Fix minor problems with non-exclusive backup cleanup.

robertmhaas · robertmhaas · commit f7013683d9bb · 2020-08-06T14:06:24.000-04:00
The previous coding imagined that it could call before_shmem_exit() when a non-exclusive backup began and then remove the previously-added handler by calling cancel_before_shmem_exit() when that backup ended. However, this only works provided that nothing else in the system has registered a before_shmem_exit() hook in the interim, because cancel_before_shmem_exit() is documented to remove a callback only if it is the latest callback registered. It also only works if nothing can ERROR out between the time that sessionBackupState is reset and the time that cancel_before_shmem_exit(), which doesn't seem to be strictly true. To fix, leave the handler installed for the lifetime of the session, arrange to install it just once, and teach it to quietly do nothing if there isn't a non-exclusive backup in process. This was originally committed to master as 3036401, but I did not back-patch at the time because the consequences were minor. However, now there's been a second report of this causing trouble with a slightly different test case than the one I reported originally, so now I'm back-patching as far as v11 where JIT was introduced. Patch by me, reviewed by Kyotaro Horiguchi, Michael Paquier (who preferred a different approach, but got outvoted), Fujii Masao, and Tom Lane, and with comments by various others. New problem report from Bharath Rupireddy. Discussion: http://postgr.es/m/CA+TgmobMjnyBfNhGTKQEDbqXYE3_rXWpc4CM63fhyerNCes3mA@mail.gmail.com Discussion: http://postgr.es/m/CALj2ACWk7j4F2v2fxxYfrroOF=AdFNPr1WsV+AGtHAFQOqm_pw@mail.gmail.com
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
@@ -11329,23 +11329,30 @@ do_pg_stop_backup(char *labelfile, bool waitforarchive, TimeLineID *stoptli_p)
  * system out of backup mode, thus making it a lot more safe to call from
  * an error handler.
  *
+ * The caller can pass 'arg' as 'true' or 'false' to control whether a warning
+ * is emitted.
+ *
  * NB: This is only for aborting a non-exclusive backup that doesn't write
  * backup_label. A backup started with pg_start_backup() needs to be finished
  * with pg_stop_backup().
+ *
+ * NB: This gets used as a before_shmem_exit handler, hence the odd-looking
+ * signature.
  */
 void
-do_pg_abort_backup(void)
+do_pg_abort_backup(int code, Datum arg)
 {
+	bool	emit_warning = DatumGetBool(arg);
+
 	/*
 	 * Quick exit if session is not keeping around a non-exclusive backup
 	 * already started.
 	 */
-	if (sessionBackupState == SESSION_BACKUP_NONE)
+	if (sessionBackupState != SESSION_BACKUP_NON_EXCLUSIVE)
 		return;
 
 	WALInsertLockAcquireExclusive();
 	Assert(XLogCtl->Insert.nonExclusiveBackups > 0);
-	Assert(sessionBackupState == SESSION_BACKUP_NON_EXCLUSIVE);
 	XLogCtl->Insert.nonExclusiveBackups--;
 
 	if (XLogCtl->Insert.exclusiveBackupState == EXCLUSIVE_BACKUP_NONE &&
@@ -11354,6 +11361,25 @@ do_pg_abort_backup(void)
 		XLogCtl->Insert.forcePageWrites = false;
 	}
 	WALInsertLockRelease();
+
+	if (emit_warning)
+		ereport(WARNING,
+				(errmsg("aborting backup due to backend exiting before pg_stop_back up was called")));
+}
+
+/*
+ * Register a handler that will warn about unterminated backups at end of
+ * session, unless this has already been done.
+ */
+void
+register_persistent_abort_backup_handler(void)
+{
+	static bool already_done = false;
+
+	if (already_done)
+		return;
+	before_shmem_exit(do_pg_abort_backup, DatumGetBool(true));
+	already_done = true;
 }
 
 /*
diff --git a/src/backend/access/transam/xlogfuncs.c b/src/backend/access/transam/xlogfuncs.c
@@ -42,18 +42,6 @@
 static StringInfo label_file;
 static StringInfo tblspc_map_file;
 
-/*
- * Called when the backend exits with a running non-exclusive base backup,
- * to clean up state.
- */
-static void
-nonexclusive_base_backup_cleanup(int code, Datum arg)
-{
-	do_pg_abort_backup();
-	ereport(WARNING,
-			(errmsg("aborting backup due to backend exiting before pg_stop_backup was called")));
-}
-
 /*
  * pg_start_backup: set up for taking an on-line backup dump
  *
@@ -101,10 +89,10 @@ pg_start_backup(PG_FUNCTION_ARGS)
 		tblspc_map_file = makeStringInfo();
 		MemoryContextSwitchTo(oldcontext);
 
+		register_persistent_abort_backup_handler();
+
 		startpoint = do_pg_start_backup(backupidstr, fast, NULL, label_file,
 										NULL, tblspc_map_file, false, true);
-
-		before_shmem_exit(nonexclusive_base_backup_cleanup, (Datum) 0);
 	}
 
 	PG_RETURN_LSN(startpoint);
@@ -246,7 +234,6 @@ pg_stop_backup_v2(PG_FUNCTION_ARGS)
 		 * and tablespace map so they can be written to disk by the caller.
 		 */
 		stoppoint = do_pg_stop_backup(label_file->data, waitforarchive, NULL);
-		cancel_before_shmem_exit(nonexclusive_base_backup_cleanup, (Datum) 0);
 
 		values[1] = CStringGetTextDatum(label_file->data);
 		values[2] = CStringGetTextDatum(tblspc_map_file->data);
diff --git a/src/backend/replication/basebackup.c b/src/backend/replication/basebackup.c
@@ -66,7 +66,6 @@ static int64 _tarWriteDir(const char *pathbuf, int basepathlen, struct stat *sta
 			 bool sizeonly);
 static void send_int8_string(StringInfoData *buf, int64 intval);
 static void SendBackupHeader(List *tablespaces);
-static void base_backup_cleanup(int code, Datum arg);
 static void perform_base_backup(basebackup_options *opt);
 static void parse_basebackup_options(List *options, basebackup_options *opt);
 static void SendXlogRecPtrResult(XLogRecPtr ptr, TimeLineID tli);
@@ -231,17 +230,6 @@ static const struct exclude_list_item noChecksumFiles[] = {
 	{NULL, false}
 };
 
-
-/*
- * Called when ERROR or FATAL happens in perform_base_backup() after
- * we have started the backup - make sure we end it!
- */
-static void
-base_backup_cleanup(int code, Datum arg)
-{
-	do_pg_abort_backup();
-}
-
 /*
  * Actually do a base backup for the specified tablespaces.
  *
@@ -280,7 +268,7 @@ perform_base_backup(basebackup_options *opt)
 	 * do_pg_stop_backup() should be inside the error cleanup block!
 	 */
 
-	PG_ENSURE_ERROR_CLEANUP(base_backup_cleanup, (Datum) 0);
+	PG_ENSURE_ERROR_CLEANUP(do_pg_abort_backup, BoolGetDatum(false));
 	{
 		ListCell   *lc;
 		tablespaceinfo *ti;
@@ -389,7 +377,7 @@ perform_base_backup(basebackup_options *opt)
 
 		endptr = do_pg_stop_backup(labelfile->data, !opt->nowait, &endtli);
 	}
-	PG_END_ENSURE_ERROR_CLEANUP(base_backup_cleanup, (Datum) 0);
+	PG_END_ENSURE_ERROR_CLEANUP(do_pg_abort_backup, BoolGetDatum(false));
 
 
 	if (opt->includewal)
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
@@ -326,7 +326,8 @@ extern XLogRecPtr do_pg_start_backup(const char *backupidstr, bool fast,
 				   bool needtblspcmapfile);
 extern XLogRecPtr do_pg_stop_backup(char *labelfile, bool waitforarchive,
 				  TimeLineID *stoptli_p);
-extern void do_pg_abort_backup(void);
+extern void do_pg_abort_backup(int code, Datum arg);
+extern void register_persistent_abort_backup_handler(void);
 extern SessionBackupState get_backup_status(void);
 
 /* File path names (all relative to $PGDATA) */
