[i].toread;
sh->dev[i].toread = NULL;
if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
@@ -1457,6 +1498,27 @@ static void handle_stripe(struct stripe_head *sh, struct page *tmp_page)
clear_bit(STRIPE_SYNCING, &sh->state);
}
+ /* If the failed drives are just a ReadError, then we might need
+ * to progress the repair/check process
+ */
+ if (failed <= 2 && ! conf->mddev->ro)
+ for (i=0; i<failed;i++) {
+ dev = &sh->dev[failed_num[i]];
+ if (test_bit(R5_ReadError, &dev->flags)
+ && !test_bit(R5_LOCKED, &dev->flags)
+ && test_bit(R5_UPTODATE, &dev->flags)
+ ) {
+ if (!test_bit(R5_ReWrite, &dev->flags)) {
+ set_bit(R5_Wantwrite, &dev->flags);
+ set_bit(R5_ReWrite, &dev->flags);
+ set_bit(R5_LOCKED, &dev->flags);
+ } else {
+ /* let's read it back */
+ set_bit(R5_Wantread, &dev->flags);
+ set_bit(R5_LOCKED, &dev->flags);
+ }
+ }
+ }
spin_unlock(&sh->lock);
while ((bi=return_bi)) {