Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 898effac authored by Kurt Hackel's avatar Kurt Hackel Committed by Mark Fasheh
Browse files

[PATCH] ocfs2: recheck recovery state after getting lock 



* after successfully taking the $RECOVERY lock in EX mode, recheck to make
  sure that recovery has not already begun or completed on another node

Signed-off-by: default avatarKurt Hackel <kurt.hackel@oracle.com>
Signed-off-by: default avatarMark Fasheh <mark.fasheh@oracle.com>
parent 90f9dd8f

fs/ocfs2/dlm/dlmrecovery.c

+24 −0
Original line number Diff line number Diff line
@@ -2032,6 +2032,30 @@ static int dlm_pick_recovery_master(struct dlm_ctxt *dlm) 
			     dlm->reco.new_master);

			status = -EEXIST;

		} else {

			status = 0;



			/* see if recovery was already finished elsewhere */

			spin_lock(&dlm->spinlock);

			if (dlm->reco.dead_node == O2NM_INVALID_NODE_NUM) {

				status = -EINVAL;	

				mlog(0, "%s: got reco EX lock, but "

				     "node got recovered already\n", dlm->name);

				if (dlm->reco.new_master != O2NM_INVALID_NODE_NUM) {

					mlog(ML_ERROR, "%s: new master is %u "

					     "but no dead node!\n", 

					     dlm->name, dlm->reco.new_master);

					BUG();

				}

			}

			spin_unlock(&dlm->spinlock);

		}



		/* if this node has actually become the recovery master,

		 * set the master and send the messages to begin recovery */

		if (!status) {

			mlog(0, "%s: dead=%u, this=%u, sending "

			     "begin_reco now\n", dlm->name, 

			     dlm->reco.dead_node, dlm->node_num);

			status = dlm_send_begin_reco_message(dlm,

				      dlm->reco.dead_node);

			/* this always succeeds */