From 328ed78356e2b270ffe4c84baa462eb6b8e6befb Mon Sep 17 00:00:00 2001 From: Alexey Kondratov Date: Tue, 19 Feb 2019 19:14:53 +0300 Subject: [PATCH v9] pg_rewind: options to use restore_command from command line or cluster config Previously, when pg_rewind could not find required WAL files in the target data directory the rewind process would fail. One had to manually figure out which of required WAL files have already moved to the archival storage and copy them back. This patch adds possibility to specify restore_command via command line option or use one specified inside postgresql.conf. Specified restore_command will be used for automatic retrieval of missing WAL files from archival storage. --- doc/src/sgml/ref/pg_rewind.sgml | 49 +++++++- src/bin/pg_rewind/parsexlog.c | 164 +++++++++++++++++++++++++- src/bin/pg_rewind/pg_rewind.c | 92 ++++++++++++++- src/bin/pg_rewind/pg_rewind.h | 6 +- src/bin/pg_rewind/t/001_basic.pl | 4 +- src/bin/pg_rewind/t/002_databases.pl | 4 +- src/bin/pg_rewind/t/003_extrafiles.pl | 4 +- src/bin/pg_rewind/t/RewindTest.pm | 84 ++++++++++++- 8 files changed, 386 insertions(+), 21 deletions(-) diff --git a/doc/src/sgml/ref/pg_rewind.sgml b/doc/src/sgml/ref/pg_rewind.sgml index 52a1caa246..d5a14a2e08 100644 --- a/doc/src/sgml/ref/pg_rewind.sgml +++ b/doc/src/sgml/ref/pg_rewind.sgml @@ -66,11 +66,12 @@ PostgreSQL documentation can be found either on the target timeline, the source timeline, or their common ancestor. In the typical failover scenario where the target cluster was shut down soon after the divergence, this is not a problem, but if the - target cluster ran for a long time after the divergence, the old WAL - files might no longer be present. In that case, they can be manually - copied from the WAL archive to the pg_wal directory, or - fetched on startup by configuring or - . The use of + target cluster ran for a long time after the divergence, its old WAL + files might no longer be present. In this case, you can manually copy them + from the WAL archive to the pg_wal directory, or run + pg_rewind with the -r or + -R option to automatically retrieve them from the WAL + archive. The use of pg_rewind is not limited to failover, e.g. a standby server can be promoted, run some write transactions, and then rewinded to become a standby again. @@ -202,6 +203,39 @@ PostgreSQL documentation + + + + + + Use the restore_command defined in + postgresql.conf to retrieve WAL files from + the WAL archive if these files are no longer available in the + pg_wal directory of the target cluster. + + + This option cannot be used together with . + + + + + + + + + + Specifies the restore_command to use for retrieving + WAL files from the WAL archive if these files are no longer available + in the pg_wal directory of the target cluster. + + + If restore_command is already set in + postgresql.conf, you can provide the + option instead. + + + + @@ -288,7 +322,10 @@ GRANT EXECUTE ON function pg_catalog.pg_read_binary_file(text, bigint, bigint, b history forked off from the target cluster. For each WAL record, record each data block that was touched. This yields a list of all the data blocks that were changed in the target cluster, after the - source cluster forked off. + source cluster forked off. If some of the WAL files are no longer + available, try re-running pg_rewind with + the or option to search + for the missing files in the WAL archive. diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index f0439edce3..6326e9a899 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -12,6 +12,7 @@ #include "postgres_fe.h" #include +#include #include "pg_rewind.h" #include "filemap.h" @@ -44,6 +45,7 @@ static char xlogfpath[MAXPGPATH]; typedef struct XLogPageReadPrivate { const char *datadir; + const char *restoreCommand; int tliIndex; } XLogPageReadPrivate; @@ -52,6 +54,9 @@ static int SimpleXLogPageRead(XLogReaderState *xlogreader, int reqLen, XLogRecPtr targetRecPtr, char *readBuf, TimeLineID *pageTLI); +static int RestoreArchivedWAL(const char *path, const char *xlogfname, + off_t expectedSize, const char *restoreCommand); + /* * Read WAL from the datadir/pg_wal, starting from 'startpoint' on timeline * index 'tliIndex' in target timeline history, until 'endpoint'. Make note of @@ -59,7 +64,7 @@ static int SimpleXLogPageRead(XLogReaderState *xlogreader, */ void extractPageMap(const char *datadir, XLogRecPtr startpoint, int tliIndex, - XLogRecPtr endpoint) + XLogRecPtr endpoint, const char *restore_command) { XLogRecord *record; XLogReaderState *xlogreader; @@ -68,6 +73,7 @@ extractPageMap(const char *datadir, XLogRecPtr startpoint, int tliIndex, private.datadir = datadir; private.tliIndex = tliIndex; + private.restoreCommand = restore_command; xlogreader = XLogReaderAllocate(WalSegSz, &SimpleXLogPageRead, &private); if (xlogreader == NULL) @@ -154,7 +160,7 @@ readOneRecord(const char *datadir, XLogRecPtr ptr, int tliIndex) void findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex, XLogRecPtr *lastchkptrec, TimeLineID *lastchkpttli, - XLogRecPtr *lastchkptredo) + XLogRecPtr *lastchkptredo, const char *restoreCommand) { /* Walk backwards, starting from the given record */ XLogRecord *record; @@ -179,6 +185,7 @@ findLastCheckpoint(const char *datadir, XLogRecPtr forkptr, int tliIndex, private.datadir = datadir; private.tliIndex = tliIndex; + private.restoreCommand = restoreCommand; xlogreader = XLogReaderAllocate(WalSegSz, &SimpleXLogPageRead, &private); if (xlogreader == NULL) @@ -289,8 +296,29 @@ SimpleXLogPageRead(XLogReaderState *xlogreader, XLogRecPtr targetPagePtr, if (xlogreadfd < 0) { - pg_log_error("could not open file \"%s\": %m", xlogfpath); - return -1; + /* + * If we have no restore_command to execute, then exit. + */ + if (private->restoreCommand == NULL) + { + pg_log_error("could not open file \"%s\": %m", xlogfpath); + return -1; + } + + /* + * Since we have restore_command to execute, then try to retrieve + * missing WAL file from the archive. + */ + xlogreadfd = RestoreArchivedWAL(private->datadir, + xlogfname, + WalSegSz, + private->restoreCommand); + + if (xlogreadfd < 0) + return -1; + else + pg_log_debug("using file \"%s\" restored from archive", + xlogfpath); } } @@ -404,3 +432,131 @@ extractPageInfo(XLogReaderState *record) process_block_change(forknum, rnode, blkno); } } + +/* + * Attempt to retrieve the specified file from off-line archival storage. + * If successful return a file descriptor of restored WAL file, else + * return -1. + * + * For fixed-size files, the caller may pass the expected size as an + * additional crosscheck on successful recovery. If the file size is not + * known, set expectedSize = 0. + */ +static int +RestoreArchivedWAL(const char *path, const char *xlogfname, + off_t expectedSize, const char *restoreCommand) +{ + char xlogpath[MAXPGPATH], + xlogRestoreCmd[MAXPGPATH], + *dp, + *endp; + const char *sp; + int rc, + xlogfd; + struct stat stat_buf; + + snprintf(xlogpath, MAXPGPATH, "%s/" XLOGDIR "/%s", path, xlogfname); + + /* + * Construct the command to be executed. + */ + dp = xlogRestoreCmd; + endp = xlogRestoreCmd + MAXPGPATH - 1; + *endp = '\0'; + + for (sp = restoreCommand; *sp; sp++) + { + if (*sp == '%') + { + switch (sp[1]) + { + case 'p': + /* %p: relative path of target file */ + sp++; + StrNCpy(dp, xlogpath, endp - dp); + make_native_path(dp); + dp += strlen(dp); + break; + case 'f': + /* %f: filename of desired file */ + sp++; + StrNCpy(dp, xlogfname, endp - dp); + dp += strlen(dp); + break; + case 'r': + /* %r: filename of last restartpoint */ + pg_fatal("restore_command with %%r cannot be used with pg_rewind."); + break; + case '%': + /* convert %% to a single % */ + sp++; + if (dp < endp) + *dp++ = *sp; + break; + default: + /* otherwise treat the % as not special */ + if (dp < endp) + *dp++ = *sp; + break; + } + } + else + { + if (dp < endp) + *dp++ = *sp; + } + } + *dp = '\0'; + + /* + * Execute restore_command, which should copy + * the missing WAL file from archival storage. + */ + rc = system(xlogRestoreCmd); + + if (rc == 0) + { + /* + * Command apparently succeeded, but let's make sure the file is + * really there now and has the correct size. + */ + if (stat(xlogpath, &stat_buf) == 0) + { + if (expectedSize > 0 && stat_buf.st_size != expectedSize) + { + pg_log_error("archive file \"%s\" has wrong size: %lu instead of %lu, %s", + xlogfname, (unsigned long) stat_buf.st_size, + (unsigned long) expectedSize, strerror(errno)); + } + else + { + xlogfd = open(xlogpath, O_RDONLY | PG_BINARY, 0); + + if (xlogfd < 0) + pg_log_error("could not open file \"%s\" restored from archive: %s\n", + xlogpath, strerror(errno)); + else + return xlogfd; + } + } + else + { + /* Stat failed */ + pg_log_error("could not stat file \"%s\" restored from archive: %s", + xlogpath, strerror(errno)); + } + } + + /* + * If the failure was due to any sort of signal, then it will be + * misleading to return message 'could not restore file...' and + * propagate result to the upper levels. We should exit right now. + */ + if (wait_result_is_any_signal(rc, false)) + pg_fatal("restore_command failed due to the signal: %s", + wait_result_to_str(rc)); + + pg_log_error("could not restore file \"%s\" from archive\n", + xlogfname); + return -1; +} diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index d378053de4..1633e0271d 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -51,11 +51,13 @@ int WalSegSz; char *datadir_target = NULL; char *datadir_source = NULL; char *connstr_source = NULL; +char *restore_command = NULL; static bool debug = false; bool showprogress = false; bool dry_run = false; bool do_sync = true; +bool restore_wals = false; /* Target history */ TimeLineHistoryEntry *targetHistory; @@ -79,6 +81,9 @@ usage(const char *progname) printf(_(" -N, --no-sync do not wait for changes to be written\n" " safely to disk\n")); printf(_(" -P, --progress write progress messages\n")); + printf(_(" -r, --use-postgresql-conf use restore_command in the postgresql.conf to\n")); + printf(_(" retrieve WALs from archive\n")); + printf(_(" -R, --restore-command=COMMAND restore_command\n")); printf(_(" --debug write a lot of debug messages\n")); printf(_(" -V, --version output version information, then exit\n")); printf(_(" -?, --help show this help, then exit\n")); @@ -98,6 +103,8 @@ main(int argc, char **argv) {"dry-run", no_argument, NULL, 'n'}, {"no-sync", no_argument, NULL, 'N'}, {"progress", no_argument, NULL, 'P'}, + {"use-postgresql-conf", no_argument, NULL, 'r'}, + {"restore-command", required_argument, NULL, 'R'}, {"debug", no_argument, NULL, 3}, {NULL, 0, NULL, 0} }; @@ -134,7 +141,7 @@ main(int argc, char **argv) } } - while ((c = getopt_long(argc, argv, "D:nNP", long_options, &option_index)) != -1) + while ((c = getopt_long(argc, argv, "D:nNPR:r", long_options, &option_index)) != -1) { switch (c) { @@ -146,6 +153,10 @@ main(int argc, char **argv) showprogress = true; break; + case 'r': + restore_wals = true; + break; + case 'n': dry_run = true; break; @@ -163,6 +174,10 @@ main(int argc, char **argv) datadir_target = pg_strdup(optarg); break; + case 'R': + restore_command = pg_strdup(optarg); + break; + case 1: /* --source-pgdata */ datadir_source = pg_strdup(optarg); break; @@ -229,6 +244,74 @@ main(int argc, char **argv) umask(pg_mode_mask); + if (restore_command != NULL) + { + if (restore_wals) + { + pg_log_error("conflicting options: both -r and -R are specified"); + fprintf(stderr, _("You must run %s with either -r/--use-postgresql-conf " + "or -R/--restore-command.\n"), progname); + exit(1); + } + + pg_log_debug("using command line restore_command=\'%s\'.", restore_command); + } + else if (restore_wals) + { + int rc; + char postgres_exec_path[MAXPGPATH], + postgres_cmd[MAXPGPATH], + cmd_output[MAXPGPATH]; + FILE *output_fp; + + /* Find postgres executable. */ + rc = find_other_exec(argv[0], "postgres", + PG_BACKEND_VERSIONSTR, + postgres_exec_path); + + if (rc < 0) + { + char full_path[MAXPGPATH]; + + if (find_my_exec(argv[0], full_path) < 0) + strlcpy(full_path, progname, sizeof(full_path)); + + if (rc == -1) + pg_log_error("The program \"postgres\" is needed by %s but was not found in the\n" + "same directory as \"%s\".\n" + "Check your installation.", + progname, full_path); + else + pg_log_error("The program \"postgres\" was found by \"%s\"\n" + "but was not the same version as %s.\n" + "Check your installation.", + full_path, progname); + exit(1); + } + + /* Build a command to execute for restore_command GUC retrieval if set. */ + snprintf(postgres_cmd, sizeof(postgres_cmd), "%s -D %s -C restore_command", + postgres_exec_path, datadir_target); + + if ((output_fp = popen(postgres_cmd, "r")) == NULL || + fgets(cmd_output, sizeof(cmd_output), output_fp) == NULL) + pg_fatal("could not get restore_command using %s: %s", + postgres_cmd, strerror(errno)); + + pclose(output_fp); + + /* Remove trailing newline */ + if (strchr(cmd_output, '\n') != NULL) + *strchr(cmd_output, '\n') = '\0'; + + if (!strcmp(cmd_output, "")) + pg_fatal("restore_command is not set on the target cluster"); + + restore_command = pg_strdup(cmd_output); + + pg_log_debug("using config variable restore_command=\'%s\'.", restore_command); + } + /* Connect to remote server */ if (connstr_source) libpqConnect(connstr_source); @@ -300,9 +383,8 @@ main(int argc, char **argv) exit(0); } - findLastCheckpoint(datadir_target, divergerec, - lastcommontliIndex, - &chkptrec, &chkpttli, &chkptredo); + findLastCheckpoint(datadir_target, divergerec, lastcommontliIndex, + &chkptrec, &chkpttli, &chkptredo, restore_command); pg_log_info("rewinding from last common checkpoint at %X/%X on timeline %u", (uint32) (chkptrec >> 32), (uint32) chkptrec, chkpttli); @@ -328,7 +410,7 @@ main(int argc, char **argv) if (showprogress) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, - ControlFile_target.checkPoint); + ControlFile_target.checkPoint, restore_command); filemap_finalize(); if (showprogress) diff --git a/src/bin/pg_rewind/pg_rewind.h b/src/bin/pg_rewind/pg_rewind.h index 1125c7e60f..7dc972dc39 100644 --- a/src/bin/pg_rewind/pg_rewind.h +++ b/src/bin/pg_rewind/pg_rewind.h @@ -40,11 +40,13 @@ extern uint64 fetch_done; /* in parsexlog.c */ extern void extractPageMap(const char *datadir, XLogRecPtr startpoint, - int tliIndex, XLogRecPtr endpoint); + int tliIndex, XLogRecPtr endpoint, + const char *restoreCommand); extern void findLastCheckpoint(const char *datadir, XLogRecPtr searchptr, int tliIndex, XLogRecPtr *lastchkptrec, TimeLineID *lastchkpttli, - XLogRecPtr *lastchkptredo); + XLogRecPtr *lastchkptredo, + const char *restoreCommand); extern XLogRecPtr readOneRecord(const char *datadir, XLogRecPtr ptr, int tliIndex); diff --git a/src/bin/pg_rewind/t/001_basic.pl b/src/bin/pg_rewind/t/001_basic.pl index 115192170e..8a6fa33016 100644 --- a/src/bin/pg_rewind/t/001_basic.pl +++ b/src/bin/pg_rewind/t/001_basic.pl @@ -1,7 +1,7 @@ use strict; use warnings; use TestLib; -use Test::More tests => 10; +use Test::More tests => 20; use FindBin; use lib $FindBin::RealBin; @@ -106,5 +106,7 @@ in master, before promotion # Run the test in both modes run_test('local'); run_test('remote'); +run_test('archive'); +run_test('archive_conf'); exit(0); diff --git a/src/bin/pg_rewind/t/002_databases.pl b/src/bin/pg_rewind/t/002_databases.pl index f1eb4fe1d2..69a3c69a85 100644 --- a/src/bin/pg_rewind/t/002_databases.pl +++ b/src/bin/pg_rewind/t/002_databases.pl @@ -1,7 +1,7 @@ use strict; use warnings; use TestLib; -use Test::More tests => 6; +use Test::More tests => 12; use FindBin; use lib $FindBin::RealBin; @@ -70,5 +70,7 @@ template1 # Run the test in both modes. run_test('local'); run_test('remote'); +run_test('archive'); +run_test('archive_conf'); exit(0); diff --git a/src/bin/pg_rewind/t/003_extrafiles.pl b/src/bin/pg_rewind/t/003_extrafiles.pl index c4040bd562..24cec256de 100644 --- a/src/bin/pg_rewind/t/003_extrafiles.pl +++ b/src/bin/pg_rewind/t/003_extrafiles.pl @@ -3,7 +3,7 @@ use strict; use warnings; use TestLib; -use Test::More tests => 4; +use Test::More tests => 8; use File::Find; @@ -90,5 +90,7 @@ sub run_test # Run the test in both modes. run_test('local'); run_test('remote'); +run_test('archive'); +run_test('archive_conf'); exit(0); diff --git a/src/bin/pg_rewind/t/RewindTest.pm b/src/bin/pg_rewind/t/RewindTest.pm index 68b6004e94..9f39224192 100644 --- a/src/bin/pg_rewind/t/RewindTest.pm +++ b/src/bin/pg_rewind/t/RewindTest.pm @@ -35,7 +35,9 @@ use Carp; use Config; use Exporter 'import'; use File::Copy; -use File::Path qw(rmtree); +use File::Glob ':bsd_glob'; +use File::Path qw(remove_tree make_path); +use File::Spec::Functions qw(catdir catfile); use IPC::Run qw(run); use PostgresNode; use TestLib; @@ -216,6 +218,38 @@ sub promote_standby return; } +# Moves WAL files to the temporary location and returns restore_command +# to get them back. +sub move_wals +{ + my $tmp_dir = shift; + my $master_pgdata = shift; + my $wals_archive_dir = catdir($tmp_dir, "master_wals_archive"); + my @wal_files = bsd_glob catfile($master_pgdata, "pg_wal", "0000000*"); + my $restore_command; + + remove_tree($wals_archive_dir); + make_path($wals_archive_dir) or die; + + # Move all old master WAL files to the archive. + # Old master should be stopped at this point. + foreach my $wal_file (@wal_files) + { + move($wal_file, "$wals_archive_dir") or die; + } + + if ($windows_os) + { + $restore_command = "copy $wals_archive_dir\\\%f \%p"; + } + else + { + $restore_command = "cp $wals_archive_dir/\%f \%p"; + } + + return $restore_command; +} + sub run_pg_rewind { my $test_mode = shift; @@ -270,6 +304,54 @@ sub run_pg_rewind ], 'pg_rewind remote'); } + elsif ($test_mode eq "archive") + { + + # Do rewind using a local pgdata as source and + # specified directory with target WALs archive. + my $restore_command = move_wals($tmp_folder, $master_pgdata); + + # Stop the new master and be ready to perform the rewind. + $node_standby->stop; + + command_ok( + [ + 'pg_rewind', + "--debug", + "--source-pgdata=$standby_pgdata", + "--target-pgdata=$master_pgdata", + "--no-sync", + "--restore-command=$restore_command" + ], + 'pg_rewind archive'); + } + elsif ($test_mode eq "archive_conf") + { + + # Do rewind using a local pgdata as source and + # specified directory with target WALs archive. + my $master_conf_path = catfile($master_pgdata, 'postgresql.conf'); + my $restore_command = move_wals($tmp_folder, $master_pgdata); + + # Stop the new master and be ready to perform the rewind. + $node_standby->stop; + + # Add restore_command to postgresql.conf of target cluster. + open(my $conf_fd, ">>", $master_conf_path) or die; + print $conf_fd "\nrestore_command='$restore_command'"; + close $conf_fd; + + command_ok( + [ + 'pg_rewind', + "--debug", + "--source-pgdata=$standby_pgdata", + "--target-pgdata=$master_pgdata", + "--no-sync", + "-r" + ], + 'pg_rewind archive_conf'); + } else { base-commit: da9456d22a7697ef2c5ba9dd1402d948b2ec7f09 -- 2.17.1