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.
This commit is contained in:
Heikki Linnakangas 2010-10-26 21:15:42 +03:00
parent 62f86b32ea
commit 35b66df6e7
1 changed files with 17 additions and 2 deletions

View File

@ -4423,14 +4423,29 @@ 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* segment that's already been archived.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)));
}
@ -4464,10 +4479,10 @@ 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,