- Add a state flag 'external' to indicate that the metadata is managed
externally (by user-space) so important changes need to be
left of user-space to handle.
Alternates are non-persistant ('none') where there is no stable metadata -
after the array is stopped there is no record of it's status - and
internal which can be version 0.90 or version 1.x
These are selected by writing to the 'metadata' attribute.
- move the updating of superblocks (sync_sbs) to after we have checked if
there are any superblocks or not.
- New array state 'write_pending'. This means that the metadata records
the array as 'clean', but a write has been requested, so the metadata has
to be updated to record a 'dirty' array before the write can continue.
This change is reported to md by writing 'active' to the array_state
attribute.
- tidy up marking of sb_dirty:
- don't set sb_dirty when resync finishes as md_check_recovery
calls md_update_sb when the sync thread finishes anyway.
- Don't set sb_dirty in multipath_run as the array might not be dirty.
- don't mark superblock dirty when switching to 'clean' if there
is no internal superblock (if external, userspace can choose to
update the superblock whenever it chooses to).
Signed-off-by: Neil Brown <[EMAIL PROTECTED]>
### Diffstat output
./drivers/md/md.c | 77 +---
./include/linux/raid/md_k.h |3 +
2 files changed, 61 insertions(+), 19 deletions(-)
diff .prev/drivers/md/md.c ./drivers/md/md.c
--- .prev/drivers/md/md.c 2007-12-14 16:07:51.0 +1100
+++ ./drivers/md/md.c 2007-12-14 16:08:28.0 +1100
@@ -778,7 +778,8 @@ static int super_90_validate(mddev_t *md
mddev->major_version = 0;
mddev->minor_version = sb->minor_version;
mddev->patch_version = sb->patch_version;
- mddev->persistent = ! sb->not_persistent;
+ mddev->persistent = 1;
+ mddev->external = 0;
mddev->chunk_size = sb->chunk_size;
mddev->ctime = sb->ctime;
mddev->utime = sb->utime;
@@ -904,7 +905,7 @@ static void super_90_sync(mddev_t *mddev
sb->size = mddev->size;
sb->raid_disks = mddev->raid_disks;
sb->md_minor = mddev->md_minor;
- sb->not_persistent = !mddev->persistent;
+ sb->not_persistent = 0;
sb->utime = mddev->utime;
sb->state = 0;
sb->events_hi = (mddev->events>>32);
@@ -1158,6 +1159,7 @@ static int super_1_validate(mddev_t *mdd
mddev->major_version = 1;
mddev->patch_version = 0;
mddev->persistent = 1;
+ mddev->external = 0;
mddev->chunk_size = le32_to_cpu(sb->chunksize) << 9;
mddev->ctime = le64_to_cpu(sb->ctime) & ((1ULL << 32)-1);
mddev->utime = le64_to_cpu(sb->utime) & ((1ULL << 32)-1);
@@ -1699,18 +1701,20 @@ repeat:
MD_BUG();
mddev->events --;
}
- sync_sbs(mddev, nospares);
/*
* do not write anything to disk if using
* nonpersistent superblocks
*/
if (!mddev->persistent) {
- clear_bit(MD_CHANGE_PENDING, &mddev->flags);
+ if (!mddev->external)
+ clear_bit(MD_CHANGE_PENDING, &mddev->flags);
+
spin_unlock_irq(&mddev->write_lock);
wake_up(&mddev->sb_wait);
return;
}
+ sync_sbs(mddev, nospares);
spin_unlock_irq(&mddev->write_lock);
dprintk(KERN_INFO
@@ -2430,6 +2434,8 @@ array_state_show(mddev_t *mddev, char *p
case 0:
if (mddev->in_sync)
st = clean;
+ else if (test_bit(MD_CHANGE_CLEAN, &mddev->flags))
+ st = write_pending;
else if (mddev->safemode)
st = active_idle;
else
@@ -2460,11 +2466,9 @@ array_state_store(mddev_t *mddev, const
break;
case clear:
/* stopping an active array */
- if (mddev->pers) {
- if (atomic_read(&mddev->active) > 1)
- return -EBUSY;
- err = do_md_stop(mddev, 0);
- }
+ if (atomic_read(&mddev->active) > 1)
+ return -EBUSY;
+ err = do_md_stop(mddev, 0);
break;
case inactive:
/* stopping an active array */
@@ -2472,7 +2476,8 @@ array_state_store(mddev_t *mddev, const
if (atomic_read(&mddev->active) > 1)
return -EBUSY;
err = do_md_stop(mddev, 2);
- }
+ } else
+ err = 0; /* already
