From 078e81ce389680fb98a8b5c2fb6cfb3fb42f892e Mon Sep 17 00:00:00 2001 From: Nathan Bossart Date: Fri, 23 Dec 2022 16:35:25 -0800 Subject: [PATCH v6 1/3] Move the code to restore files via the shell to a separate file. This is preparatory work for allowing more extensibility in this area. --- src/backend/access/transam/Makefile | 1 + src/backend/access/transam/meson.build | 1 + src/backend/access/transam/shell_restore.c | 158 +++++++++++++++++++++ src/backend/access/transam/xlog.c | 37 +++-- src/backend/access/transam/xlogarchive.c | 120 +--------------- src/include/access/xlogarchive.h | 7 +- 6 files changed, 197 insertions(+), 127 deletions(-) create mode 100644 src/backend/access/transam/shell_restore.c diff --git a/src/backend/access/transam/Makefile b/src/backend/access/transam/Makefile index 661c55a9db..099c315d03 100644 --- a/src/backend/access/transam/Makefile +++ b/src/backend/access/transam/Makefile @@ -19,6 +19,7 @@ OBJS = \ multixact.o \ parallel.o \ rmgr.o \ + shell_restore.o \ slru.o \ subtrans.o \ timeline.o \ diff --git a/src/backend/access/transam/meson.build b/src/backend/access/transam/meson.build index 8920c1bfce..3031c2f6cf 100644 --- a/src/backend/access/transam/meson.build +++ b/src/backend/access/transam/meson.build @@ -7,6 +7,7 @@ backend_sources += files( 'multixact.c', 'parallel.c', 'rmgr.c', + 'shell_restore.c', 'slru.c', 'subtrans.c', 'timeline.c', diff --git a/src/backend/access/transam/shell_restore.c b/src/backend/access/transam/shell_restore.c new file mode 100644 index 0000000000..f52f0b92a4 --- /dev/null +++ b/src/backend/access/transam/shell_restore.c @@ -0,0 +1,158 @@ +/*------------------------------------------------------------------------- + * + * shell_restore.c + * + * These recovery functions use a user-specified shell command (e.g., the + * restore_command GUC). + * + * Copyright (c) 2022, PostgreSQL Global Development Group + * + * IDENTIFICATION + * src/backend/access/transam/shell_restore.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include + +#include "access/xlogarchive.h" +#include "access/xlogrecovery.h" +#include "common/archive.h" +#include "common/percentrepl.h" +#include "storage/ipc.h" +#include "utils/wait_event.h" + +static void ExecuteRecoveryCommand(const char *command, + const char *commandName, bool failOnSignal, + uint32 wait_event_info, + const char *lastRestartPointFileName); + +bool +shell_restore(const char *file, const char *path, + const char *lastRestartPointFileName) +{ + char *cmd; + int rc; + + /* Build the restore command to execute */ + cmd = BuildRestoreCommand(recoveryRestoreCommand, path, file, + lastRestartPointFileName); + + ereport(DEBUG3, + (errmsg_internal("executing restore command \"%s\"", cmd))); + + /* + * Copy xlog from archival storage to XLOGDIR + */ + fflush(NULL); + pgstat_report_wait_start(WAIT_EVENT_RESTORE_COMMAND); + rc = system(cmd); + pgstat_report_wait_end(); + + pfree(cmd); + + /* + * Remember, we rollforward UNTIL the restore fails so failure here is + * just part of the process... that makes it difficult to determine + * whether the restore failed because there isn't an archive to restore, + * or because the administrator has specified the restore program + * incorrectly. We have to assume the former. + * + * However, if the failure was due to any sort of signal, it's best to + * punt and abort recovery. (If we "return false" here, upper levels will + * assume that recovery is complete and start up the database!) It's + * essential to abort on child SIGINT and SIGQUIT, because per spec + * system() ignores SIGINT and SIGQUIT while waiting; if we see one of + * those it's a good bet we should have gotten it too. + * + * On SIGTERM, assume we have received a fast shutdown request, and exit + * cleanly. It's pure chance whether we receive the SIGTERM first, or the + * child process. If we receive it first, the signal handler will call + * proc_exit, otherwise we do it here. If we or the child process received + * SIGTERM for any other reason than a fast shutdown request, postmaster + * will perform an immediate shutdown when it sees us exiting + * unexpectedly. + * + * We treat hard shell errors such as "command not found" as fatal, too. + */ + if (wait_result_is_signal(rc, SIGTERM)) + proc_exit(1); + + ereport(wait_result_is_any_signal(rc, true) ? FATAL : DEBUG2, + (errmsg("could not restore file \"%s\" from archive: %s", + file, wait_result_to_str(rc)))); + + return (rc == 0); +} + +void +shell_archive_cleanup(const char *lastRestartPointFileName) +{ + ExecuteRecoveryCommand(archiveCleanupCommand, "archive_cleanup_command", + false, WAIT_EVENT_ARCHIVE_CLEANUP_COMMAND, + lastRestartPointFileName); +} + +void +shell_recovery_end(const char *lastRestartPointFileName) +{ + ExecuteRecoveryCommand(recoveryEndCommand, "recovery_end_command", true, + WAIT_EVENT_RECOVERY_END_COMMAND, + lastRestartPointFileName); +} + +/* + * Attempt to execute an external shell command during recovery. + * + * 'command' is the shell command to be executed, 'commandName' is a + * human-readable name describing the command emitted in the logs. If + * 'failOnSignal' is true and the command is killed by a signal, a FATAL + * error is thrown. Otherwise a WARNING is emitted. + * + * This is currently used for recovery_end_command and archive_cleanup_command. + */ +static void +ExecuteRecoveryCommand(const char *command, const char *commandName, + bool failOnSignal, uint32 wait_event_info, + const char *lastRestartPointFileName) +{ + char *xlogRecoveryCmd; + int rc; + + Assert(command && commandName); + + /* + * construct the command to be executed + */ + xlogRecoveryCmd = replace_percent_placeholders(command, commandName, "r", + lastRestartPointFileName); + + ereport(DEBUG3, + (errmsg_internal("executing %s \"%s\"", commandName, command))); + + /* + * execute the constructed command + */ + fflush(NULL); + pgstat_report_wait_start(wait_event_info); + rc = system(xlogRecoveryCmd); + pgstat_report_wait_end(); + + pfree(xlogRecoveryCmd); + + if (rc != 0) + { + /* + * If the failure was due to any sort of signal, it's best to punt and + * abort recovery. See comments in shell_restore(). + */ + ereport((failOnSignal && wait_result_is_any_signal(rc, true)) ? FATAL : WARNING, + /*------ + translator: First %s represents a postgresql.conf parameter name like + "recovery_end_command", the 2nd is the value of that parameter, the + third an already translated error message. */ + (errmsg("%s \"%s\": %s", commandName, + command, wait_result_to_str(rc)))); + } +} diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 0070d56b0b..8f47fb7570 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -692,6 +692,7 @@ static char *GetXLogBuffer(XLogRecPtr ptr, TimeLineID tli); static XLogRecPtr XLogBytePosToRecPtr(uint64 bytepos); static XLogRecPtr XLogBytePosToEndRecPtr(uint64 bytepos); static uint64 XLogRecPtrToBytePos(XLogRecPtr ptr); +static void GetOldestRestartPointFileName(char *fname); static void WALInsertLockAcquire(void); static void WALInsertLockAcquireExclusive(void); @@ -4887,10 +4888,12 @@ CleanupAfterArchiveRecovery(TimeLineID EndOfLogTLI, XLogRecPtr EndOfLog, * Execute the recovery_end_command, if any. */ if (recoveryEndCommand && strcmp(recoveryEndCommand, "") != 0) - ExecuteRecoveryCommand(recoveryEndCommand, - "recovery_end_command", - true, - WAIT_EVENT_RECOVERY_END_COMMAND); + { + char lastRestartPointFname[MAXFNAMELEN]; + + GetOldestRestartPointFileName(lastRestartPointFname); + shell_recovery_end(lastRestartPointFname); + } /* * We switched to a new timeline. Clean up segments on the old timeline. @@ -7307,10 +7310,12 @@ CreateRestartPoint(int flags) * Finally, execute archive_cleanup_command, if any. */ if (archiveCleanupCommand && strcmp(archiveCleanupCommand, "") != 0) - ExecuteRecoveryCommand(archiveCleanupCommand, - "archive_cleanup_command", - false, - WAIT_EVENT_ARCHIVE_CLEANUP_COMMAND); + { + char lastRestartPointFname[MAXFNAMELEN]; + + GetOldestRestartPointFileName(lastRestartPointFname); + shell_archive_cleanup(lastRestartPointFname); + } return true; } @@ -8884,6 +8889,22 @@ GetOldestRestartPoint(XLogRecPtr *oldrecptr, TimeLineID *oldtli) LWLockRelease(ControlFileLock); } +/* + * Returns the WAL file name for the last checkpoint or restartpoint. This is + * the oldest WAL file that we still need if we have to restart recovery. + */ +static void +GetOldestRestartPointFileName(char *fname) +{ + XLogRecPtr restartRedoPtr; + TimeLineID restartTli; + XLogSegNo restartSegNo; + + GetOldestRestartPoint(&restartRedoPtr, &restartTli); + XLByteToSeg(restartRedoPtr, restartSegNo, wal_segment_size); + XLogFileName(fname, restartTli, restartSegNo, wal_segment_size); +} + /* Thin wrapper around ShutdownWalRcv(). */ void XLogShutdownWalRcv(void) diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index fcc87ff44f..b5cb060d55 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -23,7 +23,6 @@ #include "access/xlog_internal.h" #include "access/xlogarchive.h" #include "common/archive.h" -#include "common/percentrepl.h" #include "miscadmin.h" #include "pgstat.h" #include "postmaster/startup.h" @@ -57,9 +56,8 @@ RestoreArchivedFile(char *path, const char *xlogfname, bool cleanupEnabled) { char xlogpath[MAXPGPATH]; - char *xlogRestoreCmd; char lastRestartPointFname[MAXPGPATH]; - int rc; + bool ret; struct stat stat_buf; XLogSegNo restartSegNo; XLogRecPtr restartRedoPtr; @@ -150,15 +148,6 @@ RestoreArchivedFile(char *path, const char *xlogfname, else XLogFileName(lastRestartPointFname, 0, 0L, wal_segment_size); - /* Build the restore command to execute */ - xlogRestoreCmd = BuildRestoreCommand(recoveryRestoreCommand, - xlogpath, xlogfname, - lastRestartPointFname); - - ereport(DEBUG3, - (errmsg_internal("executing restore command \"%s\"", - xlogRestoreCmd))); - /* * Check signals before restore command and reset afterwards. */ @@ -167,15 +156,11 @@ RestoreArchivedFile(char *path, const char *xlogfname, /* * Copy xlog from archival storage to XLOGDIR */ - fflush(NULL); - pgstat_report_wait_start(WAIT_EVENT_RESTORE_COMMAND); - rc = system(xlogRestoreCmd); - pgstat_report_wait_end(); + ret = shell_restore(xlogfname, xlogpath, lastRestartPointFname); PostRestoreCommand(); - pfree(xlogRestoreCmd); - if (rc == 0) + if (ret) { /* * command apparently succeeded, but let's make sure the file is @@ -231,37 +216,6 @@ RestoreArchivedFile(char *path, const char *xlogfname, } } - /* - * Remember, we rollforward UNTIL the restore fails so failure here is - * just part of the process... that makes it difficult to determine - * whether the restore failed because there isn't an archive to restore, - * or because the administrator has specified the restore program - * incorrectly. We have to assume the former. - * - * However, if the failure was due to any sort of signal, it's best to - * punt and abort recovery. (If we "return false" here, upper levels will - * assume that recovery is complete and start up the database!) It's - * essential to abort on child SIGINT and SIGQUIT, because per spec - * system() ignores SIGINT and SIGQUIT while waiting; if we see one of - * those it's a good bet we should have gotten it too. - * - * On SIGTERM, assume we have received a fast shutdown request, and exit - * cleanly. It's pure chance whether we receive the SIGTERM first, or the - * child process. If we receive it first, the signal handler will call - * proc_exit, otherwise we do it here. If we or the child process received - * SIGTERM for any other reason than a fast shutdown request, postmaster - * will perform an immediate shutdown when it sees us exiting - * unexpectedly. - * - * We treat hard shell errors such as "command not found" as fatal, too. - */ - if (wait_result_is_signal(rc, SIGTERM)) - proc_exit(1); - - ereport(wait_result_is_any_signal(rc, true) ? FATAL : DEBUG2, - (errmsg("could not restore file \"%s\" from archive: %s", - xlogfname, wait_result_to_str(rc)))); - not_available: /* @@ -275,74 +229,6 @@ not_available: return false; } -/* - * Attempt to execute an external shell command during recovery. - * - * 'command' is the shell command to be executed, 'commandName' is a - * human-readable name describing the command emitted in the logs. If - * 'failOnSignal' is true and the command is killed by a signal, a FATAL - * error is thrown. Otherwise a WARNING is emitted. - * - * This is currently used for recovery_end_command and archive_cleanup_command. - */ -void -ExecuteRecoveryCommand(const char *command, const char *commandName, - bool failOnSignal, uint32 wait_event_info) -{ - char *xlogRecoveryCmd; - char lastRestartPointFname[MAXPGPATH]; - int rc; - XLogSegNo restartSegNo; - XLogRecPtr restartRedoPtr; - TimeLineID restartTli; - - Assert(command && commandName); - - /* - * Calculate the archive file cutoff point for use during log shipping - * replication. All files earlier than this point can be deleted from the - * archive, though there is no requirement to do so. - */ - GetOldestRestartPoint(&restartRedoPtr, &restartTli); - XLByteToSeg(restartRedoPtr, restartSegNo, wal_segment_size); - XLogFileName(lastRestartPointFname, restartTli, restartSegNo, - wal_segment_size); - - /* - * construct the command to be executed - */ - xlogRecoveryCmd = replace_percent_placeholders(command, commandName, "r", lastRestartPointFname); - - ereport(DEBUG3, - (errmsg_internal("executing %s \"%s\"", commandName, command))); - - /* - * execute the constructed command - */ - fflush(NULL); - pgstat_report_wait_start(wait_event_info); - rc = system(xlogRecoveryCmd); - pgstat_report_wait_end(); - - pfree(xlogRecoveryCmd); - - if (rc != 0) - { - /* - * If the failure was due to any sort of signal, it's best to punt and - * abort recovery. See comments in RestoreArchivedFile(). - */ - ereport((failOnSignal && wait_result_is_any_signal(rc, true)) ? FATAL : WARNING, - /*------ - translator: First %s represents a postgresql.conf parameter name like - "recovery_end_command", the 2nd is the value of that parameter, the - third an already translated error message. */ - (errmsg("%s \"%s\": %s", commandName, - command, wait_result_to_str(rc)))); - } -} - - /* * A file was restored from the archive under a temporary filename (path), * and now we want to keep it. Rename it under the permanent filename in diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 31ff206034..299304703e 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -20,8 +20,6 @@ extern bool RestoreArchivedFile(char *path, const char *xlogfname, const char *recovername, off_t expectedSize, bool cleanupEnabled); -extern void ExecuteRecoveryCommand(const char *command, const char *commandName, - bool failOnSignal, uint32 wait_event_info); extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); extern void XLogArchiveNotify(const char *xlog); extern void XLogArchiveNotifySeg(XLogSegNo segno, TimeLineID tli); @@ -32,4 +30,9 @@ extern bool XLogArchiveIsReady(const char *xlog); extern bool XLogArchiveIsReadyOrDone(const char *xlog); extern void XLogArchiveCleanup(const char *xlog); +extern bool shell_restore(const char *file, const char *path, + const char *lastRestartPointFileName); +extern void shell_archive_cleanup(const char *lastRestartPointFileName); +extern void shell_recovery_end(const char *lastRestartPointFileName); + #endif /* XLOG_ARCHIVE_H */ -- 2.25.1