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 67081754c665f8e409cdc5ba83dd49ff3cabcfde..3cd53fd5fa413471f728b15292d0242de77d9483 100644 (file)
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -4780,14 +4780,29 @@ StartupXLOG(void)
        record = ReadCheckpointRecord(checkPointLoc, 0);
        if (record != NULL)
        {
+           memcpy(&checkPoint, XLogRecGetData(record), sizeof(CheckPoint));
            ereport(LOG,
                    (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+            * segment that's already been archived.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)));
        }
@@ -4823,10 +4838,10 @@ 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(LOG,