Before removing backup_label and irrevocably changing pg_control file, check

that WAL file containing the checkpoint redo-location can be found. This
avoids making the cluster irrecoverable if the redo location is in an earlie
WAL file than the checkpoint record.

Report, analysis and patch by Jeff Davis, with small changes by me.

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 27683452eaa4b036385c3018468d56fa849f6eda..698434cc5e88c79b0d6eca92d5dff55477fa6c95 100644 (file)
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -5323,14 +5323,29 @@ StartupXLOG(void)
                record = ReadCheckpointRecord(checkPointLoc, 0);
                if (record != NULL)
                {
+                       memcpy(&checkPoint, XLogRecGetData(record), sizeof(CheckPoint));
                        ereport(DEBUG1,
                                        (errmsg("checkpoint record is at %X/%X",
                                                        checkPointLoc.xlogid, checkPointLoc.xrecoff)));
                        InRecovery = true;      /* force recovery even if SHUTDOWNED */
+
+                       /*
+                        * Make sure that REDO location exists. This may not be
+                        * the case if there was a crash during an online backup,
+                        * which left a backup_label around that references a WAL
+                        * segment that's already been archived.
+                        */
+                       if (XLByteLT(checkPoint.redo, checkPointLoc))
+                       {
+                               if (!ReadRecord(&(checkPoint.redo), LOG))
+                                       ereport(FATAL,
+                                                       (errmsg("could not find redo location referenced by checkpoint record"),
+                                                        errhint("If you are not restoring from a backup, try removing the file \"%s/backup_label\".", DataDir)));
+                       }
                }
                else
                {
-                       ereport(PANIC,
+                       ereport(FATAL,
                                        (errmsg("could not locate required checkpoint record"),
                                         errhint("If you are not restoring from a backup, try removing the file \"%s/backup_label\".", DataDir)));
                }
@@ -5366,10 +5381,10 @@ StartupXLOG(void)
                                ereport(PANIC,
                                         (errmsg("could not locate a valid checkpoint record")));
                }
+               memcpy(&checkPoint, XLogRecGetData(record), sizeof(CheckPoint));
        }
 
        LastRec = RecPtr = checkPointLoc;
-       memcpy(&checkPoint, XLogRecGetData(record), sizeof(CheckPoint));
        wasShutdown = (record->xl_info == XLOG_CHECKPOINT_SHUTDOWN);
 
        ereport(DEBUG1,