From fdf1f4a46a2f870ee2aeda11f909c465ed12450a Mon Sep 17 00:00:00 2001 From: Michael Paquier Date: Wed, 22 Oct 2014 15:18:33 +0200 Subject: [PATCH] Enforce all WAL segment files to be marked as .done at node promotion This is a safety mechanism to ensure that there are no files that are not considered as .done as some segments may have been missed particularly in the case of partially written files or files being written when a disconnection occurred between a streaming standby and its root node. This makes the node reaching promotion having a state consistent with what is expected using the assumption that all the WAL segment files that are done being streamed should be always considered as archived by the node. --- src/backend/access/transam/xlog.c | 10 ++++++++ src/backend/access/transam/xlogarchive.c | 39 +++++++++++++++++++++++++++++++- src/include/access/xlog_internal.h | 1 + 3 files changed, 49 insertions(+), 1 deletion(-) diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 235b442..7179003 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -6862,6 +6862,16 @@ StartupXLOG(void) } /* + * Create a .done entry for each WAL file present in pg_xlog that has + * not been yet marked as such for a node that has been promoted. In some + * cases where for example a streaming replica has had a connection to a + * remote node cut abruptly, such WAL files may have been only partially + * written or even not flagged correctly with .done. + */ + if (InRecovery && CheckForStandbyTrigger()) + XLogArchiveForceDoneAll(); + + /* * Kill WAL receiver, if it's still running, before we continue to write * the startup checkpoint record. It will trump over the checkpoint and * subsequent records if it's still alive when we start writing WAL. diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 047efa2..931106f 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -554,6 +554,40 @@ XLogArchiveNotifySeg(XLogSegNo segno) } /* + * XLogArchiveForceDoneAll + * + * Wrapper of XLogArchiveForceDone scanning all the XLOG segments files in + * XLOGDIR, switching them forcibly to .done. + */ +void +XLogArchiveForceDoneAll(void) +{ + DIR *xldir; + struct dirent *xlde; + + + xldir = AllocateDir(XLOGDIR); + if (xldir == NULL) + ereport(ERROR, + (errcode_for_file_access(), + errmsg("could not open transaction log directory \"%s\": %m", + XLOGDIR))); + + /* + * Scan all the WAL segments present in the archives and switch them to + * .done. + */ + while ((xlde = ReadDir(xldir, XLOGDIR)) != NULL) + { + if (strlen(xlde->d_name) == 24 && + strspn(xlde->d_name, "0123456789ABCDEF") == 24) + XLogArchiveForceDone(xlde->d_name); + } + + FreeDir(xldir); +} + +/* * XLogArchiveForceDone * * Emit notification forcibly that an XLOG segment file has been successfully @@ -582,7 +616,6 @@ XLogArchiveForceDone(const char *xlog) (errcode_for_file_access(), errmsg("could not rename file \"%s\" to \"%s\": %m", archiveReady, archiveDone))); - return; } @@ -604,6 +637,10 @@ XLogArchiveForceDone(const char *xlog) archiveDone))); return; } + + ereport(DEBUG2, + (errmsg("archive status file of \"%s\" has been forcibly switched from \"%s\" to \"%s\"", + xlog, archiveReady, archiveDone))); } /* diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 27b9899..04a0de3 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -286,6 +286,7 @@ extern void ExecuteRecoveryCommand(char *command, char *commandName, extern void KeepFileRestoredFromArchive(char *path, char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveForceDoneAll(void); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); -- 2.1.2