The attached patch makes sure that resync/recovery get aborted (and
status recorded correctly) when there are no spare drives left (due to
the failure of a spare during a resync). Previously, if a spare failed
during a resync, the resync would continue until completed (and would
appear to be successful).
Also, there was an erroneous usage of master_bio->bi_bdev field (which
is not always properly set) that has been changed to the simpler
comparison vs. r1_bio->read_disk (as is done in raid1_end_request). I
think Neil has already addressed this issue in another patch that has
been pushed to Andrew...
Thanks,
Paul
--- raid1.c.PRISTINE Tue Feb 24 16:10:26 2004
+++ raid1.c Wed Feb 25 16:22:34 2004
@@ -818,6 +818,8 @@ static void sync_request_write(mddev_t *
put_buf(r1_bio);
return;
}
+ /* assume failure until we find a drive to write this to */
+ clear_bit(R1BIO_Uptodate, &r1_bio->state);
spin_lock_irq(&conf->device_lock);
for (i = 0; i < disks ; i++) {
@@ -825,7 +827,7 @@ static void sync_request_write(mddev_t *
if (!conf->mirrors[i].rdev ||
conf->mirrors[i].rdev->faulty)
continue;
- if (conf->mirrors[i].rdev->bdev == bio->bi_bdev)
+ if (i == r1_bio->read_disk)
/*
* we read from here, no need to write
*/
@@ -838,6 +840,8 @@ static void sync_request_write(mddev_t *
continue;
atomic_inc(&conf->mirrors[i].rdev->nr_pending);
r1_bio->write_bios[i] = bio;
+ /* we found a drive to write to */
+ set_bit(R1BIO_Uptodate, &r1_bio->state);
}
spin_unlock_irq(&conf->device_lock);
@@ -859,7 +863,8 @@ static void sync_request_write(mddev_t *
}
if (atomic_dec_and_test(&r1_bio->remaining)) {
- md_done_sync(mddev, r1_bio->master_bio->bi_size >> 9, 1);
+ md_done_sync(mddev, r1_bio->master_bio->bi_size >> 9,
+ test_bit(R1BIO_Uptodate, &r1_bio->state));
put_buf(r1_bio);
}
}
