Merge commit 'rusty/ports-from-1.0.112' into foo

(This used to be ctdb commit 13e58d92f5f1723e850a82ae030d0ca57e89b1ee)

ctdb/client/ctdb_client.c

@@ -3827,9 +3827,15 @@ int ctdb_ctrl_recd_ping(struct ctdb_context *ctdb)
  * to the daemon as a client process, this function can be used to change
  * the ctdb context from daemon into client mode
  */
-int switch_from_server_to_client(struct ctdb_context *ctdb)
+int switch_from_server_to_client(struct ctdb_context *ctdb, const char *fmt, ...)
 {
 	int ret;
+	va_list ap;
+
+	/* Add extra information so we can identify this in the logs */
+	va_start(ap, fmt);
+	debug_extra = talloc_append_string(NULL, talloc_vasprintf(NULL, fmt, ap), ":");
+	va_end(ap);
 
 	/* shutdown the transport */
 	if (ctdb->methods) {

ctdb/common/ctdb_logging.c

@@ -164,7 +164,7 @@ int32_t ctdb_control_get_log(struct ctdb_context *ctdb, TDB_DATA addr)
 	}
 
 	if (child == 0) {
-		if (switch_from_server_to_client(ctdb) != 0) {
+		if (switch_from_server_to_client(ctdb, "log-collector") != 0) {
 			DEBUG(DEBUG_CRIT, (__location__ "ERROR: failed to switch log collector child into client mode.\n"));
 			_exit(1);
 		}

ctdb/config/events.d/11.natgw

@@ -69,6 +69,12 @@ case "$1" in
 		# This is the first node, set it up as the NAT GW
 		echo 1 >/proc/sys/net/ipv4/ip_forward
 		iptables -A POSTROUTING -t nat -s $CTDB_NATGW_PRIVATE_NETWORK -d ! $CTDB_NATGW_PRIVATE_NETWORK -j MASQUERADE
+
+		# block all incoming connections to the natgw address
+		CTDB_NATGW_PUBLIC_IP_HOST=`echo $CTDB_NATGW_PUBLIC_IP | sed -e "s/\/.*/\/32/"`
+		iptables -D INPUT -p tcp --syn -d $CTDB_NATGW_PUBLIC_IP_HOST -j REJECT 2>/dev/null
+		iptables -I INPUT -p tcp --syn -d $CTDB_NATGW_PUBLIC_IP_HOST -j REJECT 2>/dev/null
+
 		ip addr add $CTDB_NATGW_PUBLIC_IP dev $CTDB_NATGW_PUBLIC_IFACE
 		ip route add 0.0.0.0/0 via $CTDB_NATGW_DEFAULT_GATEWAY >/dev/null 2>/dev/null
 	else

ctdb/include/ctdb_client.h

@@ -551,7 +551,8 @@ int ctdb_transaction_commit(struct ctdb_transaction_handle *h);
 
 int ctdb_ctrl_recd_ping(struct ctdb_context *ctdb);
 
-int switch_from_server_to_client(struct ctdb_context *ctdb);
+int switch_from_server_to_client(struct ctdb_context *ctdb, const char *fmt,
+				 ...);
 
 int ctdb_ctrl_getscriptstatus(struct ctdb_context *ctdb,
 		    struct timeval timeout, uint32_t destnode,

ctdb/lib/util/debug.c

@@ -42,13 +42,15 @@ static void _do_debug_v(const char *format, va_list ap)
 
 	strftime(tbuf,sizeof(tbuf)-1,"%Y/%m/%d %H:%M:%S", tm);
 
-	fprintf(stderr, "%s.%06u [%5u]: %s", tbuf, (unsigned)t.tv_usec, (unsigned)getpid(), s);
+	fprintf(stderr, "%s.%06u [%s%5u]: %s", tbuf, (unsigned)t.tv_usec,
+		debug_extra, (unsigned)getpid(), s);
 	fflush(stderr);
 	free(s);
 }
 
 /* default logging function */
 void (*do_debug_v)(const char *, va_list ap) = _do_debug_v;
+const char *debug_extra = "";
 
 void do_debug(const char *format, ...)
 {

ctdb/lib/util/debug.h

@@ -18,6 +18,7 @@
 */
 
 void (*do_debug_v)(const char *, va_list ap);
+const char *debug_extra;
 void (*do_debug_add_v)(const char *, va_list ap);
 void log_ringbuffer(const char *format, ...);
 void do_debug(const char *format, ...) PRINTF_ATTRIBUTE(1, 2);

ctdb/server/ctdb_freeze.c

@@ -202,6 +202,7 @@ static struct ctdb_freeze_handle *ctdb_freeze_lock(struct ctdb_context *ctdb, ui
 		/* in the child */
 		close(fd[0]);
 
+		debug_extra = talloc_asprintf(NULL, "freeze_lock-%u:", priority);
 		ret = ctdb_lock_all_databases(ctdb, priority);
 		if (ret != 0) {
 			_exit(0);

ctdb/server/ctdb_lockwait.c

@@ -136,6 +136,7 @@ struct lockwait_handle *ctdb_lockwait(struct ctdb_db_context *ctdb_db,
 	if (result->child == 0) {
 		char c = 0;
 		close(result->fd[0]);
+		debug_extra = talloc_asprintf(NULL, "chainlock-%s:", ctdb_db->db_name);
 		tdb_chainlock(ctdb_db->ltdb->tdb, key);
 		write(result->fd[1], &c, 1);
 		/* make sure we die when our parent dies */

ctdb/server/ctdb_logging.c

@@ -116,6 +116,7 @@ int start_syslog_daemon(struct ctdb_context *ctdb)
 		return 0;
 	}
 
+	debug_extra = talloc_asprintf(NULL, "syslogd:");
 	talloc_free(ctdb->ev);
 	ctdb->ev = event_context_init(NULL);
 	tevent_loop_allow_nesting(ctdb->ev);
@@ -217,15 +218,16 @@ static void ctdb_syslog_log(const char *format, va_list ap)
 		break;		
 	}
 
-	len = offsetof(struct syslog_message, message) + strlen(s) + 1;
+	len = offsetof(struct syslog_message, message) + strlen(debug_extra) + strlen(s) + 1;
 	msg = malloc(len);
 	if (msg == NULL) {
 		free(s);
 		return;
 	}
 	msg->level = level;
-	msg->len   = strlen(s);
-	strcpy(msg->message, s);
+	msg->len   = strlen(debug_extra) + strlen(s);
+	strcpy(msg->message, debug_extra);
+	strcat(msg->message, s);
 
 	if (syslogd_is_started == 0) {
 		syslog(msg->level, "%s", msg->message);
@@ -279,8 +281,9 @@ static void ctdb_logfile_log(const char *format, va_list ap)
 
 	strftime(tbuf,sizeof(tbuf)-1,"%Y/%m/%d %H:%M:%S", tm);
 
-	ret = asprintf(&s2, "%s.%06u [%5u]: %s",
-		 tbuf, (unsigned)t.tv_usec, (unsigned)getpid(), s);
+	ret = asprintf(&s2, "%s.%06u [%s%5u]: %s",
+		       tbuf, (unsigned)t.tv_usec,
+		       debug_extra, (unsigned)getpid(), s);
 	free(s);
 	if (ret == -1) {
 		const char *errstr = "asprintf failed\n";

ctdb/server/ctdb_monitor.c

@@ -91,6 +91,7 @@ void ctdb_run_notification_script(struct ctdb_context *ctdb, const char *event)
 	if (child == 0) {
 		int ret;
 
+		debug_extra = talloc_asprintf(NULL, "notification-%s:", event);
 		ret = ctdb_run_notification_script_child(ctdb, event);
 		if (ret != 0) {
 			DEBUG(DEBUG_ERR,(__location__ " Notification script failed\n"));

ctdb/server/ctdb_persistent.c

@@ -543,6 +543,7 @@ struct childwrite_handle *ctdb_childwrite(struct ctdb_db_context *ctdb_db,
 		char c = 0;
 
 		close(result->fd[0]);
+		debug_extra = talloc_asprintf(NULL, "childwrite-%s:", ctdb_db->db_name);
 		ret = ctdb_persistent_store(state);
 		if (ret != 0) {
 			DEBUG(DEBUG_ERR, (__location__ " Failed to write persistent data\n"));

ctdb/server/ctdb_recover.c

@@ -725,6 +725,7 @@ int32_t ctdb_control_set_recmode(struct ctdb_context *ctdb,
 		char cc = 0;
 		close(state->fd[0]);
 
+		debug_extra = talloc_asprintf(NULL, "set_recmode:");
 		/* we should not be able to get the lock on the reclock file, 
 		  as it should  be held by the recovery master 
 		*/

ctdb/server/ctdb_recoverd.c

@@ -2774,6 +2774,7 @@ static int check_recovery_lock(struct ctdb_context *ctdb)
 		close(state->fd[0]);
 		state->fd[0] = -1;
 
+		debug_extra = talloc_asprintf(NULL, "recovery-lock:");
 		if (pread(ctdb->recovery_lock_fd, &cc, 1, 0) == -1) {
 			DEBUG(DEBUG_CRIT,("failed read from recovery_lock_fd - %s\n", strerror(errno)));
 			cc = RECLOCK_FAILED;
@@ -3584,7 +3585,7 @@ int ctdb_start_recoverd(struct ctdb_context *ctdb)
 
 	srandom(getpid() ^ time(NULL));
 
-	if (switch_from_server_to_client(ctdb) != 0) {
+	if (switch_from_server_to_client(ctdb, "recoverd") != 0) {
 		DEBUG(DEBUG_CRIT, (__location__ "ERROR: failed to switch recovery daemon into client mode. shutting down.\n"));
 		exit(1);
 	}

ctdb/server/ctdb_takeover.c

@@ -2283,7 +2283,8 @@ static void tickle_connection_traverse(void *param, void *data)
 
 	/* have tried too many times, just give up */
 	if (con->count >= 5) {
-		talloc_free(con);
+		/* can't delete in traverse: reparent to delete_cons */
+		talloc_steal(param, con);
 		return;
 	}
 
@@ -2303,11 +2304,13 @@ static void ctdb_tickle_sentenced_connections(struct event_context *ev, struct t
 					      struct timeval t, void *private_data)
 {
 	struct ctdb_kill_tcp *killtcp = talloc_get_type(private_data, struct ctdb_kill_tcp);
-
+	void *delete_cons = talloc_new(NULL);
 
 	/* loop over all connections sending tickle ACKs */
-	trbt_traversearray32(killtcp->connections, KILLTCP_KEYLEN, tickle_connection_traverse, NULL);
+	trbt_traversearray32(killtcp->connections, KILLTCP_KEYLEN, tickle_connection_traverse, delete_cons);
 
+	/* now we've finished traverse, it's safe to do deletion. */
+	talloc_free(delete_cons);
 
 	/* If there are no more connections to kill we can remove the
 	   entire killtcp structure

ctdb/server/ctdb_traverse.c

@@ -171,6 +171,8 @@ static struct ctdb_traverse_local_handle *ctdb_traverse_local(struct ctdb_db_con
 	if (h->child == 0) {
 		/* start the traverse in the child */
 		close(h->fd[0]);
+		debug_extra = talloc_asprintf(NULL, "traverse_local-%s:",
+					      ctdb_db->db_name);
 		tdb_traverse_read(ctdb_db->ltdb->tdb, ctdb_traverse_local_fn, h);
 		_exit(0);
 	}

ctdb/server/ctdb_vacuum.c

@@ -853,7 +853,7 @@ ctdb_vacuum_event(struct event_context *ev, struct timed_event *te,
 
 		DEBUG(DEBUG_INFO,("Vacuuming child process %d for db %s started\n", getpid(), ctdb_db->db_name));
 	
-		if (switch_from_server_to_client(ctdb) != 0) {
+		if (switch_from_server_to_client(ctdb, "vacuum-%s", ctdb_db->db_name) != 0) {
 			DEBUG(DEBUG_CRIT, (__location__ "ERROR: failed to switch vacuum daemon into client mode. Shutting down.\n"));
 			_exit(1);
 		}

ctdb/server/eventscript.c

@@ -386,6 +386,9 @@ static int fork_child_for_script(struct ctdb_context *ctdb,
 	if (state->child == 0) {
 		int rt;
 
+		debug_extra = talloc_asprintf(NULL, "eventscript-%s-%s:",
+					      current->name,
+					      ctdb_eventscript_call_names[state->call]);
 		close(state->fd[0]);
 		set_close_on_exec(state->fd[1]);