drbd: fix "stalled" empty resync
With sync-after dependencies, given "lucky" timing of pause/unpause events, and the end of an empty (0 bits set) resync was sometimes not detected on the SyncTarget, leading to a "stalled" SyncSource state. Fixed this by expecting not only "Inconsistent -> UpToDate" but also "Consistent -> UpToDate" transitions for the peer disk state to end a resync. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
This commit is contained in:
parent
22d81140ae
commit
9bcd252182
|
@ -2262,7 +2262,7 @@ int drbd_adm_resize(struct sk_buff *skb, struct genl_info *info)
|
|||
|
||||
if (rs.no_resync && mdev->tconn->agreed_pro_version < 93) {
|
||||
retcode = ERR_NEED_APV_93;
|
||||
goto fail;
|
||||
goto fail_ldev;
|
||||
}
|
||||
|
||||
rcu_read_lock();
|
||||
|
@ -2272,7 +2272,7 @@ int drbd_adm_resize(struct sk_buff *skb, struct genl_info *info)
|
|||
new_disk_conf = kmalloc(sizeof(struct disk_conf), GFP_KERNEL);
|
||||
if (!new_disk_conf) {
|
||||
retcode = ERR_NOMEM;
|
||||
goto fail;
|
||||
goto fail_ldev;
|
||||
}
|
||||
}
|
||||
|
||||
|
@ -2310,6 +2310,10 @@ int drbd_adm_resize(struct sk_buff *skb, struct genl_info *info)
|
|||
fail:
|
||||
drbd_adm_finish(info, retcode);
|
||||
return 0;
|
||||
|
||||
fail_ldev:
|
||||
put_ldev(mdev);
|
||||
goto fail;
|
||||
}
|
||||
|
||||
int drbd_adm_resource_opts(struct sk_buff *skb, struct genl_info *info)
|
||||
|
|
|
@ -3748,9 +3748,14 @@ static int receive_state(struct drbd_tconn *tconn, struct packet_info *pi)
|
|||
os = ns = drbd_read_state(mdev);
|
||||
spin_unlock_irq(&mdev->tconn->req_lock);
|
||||
|
||||
/* peer says his disk is uptodate, while we think it is inconsistent,
|
||||
* and this happens while we think we have a sync going on. */
|
||||
if (os.pdsk == D_INCONSISTENT && real_peer_disk == D_UP_TO_DATE &&
|
||||
/* If this is the "end of sync" confirmation, usually the peer disk
|
||||
* transitions from D_INCONSISTENT to D_UP_TO_DATE. For empty (0 bits
|
||||
* set) resync started in PausedSyncT, or if the timing of pause-/
|
||||
* unpause-sync events has been "just right", the peer disk may
|
||||
* transition from D_CONSISTENT to D_UP_TO_DATE as well.
|
||||
*/
|
||||
if ((os.pdsk == D_INCONSISTENT || os.pdsk == D_CONSISTENT) &&
|
||||
real_peer_disk == D_UP_TO_DATE &&
|
||||
os.conn > C_CONNECTED && os.disk == D_UP_TO_DATE) {
|
||||
/* If we are (becoming) SyncSource, but peer is still in sync
|
||||
* preparation, ignore its uptodate-ness to avoid flapping, it
|
||||
|
|
Loading…
Reference in New Issue