logging: give a unique logging name to each forked child.

This means we can distinguish which child is logging, esp. via syslog where we have no pid.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>

(This used to be ctdb commit 68b3761a0874429b90731741f0531f76dcfbb081)

15 files changed, 35 insertions, 11 deletions

diff --git a/ctdb/client/ctdb_client.c b/ctdb/client/ctdb_client.c
index adba17c2c1..82b7304075 100644
--- a/ctdb/client/ctdb_client.c
+++ b/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) {
diff --git a/ctdb/common/ctdb_logging.c b/ctdb/common/ctdb_logging.c
index 18aafa2332..de29333582 100644
--- a/ctdb/common/ctdb_logging.c
+++ b/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);
 		}
diff --git a/ctdb/include/ctdb_client.h b/ctdb/include/ctdb_client.h
index e9aa8d17fb..b3b0d67516 100644
--- a/ctdb/include/ctdb_client.h
+++ b/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,
diff --git a/ctdb/lib/util/debug.c b/ctdb/lib/util/debug.c
index 1cbaa230f1..e9365d88f6 100644
--- a/ctdb/lib/util/debug.c
+++ b/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, ...)
 {
diff --git a/ctdb/lib/util/debug.h b/ctdb/lib/util/debug.h
index 11ecb19786..27490a3dbf 100644
--- a/ctdb/lib/util/debug.h
+++ b/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);
diff --git a/ctdb/server/ctdb_freeze.c b/ctdb/server/ctdb_freeze.c
index e641ef3ae6..bf4c83e88b 100644
--- a/ctdb/server/ctdb_freeze.c
+++ b/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);
diff --git a/ctdb/server/ctdb_lockwait.c b/ctdb/server/ctdb_lockwait.c
index afbb921439..b7ae55c6c9 100644
--- a/ctdb/server/ctdb_lockwait.c
+++ b/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 */
diff --git a/ctdb/server/ctdb_logging.c b/ctdb/server/ctdb_logging.c
index 807bb179e0..880f844f85 100644
--- a/ctdb/server/ctdb_logging.c
+++ b/ctdb/server/ctdb_logging.c
@@ -115,6 +115,7 @@ 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);
 
@@ -213,15 +214,16 @@ 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);
@@ -275,8 +277,9 @@ 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";
diff --git a/ctdb/server/ctdb_monitor.c b/ctdb/server/ctdb_monitor.c
index 3343501624..55cd4e3842 100644
--- a/ctdb/server/ctdb_monitor.c
+++ b/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"));
diff --git a/ctdb/server/ctdb_persistent.c b/ctdb/server/ctdb_persistent.c
index d38aa8d9e7..4401bcda6b 100644
--- a/ctdb/server/ctdb_persistent.c
+++ b/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"));
diff --git a/ctdb/server/ctdb_recover.c b/ctdb/server/ctdb_recover.c
index 22e48986f4..f61b6e7b6f 100644
--- a/ctdb/server/ctdb_recover.c
+++ b/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 
 		*/
diff --git a/ctdb/server/ctdb_recoverd.c b/ctdb/server/ctdb_recoverd.c
index 82fe62ea2d..3145cd0712 100644
--- a/ctdb/server/ctdb_recoverd.c
+++ b/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;
@@ -3582,7 +3583,7 @@ 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);
 	}
diff --git a/ctdb/server/ctdb_traverse.c b/ctdb/server/ctdb_traverse.c
index 3549007cfa..52c2f709a7 100644
--- a/ctdb/server/ctdb_traverse.c
+++ b/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);
 	}
diff --git a/ctdb/server/ctdb_vacuum.c b/ctdb/server/ctdb_vacuum.c
index f1e61dbf11..375d4eff6c 100644
--- a/ctdb/server/ctdb_vacuum.c
+++ b/ctdb/server/ctdb_vacuum.c
@@ -841,7 +841,7 @@ 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);
 		}
diff --git a/ctdb/server/eventscript.c b/ctdb/server/eventscript.c
index 8011269e26..c4ffd26285 100644
--- a/ctdb/server/eventscript.c
+++ b/ctdb/server/eventscript.c
@@ -385,6 +385,9 @@ 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]);