[Cluster-devel] cluster/group/gfs_controld plock.c recover.c

[teigland at sourceware.org]

CVSROOT:	/cvs/cluster
Module name:	cluster
Changes by:	teigland at sourceware.org	2006-08-02 20:50:40

Modified files:
	group/gfs_controld: plock.c recover.c 

Log message:
	- complain and ignore checkpoint sections with a bad size
	- do checkpoint for new nodes if low node in charge of that failed

Patches:
http://sourceware.org/cgi-bin/cvsweb.cgi/cluster/group/gfs_controld/plock.c.diff?cvsroot=cluster&r1=1.5&r2=1.6
http://sourceware.org/cgi-bin/cvsweb.cgi/cluster/group/gfs_controld/recover.c.diff?cvsroot=cluster&r1=1.6&r2=1.7

--- cluster/group/gfs_controld/plock.c	2006/08/02 19:23:41	1.5
+++ cluster/group/gfs_controld/plock.c	2006/08/02 20:50:40	1.6
@@ -1235,6 +1235,12 @@
 			  iov.readSize);
 		section_len = iov.readSize;
 
+		if (!section_len || section_len % sizeof(struct pack_plock)) {
+			log_error("retrieve_plocks: bad section len %d %s",
+				  section_len, mg->name);
+			continue;
+		}
+
 		unpack_section_buf(mg, desc.sectionId.id, desc.sectionId.idLen);
 	}
 
--- cluster/group/gfs_controld/recover.c	2006/08/02 18:27:57	1.6
+++ cluster/group/gfs_controld/recover.c	2006/08/02 20:50:40	1.7
@@ -1887,15 +1887,23 @@
 /* New mounters may be waiting for a journals message that a failed node (as
    low nodeid) would have sent.  If the low nodeid failed and we're the new low
    nodeid, then send a journals message to any nodes for whom we've not seen a
-   journals message. */
+   journals message.  We also need to checkpoint the plock state for the new
+   nodes to read after they get their journals message. */
 
 void resend_journals(struct mountgroup *mg)
 {
 	struct mg_member *memb;
+	int stored_plocks = 0;
 
 	list_for_each_entry(memb, &mg->members, list) {
 		if (!memb->needs_journals)
 			continue;
+
+		if (!stored_plocks) {
+			store_plocks(mg);
+			stored_plocks = 1;
+		}
+
 		log_group(mg, "resend_journals to %d", memb->nodeid);
 		send_journals(mg, memb->nodeid);
 	}