From 91c0dc93a1a6bbdd79707ed311e48b4397df177f Mon Sep 17 00:00:00 2001 From: David Teigland Date: Tue, 31 Oct 2006 11:56:01 -0600 Subject: [DLM] fix aborted recovery during node removal Red Hat BZ 211914 With the new cluster infrastructure, dlm recovery for a node removal can be aborted and restarted for a node addition. When this happens, the restarted recovery isn't aware that it's doing recovery for the earlier removal as well as the addition. So, it then skips the recovery steps only required when nodes are removed. This can result in locks not being purged for failed/removed nodes. The fix is to check for removed nodes for which recovery has not been completed at the start of a new recovery sequence. Signed-off-by: David Teigland Signed-off-by: Steven Whitehouse --- fs/dlm/member.c | 8 ++++++++ fs/dlm/recoverd.c | 7 +++++++ 2 files changed, 15 insertions(+) (limited to 'fs') diff --git a/fs/dlm/member.c b/fs/dlm/member.c index a3f7de7f3a8f..85e2897bd740 100644 --- a/fs/dlm/member.c +++ b/fs/dlm/member.c @@ -186,6 +186,14 @@ int dlm_recover_members(struct dlm_ls *ls, struct dlm_recover *rv, int *neg_out) struct dlm_member *memb, *safe; int i, error, found, pos = 0, neg = 0, low = -1; + /* previously removed members that we've not finished removing need to + count as a negative change so the "neg" recovery steps will happen */ + + list_for_each_entry(memb, &ls->ls_nodes_gone, list) { + log_debug(ls, "prev removed member %d", memb->nodeid); + neg++; + } + /* move departed members from ls_nodes to ls_nodes_gone */ list_for_each_entry_safe(memb, safe, &ls->ls_nodes, list) { diff --git a/fs/dlm/recoverd.c b/fs/dlm/recoverd.c index 362e3eff4dc9..4a1d6023fd9b 100644 --- a/fs/dlm/recoverd.c +++ b/fs/dlm/recoverd.c @@ -164,6 +164,13 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv) */ dlm_recover_rsbs(ls); + } else { + /* + * Other lockspace members may be going through the "neg" steps + * while also adding us to the lockspace, in which case they'll + * be looking for this status bit during dlm_recover_locks(). + */ + dlm_set_recover_status(ls, DLM_RS_LOCKS); } dlm_release_root_list(ls); -- cgit v1.2.2