public inbox for [email protected]help / color / mirror / Atom feed
[PATCH 3/5] Adjust catcachebench for later patches 11+ messages / 4 participants [nested] [flat]
* [PATCH 3/5] Adjust catcachebench for later patches @ 2019-07-01 06:08 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 11+ messages in thread From: Kyotaro Horiguchi @ 2019-07-01 06:08 UTC (permalink / raw) Make the benchmark use SetCatCacheClock, which is being introduced by the next patch. This temprarily breaks consistency until the next patch is applied. --- contrib/catcachebench/catcachebench.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/contrib/catcachebench/catcachebench.c b/contrib/catcachebench/catcachebench.c index 0cebbbde4f..63a7400463 100644 --- a/contrib/catcachebench/catcachebench.c +++ b/contrib/catcachebench/catcachebench.c @@ -116,9 +116,7 @@ catcachebench2(void) */ if (--ct < 0) { - // We don't have it yet. - //SetCatCacheClock(GetCurrentTimestamp()); - GetCurrentTimestamp(); + SetCatCacheClock(GetCurrentTimestamp()); ct = clock_step; } for (a = 0 ; a < natts ; a++) @@ -168,9 +166,7 @@ catcachebench3(void) */ if (--ct < 0) { - // We don't have it yet. - //SetCatCacheClock(GetCurrentTimestamp()); - GetCurrentTimestamp(); + SetCatCacheClock(GetCurrentTimestamp()); ct = clock_step; } for (a = 0 ; a < natts ; a++) -- 2.16.3 ----Next_Part(Mon_Jul_01_16_02_59_2019_106)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v18-0004-Catcache-pruning-feature.patch" ^ permalink raw reply [nested|flat] 11+ messages in thread
* [PATCH v8 3/4] add support for syncfs in frontend support functions @ 2023-08-31 14:59 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 11+ messages in thread From: Nathan Bossart @ 2023-08-31 14:59 UTC (permalink / raw) --- src/bin/initdb/initdb.c | 5 +- src/bin/pg_basebackup/pg_basebackup.c | 5 +- src/bin/pg_checksums/pg_checksums.c | 3 +- src/bin/pg_dump/pg_backup.h | 4 +- src/bin/pg_dump/pg_backup_archiver.c | 14 ++- src/bin/pg_dump/pg_backup_archiver.h | 1 + src/bin/pg_dump/pg_backup_directory.c | 2 +- src/bin/pg_dump/pg_dump.c | 3 +- src/bin/pg_rewind/file_ops.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 1 + src/bin/pg_rewind/pg_rewind.h | 2 + src/common/file_utils.c | 170 +++++++++++++++++++++----- src/include/common/file_utils.h | 5 +- 13 files changed, 172 insertions(+), 45 deletions(-) diff --git a/src/bin/initdb/initdb.c b/src/bin/initdb/initdb.c index 905b979947..bbea1e412b 100644 --- a/src/bin/initdb/initdb.c +++ b/src/bin/initdb/initdb.c @@ -165,6 +165,7 @@ static bool show_setting = false; static bool data_checksums = false; static char *xlog_dir = NULL; static int wal_segment_size_mb = (DEFAULT_XLOG_SEG_SIZE) / (1024 * 1024); +static DataDirSyncMethod sync_method = DATA_DIR_SYNC_METHOD_FSYNC; /* internal vars */ @@ -3333,7 +3334,7 @@ main(int argc, char *argv[]) fputs(_("syncing data to disk ... "), stdout); fflush(stdout); - fsync_pgdata(pg_data, PG_VERSION_NUM); + fsync_pgdata(pg_data, PG_VERSION_NUM, sync_method); check_ok(); return 0; } @@ -3396,7 +3397,7 @@ main(int argc, char *argv[]) { fputs(_("syncing data to disk ... "), stdout); fflush(stdout); - fsync_pgdata(pg_data, PG_VERSION_NUM); + fsync_pgdata(pg_data, PG_VERSION_NUM, sync_method); check_ok(); } else diff --git a/src/bin/pg_basebackup/pg_basebackup.c b/src/bin/pg_basebackup/pg_basebackup.c index 1dc8efe0cb..1a6eacf6d5 100644 --- a/src/bin/pg_basebackup/pg_basebackup.c +++ b/src/bin/pg_basebackup/pg_basebackup.c @@ -148,6 +148,7 @@ static bool verify_checksums = true; static bool manifest = true; static bool manifest_force_encode = false; static char *manifest_checksums = NULL; +static DataDirSyncMethod sync_method = DATA_DIR_SYNC_METHOD_FSYNC; static bool success = false; static bool made_new_pgdata = false; @@ -2199,11 +2200,11 @@ BaseBackup(char *compression_algorithm, char *compression_detail, if (format == 't') { if (strcmp(basedir, "-") != 0) - (void) fsync_dir_recurse(basedir); + (void) fsync_dir_recurse(basedir, sync_method); } else { - (void) fsync_pgdata(basedir, serverVersion); + (void) fsync_pgdata(basedir, serverVersion, sync_method); } } diff --git a/src/bin/pg_checksums/pg_checksums.c b/src/bin/pg_checksums/pg_checksums.c index 9011a19b4e..123450f483 100644 --- a/src/bin/pg_checksums/pg_checksums.c +++ b/src/bin/pg_checksums/pg_checksums.c @@ -44,6 +44,7 @@ static char *only_filenode = NULL; static bool do_sync = true; static bool verbose = false; static bool showprogress = false; +static DataDirSyncMethod sync_method = DATA_DIR_SYNC_METHOD_FSYNC; typedef enum { @@ -623,7 +624,7 @@ main(int argc, char *argv[]) if (do_sync) { pg_log_info("syncing data directory"); - fsync_pgdata(DataDir, PG_VERSION_NUM); + fsync_pgdata(DataDir, PG_VERSION_NUM, sync_method); } pg_log_info("updating control file"); diff --git a/src/bin/pg_dump/pg_backup.h b/src/bin/pg_dump/pg_backup.h index aba780ef4b..3a57cdd97d 100644 --- a/src/bin/pg_dump/pg_backup.h +++ b/src/bin/pg_dump/pg_backup.h @@ -24,6 +24,7 @@ #define PG_BACKUP_H #include "common/compression.h" +#include "common/file_utils.h" #include "fe_utils/simple_list.h" #include "libpq-fe.h" @@ -307,7 +308,8 @@ extern Archive *OpenArchive(const char *FileSpec, const ArchiveFormat fmt); extern Archive *CreateArchive(const char *FileSpec, const ArchiveFormat fmt, const pg_compress_specification compression_spec, bool dosync, ArchiveMode mode, - SetupWorkerPtrType setupDumpWorker); + SetupWorkerPtrType setupDumpWorker, + DataDirSyncMethod sync_method); /* The --list option */ extern void PrintTOCSummary(Archive *AHX); diff --git a/src/bin/pg_dump/pg_backup_archiver.c b/src/bin/pg_dump/pg_backup_archiver.c index 39ebcfec32..4d83381d84 100644 --- a/src/bin/pg_dump/pg_backup_archiver.c +++ b/src/bin/pg_dump/pg_backup_archiver.c @@ -66,7 +66,8 @@ typedef struct _parallelReadyList static ArchiveHandle *_allocAH(const char *FileSpec, const ArchiveFormat fmt, const pg_compress_specification compression_spec, bool dosync, ArchiveMode mode, - SetupWorkerPtrType setupWorkerPtr); + SetupWorkerPtrType setupWorkerPtr, + DataDirSyncMethod sync_method); static void _getObjectDescription(PQExpBuffer buf, const TocEntry *te); static void _printTocEntry(ArchiveHandle *AH, TocEntry *te, bool isData); static char *sanitize_line(const char *str, bool want_hyphen); @@ -238,11 +239,12 @@ Archive * CreateArchive(const char *FileSpec, const ArchiveFormat fmt, const pg_compress_specification compression_spec, bool dosync, ArchiveMode mode, - SetupWorkerPtrType setupDumpWorker) + SetupWorkerPtrType setupDumpWorker, + DataDirSyncMethod sync_method) { ArchiveHandle *AH = _allocAH(FileSpec, fmt, compression_spec, - dosync, mode, setupDumpWorker); + dosync, mode, setupDumpWorker, sync_method); return (Archive *) AH; } @@ -257,7 +259,8 @@ OpenArchive(const char *FileSpec, const ArchiveFormat fmt) compression_spec.algorithm = PG_COMPRESSION_NONE; AH = _allocAH(FileSpec, fmt, compression_spec, true, - archModeRead, setupRestoreWorker); + archModeRead, setupRestoreWorker, + DATA_DIR_SYNC_METHOD_FSYNC); return (Archive *) AH; } @@ -2233,7 +2236,7 @@ static ArchiveHandle * _allocAH(const char *FileSpec, const ArchiveFormat fmt, const pg_compress_specification compression_spec, bool dosync, ArchiveMode mode, - SetupWorkerPtrType setupWorkerPtr) + SetupWorkerPtrType setupWorkerPtr, DataDirSyncMethod sync_method) { ArchiveHandle *AH; CompressFileHandle *CFH; @@ -2287,6 +2290,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, AH->mode = mode; AH->compression_spec = compression_spec; AH->dosync = dosync; + AH->sync_method = sync_method; memset(&(AH->sqlparse), 0, sizeof(AH->sqlparse)); diff --git a/src/bin/pg_dump/pg_backup_archiver.h b/src/bin/pg_dump/pg_backup_archiver.h index 18b38c17ab..b07673933d 100644 --- a/src/bin/pg_dump/pg_backup_archiver.h +++ b/src/bin/pg_dump/pg_backup_archiver.h @@ -312,6 +312,7 @@ struct _archiveHandle pg_compress_specification compression_spec; /* Requested specification for * compression */ bool dosync; /* data requested to be synced on sight */ + DataDirSyncMethod sync_method; ArchiveMode mode; /* File mode - r or w */ void *formatData; /* Header data specific to file format */ diff --git a/src/bin/pg_dump/pg_backup_directory.c b/src/bin/pg_dump/pg_backup_directory.c index 7f2ac7c7fd..6faa3a511f 100644 --- a/src/bin/pg_dump/pg_backup_directory.c +++ b/src/bin/pg_dump/pg_backup_directory.c @@ -613,7 +613,7 @@ _CloseArchive(ArchiveHandle *AH) * individually. Just recurse once through all the files generated. */ if (AH->dosync) - fsync_dir_recurse(ctx->directory); + fsync_dir_recurse(ctx->directory, AH->sync_method); } AH->FH = NULL; } diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c index 65f64c282d..39a468b131 100644 --- a/src/bin/pg_dump/pg_dump.c +++ b/src/bin/pg_dump/pg_dump.c @@ -357,6 +357,7 @@ main(int argc, char **argv) char *compression_algorithm_str = "none"; char *error_detail = NULL; bool user_compression_defined = false; + DataDirSyncMethod sync_method = DATA_DIR_SYNC_METHOD_FSYNC; static DumpOptions dopt; @@ -777,7 +778,7 @@ main(int argc, char **argv) /* Open the output file */ fout = CreateArchive(filename, archiveFormat, compression_spec, - dosync, archiveMode, setupDumpWorker); + dosync, archiveMode, setupDumpWorker, sync_method); /* Make dump options accessible right away */ SetArchiveOptions(fout, &dopt, NULL); diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 25996b4da4..451fb1856e 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -296,7 +296,7 @@ sync_target_dir(void) if (!do_sync || dry_run) return; - fsync_pgdata(datadir_target, PG_VERSION_NUM); + fsync_pgdata(datadir_target, PG_VERSION_NUM, sync_method); } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index 7f69f02441..bdfacf3263 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -74,6 +74,7 @@ bool showprogress = false; bool dry_run = false; bool do_sync = true; bool restore_wal = false; +DataDirSyncMethod sync_method = DATA_DIR_SYNC_METHOD_FSYNC; /* Target history */ TimeLineHistoryEntry *targetHistory; diff --git a/src/bin/pg_rewind/pg_rewind.h b/src/bin/pg_rewind/pg_rewind.h index ef8bdc1fbb..05729adfef 100644 --- a/src/bin/pg_rewind/pg_rewind.h +++ b/src/bin/pg_rewind/pg_rewind.h @@ -13,6 +13,7 @@ #include "access/timeline.h" #include "common/logging.h" +#include "common/file_utils.h" #include "datapagemap.h" #include "libpq-fe.h" #include "storage/block.h" @@ -24,6 +25,7 @@ extern bool showprogress; extern bool dry_run; extern bool do_sync; extern int WalSegSz; +extern DataDirSyncMethod sync_method; /* Target history */ extern TimeLineHistoryEntry *targetHistory; diff --git a/src/common/file_utils.c b/src/common/file_utils.c index 74833c4acb..05c73c0bb7 100644 --- a/src/common/file_utils.c +++ b/src/common/file_utils.c @@ -51,6 +51,31 @@ static void walkdir(const char *path, int (*action) (const char *fname, bool isdir), bool process_symlinks); +#ifdef HAVE_SYNCFS +static void +do_syncfs(const char *path) +{ + int fd; + + fd = open(path, O_RDONLY, 0); + + if (fd < 0) + { + pg_log_error("could not open file \"%s\": %m", path); + return; + } + + if (syncfs(fd) < 0) + { + pg_log_error("could not synchronize file system for file \"%s\": %m", path); + (void) close(fd); + exit(EXIT_FAILURE); + } + + (void) close(fd); +} +#endif + /* * Issue fsync recursively on PGDATA and all its contents. * @@ -63,7 +88,8 @@ static void walkdir(const char *path, */ void fsync_pgdata(const char *pg_data, - int serverVersion) + int serverVersion, + DataDirSyncMethod sync_method) { bool xlog_is_symlink; char pg_wal[MAXPGPATH]; @@ -89,30 +115,93 @@ fsync_pgdata(const char *pg_data, xlog_is_symlink = true; } - /* - * If possible, hint to the kernel that we're soon going to fsync the data - * directory and its contents. - */ + switch (sync_method) + { + case DATA_DIR_SYNC_METHOD_SYNCFS: + { +#ifndef HAVE_SYNCFS + pg_log_error("this build does not support sync method \"%s\"", + "syncfs"); + exit(EXIT_FAILURE); +#else + DIR *dir; + struct dirent *de; + + /* + * On Linux, we don't have to open every single file one by + * one. We can use syncfs() to sync whole filesystems. We + * only expect filesystem boundaries to exist where we + * tolerate symlinks, namely pg_wal and the tablespaces, so we + * call syncfs() for each of those directories. + */ + + /* Sync the top level pgdata directory. */ + do_syncfs(pg_data); + + /* If any tablespaces are configured, sync each of those. */ + dir = opendir(pg_tblspc); + if (dir == NULL) + pg_log_error("could not open directory \"%s\": %m", + pg_tblspc); + else + { + while (errno = 0, (de = readdir(dir)) != NULL) + { + char subpath[MAXPGPATH * 2]; + + if (strcmp(de->d_name, ".") == 0 || + strcmp(de->d_name, "..") == 0) + continue; + + snprintf(subpath, sizeof(subpath), "%s/%s", + pg_tblspc, de->d_name); + do_syncfs(subpath); + } + + if (errno) + pg_log_error("could not read directory \"%s\": %m", + pg_tblspc); + + (void) closedir(dir); + } + + /* If pg_wal is a symlink, process that too. */ + if (xlog_is_symlink) + do_syncfs(pg_wal); +#endif /* HAVE_SYNCFS */ + } + break; + + case DATA_DIR_SYNC_METHOD_FSYNC: + { + /* + * If possible, hint to the kernel that we're soon going to + * fsync the data directory and its contents. + */ #ifdef PG_FLUSH_DATA_WORKS - walkdir(pg_data, pre_sync_fname, false); - if (xlog_is_symlink) - walkdir(pg_wal, pre_sync_fname, false); - walkdir(pg_tblspc, pre_sync_fname, true); + walkdir(pg_data, pre_sync_fname, false); + if (xlog_is_symlink) + walkdir(pg_wal, pre_sync_fname, false); + walkdir(pg_tblspc, pre_sync_fname, true); #endif - /* - * Now we do the fsync()s in the same order. - * - * The main call ignores symlinks, so in addition to specially processing - * pg_wal if it's a symlink, pg_tblspc has to be visited separately with - * process_symlinks = true. Note that if there are any plain directories - * in pg_tblspc, they'll get fsync'd twice. That's not an expected case - * so we don't worry about optimizing it. - */ - walkdir(pg_data, fsync_fname, false); - if (xlog_is_symlink) - walkdir(pg_wal, fsync_fname, false); - walkdir(pg_tblspc, fsync_fname, true); + /* + * Now we do the fsync()s in the same order. + * + * The main call ignores symlinks, so in addition to specially + * processing pg_wal if it's a symlink, pg_tblspc has to be + * visited separately with process_symlinks = true. Note that + * if there are any plain directories in pg_tblspc, they'll + * get fsync'd twice. That's not an expected case so we don't + * worry about optimizing it. + */ + walkdir(pg_data, fsync_fname, false); + if (xlog_is_symlink) + walkdir(pg_wal, fsync_fname, false); + walkdir(pg_tblspc, fsync_fname, true); + } + break; + } } /* @@ -121,17 +210,40 @@ fsync_pgdata(const char *pg_data, * This is a convenient wrapper on top of walkdir(). */ void -fsync_dir_recurse(const char *dir) +fsync_dir_recurse(const char *dir, DataDirSyncMethod sync_method) { - /* - * If possible, hint to the kernel that we're soon going to fsync the data - * directory and its contents. - */ + switch (sync_method) + { + case DATA_DIR_SYNC_METHOD_SYNCFS: + { +#ifndef HAVE_SYNCFS + pg_log_error("this build does not support sync method \"%s\"", + "syncfs"); + exit(EXIT_FAILURE); +#else + /* + * On Linux, we don't have to open every single file one by + * one. We can use syncfs() to sync the whole filesystem. + */ + do_syncfs(dir); +#endif /* HAVE_SYNCFS */ + } + break; + + case DATA_DIR_SYNC_METHOD_FSYNC: + { + /* + * If possible, hint to the kernel that we're soon going to + * fsync the data directory and its contents. + */ #ifdef PG_FLUSH_DATA_WORKS - walkdir(dir, pre_sync_fname, false); + walkdir(dir, pre_sync_fname, false); #endif - walkdir(dir, fsync_fname, false); + walkdir(dir, fsync_fname, false); + } + break; + } } /* diff --git a/src/include/common/file_utils.h b/src/include/common/file_utils.h index 7da21f15e6..cae6159bf6 100644 --- a/src/include/common/file_utils.h +++ b/src/include/common/file_utils.h @@ -34,8 +34,9 @@ struct iovec; /* avoid including port/pg_iovec.h here */ #ifdef FRONTEND extern int fsync_fname(const char *fname, bool isdir); -extern void fsync_pgdata(const char *pg_data, int serverVersion); -extern void fsync_dir_recurse(const char *dir); +extern void fsync_pgdata(const char *pg_data, int serverVersion, + DataDirSyncMethod sync_method); +extern void fsync_dir_recurse(const char *dir, DataDirSyncMethod sync_method); extern int durable_rename(const char *oldfile, const char *newfile); extern int fsync_parent_path(const char *fname); #endif -- 2.25.1 --oyUTqETQ0mS9luUI Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0004-allow-syncfs-in-frontend-utilities.patch" ^ permalink raw reply [nested|flat] 11+ messages in thread
* [PATCH v8 3/4] add support for syncfs in frontend support functions @ 2023-08-31 14:59 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 11+ messages in thread From: Nathan Bossart @ 2023-08-31 14:59 UTC (permalink / raw) --- src/bin/initdb/initdb.c | 5 +- src/bin/pg_basebackup/pg_basebackup.c | 5 +- src/bin/pg_checksums/pg_checksums.c | 3 +- src/bin/pg_dump/pg_backup.h | 4 +- src/bin/pg_dump/pg_backup_archiver.c | 14 ++- src/bin/pg_dump/pg_backup_archiver.h | 1 + src/bin/pg_dump/pg_backup_directory.c | 2 +- src/bin/pg_dump/pg_dump.c | 3 +- src/bin/pg_rewind/file_ops.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 1 + src/bin/pg_rewind/pg_rewind.h | 2 + src/common/file_utils.c | 170 +++++++++++++++++++++----- src/include/common/file_utils.h | 5 +- 13 files changed, 172 insertions(+), 45 deletions(-) diff --git a/src/bin/initdb/initdb.c b/src/bin/initdb/initdb.c index 905b979947..bbea1e412b 100644 --- a/src/bin/initdb/initdb.c +++ b/src/bin/initdb/initdb.c @@ -165,6 +165,7 @@ static bool show_setting = false; static bool data_checksums = false; static char *xlog_dir = NULL; static int wal_segment_size_mb = (DEFAULT_XLOG_SEG_SIZE) / (1024 * 1024); +static DataDirSyncMethod sync_method = DATA_DIR_SYNC_METHOD_FSYNC; /* internal vars */ @@ -3333,7 +3334,7 @@ main(int argc, char *argv[]) fputs(_("syncing data to disk ... "), stdout); fflush(stdout); - fsync_pgdata(pg_data, PG_VERSION_NUM); + fsync_pgdata(pg_data, PG_VERSION_NUM, sync_method); check_ok(); return 0; } @@ -3396,7 +3397,7 @@ main(int argc, char *argv[]) { fputs(_("syncing data to disk ... "), stdout); fflush(stdout); - fsync_pgdata(pg_data, PG_VERSION_NUM); + fsync_pgdata(pg_data, PG_VERSION_NUM, sync_method); check_ok(); } else diff --git a/src/bin/pg_basebackup/pg_basebackup.c b/src/bin/pg_basebackup/pg_basebackup.c index 1dc8efe0cb..1a6eacf6d5 100644 --- a/src/bin/pg_basebackup/pg_basebackup.c +++ b/src/bin/pg_basebackup/pg_basebackup.c @@ -148,6 +148,7 @@ static bool verify_checksums = true; static bool manifest = true; static bool manifest_force_encode = false; static char *manifest_checksums = NULL; +static DataDirSyncMethod sync_method = DATA_DIR_SYNC_METHOD_FSYNC; static bool success = false; static bool made_new_pgdata = false; @@ -2199,11 +2200,11 @@ BaseBackup(char *compression_algorithm, char *compression_detail, if (format == 't') { if (strcmp(basedir, "-") != 0) - (void) fsync_dir_recurse(basedir); + (void) fsync_dir_recurse(basedir, sync_method); } else { - (void) fsync_pgdata(basedir, serverVersion); + (void) fsync_pgdata(basedir, serverVersion, sync_method); } } diff --git a/src/bin/pg_checksums/pg_checksums.c b/src/bin/pg_checksums/pg_checksums.c index 9011a19b4e..123450f483 100644 --- a/src/bin/pg_checksums/pg_checksums.c +++ b/src/bin/pg_checksums/pg_checksums.c @@ -44,6 +44,7 @@ static char *only_filenode = NULL; static bool do_sync = true; static bool verbose = false; static bool showprogress = false; +static DataDirSyncMethod sync_method = DATA_DIR_SYNC_METHOD_FSYNC; typedef enum { @@ -623,7 +624,7 @@ main(int argc, char *argv[]) if (do_sync) { pg_log_info("syncing data directory"); - fsync_pgdata(DataDir, PG_VERSION_NUM); + fsync_pgdata(DataDir, PG_VERSION_NUM, sync_method); } pg_log_info("updating control file"); diff --git a/src/bin/pg_dump/pg_backup.h b/src/bin/pg_dump/pg_backup.h index aba780ef4b..3a57cdd97d 100644 --- a/src/bin/pg_dump/pg_backup.h +++ b/src/bin/pg_dump/pg_backup.h @@ -24,6 +24,7 @@ #define PG_BACKUP_H #include "common/compression.h" +#include "common/file_utils.h" #include "fe_utils/simple_list.h" #include "libpq-fe.h" @@ -307,7 +308,8 @@ extern Archive *OpenArchive(const char *FileSpec, const ArchiveFormat fmt); extern Archive *CreateArchive(const char *FileSpec, const ArchiveFormat fmt, const pg_compress_specification compression_spec, bool dosync, ArchiveMode mode, - SetupWorkerPtrType setupDumpWorker); + SetupWorkerPtrType setupDumpWorker, + DataDirSyncMethod sync_method); /* The --list option */ extern void PrintTOCSummary(Archive *AHX); diff --git a/src/bin/pg_dump/pg_backup_archiver.c b/src/bin/pg_dump/pg_backup_archiver.c index 39ebcfec32..4d83381d84 100644 --- a/src/bin/pg_dump/pg_backup_archiver.c +++ b/src/bin/pg_dump/pg_backup_archiver.c @@ -66,7 +66,8 @@ typedef struct _parallelReadyList static ArchiveHandle *_allocAH(const char *FileSpec, const ArchiveFormat fmt, const pg_compress_specification compression_spec, bool dosync, ArchiveMode mode, - SetupWorkerPtrType setupWorkerPtr); + SetupWorkerPtrType setupWorkerPtr, + DataDirSyncMethod sync_method); static void _getObjectDescription(PQExpBuffer buf, const TocEntry *te); static void _printTocEntry(ArchiveHandle *AH, TocEntry *te, bool isData); static char *sanitize_line(const char *str, bool want_hyphen); @@ -238,11 +239,12 @@ Archive * CreateArchive(const char *FileSpec, const ArchiveFormat fmt, const pg_compress_specification compression_spec, bool dosync, ArchiveMode mode, - SetupWorkerPtrType setupDumpWorker) + SetupWorkerPtrType setupDumpWorker, + DataDirSyncMethod sync_method) { ArchiveHandle *AH = _allocAH(FileSpec, fmt, compression_spec, - dosync, mode, setupDumpWorker); + dosync, mode, setupDumpWorker, sync_method); return (Archive *) AH; } @@ -257,7 +259,8 @@ OpenArchive(const char *FileSpec, const ArchiveFormat fmt) compression_spec.algorithm = PG_COMPRESSION_NONE; AH = _allocAH(FileSpec, fmt, compression_spec, true, - archModeRead, setupRestoreWorker); + archModeRead, setupRestoreWorker, + DATA_DIR_SYNC_METHOD_FSYNC); return (Archive *) AH; } @@ -2233,7 +2236,7 @@ static ArchiveHandle * _allocAH(const char *FileSpec, const ArchiveFormat fmt, const pg_compress_specification compression_spec, bool dosync, ArchiveMode mode, - SetupWorkerPtrType setupWorkerPtr) + SetupWorkerPtrType setupWorkerPtr, DataDirSyncMethod sync_method) { ArchiveHandle *AH; CompressFileHandle *CFH; @@ -2287,6 +2290,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, AH->mode = mode; AH->compression_spec = compression_spec; AH->dosync = dosync; + AH->sync_method = sync_method; memset(&(AH->sqlparse), 0, sizeof(AH->sqlparse)); diff --git a/src/bin/pg_dump/pg_backup_archiver.h b/src/bin/pg_dump/pg_backup_archiver.h index 18b38c17ab..b07673933d 100644 --- a/src/bin/pg_dump/pg_backup_archiver.h +++ b/src/bin/pg_dump/pg_backup_archiver.h @@ -312,6 +312,7 @@ struct _archiveHandle pg_compress_specification compression_spec; /* Requested specification for * compression */ bool dosync; /* data requested to be synced on sight */ + DataDirSyncMethod sync_method; ArchiveMode mode; /* File mode - r or w */ void *formatData; /* Header data specific to file format */ diff --git a/src/bin/pg_dump/pg_backup_directory.c b/src/bin/pg_dump/pg_backup_directory.c index 7f2ac7c7fd..6faa3a511f 100644 --- a/src/bin/pg_dump/pg_backup_directory.c +++ b/src/bin/pg_dump/pg_backup_directory.c @@ -613,7 +613,7 @@ _CloseArchive(ArchiveHandle *AH) * individually. Just recurse once through all the files generated. */ if (AH->dosync) - fsync_dir_recurse(ctx->directory); + fsync_dir_recurse(ctx->directory, AH->sync_method); } AH->FH = NULL; } diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c index 65f64c282d..39a468b131 100644 --- a/src/bin/pg_dump/pg_dump.c +++ b/src/bin/pg_dump/pg_dump.c @@ -357,6 +357,7 @@ main(int argc, char **argv) char *compression_algorithm_str = "none"; char *error_detail = NULL; bool user_compression_defined = false; + DataDirSyncMethod sync_method = DATA_DIR_SYNC_METHOD_FSYNC; static DumpOptions dopt; @@ -777,7 +778,7 @@ main(int argc, char **argv) /* Open the output file */ fout = CreateArchive(filename, archiveFormat, compression_spec, - dosync, archiveMode, setupDumpWorker); + dosync, archiveMode, setupDumpWorker, sync_method); /* Make dump options accessible right away */ SetArchiveOptions(fout, &dopt, NULL); diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 25996b4da4..451fb1856e 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -296,7 +296,7 @@ sync_target_dir(void) if (!do_sync || dry_run) return; - fsync_pgdata(datadir_target, PG_VERSION_NUM); + fsync_pgdata(datadir_target, PG_VERSION_NUM, sync_method); } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index 7f69f02441..bdfacf3263 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -74,6 +74,7 @@ bool showprogress = false; bool dry_run = false; bool do_sync = true; bool restore_wal = false; +DataDirSyncMethod sync_method = DATA_DIR_SYNC_METHOD_FSYNC; /* Target history */ TimeLineHistoryEntry *targetHistory; diff --git a/src/bin/pg_rewind/pg_rewind.h b/src/bin/pg_rewind/pg_rewind.h index ef8bdc1fbb..05729adfef 100644 --- a/src/bin/pg_rewind/pg_rewind.h +++ b/src/bin/pg_rewind/pg_rewind.h @@ -13,6 +13,7 @@ #include "access/timeline.h" #include "common/logging.h" +#include "common/file_utils.h" #include "datapagemap.h" #include "libpq-fe.h" #include "storage/block.h" @@ -24,6 +25,7 @@ extern bool showprogress; extern bool dry_run; extern bool do_sync; extern int WalSegSz; +extern DataDirSyncMethod sync_method; /* Target history */ extern TimeLineHistoryEntry *targetHistory; diff --git a/src/common/file_utils.c b/src/common/file_utils.c index 74833c4acb..05c73c0bb7 100644 --- a/src/common/file_utils.c +++ b/src/common/file_utils.c @@ -51,6 +51,31 @@ static void walkdir(const char *path, int (*action) (const char *fname, bool isdir), bool process_symlinks); +#ifdef HAVE_SYNCFS +static void +do_syncfs(const char *path) +{ + int fd; + + fd = open(path, O_RDONLY, 0); + + if (fd < 0) + { + pg_log_error("could not open file \"%s\": %m", path); + return; + } + + if (syncfs(fd) < 0) + { + pg_log_error("could not synchronize file system for file \"%s\": %m", path); + (void) close(fd); + exit(EXIT_FAILURE); + } + + (void) close(fd); +} +#endif + /* * Issue fsync recursively on PGDATA and all its contents. * @@ -63,7 +88,8 @@ static void walkdir(const char *path, */ void fsync_pgdata(const char *pg_data, - int serverVersion) + int serverVersion, + DataDirSyncMethod sync_method) { bool xlog_is_symlink; char pg_wal[MAXPGPATH]; @@ -89,30 +115,93 @@ fsync_pgdata(const char *pg_data, xlog_is_symlink = true; } - /* - * If possible, hint to the kernel that we're soon going to fsync the data - * directory and its contents. - */ + switch (sync_method) + { + case DATA_DIR_SYNC_METHOD_SYNCFS: + { +#ifndef HAVE_SYNCFS + pg_log_error("this build does not support sync method \"%s\"", + "syncfs"); + exit(EXIT_FAILURE); +#else + DIR *dir; + struct dirent *de; + + /* + * On Linux, we don't have to open every single file one by + * one. We can use syncfs() to sync whole filesystems. We + * only expect filesystem boundaries to exist where we + * tolerate symlinks, namely pg_wal and the tablespaces, so we + * call syncfs() for each of those directories. + */ + + /* Sync the top level pgdata directory. */ + do_syncfs(pg_data); + + /* If any tablespaces are configured, sync each of those. */ + dir = opendir(pg_tblspc); + if (dir == NULL) + pg_log_error("could not open directory \"%s\": %m", + pg_tblspc); + else + { + while (errno = 0, (de = readdir(dir)) != NULL) + { + char subpath[MAXPGPATH * 2]; + + if (strcmp(de->d_name, ".") == 0 || + strcmp(de->d_name, "..") == 0) + continue; + + snprintf(subpath, sizeof(subpath), "%s/%s", + pg_tblspc, de->d_name); + do_syncfs(subpath); + } + + if (errno) + pg_log_error("could not read directory \"%s\": %m", + pg_tblspc); + + (void) closedir(dir); + } + + /* If pg_wal is a symlink, process that too. */ + if (xlog_is_symlink) + do_syncfs(pg_wal); +#endif /* HAVE_SYNCFS */ + } + break; + + case DATA_DIR_SYNC_METHOD_FSYNC: + { + /* + * If possible, hint to the kernel that we're soon going to + * fsync the data directory and its contents. + */ #ifdef PG_FLUSH_DATA_WORKS - walkdir(pg_data, pre_sync_fname, false); - if (xlog_is_symlink) - walkdir(pg_wal, pre_sync_fname, false); - walkdir(pg_tblspc, pre_sync_fname, true); + walkdir(pg_data, pre_sync_fname, false); + if (xlog_is_symlink) + walkdir(pg_wal, pre_sync_fname, false); + walkdir(pg_tblspc, pre_sync_fname, true); #endif - /* - * Now we do the fsync()s in the same order. - * - * The main call ignores symlinks, so in addition to specially processing - * pg_wal if it's a symlink, pg_tblspc has to be visited separately with - * process_symlinks = true. Note that if there are any plain directories - * in pg_tblspc, they'll get fsync'd twice. That's not an expected case - * so we don't worry about optimizing it. - */ - walkdir(pg_data, fsync_fname, false); - if (xlog_is_symlink) - walkdir(pg_wal, fsync_fname, false); - walkdir(pg_tblspc, fsync_fname, true); + /* + * Now we do the fsync()s in the same order. + * + * The main call ignores symlinks, so in addition to specially + * processing pg_wal if it's a symlink, pg_tblspc has to be + * visited separately with process_symlinks = true. Note that + * if there are any plain directories in pg_tblspc, they'll + * get fsync'd twice. That's not an expected case so we don't + * worry about optimizing it. + */ + walkdir(pg_data, fsync_fname, false); + if (xlog_is_symlink) + walkdir(pg_wal, fsync_fname, false); + walkdir(pg_tblspc, fsync_fname, true); + } + break; + } } /* @@ -121,17 +210,40 @@ fsync_pgdata(const char *pg_data, * This is a convenient wrapper on top of walkdir(). */ void -fsync_dir_recurse(const char *dir) +fsync_dir_recurse(const char *dir, DataDirSyncMethod sync_method) { - /* - * If possible, hint to the kernel that we're soon going to fsync the data - * directory and its contents. - */ + switch (sync_method) + { + case DATA_DIR_SYNC_METHOD_SYNCFS: + { +#ifndef HAVE_SYNCFS + pg_log_error("this build does not support sync method \"%s\"", + "syncfs"); + exit(EXIT_FAILURE); +#else + /* + * On Linux, we don't have to open every single file one by + * one. We can use syncfs() to sync the whole filesystem. + */ + do_syncfs(dir); +#endif /* HAVE_SYNCFS */ + } + break; + + case DATA_DIR_SYNC_METHOD_FSYNC: + { + /* + * If possible, hint to the kernel that we're soon going to + * fsync the data directory and its contents. + */ #ifdef PG_FLUSH_DATA_WORKS - walkdir(dir, pre_sync_fname, false); + walkdir(dir, pre_sync_fname, false); #endif - walkdir(dir, fsync_fname, false); + walkdir(dir, fsync_fname, false); + } + break; + } } /* diff --git a/src/include/common/file_utils.h b/src/include/common/file_utils.h index 7da21f15e6..cae6159bf6 100644 --- a/src/include/common/file_utils.h +++ b/src/include/common/file_utils.h @@ -34,8 +34,9 @@ struct iovec; /* avoid including port/pg_iovec.h here */ #ifdef FRONTEND extern int fsync_fname(const char *fname, bool isdir); -extern void fsync_pgdata(const char *pg_data, int serverVersion); -extern void fsync_dir_recurse(const char *dir); +extern void fsync_pgdata(const char *pg_data, int serverVersion, + DataDirSyncMethod sync_method); +extern void fsync_dir_recurse(const char *dir, DataDirSyncMethod sync_method); extern int durable_rename(const char *oldfile, const char *newfile); extern int fsync_parent_path(const char *fname); #endif -- 2.25.1 --oyUTqETQ0mS9luUI Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0004-allow-syncfs-in-frontend-utilities.patch" ^ permalink raw reply [nested|flat] 11+ messages in thread
* [PATCH v9 3/4] add support for syncfs in frontend support functions @ 2023-08-31 14:59 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 11+ messages in thread From: Nathan Bossart @ 2023-08-31 14:59 UTC (permalink / raw) --- src/bin/initdb/initdb.c | 5 +- src/bin/pg_basebackup/pg_basebackup.c | 5 +- src/bin/pg_checksums/pg_checksums.c | 3 +- src/bin/pg_dump/pg_backup.h | 4 +- src/bin/pg_dump/pg_backup_archiver.c | 14 ++- src/bin/pg_dump/pg_backup_archiver.h | 1 + src/bin/pg_dump/pg_backup_directory.c | 2 +- src/bin/pg_dump/pg_dump.c | 3 +- src/bin/pg_rewind/file_ops.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 1 + src/bin/pg_rewind/pg_rewind.h | 2 + src/common/file_utils.c | 170 +++++++++++++++++++++----- src/include/common/file_utils.h | 5 +- 13 files changed, 172 insertions(+), 45 deletions(-) diff --git a/src/bin/initdb/initdb.c b/src/bin/initdb/initdb.c index 905b979947..bbea1e412b 100644 --- a/src/bin/initdb/initdb.c +++ b/src/bin/initdb/initdb.c @@ -165,6 +165,7 @@ static bool show_setting = false; static bool data_checksums = false; static char *xlog_dir = NULL; static int wal_segment_size_mb = (DEFAULT_XLOG_SEG_SIZE) / (1024 * 1024); +static DataDirSyncMethod sync_method = DATA_DIR_SYNC_METHOD_FSYNC; /* internal vars */ @@ -3333,7 +3334,7 @@ main(int argc, char *argv[]) fputs(_("syncing data to disk ... "), stdout); fflush(stdout); - fsync_pgdata(pg_data, PG_VERSION_NUM); + fsync_pgdata(pg_data, PG_VERSION_NUM, sync_method); check_ok(); return 0; } @@ -3396,7 +3397,7 @@ main(int argc, char *argv[]) { fputs(_("syncing data to disk ... "), stdout); fflush(stdout); - fsync_pgdata(pg_data, PG_VERSION_NUM); + fsync_pgdata(pg_data, PG_VERSION_NUM, sync_method); check_ok(); } else diff --git a/src/bin/pg_basebackup/pg_basebackup.c b/src/bin/pg_basebackup/pg_basebackup.c index 1dc8efe0cb..1a6eacf6d5 100644 --- a/src/bin/pg_basebackup/pg_basebackup.c +++ b/src/bin/pg_basebackup/pg_basebackup.c @@ -148,6 +148,7 @@ static bool verify_checksums = true; static bool manifest = true; static bool manifest_force_encode = false; static char *manifest_checksums = NULL; +static DataDirSyncMethod sync_method = DATA_DIR_SYNC_METHOD_FSYNC; static bool success = false; static bool made_new_pgdata = false; @@ -2199,11 +2200,11 @@ BaseBackup(char *compression_algorithm, char *compression_detail, if (format == 't') { if (strcmp(basedir, "-") != 0) - (void) fsync_dir_recurse(basedir); + (void) fsync_dir_recurse(basedir, sync_method); } else { - (void) fsync_pgdata(basedir, serverVersion); + (void) fsync_pgdata(basedir, serverVersion, sync_method); } } diff --git a/src/bin/pg_checksums/pg_checksums.c b/src/bin/pg_checksums/pg_checksums.c index 9011a19b4e..123450f483 100644 --- a/src/bin/pg_checksums/pg_checksums.c +++ b/src/bin/pg_checksums/pg_checksums.c @@ -44,6 +44,7 @@ static char *only_filenode = NULL; static bool do_sync = true; static bool verbose = false; static bool showprogress = false; +static DataDirSyncMethod sync_method = DATA_DIR_SYNC_METHOD_FSYNC; typedef enum { @@ -623,7 +624,7 @@ main(int argc, char *argv[]) if (do_sync) { pg_log_info("syncing data directory"); - fsync_pgdata(DataDir, PG_VERSION_NUM); + fsync_pgdata(DataDir, PG_VERSION_NUM, sync_method); } pg_log_info("updating control file"); diff --git a/src/bin/pg_dump/pg_backup.h b/src/bin/pg_dump/pg_backup.h index aba780ef4b..3a57cdd97d 100644 --- a/src/bin/pg_dump/pg_backup.h +++ b/src/bin/pg_dump/pg_backup.h @@ -24,6 +24,7 @@ #define PG_BACKUP_H #include "common/compression.h" +#include "common/file_utils.h" #include "fe_utils/simple_list.h" #include "libpq-fe.h" @@ -307,7 +308,8 @@ extern Archive *OpenArchive(const char *FileSpec, const ArchiveFormat fmt); extern Archive *CreateArchive(const char *FileSpec, const ArchiveFormat fmt, const pg_compress_specification compression_spec, bool dosync, ArchiveMode mode, - SetupWorkerPtrType setupDumpWorker); + SetupWorkerPtrType setupDumpWorker, + DataDirSyncMethod sync_method); /* The --list option */ extern void PrintTOCSummary(Archive *AHX); diff --git a/src/bin/pg_dump/pg_backup_archiver.c b/src/bin/pg_dump/pg_backup_archiver.c index 39ebcfec32..4d83381d84 100644 --- a/src/bin/pg_dump/pg_backup_archiver.c +++ b/src/bin/pg_dump/pg_backup_archiver.c @@ -66,7 +66,8 @@ typedef struct _parallelReadyList static ArchiveHandle *_allocAH(const char *FileSpec, const ArchiveFormat fmt, const pg_compress_specification compression_spec, bool dosync, ArchiveMode mode, - SetupWorkerPtrType setupWorkerPtr); + SetupWorkerPtrType setupWorkerPtr, + DataDirSyncMethod sync_method); static void _getObjectDescription(PQExpBuffer buf, const TocEntry *te); static void _printTocEntry(ArchiveHandle *AH, TocEntry *te, bool isData); static char *sanitize_line(const char *str, bool want_hyphen); @@ -238,11 +239,12 @@ Archive * CreateArchive(const char *FileSpec, const ArchiveFormat fmt, const pg_compress_specification compression_spec, bool dosync, ArchiveMode mode, - SetupWorkerPtrType setupDumpWorker) + SetupWorkerPtrType setupDumpWorker, + DataDirSyncMethod sync_method) { ArchiveHandle *AH = _allocAH(FileSpec, fmt, compression_spec, - dosync, mode, setupDumpWorker); + dosync, mode, setupDumpWorker, sync_method); return (Archive *) AH; } @@ -257,7 +259,8 @@ OpenArchive(const char *FileSpec, const ArchiveFormat fmt) compression_spec.algorithm = PG_COMPRESSION_NONE; AH = _allocAH(FileSpec, fmt, compression_spec, true, - archModeRead, setupRestoreWorker); + archModeRead, setupRestoreWorker, + DATA_DIR_SYNC_METHOD_FSYNC); return (Archive *) AH; } @@ -2233,7 +2236,7 @@ static ArchiveHandle * _allocAH(const char *FileSpec, const ArchiveFormat fmt, const pg_compress_specification compression_spec, bool dosync, ArchiveMode mode, - SetupWorkerPtrType setupWorkerPtr) + SetupWorkerPtrType setupWorkerPtr, DataDirSyncMethod sync_method) { ArchiveHandle *AH; CompressFileHandle *CFH; @@ -2287,6 +2290,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, AH->mode = mode; AH->compression_spec = compression_spec; AH->dosync = dosync; + AH->sync_method = sync_method; memset(&(AH->sqlparse), 0, sizeof(AH->sqlparse)); diff --git a/src/bin/pg_dump/pg_backup_archiver.h b/src/bin/pg_dump/pg_backup_archiver.h index 18b38c17ab..b07673933d 100644 --- a/src/bin/pg_dump/pg_backup_archiver.h +++ b/src/bin/pg_dump/pg_backup_archiver.h @@ -312,6 +312,7 @@ struct _archiveHandle pg_compress_specification compression_spec; /* Requested specification for * compression */ bool dosync; /* data requested to be synced on sight */ + DataDirSyncMethod sync_method; ArchiveMode mode; /* File mode - r or w */ void *formatData; /* Header data specific to file format */ diff --git a/src/bin/pg_dump/pg_backup_directory.c b/src/bin/pg_dump/pg_backup_directory.c index 7f2ac7c7fd..6faa3a511f 100644 --- a/src/bin/pg_dump/pg_backup_directory.c +++ b/src/bin/pg_dump/pg_backup_directory.c @@ -613,7 +613,7 @@ _CloseArchive(ArchiveHandle *AH) * individually. Just recurse once through all the files generated. */ if (AH->dosync) - fsync_dir_recurse(ctx->directory); + fsync_dir_recurse(ctx->directory, AH->sync_method); } AH->FH = NULL; } diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c index 65f64c282d..39a468b131 100644 --- a/src/bin/pg_dump/pg_dump.c +++ b/src/bin/pg_dump/pg_dump.c @@ -357,6 +357,7 @@ main(int argc, char **argv) char *compression_algorithm_str = "none"; char *error_detail = NULL; bool user_compression_defined = false; + DataDirSyncMethod sync_method = DATA_DIR_SYNC_METHOD_FSYNC; static DumpOptions dopt; @@ -777,7 +778,7 @@ main(int argc, char **argv) /* Open the output file */ fout = CreateArchive(filename, archiveFormat, compression_spec, - dosync, archiveMode, setupDumpWorker); + dosync, archiveMode, setupDumpWorker, sync_method); /* Make dump options accessible right away */ SetArchiveOptions(fout, &dopt, NULL); diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 25996b4da4..451fb1856e 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -296,7 +296,7 @@ sync_target_dir(void) if (!do_sync || dry_run) return; - fsync_pgdata(datadir_target, PG_VERSION_NUM); + fsync_pgdata(datadir_target, PG_VERSION_NUM, sync_method); } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index 7f69f02441..bdfacf3263 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -74,6 +74,7 @@ bool showprogress = false; bool dry_run = false; bool do_sync = true; bool restore_wal = false; +DataDirSyncMethod sync_method = DATA_DIR_SYNC_METHOD_FSYNC; /* Target history */ TimeLineHistoryEntry *targetHistory; diff --git a/src/bin/pg_rewind/pg_rewind.h b/src/bin/pg_rewind/pg_rewind.h index ef8bdc1fbb..05729adfef 100644 --- a/src/bin/pg_rewind/pg_rewind.h +++ b/src/bin/pg_rewind/pg_rewind.h @@ -13,6 +13,7 @@ #include "access/timeline.h" #include "common/logging.h" +#include "common/file_utils.h" #include "datapagemap.h" #include "libpq-fe.h" #include "storage/block.h" @@ -24,6 +25,7 @@ extern bool showprogress; extern bool dry_run; extern bool do_sync; extern int WalSegSz; +extern DataDirSyncMethod sync_method; /* Target history */ extern TimeLineHistoryEntry *targetHistory; diff --git a/src/common/file_utils.c b/src/common/file_utils.c index 74833c4acb..05c73c0bb7 100644 --- a/src/common/file_utils.c +++ b/src/common/file_utils.c @@ -51,6 +51,31 @@ static void walkdir(const char *path, int (*action) (const char *fname, bool isdir), bool process_symlinks); +#ifdef HAVE_SYNCFS +static void +do_syncfs(const char *path) +{ + int fd; + + fd = open(path, O_RDONLY, 0); + + if (fd < 0) + { + pg_log_error("could not open file \"%s\": %m", path); + return; + } + + if (syncfs(fd) < 0) + { + pg_log_error("could not synchronize file system for file \"%s\": %m", path); + (void) close(fd); + exit(EXIT_FAILURE); + } + + (void) close(fd); +} +#endif + /* * Issue fsync recursively on PGDATA and all its contents. * @@ -63,7 +88,8 @@ static void walkdir(const char *path, */ void fsync_pgdata(const char *pg_data, - int serverVersion) + int serverVersion, + DataDirSyncMethod sync_method) { bool xlog_is_symlink; char pg_wal[MAXPGPATH]; @@ -89,30 +115,93 @@ fsync_pgdata(const char *pg_data, xlog_is_symlink = true; } - /* - * If possible, hint to the kernel that we're soon going to fsync the data - * directory and its contents. - */ + switch (sync_method) + { + case DATA_DIR_SYNC_METHOD_SYNCFS: + { +#ifndef HAVE_SYNCFS + pg_log_error("this build does not support sync method \"%s\"", + "syncfs"); + exit(EXIT_FAILURE); +#else + DIR *dir; + struct dirent *de; + + /* + * On Linux, we don't have to open every single file one by + * one. We can use syncfs() to sync whole filesystems. We + * only expect filesystem boundaries to exist where we + * tolerate symlinks, namely pg_wal and the tablespaces, so we + * call syncfs() for each of those directories. + */ + + /* Sync the top level pgdata directory. */ + do_syncfs(pg_data); + + /* If any tablespaces are configured, sync each of those. */ + dir = opendir(pg_tblspc); + if (dir == NULL) + pg_log_error("could not open directory \"%s\": %m", + pg_tblspc); + else + { + while (errno = 0, (de = readdir(dir)) != NULL) + { + char subpath[MAXPGPATH * 2]; + + if (strcmp(de->d_name, ".") == 0 || + strcmp(de->d_name, "..") == 0) + continue; + + snprintf(subpath, sizeof(subpath), "%s/%s", + pg_tblspc, de->d_name); + do_syncfs(subpath); + } + + if (errno) + pg_log_error("could not read directory \"%s\": %m", + pg_tblspc); + + (void) closedir(dir); + } + + /* If pg_wal is a symlink, process that too. */ + if (xlog_is_symlink) + do_syncfs(pg_wal); +#endif /* HAVE_SYNCFS */ + } + break; + + case DATA_DIR_SYNC_METHOD_FSYNC: + { + /* + * If possible, hint to the kernel that we're soon going to + * fsync the data directory and its contents. + */ #ifdef PG_FLUSH_DATA_WORKS - walkdir(pg_data, pre_sync_fname, false); - if (xlog_is_symlink) - walkdir(pg_wal, pre_sync_fname, false); - walkdir(pg_tblspc, pre_sync_fname, true); + walkdir(pg_data, pre_sync_fname, false); + if (xlog_is_symlink) + walkdir(pg_wal, pre_sync_fname, false); + walkdir(pg_tblspc, pre_sync_fname, true); #endif - /* - * Now we do the fsync()s in the same order. - * - * The main call ignores symlinks, so in addition to specially processing - * pg_wal if it's a symlink, pg_tblspc has to be visited separately with - * process_symlinks = true. Note that if there are any plain directories - * in pg_tblspc, they'll get fsync'd twice. That's not an expected case - * so we don't worry about optimizing it. - */ - walkdir(pg_data, fsync_fname, false); - if (xlog_is_symlink) - walkdir(pg_wal, fsync_fname, false); - walkdir(pg_tblspc, fsync_fname, true); + /* + * Now we do the fsync()s in the same order. + * + * The main call ignores symlinks, so in addition to specially + * processing pg_wal if it's a symlink, pg_tblspc has to be + * visited separately with process_symlinks = true. Note that + * if there are any plain directories in pg_tblspc, they'll + * get fsync'd twice. That's not an expected case so we don't + * worry about optimizing it. + */ + walkdir(pg_data, fsync_fname, false); + if (xlog_is_symlink) + walkdir(pg_wal, fsync_fname, false); + walkdir(pg_tblspc, fsync_fname, true); + } + break; + } } /* @@ -121,17 +210,40 @@ fsync_pgdata(const char *pg_data, * This is a convenient wrapper on top of walkdir(). */ void -fsync_dir_recurse(const char *dir) +fsync_dir_recurse(const char *dir, DataDirSyncMethod sync_method) { - /* - * If possible, hint to the kernel that we're soon going to fsync the data - * directory and its contents. - */ + switch (sync_method) + { + case DATA_DIR_SYNC_METHOD_SYNCFS: + { +#ifndef HAVE_SYNCFS + pg_log_error("this build does not support sync method \"%s\"", + "syncfs"); + exit(EXIT_FAILURE); +#else + /* + * On Linux, we don't have to open every single file one by + * one. We can use syncfs() to sync the whole filesystem. + */ + do_syncfs(dir); +#endif /* HAVE_SYNCFS */ + } + break; + + case DATA_DIR_SYNC_METHOD_FSYNC: + { + /* + * If possible, hint to the kernel that we're soon going to + * fsync the data directory and its contents. + */ #ifdef PG_FLUSH_DATA_WORKS - walkdir(dir, pre_sync_fname, false); + walkdir(dir, pre_sync_fname, false); #endif - walkdir(dir, fsync_fname, false); + walkdir(dir, fsync_fname, false); + } + break; + } } /* diff --git a/src/include/common/file_utils.h b/src/include/common/file_utils.h index 7da21f15e6..cae6159bf6 100644 --- a/src/include/common/file_utils.h +++ b/src/include/common/file_utils.h @@ -34,8 +34,9 @@ struct iovec; /* avoid including port/pg_iovec.h here */ #ifdef FRONTEND extern int fsync_fname(const char *fname, bool isdir); -extern void fsync_pgdata(const char *pg_data, int serverVersion); -extern void fsync_dir_recurse(const char *dir); +extern void fsync_pgdata(const char *pg_data, int serverVersion, + DataDirSyncMethod sync_method); +extern void fsync_dir_recurse(const char *dir, DataDirSyncMethod sync_method); extern int durable_rename(const char *oldfile, const char *newfile); extern int fsync_parent_path(const char *fname); #endif -- 2.25.1 --2fHTh5uZTiUOsy+g Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v9-0004-allow-syncfs-in-frontend-utilities.patch" ^ permalink raw reply [nested|flat] 11+ messages in thread
* [PATCH v9 3/4] add support for syncfs in frontend support functions @ 2023-08-31 14:59 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 11+ messages in thread From: Nathan Bossart @ 2023-08-31 14:59 UTC (permalink / raw) --- src/bin/initdb/initdb.c | 5 +- src/bin/pg_basebackup/pg_basebackup.c | 5 +- src/bin/pg_checksums/pg_checksums.c | 3 +- src/bin/pg_dump/pg_backup.h | 4 +- src/bin/pg_dump/pg_backup_archiver.c | 14 ++- src/bin/pg_dump/pg_backup_archiver.h | 1 + src/bin/pg_dump/pg_backup_directory.c | 2 +- src/bin/pg_dump/pg_dump.c | 3 +- src/bin/pg_rewind/file_ops.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 1 + src/bin/pg_rewind/pg_rewind.h | 2 + src/common/file_utils.c | 170 +++++++++++++++++++++----- src/include/common/file_utils.h | 5 +- 13 files changed, 172 insertions(+), 45 deletions(-) diff --git a/src/bin/initdb/initdb.c b/src/bin/initdb/initdb.c index 905b979947..bbea1e412b 100644 --- a/src/bin/initdb/initdb.c +++ b/src/bin/initdb/initdb.c @@ -165,6 +165,7 @@ static bool show_setting = false; static bool data_checksums = false; static char *xlog_dir = NULL; static int wal_segment_size_mb = (DEFAULT_XLOG_SEG_SIZE) / (1024 * 1024); +static DataDirSyncMethod sync_method = DATA_DIR_SYNC_METHOD_FSYNC; /* internal vars */ @@ -3333,7 +3334,7 @@ main(int argc, char *argv[]) fputs(_("syncing data to disk ... "), stdout); fflush(stdout); - fsync_pgdata(pg_data, PG_VERSION_NUM); + fsync_pgdata(pg_data, PG_VERSION_NUM, sync_method); check_ok(); return 0; } @@ -3396,7 +3397,7 @@ main(int argc, char *argv[]) { fputs(_("syncing data to disk ... "), stdout); fflush(stdout); - fsync_pgdata(pg_data, PG_VERSION_NUM); + fsync_pgdata(pg_data, PG_VERSION_NUM, sync_method); check_ok(); } else diff --git a/src/bin/pg_basebackup/pg_basebackup.c b/src/bin/pg_basebackup/pg_basebackup.c index 1dc8efe0cb..1a6eacf6d5 100644 --- a/src/bin/pg_basebackup/pg_basebackup.c +++ b/src/bin/pg_basebackup/pg_basebackup.c @@ -148,6 +148,7 @@ static bool verify_checksums = true; static bool manifest = true; static bool manifest_force_encode = false; static char *manifest_checksums = NULL; +static DataDirSyncMethod sync_method = DATA_DIR_SYNC_METHOD_FSYNC; static bool success = false; static bool made_new_pgdata = false; @@ -2199,11 +2200,11 @@ BaseBackup(char *compression_algorithm, char *compression_detail, if (format == 't') { if (strcmp(basedir, "-") != 0) - (void) fsync_dir_recurse(basedir); + (void) fsync_dir_recurse(basedir, sync_method); } else { - (void) fsync_pgdata(basedir, serverVersion); + (void) fsync_pgdata(basedir, serverVersion, sync_method); } } diff --git a/src/bin/pg_checksums/pg_checksums.c b/src/bin/pg_checksums/pg_checksums.c index 9011a19b4e..123450f483 100644 --- a/src/bin/pg_checksums/pg_checksums.c +++ b/src/bin/pg_checksums/pg_checksums.c @@ -44,6 +44,7 @@ static char *only_filenode = NULL; static bool do_sync = true; static bool verbose = false; static bool showprogress = false; +static DataDirSyncMethod sync_method = DATA_DIR_SYNC_METHOD_FSYNC; typedef enum { @@ -623,7 +624,7 @@ main(int argc, char *argv[]) if (do_sync) { pg_log_info("syncing data directory"); - fsync_pgdata(DataDir, PG_VERSION_NUM); + fsync_pgdata(DataDir, PG_VERSION_NUM, sync_method); } pg_log_info("updating control file"); diff --git a/src/bin/pg_dump/pg_backup.h b/src/bin/pg_dump/pg_backup.h index aba780ef4b..3a57cdd97d 100644 --- a/src/bin/pg_dump/pg_backup.h +++ b/src/bin/pg_dump/pg_backup.h @@ -24,6 +24,7 @@ #define PG_BACKUP_H #include "common/compression.h" +#include "common/file_utils.h" #include "fe_utils/simple_list.h" #include "libpq-fe.h" @@ -307,7 +308,8 @@ extern Archive *OpenArchive(const char *FileSpec, const ArchiveFormat fmt); extern Archive *CreateArchive(const char *FileSpec, const ArchiveFormat fmt, const pg_compress_specification compression_spec, bool dosync, ArchiveMode mode, - SetupWorkerPtrType setupDumpWorker); + SetupWorkerPtrType setupDumpWorker, + DataDirSyncMethod sync_method); /* The --list option */ extern void PrintTOCSummary(Archive *AHX); diff --git a/src/bin/pg_dump/pg_backup_archiver.c b/src/bin/pg_dump/pg_backup_archiver.c index 39ebcfec32..4d83381d84 100644 --- a/src/bin/pg_dump/pg_backup_archiver.c +++ b/src/bin/pg_dump/pg_backup_archiver.c @@ -66,7 +66,8 @@ typedef struct _parallelReadyList static ArchiveHandle *_allocAH(const char *FileSpec, const ArchiveFormat fmt, const pg_compress_specification compression_spec, bool dosync, ArchiveMode mode, - SetupWorkerPtrType setupWorkerPtr); + SetupWorkerPtrType setupWorkerPtr, + DataDirSyncMethod sync_method); static void _getObjectDescription(PQExpBuffer buf, const TocEntry *te); static void _printTocEntry(ArchiveHandle *AH, TocEntry *te, bool isData); static char *sanitize_line(const char *str, bool want_hyphen); @@ -238,11 +239,12 @@ Archive * CreateArchive(const char *FileSpec, const ArchiveFormat fmt, const pg_compress_specification compression_spec, bool dosync, ArchiveMode mode, - SetupWorkerPtrType setupDumpWorker) + SetupWorkerPtrType setupDumpWorker, + DataDirSyncMethod sync_method) { ArchiveHandle *AH = _allocAH(FileSpec, fmt, compression_spec, - dosync, mode, setupDumpWorker); + dosync, mode, setupDumpWorker, sync_method); return (Archive *) AH; } @@ -257,7 +259,8 @@ OpenArchive(const char *FileSpec, const ArchiveFormat fmt) compression_spec.algorithm = PG_COMPRESSION_NONE; AH = _allocAH(FileSpec, fmt, compression_spec, true, - archModeRead, setupRestoreWorker); + archModeRead, setupRestoreWorker, + DATA_DIR_SYNC_METHOD_FSYNC); return (Archive *) AH; } @@ -2233,7 +2236,7 @@ static ArchiveHandle * _allocAH(const char *FileSpec, const ArchiveFormat fmt, const pg_compress_specification compression_spec, bool dosync, ArchiveMode mode, - SetupWorkerPtrType setupWorkerPtr) + SetupWorkerPtrType setupWorkerPtr, DataDirSyncMethod sync_method) { ArchiveHandle *AH; CompressFileHandle *CFH; @@ -2287,6 +2290,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, AH->mode = mode; AH->compression_spec = compression_spec; AH->dosync = dosync; + AH->sync_method = sync_method; memset(&(AH->sqlparse), 0, sizeof(AH->sqlparse)); diff --git a/src/bin/pg_dump/pg_backup_archiver.h b/src/bin/pg_dump/pg_backup_archiver.h index 18b38c17ab..b07673933d 100644 --- a/src/bin/pg_dump/pg_backup_archiver.h +++ b/src/bin/pg_dump/pg_backup_archiver.h @@ -312,6 +312,7 @@ struct _archiveHandle pg_compress_specification compression_spec; /* Requested specification for * compression */ bool dosync; /* data requested to be synced on sight */ + DataDirSyncMethod sync_method; ArchiveMode mode; /* File mode - r or w */ void *formatData; /* Header data specific to file format */ diff --git a/src/bin/pg_dump/pg_backup_directory.c b/src/bin/pg_dump/pg_backup_directory.c index 7f2ac7c7fd..6faa3a511f 100644 --- a/src/bin/pg_dump/pg_backup_directory.c +++ b/src/bin/pg_dump/pg_backup_directory.c @@ -613,7 +613,7 @@ _CloseArchive(ArchiveHandle *AH) * individually. Just recurse once through all the files generated. */ if (AH->dosync) - fsync_dir_recurse(ctx->directory); + fsync_dir_recurse(ctx->directory, AH->sync_method); } AH->FH = NULL; } diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c index 65f64c282d..39a468b131 100644 --- a/src/bin/pg_dump/pg_dump.c +++ b/src/bin/pg_dump/pg_dump.c @@ -357,6 +357,7 @@ main(int argc, char **argv) char *compression_algorithm_str = "none"; char *error_detail = NULL; bool user_compression_defined = false; + DataDirSyncMethod sync_method = DATA_DIR_SYNC_METHOD_FSYNC; static DumpOptions dopt; @@ -777,7 +778,7 @@ main(int argc, char **argv) /* Open the output file */ fout = CreateArchive(filename, archiveFormat, compression_spec, - dosync, archiveMode, setupDumpWorker); + dosync, archiveMode, setupDumpWorker, sync_method); /* Make dump options accessible right away */ SetArchiveOptions(fout, &dopt, NULL); diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 25996b4da4..451fb1856e 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -296,7 +296,7 @@ sync_target_dir(void) if (!do_sync || dry_run) return; - fsync_pgdata(datadir_target, PG_VERSION_NUM); + fsync_pgdata(datadir_target, PG_VERSION_NUM, sync_method); } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index 7f69f02441..bdfacf3263 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -74,6 +74,7 @@ bool showprogress = false; bool dry_run = false; bool do_sync = true; bool restore_wal = false; +DataDirSyncMethod sync_method = DATA_DIR_SYNC_METHOD_FSYNC; /* Target history */ TimeLineHistoryEntry *targetHistory; diff --git a/src/bin/pg_rewind/pg_rewind.h b/src/bin/pg_rewind/pg_rewind.h index ef8bdc1fbb..05729adfef 100644 --- a/src/bin/pg_rewind/pg_rewind.h +++ b/src/bin/pg_rewind/pg_rewind.h @@ -13,6 +13,7 @@ #include "access/timeline.h" #include "common/logging.h" +#include "common/file_utils.h" #include "datapagemap.h" #include "libpq-fe.h" #include "storage/block.h" @@ -24,6 +25,7 @@ extern bool showprogress; extern bool dry_run; extern bool do_sync; extern int WalSegSz; +extern DataDirSyncMethod sync_method; /* Target history */ extern TimeLineHistoryEntry *targetHistory; diff --git a/src/common/file_utils.c b/src/common/file_utils.c index 74833c4acb..05c73c0bb7 100644 --- a/src/common/file_utils.c +++ b/src/common/file_utils.c @@ -51,6 +51,31 @@ static void walkdir(const char *path, int (*action) (const char *fname, bool isdir), bool process_symlinks); +#ifdef HAVE_SYNCFS +static void +do_syncfs(const char *path) +{ + int fd; + + fd = open(path, O_RDONLY, 0); + + if (fd < 0) + { + pg_log_error("could not open file \"%s\": %m", path); + return; + } + + if (syncfs(fd) < 0) + { + pg_log_error("could not synchronize file system for file \"%s\": %m", path); + (void) close(fd); + exit(EXIT_FAILURE); + } + + (void) close(fd); +} +#endif + /* * Issue fsync recursively on PGDATA and all its contents. * @@ -63,7 +88,8 @@ static void walkdir(const char *path, */ void fsync_pgdata(const char *pg_data, - int serverVersion) + int serverVersion, + DataDirSyncMethod sync_method) { bool xlog_is_symlink; char pg_wal[MAXPGPATH]; @@ -89,30 +115,93 @@ fsync_pgdata(const char *pg_data, xlog_is_symlink = true; } - /* - * If possible, hint to the kernel that we're soon going to fsync the data - * directory and its contents. - */ + switch (sync_method) + { + case DATA_DIR_SYNC_METHOD_SYNCFS: + { +#ifndef HAVE_SYNCFS + pg_log_error("this build does not support sync method \"%s\"", + "syncfs"); + exit(EXIT_FAILURE); +#else + DIR *dir; + struct dirent *de; + + /* + * On Linux, we don't have to open every single file one by + * one. We can use syncfs() to sync whole filesystems. We + * only expect filesystem boundaries to exist where we + * tolerate symlinks, namely pg_wal and the tablespaces, so we + * call syncfs() for each of those directories. + */ + + /* Sync the top level pgdata directory. */ + do_syncfs(pg_data); + + /* If any tablespaces are configured, sync each of those. */ + dir = opendir(pg_tblspc); + if (dir == NULL) + pg_log_error("could not open directory \"%s\": %m", + pg_tblspc); + else + { + while (errno = 0, (de = readdir(dir)) != NULL) + { + char subpath[MAXPGPATH * 2]; + + if (strcmp(de->d_name, ".") == 0 || + strcmp(de->d_name, "..") == 0) + continue; + + snprintf(subpath, sizeof(subpath), "%s/%s", + pg_tblspc, de->d_name); + do_syncfs(subpath); + } + + if (errno) + pg_log_error("could not read directory \"%s\": %m", + pg_tblspc); + + (void) closedir(dir); + } + + /* If pg_wal is a symlink, process that too. */ + if (xlog_is_symlink) + do_syncfs(pg_wal); +#endif /* HAVE_SYNCFS */ + } + break; + + case DATA_DIR_SYNC_METHOD_FSYNC: + { + /* + * If possible, hint to the kernel that we're soon going to + * fsync the data directory and its contents. + */ #ifdef PG_FLUSH_DATA_WORKS - walkdir(pg_data, pre_sync_fname, false); - if (xlog_is_symlink) - walkdir(pg_wal, pre_sync_fname, false); - walkdir(pg_tblspc, pre_sync_fname, true); + walkdir(pg_data, pre_sync_fname, false); + if (xlog_is_symlink) + walkdir(pg_wal, pre_sync_fname, false); + walkdir(pg_tblspc, pre_sync_fname, true); #endif - /* - * Now we do the fsync()s in the same order. - * - * The main call ignores symlinks, so in addition to specially processing - * pg_wal if it's a symlink, pg_tblspc has to be visited separately with - * process_symlinks = true. Note that if there are any plain directories - * in pg_tblspc, they'll get fsync'd twice. That's not an expected case - * so we don't worry about optimizing it. - */ - walkdir(pg_data, fsync_fname, false); - if (xlog_is_symlink) - walkdir(pg_wal, fsync_fname, false); - walkdir(pg_tblspc, fsync_fname, true); + /* + * Now we do the fsync()s in the same order. + * + * The main call ignores symlinks, so in addition to specially + * processing pg_wal if it's a symlink, pg_tblspc has to be + * visited separately with process_symlinks = true. Note that + * if there are any plain directories in pg_tblspc, they'll + * get fsync'd twice. That's not an expected case so we don't + * worry about optimizing it. + */ + walkdir(pg_data, fsync_fname, false); + if (xlog_is_symlink) + walkdir(pg_wal, fsync_fname, false); + walkdir(pg_tblspc, fsync_fname, true); + } + break; + } } /* @@ -121,17 +210,40 @@ fsync_pgdata(const char *pg_data, * This is a convenient wrapper on top of walkdir(). */ void -fsync_dir_recurse(const char *dir) +fsync_dir_recurse(const char *dir, DataDirSyncMethod sync_method) { - /* - * If possible, hint to the kernel that we're soon going to fsync the data - * directory and its contents. - */ + switch (sync_method) + { + case DATA_DIR_SYNC_METHOD_SYNCFS: + { +#ifndef HAVE_SYNCFS + pg_log_error("this build does not support sync method \"%s\"", + "syncfs"); + exit(EXIT_FAILURE); +#else + /* + * On Linux, we don't have to open every single file one by + * one. We can use syncfs() to sync the whole filesystem. + */ + do_syncfs(dir); +#endif /* HAVE_SYNCFS */ + } + break; + + case DATA_DIR_SYNC_METHOD_FSYNC: + { + /* + * If possible, hint to the kernel that we're soon going to + * fsync the data directory and its contents. + */ #ifdef PG_FLUSH_DATA_WORKS - walkdir(dir, pre_sync_fname, false); + walkdir(dir, pre_sync_fname, false); #endif - walkdir(dir, fsync_fname, false); + walkdir(dir, fsync_fname, false); + } + break; + } } /* diff --git a/src/include/common/file_utils.h b/src/include/common/file_utils.h index 7da21f15e6..cae6159bf6 100644 --- a/src/include/common/file_utils.h +++ b/src/include/common/file_utils.h @@ -34,8 +34,9 @@ struct iovec; /* avoid including port/pg_iovec.h here */ #ifdef FRONTEND extern int fsync_fname(const char *fname, bool isdir); -extern void fsync_pgdata(const char *pg_data, int serverVersion); -extern void fsync_dir_recurse(const char *dir); +extern void fsync_pgdata(const char *pg_data, int serverVersion, + DataDirSyncMethod sync_method); +extern void fsync_dir_recurse(const char *dir, DataDirSyncMethod sync_method); extern int durable_rename(const char *oldfile, const char *newfile); extern int fsync_parent_path(const char *fname); #endif -- 2.25.1 --2fHTh5uZTiUOsy+g Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v9-0004-allow-syncfs-in-frontend-utilities.patch" ^ permalink raw reply [nested|flat] 11+ messages in thread
* [PATCH v9 3/4] add support for syncfs in frontend support functions @ 2023-08-31 14:59 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 11+ messages in thread From: Nathan Bossart @ 2023-08-31 14:59 UTC (permalink / raw) --- src/bin/initdb/initdb.c | 5 +- src/bin/pg_basebackup/pg_basebackup.c | 5 +- src/bin/pg_checksums/pg_checksums.c | 3 +- src/bin/pg_dump/pg_backup.h | 4 +- src/bin/pg_dump/pg_backup_archiver.c | 14 ++- src/bin/pg_dump/pg_backup_archiver.h | 1 + src/bin/pg_dump/pg_backup_directory.c | 2 +- src/bin/pg_dump/pg_dump.c | 3 +- src/bin/pg_rewind/file_ops.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 1 + src/bin/pg_rewind/pg_rewind.h | 2 + src/common/file_utils.c | 170 +++++++++++++++++++++----- src/include/common/file_utils.h | 5 +- 13 files changed, 172 insertions(+), 45 deletions(-) diff --git a/src/bin/initdb/initdb.c b/src/bin/initdb/initdb.c index 905b979947..bbea1e412b 100644 --- a/src/bin/initdb/initdb.c +++ b/src/bin/initdb/initdb.c @@ -165,6 +165,7 @@ static bool show_setting = false; static bool data_checksums = false; static char *xlog_dir = NULL; static int wal_segment_size_mb = (DEFAULT_XLOG_SEG_SIZE) / (1024 * 1024); +static DataDirSyncMethod sync_method = DATA_DIR_SYNC_METHOD_FSYNC; /* internal vars */ @@ -3333,7 +3334,7 @@ main(int argc, char *argv[]) fputs(_("syncing data to disk ... "), stdout); fflush(stdout); - fsync_pgdata(pg_data, PG_VERSION_NUM); + fsync_pgdata(pg_data, PG_VERSION_NUM, sync_method); check_ok(); return 0; } @@ -3396,7 +3397,7 @@ main(int argc, char *argv[]) { fputs(_("syncing data to disk ... "), stdout); fflush(stdout); - fsync_pgdata(pg_data, PG_VERSION_NUM); + fsync_pgdata(pg_data, PG_VERSION_NUM, sync_method); check_ok(); } else diff --git a/src/bin/pg_basebackup/pg_basebackup.c b/src/bin/pg_basebackup/pg_basebackup.c index 1dc8efe0cb..1a6eacf6d5 100644 --- a/src/bin/pg_basebackup/pg_basebackup.c +++ b/src/bin/pg_basebackup/pg_basebackup.c @@ -148,6 +148,7 @@ static bool verify_checksums = true; static bool manifest = true; static bool manifest_force_encode = false; static char *manifest_checksums = NULL; +static DataDirSyncMethod sync_method = DATA_DIR_SYNC_METHOD_FSYNC; static bool success = false; static bool made_new_pgdata = false; @@ -2199,11 +2200,11 @@ BaseBackup(char *compression_algorithm, char *compression_detail, if (format == 't') { if (strcmp(basedir, "-") != 0) - (void) fsync_dir_recurse(basedir); + (void) fsync_dir_recurse(basedir, sync_method); } else { - (void) fsync_pgdata(basedir, serverVersion); + (void) fsync_pgdata(basedir, serverVersion, sync_method); } } diff --git a/src/bin/pg_checksums/pg_checksums.c b/src/bin/pg_checksums/pg_checksums.c index 9011a19b4e..123450f483 100644 --- a/src/bin/pg_checksums/pg_checksums.c +++ b/src/bin/pg_checksums/pg_checksums.c @@ -44,6 +44,7 @@ static char *only_filenode = NULL; static bool do_sync = true; static bool verbose = false; static bool showprogress = false; +static DataDirSyncMethod sync_method = DATA_DIR_SYNC_METHOD_FSYNC; typedef enum { @@ -623,7 +624,7 @@ main(int argc, char *argv[]) if (do_sync) { pg_log_info("syncing data directory"); - fsync_pgdata(DataDir, PG_VERSION_NUM); + fsync_pgdata(DataDir, PG_VERSION_NUM, sync_method); } pg_log_info("updating control file"); diff --git a/src/bin/pg_dump/pg_backup.h b/src/bin/pg_dump/pg_backup.h index aba780ef4b..3a57cdd97d 100644 --- a/src/bin/pg_dump/pg_backup.h +++ b/src/bin/pg_dump/pg_backup.h @@ -24,6 +24,7 @@ #define PG_BACKUP_H #include "common/compression.h" +#include "common/file_utils.h" #include "fe_utils/simple_list.h" #include "libpq-fe.h" @@ -307,7 +308,8 @@ extern Archive *OpenArchive(const char *FileSpec, const ArchiveFormat fmt); extern Archive *CreateArchive(const char *FileSpec, const ArchiveFormat fmt, const pg_compress_specification compression_spec, bool dosync, ArchiveMode mode, - SetupWorkerPtrType setupDumpWorker); + SetupWorkerPtrType setupDumpWorker, + DataDirSyncMethod sync_method); /* The --list option */ extern void PrintTOCSummary(Archive *AHX); diff --git a/src/bin/pg_dump/pg_backup_archiver.c b/src/bin/pg_dump/pg_backup_archiver.c index 39ebcfec32..4d83381d84 100644 --- a/src/bin/pg_dump/pg_backup_archiver.c +++ b/src/bin/pg_dump/pg_backup_archiver.c @@ -66,7 +66,8 @@ typedef struct _parallelReadyList static ArchiveHandle *_allocAH(const char *FileSpec, const ArchiveFormat fmt, const pg_compress_specification compression_spec, bool dosync, ArchiveMode mode, - SetupWorkerPtrType setupWorkerPtr); + SetupWorkerPtrType setupWorkerPtr, + DataDirSyncMethod sync_method); static void _getObjectDescription(PQExpBuffer buf, const TocEntry *te); static void _printTocEntry(ArchiveHandle *AH, TocEntry *te, bool isData); static char *sanitize_line(const char *str, bool want_hyphen); @@ -238,11 +239,12 @@ Archive * CreateArchive(const char *FileSpec, const ArchiveFormat fmt, const pg_compress_specification compression_spec, bool dosync, ArchiveMode mode, - SetupWorkerPtrType setupDumpWorker) + SetupWorkerPtrType setupDumpWorker, + DataDirSyncMethod sync_method) { ArchiveHandle *AH = _allocAH(FileSpec, fmt, compression_spec, - dosync, mode, setupDumpWorker); + dosync, mode, setupDumpWorker, sync_method); return (Archive *) AH; } @@ -257,7 +259,8 @@ OpenArchive(const char *FileSpec, const ArchiveFormat fmt) compression_spec.algorithm = PG_COMPRESSION_NONE; AH = _allocAH(FileSpec, fmt, compression_spec, true, - archModeRead, setupRestoreWorker); + archModeRead, setupRestoreWorker, + DATA_DIR_SYNC_METHOD_FSYNC); return (Archive *) AH; } @@ -2233,7 +2236,7 @@ static ArchiveHandle * _allocAH(const char *FileSpec, const ArchiveFormat fmt, const pg_compress_specification compression_spec, bool dosync, ArchiveMode mode, - SetupWorkerPtrType setupWorkerPtr) + SetupWorkerPtrType setupWorkerPtr, DataDirSyncMethod sync_method) { ArchiveHandle *AH; CompressFileHandle *CFH; @@ -2287,6 +2290,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, AH->mode = mode; AH->compression_spec = compression_spec; AH->dosync = dosync; + AH->sync_method = sync_method; memset(&(AH->sqlparse), 0, sizeof(AH->sqlparse)); diff --git a/src/bin/pg_dump/pg_backup_archiver.h b/src/bin/pg_dump/pg_backup_archiver.h index 18b38c17ab..b07673933d 100644 --- a/src/bin/pg_dump/pg_backup_archiver.h +++ b/src/bin/pg_dump/pg_backup_archiver.h @@ -312,6 +312,7 @@ struct _archiveHandle pg_compress_specification compression_spec; /* Requested specification for * compression */ bool dosync; /* data requested to be synced on sight */ + DataDirSyncMethod sync_method; ArchiveMode mode; /* File mode - r or w */ void *formatData; /* Header data specific to file format */ diff --git a/src/bin/pg_dump/pg_backup_directory.c b/src/bin/pg_dump/pg_backup_directory.c index 7f2ac7c7fd..6faa3a511f 100644 --- a/src/bin/pg_dump/pg_backup_directory.c +++ b/src/bin/pg_dump/pg_backup_directory.c @@ -613,7 +613,7 @@ _CloseArchive(ArchiveHandle *AH) * individually. Just recurse once through all the files generated. */ if (AH->dosync) - fsync_dir_recurse(ctx->directory); + fsync_dir_recurse(ctx->directory, AH->sync_method); } AH->FH = NULL; } diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c index 65f64c282d..39a468b131 100644 --- a/src/bin/pg_dump/pg_dump.c +++ b/src/bin/pg_dump/pg_dump.c @@ -357,6 +357,7 @@ main(int argc, char **argv) char *compression_algorithm_str = "none"; char *error_detail = NULL; bool user_compression_defined = false; + DataDirSyncMethod sync_method = DATA_DIR_SYNC_METHOD_FSYNC; static DumpOptions dopt; @@ -777,7 +778,7 @@ main(int argc, char **argv) /* Open the output file */ fout = CreateArchive(filename, archiveFormat, compression_spec, - dosync, archiveMode, setupDumpWorker); + dosync, archiveMode, setupDumpWorker, sync_method); /* Make dump options accessible right away */ SetArchiveOptions(fout, &dopt, NULL); diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 25996b4da4..451fb1856e 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -296,7 +296,7 @@ sync_target_dir(void) if (!do_sync || dry_run) return; - fsync_pgdata(datadir_target, PG_VERSION_NUM); + fsync_pgdata(datadir_target, PG_VERSION_NUM, sync_method); } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index 7f69f02441..bdfacf3263 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -74,6 +74,7 @@ bool showprogress = false; bool dry_run = false; bool do_sync = true; bool restore_wal = false; +DataDirSyncMethod sync_method = DATA_DIR_SYNC_METHOD_FSYNC; /* Target history */ TimeLineHistoryEntry *targetHistory; diff --git a/src/bin/pg_rewind/pg_rewind.h b/src/bin/pg_rewind/pg_rewind.h index ef8bdc1fbb..05729adfef 100644 --- a/src/bin/pg_rewind/pg_rewind.h +++ b/src/bin/pg_rewind/pg_rewind.h @@ -13,6 +13,7 @@ #include "access/timeline.h" #include "common/logging.h" +#include "common/file_utils.h" #include "datapagemap.h" #include "libpq-fe.h" #include "storage/block.h" @@ -24,6 +25,7 @@ extern bool showprogress; extern bool dry_run; extern bool do_sync; extern int WalSegSz; +extern DataDirSyncMethod sync_method; /* Target history */ extern TimeLineHistoryEntry *targetHistory; diff --git a/src/common/file_utils.c b/src/common/file_utils.c index 74833c4acb..05c73c0bb7 100644 --- a/src/common/file_utils.c +++ b/src/common/file_utils.c @@ -51,6 +51,31 @@ static void walkdir(const char *path, int (*action) (const char *fname, bool isdir), bool process_symlinks); +#ifdef HAVE_SYNCFS +static void +do_syncfs(const char *path) +{ + int fd; + + fd = open(path, O_RDONLY, 0); + + if (fd < 0) + { + pg_log_error("could not open file \"%s\": %m", path); + return; + } + + if (syncfs(fd) < 0) + { + pg_log_error("could not synchronize file system for file \"%s\": %m", path); + (void) close(fd); + exit(EXIT_FAILURE); + } + + (void) close(fd); +} +#endif + /* * Issue fsync recursively on PGDATA and all its contents. * @@ -63,7 +88,8 @@ static void walkdir(const char *path, */ void fsync_pgdata(const char *pg_data, - int serverVersion) + int serverVersion, + DataDirSyncMethod sync_method) { bool xlog_is_symlink; char pg_wal[MAXPGPATH]; @@ -89,30 +115,93 @@ fsync_pgdata(const char *pg_data, xlog_is_symlink = true; } - /* - * If possible, hint to the kernel that we're soon going to fsync the data - * directory and its contents. - */ + switch (sync_method) + { + case DATA_DIR_SYNC_METHOD_SYNCFS: + { +#ifndef HAVE_SYNCFS + pg_log_error("this build does not support sync method \"%s\"", + "syncfs"); + exit(EXIT_FAILURE); +#else + DIR *dir; + struct dirent *de; + + /* + * On Linux, we don't have to open every single file one by + * one. We can use syncfs() to sync whole filesystems. We + * only expect filesystem boundaries to exist where we + * tolerate symlinks, namely pg_wal and the tablespaces, so we + * call syncfs() for each of those directories. + */ + + /* Sync the top level pgdata directory. */ + do_syncfs(pg_data); + + /* If any tablespaces are configured, sync each of those. */ + dir = opendir(pg_tblspc); + if (dir == NULL) + pg_log_error("could not open directory \"%s\": %m", + pg_tblspc); + else + { + while (errno = 0, (de = readdir(dir)) != NULL) + { + char subpath[MAXPGPATH * 2]; + + if (strcmp(de->d_name, ".") == 0 || + strcmp(de->d_name, "..") == 0) + continue; + + snprintf(subpath, sizeof(subpath), "%s/%s", + pg_tblspc, de->d_name); + do_syncfs(subpath); + } + + if (errno) + pg_log_error("could not read directory \"%s\": %m", + pg_tblspc); + + (void) closedir(dir); + } + + /* If pg_wal is a symlink, process that too. */ + if (xlog_is_symlink) + do_syncfs(pg_wal); +#endif /* HAVE_SYNCFS */ + } + break; + + case DATA_DIR_SYNC_METHOD_FSYNC: + { + /* + * If possible, hint to the kernel that we're soon going to + * fsync the data directory and its contents. + */ #ifdef PG_FLUSH_DATA_WORKS - walkdir(pg_data, pre_sync_fname, false); - if (xlog_is_symlink) - walkdir(pg_wal, pre_sync_fname, false); - walkdir(pg_tblspc, pre_sync_fname, true); + walkdir(pg_data, pre_sync_fname, false); + if (xlog_is_symlink) + walkdir(pg_wal, pre_sync_fname, false); + walkdir(pg_tblspc, pre_sync_fname, true); #endif - /* - * Now we do the fsync()s in the same order. - * - * The main call ignores symlinks, so in addition to specially processing - * pg_wal if it's a symlink, pg_tblspc has to be visited separately with - * process_symlinks = true. Note that if there are any plain directories - * in pg_tblspc, they'll get fsync'd twice. That's not an expected case - * so we don't worry about optimizing it. - */ - walkdir(pg_data, fsync_fname, false); - if (xlog_is_symlink) - walkdir(pg_wal, fsync_fname, false); - walkdir(pg_tblspc, fsync_fname, true); + /* + * Now we do the fsync()s in the same order. + * + * The main call ignores symlinks, so in addition to specially + * processing pg_wal if it's a symlink, pg_tblspc has to be + * visited separately with process_symlinks = true. Note that + * if there are any plain directories in pg_tblspc, they'll + * get fsync'd twice. That's not an expected case so we don't + * worry about optimizing it. + */ + walkdir(pg_data, fsync_fname, false); + if (xlog_is_symlink) + walkdir(pg_wal, fsync_fname, false); + walkdir(pg_tblspc, fsync_fname, true); + } + break; + } } /* @@ -121,17 +210,40 @@ fsync_pgdata(const char *pg_data, * This is a convenient wrapper on top of walkdir(). */ void -fsync_dir_recurse(const char *dir) +fsync_dir_recurse(const char *dir, DataDirSyncMethod sync_method) { - /* - * If possible, hint to the kernel that we're soon going to fsync the data - * directory and its contents. - */ + switch (sync_method) + { + case DATA_DIR_SYNC_METHOD_SYNCFS: + { +#ifndef HAVE_SYNCFS + pg_log_error("this build does not support sync method \"%s\"", + "syncfs"); + exit(EXIT_FAILURE); +#else + /* + * On Linux, we don't have to open every single file one by + * one. We can use syncfs() to sync the whole filesystem. + */ + do_syncfs(dir); +#endif /* HAVE_SYNCFS */ + } + break; + + case DATA_DIR_SYNC_METHOD_FSYNC: + { + /* + * If possible, hint to the kernel that we're soon going to + * fsync the data directory and its contents. + */ #ifdef PG_FLUSH_DATA_WORKS - walkdir(dir, pre_sync_fname, false); + walkdir(dir, pre_sync_fname, false); #endif - walkdir(dir, fsync_fname, false); + walkdir(dir, fsync_fname, false); + } + break; + } } /* diff --git a/src/include/common/file_utils.h b/src/include/common/file_utils.h index 7da21f15e6..cae6159bf6 100644 --- a/src/include/common/file_utils.h +++ b/src/include/common/file_utils.h @@ -34,8 +34,9 @@ struct iovec; /* avoid including port/pg_iovec.h here */ #ifdef FRONTEND extern int fsync_fname(const char *fname, bool isdir); -extern void fsync_pgdata(const char *pg_data, int serverVersion); -extern void fsync_dir_recurse(const char *dir); +extern void fsync_pgdata(const char *pg_data, int serverVersion, + DataDirSyncMethod sync_method); +extern void fsync_dir_recurse(const char *dir, DataDirSyncMethod sync_method); extern int durable_rename(const char *oldfile, const char *newfile); extern int fsync_parent_path(const char *fname); #endif -- 2.25.1 --2fHTh5uZTiUOsy+g Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v9-0004-allow-syncfs-in-frontend-utilities.patch" ^ permalink raw reply [nested|flat] 11+ messages in thread
* [PATCH v9 3/4] add support for syncfs in frontend support functions @ 2023-08-31 14:59 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 11+ messages in thread From: Nathan Bossart @ 2023-08-31 14:59 UTC (permalink / raw) --- src/bin/initdb/initdb.c | 5 +- src/bin/pg_basebackup/pg_basebackup.c | 5 +- src/bin/pg_checksums/pg_checksums.c | 3 +- src/bin/pg_dump/pg_backup.h | 4 +- src/bin/pg_dump/pg_backup_archiver.c | 14 ++- src/bin/pg_dump/pg_backup_archiver.h | 1 + src/bin/pg_dump/pg_backup_directory.c | 2 +- src/bin/pg_dump/pg_dump.c | 3 +- src/bin/pg_rewind/file_ops.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 1 + src/bin/pg_rewind/pg_rewind.h | 2 + src/common/file_utils.c | 170 +++++++++++++++++++++----- src/include/common/file_utils.h | 5 +- 13 files changed, 172 insertions(+), 45 deletions(-) diff --git a/src/bin/initdb/initdb.c b/src/bin/initdb/initdb.c index 905b979947..bbea1e412b 100644 --- a/src/bin/initdb/initdb.c +++ b/src/bin/initdb/initdb.c @@ -165,6 +165,7 @@ static bool show_setting = false; static bool data_checksums = false; static char *xlog_dir = NULL; static int wal_segment_size_mb = (DEFAULT_XLOG_SEG_SIZE) / (1024 * 1024); +static DataDirSyncMethod sync_method = DATA_DIR_SYNC_METHOD_FSYNC; /* internal vars */ @@ -3333,7 +3334,7 @@ main(int argc, char *argv[]) fputs(_("syncing data to disk ... "), stdout); fflush(stdout); - fsync_pgdata(pg_data, PG_VERSION_NUM); + fsync_pgdata(pg_data, PG_VERSION_NUM, sync_method); check_ok(); return 0; } @@ -3396,7 +3397,7 @@ main(int argc, char *argv[]) { fputs(_("syncing data to disk ... "), stdout); fflush(stdout); - fsync_pgdata(pg_data, PG_VERSION_NUM); + fsync_pgdata(pg_data, PG_VERSION_NUM, sync_method); check_ok(); } else diff --git a/src/bin/pg_basebackup/pg_basebackup.c b/src/bin/pg_basebackup/pg_basebackup.c index 1dc8efe0cb..1a6eacf6d5 100644 --- a/src/bin/pg_basebackup/pg_basebackup.c +++ b/src/bin/pg_basebackup/pg_basebackup.c @@ -148,6 +148,7 @@ static bool verify_checksums = true; static bool manifest = true; static bool manifest_force_encode = false; static char *manifest_checksums = NULL; +static DataDirSyncMethod sync_method = DATA_DIR_SYNC_METHOD_FSYNC; static bool success = false; static bool made_new_pgdata = false; @@ -2199,11 +2200,11 @@ BaseBackup(char *compression_algorithm, char *compression_detail, if (format == 't') { if (strcmp(basedir, "-") != 0) - (void) fsync_dir_recurse(basedir); + (void) fsync_dir_recurse(basedir, sync_method); } else { - (void) fsync_pgdata(basedir, serverVersion); + (void) fsync_pgdata(basedir, serverVersion, sync_method); } } diff --git a/src/bin/pg_checksums/pg_checksums.c b/src/bin/pg_checksums/pg_checksums.c index 9011a19b4e..123450f483 100644 --- a/src/bin/pg_checksums/pg_checksums.c +++ b/src/bin/pg_checksums/pg_checksums.c @@ -44,6 +44,7 @@ static char *only_filenode = NULL; static bool do_sync = true; static bool verbose = false; static bool showprogress = false; +static DataDirSyncMethod sync_method = DATA_DIR_SYNC_METHOD_FSYNC; typedef enum { @@ -623,7 +624,7 @@ main(int argc, char *argv[]) if (do_sync) { pg_log_info("syncing data directory"); - fsync_pgdata(DataDir, PG_VERSION_NUM); + fsync_pgdata(DataDir, PG_VERSION_NUM, sync_method); } pg_log_info("updating control file"); diff --git a/src/bin/pg_dump/pg_backup.h b/src/bin/pg_dump/pg_backup.h index aba780ef4b..3a57cdd97d 100644 --- a/src/bin/pg_dump/pg_backup.h +++ b/src/bin/pg_dump/pg_backup.h @@ -24,6 +24,7 @@ #define PG_BACKUP_H #include "common/compression.h" +#include "common/file_utils.h" #include "fe_utils/simple_list.h" #include "libpq-fe.h" @@ -307,7 +308,8 @@ extern Archive *OpenArchive(const char *FileSpec, const ArchiveFormat fmt); extern Archive *CreateArchive(const char *FileSpec, const ArchiveFormat fmt, const pg_compress_specification compression_spec, bool dosync, ArchiveMode mode, - SetupWorkerPtrType setupDumpWorker); + SetupWorkerPtrType setupDumpWorker, + DataDirSyncMethod sync_method); /* The --list option */ extern void PrintTOCSummary(Archive *AHX); diff --git a/src/bin/pg_dump/pg_backup_archiver.c b/src/bin/pg_dump/pg_backup_archiver.c index 39ebcfec32..4d83381d84 100644 --- a/src/bin/pg_dump/pg_backup_archiver.c +++ b/src/bin/pg_dump/pg_backup_archiver.c @@ -66,7 +66,8 @@ typedef struct _parallelReadyList static ArchiveHandle *_allocAH(const char *FileSpec, const ArchiveFormat fmt, const pg_compress_specification compression_spec, bool dosync, ArchiveMode mode, - SetupWorkerPtrType setupWorkerPtr); + SetupWorkerPtrType setupWorkerPtr, + DataDirSyncMethod sync_method); static void _getObjectDescription(PQExpBuffer buf, const TocEntry *te); static void _printTocEntry(ArchiveHandle *AH, TocEntry *te, bool isData); static char *sanitize_line(const char *str, bool want_hyphen); @@ -238,11 +239,12 @@ Archive * CreateArchive(const char *FileSpec, const ArchiveFormat fmt, const pg_compress_specification compression_spec, bool dosync, ArchiveMode mode, - SetupWorkerPtrType setupDumpWorker) + SetupWorkerPtrType setupDumpWorker, + DataDirSyncMethod sync_method) { ArchiveHandle *AH = _allocAH(FileSpec, fmt, compression_spec, - dosync, mode, setupDumpWorker); + dosync, mode, setupDumpWorker, sync_method); return (Archive *) AH; } @@ -257,7 +259,8 @@ OpenArchive(const char *FileSpec, const ArchiveFormat fmt) compression_spec.algorithm = PG_COMPRESSION_NONE; AH = _allocAH(FileSpec, fmt, compression_spec, true, - archModeRead, setupRestoreWorker); + archModeRead, setupRestoreWorker, + DATA_DIR_SYNC_METHOD_FSYNC); return (Archive *) AH; } @@ -2233,7 +2236,7 @@ static ArchiveHandle * _allocAH(const char *FileSpec, const ArchiveFormat fmt, const pg_compress_specification compression_spec, bool dosync, ArchiveMode mode, - SetupWorkerPtrType setupWorkerPtr) + SetupWorkerPtrType setupWorkerPtr, DataDirSyncMethod sync_method) { ArchiveHandle *AH; CompressFileHandle *CFH; @@ -2287,6 +2290,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, AH->mode = mode; AH->compression_spec = compression_spec; AH->dosync = dosync; + AH->sync_method = sync_method; memset(&(AH->sqlparse), 0, sizeof(AH->sqlparse)); diff --git a/src/bin/pg_dump/pg_backup_archiver.h b/src/bin/pg_dump/pg_backup_archiver.h index 18b38c17ab..b07673933d 100644 --- a/src/bin/pg_dump/pg_backup_archiver.h +++ b/src/bin/pg_dump/pg_backup_archiver.h @@ -312,6 +312,7 @@ struct _archiveHandle pg_compress_specification compression_spec; /* Requested specification for * compression */ bool dosync; /* data requested to be synced on sight */ + DataDirSyncMethod sync_method; ArchiveMode mode; /* File mode - r or w */ void *formatData; /* Header data specific to file format */ diff --git a/src/bin/pg_dump/pg_backup_directory.c b/src/bin/pg_dump/pg_backup_directory.c index 7f2ac7c7fd..6faa3a511f 100644 --- a/src/bin/pg_dump/pg_backup_directory.c +++ b/src/bin/pg_dump/pg_backup_directory.c @@ -613,7 +613,7 @@ _CloseArchive(ArchiveHandle *AH) * individually. Just recurse once through all the files generated. */ if (AH->dosync) - fsync_dir_recurse(ctx->directory); + fsync_dir_recurse(ctx->directory, AH->sync_method); } AH->FH = NULL; } diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c index 65f64c282d..39a468b131 100644 --- a/src/bin/pg_dump/pg_dump.c +++ b/src/bin/pg_dump/pg_dump.c @@ -357,6 +357,7 @@ main(int argc, char **argv) char *compression_algorithm_str = "none"; char *error_detail = NULL; bool user_compression_defined = false; + DataDirSyncMethod sync_method = DATA_DIR_SYNC_METHOD_FSYNC; static DumpOptions dopt; @@ -777,7 +778,7 @@ main(int argc, char **argv) /* Open the output file */ fout = CreateArchive(filename, archiveFormat, compression_spec, - dosync, archiveMode, setupDumpWorker); + dosync, archiveMode, setupDumpWorker, sync_method); /* Make dump options accessible right away */ SetArchiveOptions(fout, &dopt, NULL); diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 25996b4da4..451fb1856e 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -296,7 +296,7 @@ sync_target_dir(void) if (!do_sync || dry_run) return; - fsync_pgdata(datadir_target, PG_VERSION_NUM); + fsync_pgdata(datadir_target, PG_VERSION_NUM, sync_method); } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index 7f69f02441..bdfacf3263 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -74,6 +74,7 @@ bool showprogress = false; bool dry_run = false; bool do_sync = true; bool restore_wal = false; +DataDirSyncMethod sync_method = DATA_DIR_SYNC_METHOD_FSYNC; /* Target history */ TimeLineHistoryEntry *targetHistory; diff --git a/src/bin/pg_rewind/pg_rewind.h b/src/bin/pg_rewind/pg_rewind.h index ef8bdc1fbb..05729adfef 100644 --- a/src/bin/pg_rewind/pg_rewind.h +++ b/src/bin/pg_rewind/pg_rewind.h @@ -13,6 +13,7 @@ #include "access/timeline.h" #include "common/logging.h" +#include "common/file_utils.h" #include "datapagemap.h" #include "libpq-fe.h" #include "storage/block.h" @@ -24,6 +25,7 @@ extern bool showprogress; extern bool dry_run; extern bool do_sync; extern int WalSegSz; +extern DataDirSyncMethod sync_method; /* Target history */ extern TimeLineHistoryEntry *targetHistory; diff --git a/src/common/file_utils.c b/src/common/file_utils.c index 74833c4acb..05c73c0bb7 100644 --- a/src/common/file_utils.c +++ b/src/common/file_utils.c @@ -51,6 +51,31 @@ static void walkdir(const char *path, int (*action) (const char *fname, bool isdir), bool process_symlinks); +#ifdef HAVE_SYNCFS +static void +do_syncfs(const char *path) +{ + int fd; + + fd = open(path, O_RDONLY, 0); + + if (fd < 0) + { + pg_log_error("could not open file \"%s\": %m", path); + return; + } + + if (syncfs(fd) < 0) + { + pg_log_error("could not synchronize file system for file \"%s\": %m", path); + (void) close(fd); + exit(EXIT_FAILURE); + } + + (void) close(fd); +} +#endif + /* * Issue fsync recursively on PGDATA and all its contents. * @@ -63,7 +88,8 @@ static void walkdir(const char *path, */ void fsync_pgdata(const char *pg_data, - int serverVersion) + int serverVersion, + DataDirSyncMethod sync_method) { bool xlog_is_symlink; char pg_wal[MAXPGPATH]; @@ -89,30 +115,93 @@ fsync_pgdata(const char *pg_data, xlog_is_symlink = true; } - /* - * If possible, hint to the kernel that we're soon going to fsync the data - * directory and its contents. - */ + switch (sync_method) + { + case DATA_DIR_SYNC_METHOD_SYNCFS: + { +#ifndef HAVE_SYNCFS + pg_log_error("this build does not support sync method \"%s\"", + "syncfs"); + exit(EXIT_FAILURE); +#else + DIR *dir; + struct dirent *de; + + /* + * On Linux, we don't have to open every single file one by + * one. We can use syncfs() to sync whole filesystems. We + * only expect filesystem boundaries to exist where we + * tolerate symlinks, namely pg_wal and the tablespaces, so we + * call syncfs() for each of those directories. + */ + + /* Sync the top level pgdata directory. */ + do_syncfs(pg_data); + + /* If any tablespaces are configured, sync each of those. */ + dir = opendir(pg_tblspc); + if (dir == NULL) + pg_log_error("could not open directory \"%s\": %m", + pg_tblspc); + else + { + while (errno = 0, (de = readdir(dir)) != NULL) + { + char subpath[MAXPGPATH * 2]; + + if (strcmp(de->d_name, ".") == 0 || + strcmp(de->d_name, "..") == 0) + continue; + + snprintf(subpath, sizeof(subpath), "%s/%s", + pg_tblspc, de->d_name); + do_syncfs(subpath); + } + + if (errno) + pg_log_error("could not read directory \"%s\": %m", + pg_tblspc); + + (void) closedir(dir); + } + + /* If pg_wal is a symlink, process that too. */ + if (xlog_is_symlink) + do_syncfs(pg_wal); +#endif /* HAVE_SYNCFS */ + } + break; + + case DATA_DIR_SYNC_METHOD_FSYNC: + { + /* + * If possible, hint to the kernel that we're soon going to + * fsync the data directory and its contents. + */ #ifdef PG_FLUSH_DATA_WORKS - walkdir(pg_data, pre_sync_fname, false); - if (xlog_is_symlink) - walkdir(pg_wal, pre_sync_fname, false); - walkdir(pg_tblspc, pre_sync_fname, true); + walkdir(pg_data, pre_sync_fname, false); + if (xlog_is_symlink) + walkdir(pg_wal, pre_sync_fname, false); + walkdir(pg_tblspc, pre_sync_fname, true); #endif - /* - * Now we do the fsync()s in the same order. - * - * The main call ignores symlinks, so in addition to specially processing - * pg_wal if it's a symlink, pg_tblspc has to be visited separately with - * process_symlinks = true. Note that if there are any plain directories - * in pg_tblspc, they'll get fsync'd twice. That's not an expected case - * so we don't worry about optimizing it. - */ - walkdir(pg_data, fsync_fname, false); - if (xlog_is_symlink) - walkdir(pg_wal, fsync_fname, false); - walkdir(pg_tblspc, fsync_fname, true); + /* + * Now we do the fsync()s in the same order. + * + * The main call ignores symlinks, so in addition to specially + * processing pg_wal if it's a symlink, pg_tblspc has to be + * visited separately with process_symlinks = true. Note that + * if there are any plain directories in pg_tblspc, they'll + * get fsync'd twice. That's not an expected case so we don't + * worry about optimizing it. + */ + walkdir(pg_data, fsync_fname, false); + if (xlog_is_symlink) + walkdir(pg_wal, fsync_fname, false); + walkdir(pg_tblspc, fsync_fname, true); + } + break; + } } /* @@ -121,17 +210,40 @@ fsync_pgdata(const char *pg_data, * This is a convenient wrapper on top of walkdir(). */ void -fsync_dir_recurse(const char *dir) +fsync_dir_recurse(const char *dir, DataDirSyncMethod sync_method) { - /* - * If possible, hint to the kernel that we're soon going to fsync the data - * directory and its contents. - */ + switch (sync_method) + { + case DATA_DIR_SYNC_METHOD_SYNCFS: + { +#ifndef HAVE_SYNCFS + pg_log_error("this build does not support sync method \"%s\"", + "syncfs"); + exit(EXIT_FAILURE); +#else + /* + * On Linux, we don't have to open every single file one by + * one. We can use syncfs() to sync the whole filesystem. + */ + do_syncfs(dir); +#endif /* HAVE_SYNCFS */ + } + break; + + case DATA_DIR_SYNC_METHOD_FSYNC: + { + /* + * If possible, hint to the kernel that we're soon going to + * fsync the data directory and its contents. + */ #ifdef PG_FLUSH_DATA_WORKS - walkdir(dir, pre_sync_fname, false); + walkdir(dir, pre_sync_fname, false); #endif - walkdir(dir, fsync_fname, false); + walkdir(dir, fsync_fname, false); + } + break; + } } /* diff --git a/src/include/common/file_utils.h b/src/include/common/file_utils.h index 7da21f15e6..cae6159bf6 100644 --- a/src/include/common/file_utils.h +++ b/src/include/common/file_utils.h @@ -34,8 +34,9 @@ struct iovec; /* avoid including port/pg_iovec.h here */ #ifdef FRONTEND extern int fsync_fname(const char *fname, bool isdir); -extern void fsync_pgdata(const char *pg_data, int serverVersion); -extern void fsync_dir_recurse(const char *dir); +extern void fsync_pgdata(const char *pg_data, int serverVersion, + DataDirSyncMethod sync_method); +extern void fsync_dir_recurse(const char *dir, DataDirSyncMethod sync_method); extern int durable_rename(const char *oldfile, const char *newfile); extern int fsync_parent_path(const char *fname); #endif -- 2.25.1 --2fHTh5uZTiUOsy+g Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v9-0004-allow-syncfs-in-frontend-utilities.patch" ^ permalink raw reply [nested|flat] 11+ messages in thread
* [PATCH v9 3/4] add support for syncfs in frontend support functions @ 2023-08-31 14:59 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 11+ messages in thread From: Nathan Bossart @ 2023-08-31 14:59 UTC (permalink / raw) --- src/bin/initdb/initdb.c | 5 +- src/bin/pg_basebackup/pg_basebackup.c | 5 +- src/bin/pg_checksums/pg_checksums.c | 3 +- src/bin/pg_dump/pg_backup.h | 4 +- src/bin/pg_dump/pg_backup_archiver.c | 14 ++- src/bin/pg_dump/pg_backup_archiver.h | 1 + src/bin/pg_dump/pg_backup_directory.c | 2 +- src/bin/pg_dump/pg_dump.c | 3 +- src/bin/pg_rewind/file_ops.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 1 + src/bin/pg_rewind/pg_rewind.h | 2 + src/common/file_utils.c | 170 +++++++++++++++++++++----- src/include/common/file_utils.h | 5 +- 13 files changed, 172 insertions(+), 45 deletions(-) diff --git a/src/bin/initdb/initdb.c b/src/bin/initdb/initdb.c index 905b979947..bbea1e412b 100644 --- a/src/bin/initdb/initdb.c +++ b/src/bin/initdb/initdb.c @@ -165,6 +165,7 @@ static bool show_setting = false; static bool data_checksums = false; static char *xlog_dir = NULL; static int wal_segment_size_mb = (DEFAULT_XLOG_SEG_SIZE) / (1024 * 1024); +static DataDirSyncMethod sync_method = DATA_DIR_SYNC_METHOD_FSYNC; /* internal vars */ @@ -3333,7 +3334,7 @@ main(int argc, char *argv[]) fputs(_("syncing data to disk ... "), stdout); fflush(stdout); - fsync_pgdata(pg_data, PG_VERSION_NUM); + fsync_pgdata(pg_data, PG_VERSION_NUM, sync_method); check_ok(); return 0; } @@ -3396,7 +3397,7 @@ main(int argc, char *argv[]) { fputs(_("syncing data to disk ... "), stdout); fflush(stdout); - fsync_pgdata(pg_data, PG_VERSION_NUM); + fsync_pgdata(pg_data, PG_VERSION_NUM, sync_method); check_ok(); } else diff --git a/src/bin/pg_basebackup/pg_basebackup.c b/src/bin/pg_basebackup/pg_basebackup.c index 1dc8efe0cb..1a6eacf6d5 100644 --- a/src/bin/pg_basebackup/pg_basebackup.c +++ b/src/bin/pg_basebackup/pg_basebackup.c @@ -148,6 +148,7 @@ static bool verify_checksums = true; static bool manifest = true; static bool manifest_force_encode = false; static char *manifest_checksums = NULL; +static DataDirSyncMethod sync_method = DATA_DIR_SYNC_METHOD_FSYNC; static bool success = false; static bool made_new_pgdata = false; @@ -2199,11 +2200,11 @@ BaseBackup(char *compression_algorithm, char *compression_detail, if (format == 't') { if (strcmp(basedir, "-") != 0) - (void) fsync_dir_recurse(basedir); + (void) fsync_dir_recurse(basedir, sync_method); } else { - (void) fsync_pgdata(basedir, serverVersion); + (void) fsync_pgdata(basedir, serverVersion, sync_method); } } diff --git a/src/bin/pg_checksums/pg_checksums.c b/src/bin/pg_checksums/pg_checksums.c index 9011a19b4e..123450f483 100644 --- a/src/bin/pg_checksums/pg_checksums.c +++ b/src/bin/pg_checksums/pg_checksums.c @@ -44,6 +44,7 @@ static char *only_filenode = NULL; static bool do_sync = true; static bool verbose = false; static bool showprogress = false; +static DataDirSyncMethod sync_method = DATA_DIR_SYNC_METHOD_FSYNC; typedef enum { @@ -623,7 +624,7 @@ main(int argc, char *argv[]) if (do_sync) { pg_log_info("syncing data directory"); - fsync_pgdata(DataDir, PG_VERSION_NUM); + fsync_pgdata(DataDir, PG_VERSION_NUM, sync_method); } pg_log_info("updating control file"); diff --git a/src/bin/pg_dump/pg_backup.h b/src/bin/pg_dump/pg_backup.h index aba780ef4b..3a57cdd97d 100644 --- a/src/bin/pg_dump/pg_backup.h +++ b/src/bin/pg_dump/pg_backup.h @@ -24,6 +24,7 @@ #define PG_BACKUP_H #include "common/compression.h" +#include "common/file_utils.h" #include "fe_utils/simple_list.h" #include "libpq-fe.h" @@ -307,7 +308,8 @@ extern Archive *OpenArchive(const char *FileSpec, const ArchiveFormat fmt); extern Archive *CreateArchive(const char *FileSpec, const ArchiveFormat fmt, const pg_compress_specification compression_spec, bool dosync, ArchiveMode mode, - SetupWorkerPtrType setupDumpWorker); + SetupWorkerPtrType setupDumpWorker, + DataDirSyncMethod sync_method); /* The --list option */ extern void PrintTOCSummary(Archive *AHX); diff --git a/src/bin/pg_dump/pg_backup_archiver.c b/src/bin/pg_dump/pg_backup_archiver.c index 39ebcfec32..4d83381d84 100644 --- a/src/bin/pg_dump/pg_backup_archiver.c +++ b/src/bin/pg_dump/pg_backup_archiver.c @@ -66,7 +66,8 @@ typedef struct _parallelReadyList static ArchiveHandle *_allocAH(const char *FileSpec, const ArchiveFormat fmt, const pg_compress_specification compression_spec, bool dosync, ArchiveMode mode, - SetupWorkerPtrType setupWorkerPtr); + SetupWorkerPtrType setupWorkerPtr, + DataDirSyncMethod sync_method); static void _getObjectDescription(PQExpBuffer buf, const TocEntry *te); static void _printTocEntry(ArchiveHandle *AH, TocEntry *te, bool isData); static char *sanitize_line(const char *str, bool want_hyphen); @@ -238,11 +239,12 @@ Archive * CreateArchive(const char *FileSpec, const ArchiveFormat fmt, const pg_compress_specification compression_spec, bool dosync, ArchiveMode mode, - SetupWorkerPtrType setupDumpWorker) + SetupWorkerPtrType setupDumpWorker, + DataDirSyncMethod sync_method) { ArchiveHandle *AH = _allocAH(FileSpec, fmt, compression_spec, - dosync, mode, setupDumpWorker); + dosync, mode, setupDumpWorker, sync_method); return (Archive *) AH; } @@ -257,7 +259,8 @@ OpenArchive(const char *FileSpec, const ArchiveFormat fmt) compression_spec.algorithm = PG_COMPRESSION_NONE; AH = _allocAH(FileSpec, fmt, compression_spec, true, - archModeRead, setupRestoreWorker); + archModeRead, setupRestoreWorker, + DATA_DIR_SYNC_METHOD_FSYNC); return (Archive *) AH; } @@ -2233,7 +2236,7 @@ static ArchiveHandle * _allocAH(const char *FileSpec, const ArchiveFormat fmt, const pg_compress_specification compression_spec, bool dosync, ArchiveMode mode, - SetupWorkerPtrType setupWorkerPtr) + SetupWorkerPtrType setupWorkerPtr, DataDirSyncMethod sync_method) { ArchiveHandle *AH; CompressFileHandle *CFH; @@ -2287,6 +2290,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, AH->mode = mode; AH->compression_spec = compression_spec; AH->dosync = dosync; + AH->sync_method = sync_method; memset(&(AH->sqlparse), 0, sizeof(AH->sqlparse)); diff --git a/src/bin/pg_dump/pg_backup_archiver.h b/src/bin/pg_dump/pg_backup_archiver.h index 18b38c17ab..b07673933d 100644 --- a/src/bin/pg_dump/pg_backup_archiver.h +++ b/src/bin/pg_dump/pg_backup_archiver.h @@ -312,6 +312,7 @@ struct _archiveHandle pg_compress_specification compression_spec; /* Requested specification for * compression */ bool dosync; /* data requested to be synced on sight */ + DataDirSyncMethod sync_method; ArchiveMode mode; /* File mode - r or w */ void *formatData; /* Header data specific to file format */ diff --git a/src/bin/pg_dump/pg_backup_directory.c b/src/bin/pg_dump/pg_backup_directory.c index 7f2ac7c7fd..6faa3a511f 100644 --- a/src/bin/pg_dump/pg_backup_directory.c +++ b/src/bin/pg_dump/pg_backup_directory.c @@ -613,7 +613,7 @@ _CloseArchive(ArchiveHandle *AH) * individually. Just recurse once through all the files generated. */ if (AH->dosync) - fsync_dir_recurse(ctx->directory); + fsync_dir_recurse(ctx->directory, AH->sync_method); } AH->FH = NULL; } diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c index 65f64c282d..39a468b131 100644 --- a/src/bin/pg_dump/pg_dump.c +++ b/src/bin/pg_dump/pg_dump.c @@ -357,6 +357,7 @@ main(int argc, char **argv) char *compression_algorithm_str = "none"; char *error_detail = NULL; bool user_compression_defined = false; + DataDirSyncMethod sync_method = DATA_DIR_SYNC_METHOD_FSYNC; static DumpOptions dopt; @@ -777,7 +778,7 @@ main(int argc, char **argv) /* Open the output file */ fout = CreateArchive(filename, archiveFormat, compression_spec, - dosync, archiveMode, setupDumpWorker); + dosync, archiveMode, setupDumpWorker, sync_method); /* Make dump options accessible right away */ SetArchiveOptions(fout, &dopt, NULL); diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 25996b4da4..451fb1856e 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -296,7 +296,7 @@ sync_target_dir(void) if (!do_sync || dry_run) return; - fsync_pgdata(datadir_target, PG_VERSION_NUM); + fsync_pgdata(datadir_target, PG_VERSION_NUM, sync_method); } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index 7f69f02441..bdfacf3263 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -74,6 +74,7 @@ bool showprogress = false; bool dry_run = false; bool do_sync = true; bool restore_wal = false; +DataDirSyncMethod sync_method = DATA_DIR_SYNC_METHOD_FSYNC; /* Target history */ TimeLineHistoryEntry *targetHistory; diff --git a/src/bin/pg_rewind/pg_rewind.h b/src/bin/pg_rewind/pg_rewind.h index ef8bdc1fbb..05729adfef 100644 --- a/src/bin/pg_rewind/pg_rewind.h +++ b/src/bin/pg_rewind/pg_rewind.h @@ -13,6 +13,7 @@ #include "access/timeline.h" #include "common/logging.h" +#include "common/file_utils.h" #include "datapagemap.h" #include "libpq-fe.h" #include "storage/block.h" @@ -24,6 +25,7 @@ extern bool showprogress; extern bool dry_run; extern bool do_sync; extern int WalSegSz; +extern DataDirSyncMethod sync_method; /* Target history */ extern TimeLineHistoryEntry *targetHistory; diff --git a/src/common/file_utils.c b/src/common/file_utils.c index 74833c4acb..05c73c0bb7 100644 --- a/src/common/file_utils.c +++ b/src/common/file_utils.c @@ -51,6 +51,31 @@ static void walkdir(const char *path, int (*action) (const char *fname, bool isdir), bool process_symlinks); +#ifdef HAVE_SYNCFS +static void +do_syncfs(const char *path) +{ + int fd; + + fd = open(path, O_RDONLY, 0); + + if (fd < 0) + { + pg_log_error("could not open file \"%s\": %m", path); + return; + } + + if (syncfs(fd) < 0) + { + pg_log_error("could not synchronize file system for file \"%s\": %m", path); + (void) close(fd); + exit(EXIT_FAILURE); + } + + (void) close(fd); +} +#endif + /* * Issue fsync recursively on PGDATA and all its contents. * @@ -63,7 +88,8 @@ static void walkdir(const char *path, */ void fsync_pgdata(const char *pg_data, - int serverVersion) + int serverVersion, + DataDirSyncMethod sync_method) { bool xlog_is_symlink; char pg_wal[MAXPGPATH]; @@ -89,30 +115,93 @@ fsync_pgdata(const char *pg_data, xlog_is_symlink = true; } - /* - * If possible, hint to the kernel that we're soon going to fsync the data - * directory and its contents. - */ + switch (sync_method) + { + case DATA_DIR_SYNC_METHOD_SYNCFS: + { +#ifndef HAVE_SYNCFS + pg_log_error("this build does not support sync method \"%s\"", + "syncfs"); + exit(EXIT_FAILURE); +#else + DIR *dir; + struct dirent *de; + + /* + * On Linux, we don't have to open every single file one by + * one. We can use syncfs() to sync whole filesystems. We + * only expect filesystem boundaries to exist where we + * tolerate symlinks, namely pg_wal and the tablespaces, so we + * call syncfs() for each of those directories. + */ + + /* Sync the top level pgdata directory. */ + do_syncfs(pg_data); + + /* If any tablespaces are configured, sync each of those. */ + dir = opendir(pg_tblspc); + if (dir == NULL) + pg_log_error("could not open directory \"%s\": %m", + pg_tblspc); + else + { + while (errno = 0, (de = readdir(dir)) != NULL) + { + char subpath[MAXPGPATH * 2]; + + if (strcmp(de->d_name, ".") == 0 || + strcmp(de->d_name, "..") == 0) + continue; + + snprintf(subpath, sizeof(subpath), "%s/%s", + pg_tblspc, de->d_name); + do_syncfs(subpath); + } + + if (errno) + pg_log_error("could not read directory \"%s\": %m", + pg_tblspc); + + (void) closedir(dir); + } + + /* If pg_wal is a symlink, process that too. */ + if (xlog_is_symlink) + do_syncfs(pg_wal); +#endif /* HAVE_SYNCFS */ + } + break; + + case DATA_DIR_SYNC_METHOD_FSYNC: + { + /* + * If possible, hint to the kernel that we're soon going to + * fsync the data directory and its contents. + */ #ifdef PG_FLUSH_DATA_WORKS - walkdir(pg_data, pre_sync_fname, false); - if (xlog_is_symlink) - walkdir(pg_wal, pre_sync_fname, false); - walkdir(pg_tblspc, pre_sync_fname, true); + walkdir(pg_data, pre_sync_fname, false); + if (xlog_is_symlink) + walkdir(pg_wal, pre_sync_fname, false); + walkdir(pg_tblspc, pre_sync_fname, true); #endif - /* - * Now we do the fsync()s in the same order. - * - * The main call ignores symlinks, so in addition to specially processing - * pg_wal if it's a symlink, pg_tblspc has to be visited separately with - * process_symlinks = true. Note that if there are any plain directories - * in pg_tblspc, they'll get fsync'd twice. That's not an expected case - * so we don't worry about optimizing it. - */ - walkdir(pg_data, fsync_fname, false); - if (xlog_is_symlink) - walkdir(pg_wal, fsync_fname, false); - walkdir(pg_tblspc, fsync_fname, true); + /* + * Now we do the fsync()s in the same order. + * + * The main call ignores symlinks, so in addition to specially + * processing pg_wal if it's a symlink, pg_tblspc has to be + * visited separately with process_symlinks = true. Note that + * if there are any plain directories in pg_tblspc, they'll + * get fsync'd twice. That's not an expected case so we don't + * worry about optimizing it. + */ + walkdir(pg_data, fsync_fname, false); + if (xlog_is_symlink) + walkdir(pg_wal, fsync_fname, false); + walkdir(pg_tblspc, fsync_fname, true); + } + break; + } } /* @@ -121,17 +210,40 @@ fsync_pgdata(const char *pg_data, * This is a convenient wrapper on top of walkdir(). */ void -fsync_dir_recurse(const char *dir) +fsync_dir_recurse(const char *dir, DataDirSyncMethod sync_method) { - /* - * If possible, hint to the kernel that we're soon going to fsync the data - * directory and its contents. - */ + switch (sync_method) + { + case DATA_DIR_SYNC_METHOD_SYNCFS: + { +#ifndef HAVE_SYNCFS + pg_log_error("this build does not support sync method \"%s\"", + "syncfs"); + exit(EXIT_FAILURE); +#else + /* + * On Linux, we don't have to open every single file one by + * one. We can use syncfs() to sync the whole filesystem. + */ + do_syncfs(dir); +#endif /* HAVE_SYNCFS */ + } + break; + + case DATA_DIR_SYNC_METHOD_FSYNC: + { + /* + * If possible, hint to the kernel that we're soon going to + * fsync the data directory and its contents. + */ #ifdef PG_FLUSH_DATA_WORKS - walkdir(dir, pre_sync_fname, false); + walkdir(dir, pre_sync_fname, false); #endif - walkdir(dir, fsync_fname, false); + walkdir(dir, fsync_fname, false); + } + break; + } } /* diff --git a/src/include/common/file_utils.h b/src/include/common/file_utils.h index 7da21f15e6..cae6159bf6 100644 --- a/src/include/common/file_utils.h +++ b/src/include/common/file_utils.h @@ -34,8 +34,9 @@ struct iovec; /* avoid including port/pg_iovec.h here */ #ifdef FRONTEND extern int fsync_fname(const char *fname, bool isdir); -extern void fsync_pgdata(const char *pg_data, int serverVersion); -extern void fsync_dir_recurse(const char *dir); +extern void fsync_pgdata(const char *pg_data, int serverVersion, + DataDirSyncMethod sync_method); +extern void fsync_dir_recurse(const char *dir, DataDirSyncMethod sync_method); extern int durable_rename(const char *oldfile, const char *newfile); extern int fsync_parent_path(const char *fname); #endif -- 2.25.1 --2fHTh5uZTiUOsy+g Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v9-0004-allow-syncfs-in-frontend-utilities.patch" ^ permalink raw reply [nested|flat] 11+ messages in thread
* [PATCH v15 2/8] Row pattern recognition patch (parse/analysis). @ 2024-03-28 10:30 Tatsuo Ishii <[email protected]> 0 siblings, 0 replies; 11+ messages in thread From: Tatsuo Ishii @ 2024-03-28 10:30 UTC (permalink / raw) --- src/backend/parser/parse_agg.c | 7 + src/backend/parser/parse_clause.c | 296 +++++++++++++++++++++++++++++- src/backend/parser/parse_expr.c | 4 + src/backend/parser/parse_func.c | 3 + 4 files changed, 309 insertions(+), 1 deletion(-) diff --git a/src/backend/parser/parse_agg.c b/src/backend/parser/parse_agg.c index bee7d8346a..9bc22a836a 100644 --- a/src/backend/parser/parse_agg.c +++ b/src/backend/parser/parse_agg.c @@ -577,6 +577,10 @@ check_agglevels_and_constraints(ParseState *pstate, Node *expr) errkind = true; break; + case EXPR_KIND_RPR_DEFINE: + errkind = true; + break; + /* * There is intentionally no default: case here, so that the * compiler will warn if we add a new ParseExprKind without @@ -967,6 +971,9 @@ transformWindowFuncCall(ParseState *pstate, WindowFunc *wfunc, case EXPR_KIND_CYCLE_MARK: errkind = true; break; + case EXPR_KIND_RPR_DEFINE: + errkind = true; + break; /* * There is intentionally no default: case here, so that the diff --git a/src/backend/parser/parse_clause.c b/src/backend/parser/parse_clause.c index d2ac86777c..de2e5791e3 100644 --- a/src/backend/parser/parse_clause.c +++ b/src/backend/parser/parse_clause.c @@ -98,7 +98,14 @@ static WindowClause *findWindowClause(List *wclist, const char *name); static Node *transformFrameOffset(ParseState *pstate, int frameOptions, Oid rangeopfamily, Oid rangeopcintype, Oid *inRangeFunc, Node *clause); - +static void transformRPR(ParseState *pstate, WindowClause *wc, WindowDef *windef, + List **targetlist); +static List *transformDefineClause(ParseState *pstate, WindowClause *wc, WindowDef *windef, + List **targetlist); +static void transformPatternClause(ParseState *pstate, WindowClause *wc, + WindowDef *windef); +static List *transformMeasureClause(ParseState *pstate, WindowClause *wc, + WindowDef *windef); /* * transformFromClause - @@ -2948,6 +2955,10 @@ transformWindowDefinitions(ParseState *pstate, rangeopfamily, rangeopcintype, &wc->endInRangeFunc, windef->endOffset); + + /* Process Row Pattern Recognition related clauses */ + transformRPR(pstate, wc, windef, targetlist); + wc->runCondition = NIL; wc->winref = winref; @@ -3813,3 +3824,286 @@ transformFrameOffset(ParseState *pstate, int frameOptions, return node; } + +/* + * transformRPR + * Process Row Pattern Recognition related clauses + */ +static void +transformRPR(ParseState *pstate, WindowClause *wc, WindowDef *windef, + List **targetlist) +{ + /* + * Window definition exists? + */ + if (windef == NULL) + return; + + /* + * Row Pattern Common Syntax clause exists? + */ + if (windef->rpCommonSyntax == NULL) + return; + + /* Check Frame option. Frame must start at current row */ + if ((wc->frameOptions & FRAMEOPTION_START_CURRENT_ROW) == 0) + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("FRAME must start at current row when row patttern recognition is used"))); + + /* Transform AFTER MACH SKIP TO clause */ + wc->rpSkipTo = windef->rpCommonSyntax->rpSkipTo; + + /* Transform AFTER MACH SKIP TO variable */ + wc->rpSkipVariable = windef->rpCommonSyntax->rpSkipVariable; + + /* Transform SEEK or INITIAL clause */ + wc->initial = windef->rpCommonSyntax->initial; + + /* Transform DEFINE clause into list of TargetEntry's */ + wc->defineClause = transformDefineClause(pstate, wc, windef, targetlist); + + /* Check PATTERN clause and copy to patternClause */ + transformPatternClause(pstate, wc, windef); + + /* Transform MEASURE clause */ + transformMeasureClause(pstate, wc, windef); +} + +/* + * transformDefineClause Process DEFINE clause and transform ResTarget into + * list of TargetEntry. + * + * XXX we only support column reference in row pattern definition search + * condition, e.g. "price". <row pattern definition variable name>.<column + * reference> is not supported, e.g. "A.price". + */ +static List * +transformDefineClause(ParseState *pstate, WindowClause *wc, WindowDef *windef, + List **targetlist) +{ + /* DEFINE variable name initials */ + static char *defineVariableInitials = "abcdefghijklmnopqrstuvwxyz"; + + ListCell *lc, + *l; + ResTarget *restarget, + *r; + List *restargets; + List *defineClause; + char *name; + int initialLen; + int i; + + /* + * If Row Definition Common Syntax exists, DEFINE clause must exist. (the + * raw parser should have already checked it.) + */ + Assert(windef->rpCommonSyntax->rpDefs != NULL); + + /* + * Check and add "A AS A IS TRUE" if pattern variable is missing in DEFINE + * per the SQL standard. + */ + restargets = NIL; + foreach(lc, windef->rpCommonSyntax->rpPatterns) + { + A_Expr *a; + bool found = false; + + if (!IsA(lfirst(lc), A_Expr)) + ereport(ERROR, + errmsg("node type is not A_Expr")); + + a = (A_Expr *) lfirst(lc); + name = strVal(a->lexpr); + + foreach(l, windef->rpCommonSyntax->rpDefs) + { + restarget = (ResTarget *) lfirst(l); + + if (!strcmp(restarget->name, name)) + { + found = true; + break; + } + } + + if (!found) + { + /* + * "name" is missing. So create "name AS name IS TRUE" ResTarget + * node and add it to the temporary list. + */ + A_Const *n; + + restarget = makeNode(ResTarget); + n = makeNode(A_Const); + n->val.boolval.type = T_Boolean; + n->val.boolval.boolval = true; + n->location = -1; + restarget->name = pstrdup(name); + restarget->indirection = NIL; + restarget->val = (Node *) n; + restarget->location = -1; + restargets = lappend((List *) restargets, restarget); + } + } + + if (list_length(restargets) >= 1) + { + /* add missing DEFINEs */ + windef->rpCommonSyntax->rpDefs = + list_concat(windef->rpCommonSyntax->rpDefs, restargets); + list_free(restargets); + } + + /* + * Check for duplicate row pattern definition variables. The standard + * requires that no two row pattern definition variable names shall be + * equivalent. + */ + restargets = NIL; + foreach(lc, windef->rpCommonSyntax->rpDefs) + { + restarget = (ResTarget *) lfirst(lc); + name = restarget->name; + + /* + * Add DEFINE expression (Restarget->val) to the targetlist as a + * TargetEntry if it does not exist yet. Planner will add the column + * ref var node to the outer plan's target list later on. This makes + * DEFINE expression could access the outer tuple while evaluating + * PATTERN. + * + * XXX: adding whole expressions of DEFINE to the plan.targetlist is + * not so good, because it's not necessary to evalute the expression + * in the target list while running the plan. We should extract the + * var nodes only then add them to the plan.targetlist. + */ + findTargetlistEntrySQL99(pstate, (Node *) restarget->val, + targetlist, EXPR_KIND_RPR_DEFINE); + + /* + * Make sure that the row pattern definition search condition is a + * boolean expression. + */ + transformWhereClause(pstate, restarget->val, + EXPR_KIND_RPR_DEFINE, "DEFINE"); + + foreach(l, restargets) + { + char *n; + + r = (ResTarget *) lfirst(l); + n = r->name; + + if (!strcmp(n, name)) + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("row pattern definition variable name \"%s\" appears more than once in DEFINE clause", + name), + parser_errposition(pstate, exprLocation((Node *) r)))); + } + restargets = lappend(restargets, restarget); + } + list_free(restargets); + + /* + * Create list of row pattern DEFINE variable name's initial. We assign + * [a-z] to them (up to 26 variable names are allowed). + */ + restargets = NIL; + i = 0; + initialLen = strlen(defineVariableInitials); + + foreach(lc, windef->rpCommonSyntax->rpDefs) + { + char initial[2]; + + restarget = (ResTarget *) lfirst(lc); + name = restarget->name; + + if (i >= initialLen) + { + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("number of row pattern definition variable names exceeds %d", + initialLen), + parser_errposition(pstate, + exprLocation((Node *) restarget)))); + } + initial[0] = defineVariableInitials[i++]; + initial[1] = '\0'; + wc->defineInitial = lappend(wc->defineInitial, + makeString(pstrdup(initial))); + } + + defineClause = transformTargetList(pstate, windef->rpCommonSyntax->rpDefs, + EXPR_KIND_RPR_DEFINE); + + /* mark column origins */ + markTargetListOrigins(pstate, defineClause); + + /* mark all nodes in the DEFINE clause tree with collation information */ + assign_expr_collations(pstate, (Node *) defineClause); + + return defineClause; +} + +/* + * transformPatternClause + * Process PATTERN clause and return PATTERN clause in the raw parse tree + */ +static void +transformPatternClause(ParseState *pstate, WindowClause *wc, + WindowDef *windef) +{ + ListCell *lc; + + /* + * Row Pattern Common Syntax clause exists? + */ + if (windef->rpCommonSyntax == NULL) + return; + + wc->patternVariable = NIL; + wc->patternRegexp = NIL; + foreach(lc, windef->rpCommonSyntax->rpPatterns) + { + A_Expr *a; + char *name; + char *regexp; + + if (!IsA(lfirst(lc), A_Expr)) + ereport(ERROR, + errmsg("node type is not A_Expr")); + + a = (A_Expr *) lfirst(lc); + name = strVal(a->lexpr); + + wc->patternVariable = lappend(wc->patternVariable, makeString(pstrdup(name))); + regexp = strVal(lfirst(list_head(a->name))); + + wc->patternRegexp = lappend(wc->patternRegexp, makeString(pstrdup(regexp))); + } +} + +/* + * transformMeasureClause + * Process MEASURE clause + * XXX MEASURE clause is not supported yet + */ +static List * +transformMeasureClause(ParseState *pstate, WindowClause *wc, + WindowDef *windef) +{ + if (windef->rowPatternMeasures == NIL) + return NIL; + + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("%s", "MEASURE clause is not supported yet"), + parser_errposition(pstate, exprLocation((Node *) windef->rowPatternMeasures)))); + return NIL; +} diff --git a/src/backend/parser/parse_expr.c b/src/backend/parser/parse_expr.c index 73c83cea4a..8b0cc608bc 100644 --- a/src/backend/parser/parse_expr.c +++ b/src/backend/parser/parse_expr.c @@ -578,6 +578,7 @@ transformColumnRef(ParseState *pstate, ColumnRef *cref) case EXPR_KIND_COPY_WHERE: case EXPR_KIND_GENERATED_COLUMN: case EXPR_KIND_CYCLE_MARK: + case EXPR_KIND_RPR_DEFINE: /* okay */ break; @@ -1817,6 +1818,7 @@ transformSubLink(ParseState *pstate, SubLink *sublink) case EXPR_KIND_VALUES: case EXPR_KIND_VALUES_SINGLE: case EXPR_KIND_CYCLE_MARK: + case EXPR_KIND_RPR_DEFINE: /* okay */ break; case EXPR_KIND_CHECK_CONSTRAINT: @@ -3197,6 +3199,8 @@ ParseExprKindName(ParseExprKind exprKind) return "GENERATED AS"; case EXPR_KIND_CYCLE_MARK: return "CYCLE"; + case EXPR_KIND_RPR_DEFINE: + return "DEFINE"; /* * There is intentionally no default: case here, so that the diff --git a/src/backend/parser/parse_func.c b/src/backend/parser/parse_func.c index 0cbc950c95..ad982a7c17 100644 --- a/src/backend/parser/parse_func.c +++ b/src/backend/parser/parse_func.c @@ -2657,6 +2657,9 @@ check_srf_call_placement(ParseState *pstate, Node *last_srf, int location) case EXPR_KIND_CYCLE_MARK: errkind = true; break; + case EXPR_KIND_RPR_DEFINE: + errkind = true; + break; /* * There is intentionally no default: case here, so that the -- 2.25.1 ----Next_Part(Thu_Mar_28_19_59_25_2024_076)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v15-0003-Row-pattern-recognition-patch-rewriter.patch" ^ permalink raw reply [nested|flat] 11+ messages in thread
* [PATCH v8] using indexscan to speedup add not null constraints @ 2025-10-20 05:29 jian he <[email protected]> 0 siblings, 0 replies; 11+ messages in thread From: jian he @ 2025-10-20 05:29 UTC (permalink / raw) This patch tries to use index_beginscan() / index_getnext() / index_endscan() mentioned in [1] to speedup adding not-null constraints to the existing table. The main logic happens in phase3 ATRewriteTable 1. collect all not-null constraints. 2. For each not-null constraint, check whether there is a corresponding index available for validation. If not, then can not use indexscan to verify not-null constraints. 3. If any of the following conditions are true * table scan or rewrite is required, * table wasn't locked with `AccessExclusiveLock` * the NOT NULL constraint applies to a virtual generated column then index scan cannot be used for fast validation. 4. If all conditions are satisfied, attempt to use indexscan to verify whether the column contains any NULL values. concurrency concern: ALTER TABLE SET NOT NULL will take an ACCESS EXCLUSIVE lock, so there is less variant of racing issue can occur? to prove accurate, I wrote some isolation tests. see[2] performance: demo: case when: %20 percent values are NULL and have been deleted from heap but they still on the index. drop table if exists t; create unlogged table t(a int, b int) with (autovacuum_enabled = off, vacuum_index_cleanup=off); insert into t select case when g % 5 = 0 then null else g end, g+1 from generate_series(1,1_000_000) g; create index t_idx_a on t(a); delete from t where a is null; alter table t alter column a drop not null; alter table t add constraint t1 not null a; the above two statement running several times: patch Time:: 1.084 ms master Time: 12.045 ms references: [1] https://postgr.es/m/CA%2BTgmoa5NKz8iGW_9v7wz%3D-%2BzQFu%3DE4SZoaTaU1znLaEXRYp-Q%40mail.gmail.com [2] https://postgr.es/m/900056D1-32DF-4927-8251-3E0C0DC407FD%40anarazel.de discussion: https://postgr.es/m/CACJufxFiW=4k1is=F1J=r-Cx1RuByXQPUrWB331U47rSnGz+hw@mail.gmail.com commitfest entry: https://commitfest.postgresql.org/patch/5444 --- src/backend/commands/tablecmds.c | 116 +++++++++- src/backend/executor/execIndexing.c | 213 ++++++++++++++++++ src/include/executor/executor.h | 2 + .../expected/indexscan-check-notnull.out | 97 ++++++++ src/test/isolation/isolation_schedule | 1 + .../specs/indexscan-check-notnull.spec | 45 ++++ src/test/modules/test_misc/meson.build | 1 + .../t/011_indexscan_validate_notnull.pl | 163 ++++++++++++++ 8 files changed, 632 insertions(+), 6 deletions(-) create mode 100644 src/test/isolation/expected/indexscan-check-notnull.out create mode 100644 src/test/isolation/specs/indexscan-check-notnull.spec create mode 100644 src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c index f976c0e5c7e..2af06630b35 100644 --- a/src/backend/commands/tablecmds.c +++ b/src/backend/commands/tablecmds.c @@ -210,16 +210,19 @@ typedef struct AlteredTableInfo List *changedStatisticsDefs; /* string definitions of same */ } AlteredTableInfo; -/* Struct describing one new constraint to check in Phase 3 scan */ -/* Note: new not-null constraints are handled elsewhere */ +/* + * Struct describing one new constraint to check in Phase 3 scan. Note: new + * not-null constraints are handled here too. +*/ typedef struct NewConstraint { char *name; /* Constraint name, or NULL if none */ - ConstrType contype; /* CHECK or FOREIGN */ + ConstrType contype; /* CHECK or FOREIGN or NOT NULL */ Oid refrelid; /* PK rel, if FOREIGN */ Oid refindid; /* OID of PK's index, if FOREIGN */ bool conwithperiod; /* Whether the new FOREIGN KEY uses PERIOD */ Oid conid; /* OID of pg_constraint entry, if FOREIGN */ + int attnum; /* NOT NULL constraint attribute number */ Node *qual; /* Check expr or CONSTR_FOREIGN Constraint */ ExprState *qualstate; /* Execution state for CHECK expr */ } NewConstraint; @@ -6217,6 +6220,9 @@ ATRewriteTable(AlteredTableInfo *tab, Oid OIDNewHeap) needscan = true; con->qualstate = ExecPrepareExpr((Expr *) expand_generated_columns_in_expr(con->qual, oldrel, 1), estate); break; + case CONSTR_NOTNULL: + /* Nothing to do here */ + break; case CONSTR_FOREIGN: /* Nothing to do here */ break; @@ -6270,10 +6276,69 @@ ATRewriteTable(AlteredTableInfo *tab, Oid OIDNewHeap) wholeatt->attnum); } } - if (notnull_attrs || notnull_virtual_attrs) - needscan = true; } + /*- + * If we have to verify new not-null constraints and don't have any other + * reason to fully scan the table, then we can use indexes to test for + * absence of NULL values instead of scanning. The following conditions + * must be met: + * - we're operating on a regular table + * - we hold AccessExclusiveLock on the table + * - no not-null constraint covers a virtual generated column, + * because no indexes can be created on them + */ + if (!needscan && + newrel == NULL && + tab->verify_new_notnull && + notnull_virtual_attrs == NIL && + oldrel->rd_rel->relkind == RELKIND_RELATION && + CheckRelationLockedByMe(oldrel, AccessExclusiveLock, false)) + { + List *notnull_attnums = NIL; + + Assert(!tab->rewrite); + + foreach(l, tab->constraints) + { + Form_pg_attribute attr; + NewConstraint *con = lfirst(l); + + if (con->contype != CONSTR_NOTNULL) + continue; + + attr = TupleDescAttr(newTupDesc, con->attnum - 1); + + Assert(attr->attnotnull); + Assert(attr->attnum == con->attnum); + + if (attr->attgenerated == ATTRIBUTE_GENERATED_VIRTUAL) + { + needscan = true; + break; + } + + notnull_attnums = lappend_int(notnull_attnums, attr->attnum); + } + + /* + * Validate new NOT NULL constraints, unless we need a scan for other + * reasons, because we can validate them cheaply there, and doing it + * also here would be a waste of cycles. + */ + if (notnull_attnums != NIL && !needscan) + { + if (!index_check_notnull(oldrel, notnull_attnums)) + needscan = true; + else + ereport(DEBUG1, + errmsg_internal("all new not-null constraints on relation \"%s\" have been validated by using index scan", + RelationGetRelationName(oldrel))); + } + } + else if (notnull_attrs || notnull_virtual_attrs) + needscan = true; + if (newrel || needscan) { ExprContext *econtext; @@ -7949,6 +8014,7 @@ ATExecSetNotNull(List **wqueue, Relation rel, char *conName, char *colName, CookedConstraint *ccon; List *cooked; bool is_no_inherit = false; + AlteredTableInfo *tab = NULL; /* Guard against stack overflow due to overly deep inheritance tree. */ check_stack_depth(); @@ -8073,10 +8139,32 @@ ATExecSetNotNull(List **wqueue, Relation rel, char *conName, char *colName, constraint->is_no_inherit = is_no_inherit; constraint->conname = conName; + tab = ATGetQueueEntry(wqueue, rel); + /* and do it */ cooked = AddRelationNewConstraints(rel, NIL, list_make1(constraint), false, !recursing, false, NULL); ccon = linitial(cooked); + + Assert(ccon->contype == CONSTR_NOTNULL); + + /* + * We may use indexscan to vertify not-null constraint in Phase3. Add the + * to-be-validated not-null constraint to Phase 3's queue. + */ + if (!ccon->skip_validation) + { + NewConstraint *newcon; + + newcon = (NewConstraint *) palloc0(sizeof(NewConstraint)); + + newcon->name = ccon->name; + newcon->contype = ccon->contype; + newcon->attnum = ccon->attnum; + + tab->constraints = lappend(tab->constraints, newcon); + } + ObjectAddressSet(address, ConstraintRelationId, ccon->conoid); InvokeObjectPostAlterHook(RelationRelationId, @@ -9983,13 +10071,15 @@ ATAddCheckNNConstraint(List **wqueue, AlteredTableInfo *tab, Relation rel, { CookedConstraint *ccon = (CookedConstraint *) lfirst(lcon); - if (!ccon->skip_validation && ccon->contype != CONSTR_NOTNULL) + if (!ccon->skip_validation) { NewConstraint *newcon; newcon = palloc0_object(NewConstraint); newcon->name = ccon->name; newcon->contype = ccon->contype; + if (ccon->contype == CONSTR_NOTNULL) + newcon->attnum = ccon->attnum; newcon->qual = ccon->expr; tab->constraints = lappend(tab->constraints, newcon); @@ -13258,6 +13348,7 @@ QueueNNConstraintValidation(List **wqueue, Relation conrel, Relation rel, List *children = NIL; AttrNumber attnum; char *colname; + NewConstraint *newcon; con = (Form_pg_constraint) GETSTRUCT(contuple); Assert(con->contype == CONSTRAINT_NOTNULL); @@ -13321,7 +13412,20 @@ QueueNNConstraintValidation(List **wqueue, Relation conrel, Relation rel, /* Set attnotnull appropriately without queueing another validation */ set_attnotnull(NULL, rel, attnum, true, false); + /* + * Queue validation for phase 3. + * + * ALTER TABLE SET NOT NULL will add NOT NULL constraint to + * AlteredTableInfo->constraints, for consistency, do the same here. + */ + newcon = (NewConstraint *) palloc0(sizeof(NewConstraint)); + newcon->name = colname; + newcon->contype = CONSTR_NOTNULL; + newcon->attnum = attnum; + + /* Find or create work queue entry for this table */ tab = ATGetQueueEntry(wqueue, rel); + tab->constraints = lappend(tab->constraints, newcon); tab->verify_new_notnull = true; /* diff --git a/src/backend/executor/execIndexing.c b/src/backend/executor/execIndexing.c index 6ae0f959592..88694ce0335 100644 --- a/src/backend/executor/execIndexing.c +++ b/src/backend/executor/execIndexing.c @@ -108,12 +108,15 @@ #include "access/genam.h" #include "access/relscan.h" +#include "access/table.h" #include "access/tableam.h" #include "access/xact.h" #include "catalog/index.h" +#include "catalog/pg_am_d.h" #include "executor/executor.h" #include "nodes/nodeFuncs.h" #include "storage/lmgr.h" +#include "utils/fmgroids.h" #include "utils/injection_point.h" #include "utils/multirangetypes.h" #include "utils/rangetypes.h" @@ -146,6 +149,7 @@ static bool index_expression_changed_walker(Node *node, Bitmapset *allUpdatedCols); static void ExecWithoutOverlapsNotEmpty(Relation rel, NameData attname, Datum attval, char typtype, Oid atttypid); +static bool index_check_notnull_internal(Relation relation, List *attnums, List *idxs); /* ---------------------------------------------------------------- * ExecOpenIndices @@ -1178,3 +1182,212 @@ ExecWithoutOverlapsNotEmpty(Relation rel, NameData attname, Datum attval, char t errmsg("empty WITHOUT OVERLAPS value found in column \"%s\" in relation \"%s\"", NameStr(attname), RelationGetRelationName(rel)))); } + +/* + * notnull_attnums: list of attribute numbers of all new not-null constraints. + * + * First check whether the relation has a suitable index for each not-null + * attribute, then using indexscan mechanism to verify that *all* attributes on + * notnull_attnums are indeed not null. + * + * Returning true means all new not-null constraints have been verified, no + * need an extra scan to verify newly added not-null constraints. + */ +bool +index_check_notnull(Relation relation, List *notnull_attnums) +{ + Relation pg_index; + Relation index_rel; + SysScanDesc indscan; + ScanKeyData skey; + HeapTuple htup; + TupleDesc tupdesc; + Form_pg_attribute attr; + List *idxs = NIL; + List *attnums = NIL; + + tupdesc = RelationGetDescr(relation); + + /* Prepare to scan pg_index for entries having indrelid = this rel */ + ScanKeyInit(&skey, + Anum_pg_index_indrelid, + BTEqualStrategyNumber, F_OIDEQ, + ObjectIdGetDatum(RelationGetRelid(relation))); + + pg_index = table_open(IndexRelationId, AccessShareLock); + indscan = systable_beginscan(pg_index, IndexIndrelidIndexId, true, + NULL, 1, &skey); + + while (HeapTupleIsValid(htup = systable_getnext(indscan))) + { + Form_pg_index index = (Form_pg_index) GETSTRUCT(htup); + + /* + * we can only use non-deferred, validated, and alive btree index to + * validate not-null constraints + */ + if (!index->indimmediate || !index->indisvalid || !index->indislive) + continue; + + /* can not use expression index or partial index too */ + if (!heap_attisnull(htup, Anum_pg_index_indexprs, NULL) || + !heap_attisnull(htup, Anum_pg_index_indpred, NULL)) + continue; + + index_rel = index_open(index->indexrelid, AccessShareLock); + + /* can only apply to btree index */ + if (index_rel->rd_rel->relam != BTREE_AM_OID) + { + index_close(index_rel, AccessShareLock); + continue; + } + + /* collect index attnums while loop */ + for (int i = 0; i < index->indnkeyatts; i++) + { + attr = TupleDescAttr(tupdesc, (index->indkey.values[i] - 1)); + + if (attr->attisdropped) + continue; + + if (list_member_int(notnull_attnums, attr->attnum) && + !list_member_int(attnums, attr->attnum)) + { + attnums = lappend_int(attnums, attr->attnum); + idxs = lappend_oid(idxs, index->indexrelid); + } + } + index_close(index_rel, NoLock); + } + systable_endscan(indscan); + table_close(pg_index, AccessShareLock); + + if (attnums == NIL) + return false; + + /* + * every not-null constraint requires an index for indexscan. If no such + * index exists, we need to use regular table scan to validate not-null + * constraints. + */ + foreach_int(attno, notnull_attnums) + { + if (!list_member_int(attnums, attno)) + return false; + } + + return index_check_notnull_internal(relation, attnums, idxs); +} + +/* + * Use indexscan mechanism to fast verify each attribute in "attnums" are + * not-null or not. + */ +static bool +index_check_notnull_internal(Relation relation, List *attnums, List *idxs) +{ + EState *estate; + ExprContext *econtext; + TupleTableSlot *existing_slot; + bool all_not_null = true; + ListCell *lc, + *lc2; + + /* + * Need an EState for slot to hold the current tuple. + */ + estate = CreateExecutorState(); + econtext = GetPerTupleExprContext(estate); + + forboth(lc, attnums, lc2, idxs) + { + SnapshotData DirtySnapshot; + IndexScanDesc index_scan; + ScanKeyData scankeys[INDEX_MAX_KEYS]; + IndexInfo *indexInfo; + AttrNumber sk_attno = -1; + Relation index; + int indnkeyatts; + + AttrNumber attno = lfirst_int(lc); + Oid indexoid = lfirst_oid(lc2); + + existing_slot = table_slot_create(relation, NULL); + + /* Arrange for econtext's scan tuple to be the tuple under test */ + econtext->ecxt_scantuple = existing_slot; + + index = index_open(indexoid, NoLock); + + indexInfo = BuildIndexInfo(index); + indnkeyatts = IndexRelationGetNumberOfKeyAttributes(index); + + /* + * Search the tuples that are in the index for any violations, + * including tuples that aren't visible yet. + */ + InitDirtySnapshot(DirtySnapshot); + + for (int i = 0; i < indnkeyatts; i++) + { + if (indexInfo->ii_IndexAttrNumbers[i] == attno) + { + sk_attno = i + 1; + break; + } + } + + if (sk_attno == -1) + elog(ERROR, "cache lookup failed for attribute number %d on index %u", indexoid, attno); + + for (int i = 0; i < indnkeyatts; i++) + { + /* set up an IS NULL scan key so that we ignore not nulls */ + ScanKeyEntryInitialize(&scankeys[i], + SK_ISNULL | SK_SEARCHNULL, + sk_attno, /* index col to scan */ + InvalidStrategy, /* no strategy */ + InvalidOid, /* no strategy subtype */ + InvalidOid, /* no collation */ + InvalidOid, /* no reg proc for this */ + (Datum) 0); /* constant */ + } + + index_scan = index_beginscan(relation, index, &DirtySnapshot, NULL, indnkeyatts, 0); + index_rescan(index_scan, scankeys, indnkeyatts, NULL, 0); + + while (index_getnext_slot(index_scan, ForwardScanDirection, existing_slot)) + { + Datum values[INDEX_MAX_KEYS]; + bool nulls[INDEX_MAX_KEYS]; + + /* + * Extract the index column values and isnull flags from the + * existing tuple. + */ + FormIndexDatum(indexInfo, existing_slot, estate, values, nulls); + + if (nulls[sk_attno - 1]) + { + all_not_null = false; + break; + } + } + + index_endscan(index_scan); + index_close(index, NoLock); + ExecDropSingleTupleTableSlot(existing_slot); + + /* exit earlier */ + if (!all_not_null) + { + FreeExecutorState(estate); + return false; + } + } + + FreeExecutorState(estate); + + return true; +} diff --git a/src/include/executor/executor.h b/src/include/executor/executor.h index 5929aabc353..7f24caeeafb 100644 --- a/src/include/executor/executor.h +++ b/src/include/executor/executor.h @@ -756,6 +756,8 @@ extern void check_exclusion_constraint(Relation heap, Relation index, const Datum *values, const bool *isnull, EState *estate, bool newIndex); +extern bool index_check_notnull(Relation relation, List *notnull_attnums); + /* * prototypes from functions in execReplication.c */ diff --git a/src/test/isolation/expected/indexscan-check-notnull.out b/src/test/isolation/expected/indexscan-check-notnull.out new file mode 100644 index 00000000000..c6a652e2518 --- /dev/null +++ b/src/test/isolation/expected/indexscan-check-notnull.out @@ -0,0 +1,97 @@ +Parsed test spec with 2 sessions + +starting permutation: s1_b1 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1 +step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ; +step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ; +step s1_d1: DELETE FROM t; +step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...> +step s1_c1: COMMIT; +step s2_a1: <... completed> +step s2_c1: COMMIT; +step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated + FROM pg_constraint WHERE conname = 't1_nn'; + +conname|conrelid|contype|convalidated +-------+--------+-------+------------ +t1_nn |t |n |t +(1 row) + + +starting permutation: s1_b2 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1 +step s1_b2: BEGIN; +step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ; +step s1_d1: DELETE FROM t; +step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...> +step s1_c1: COMMIT; +step s2_a1: <... completed> +step s2_c1: COMMIT; +step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated + FROM pg_constraint WHERE conname = 't1_nn'; + +conname|conrelid|contype|convalidated +-------+--------+-------+------------ +t1_nn |t |n |t +(1 row) + + +starting permutation: s1_b1 s2_b2 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1 +step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ; +step s2_b2: BEGIN; +step s1_d1: DELETE FROM t; +step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...> +step s1_c1: COMMIT; +step s2_a1: <... completed> +step s2_c1: COMMIT; +step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated + FROM pg_constraint WHERE conname = 't1_nn'; + +conname|conrelid|contype|convalidated +-------+--------+-------+------------ +t1_nn |t |n |t +(1 row) + + +starting permutation: s1_b1 s2_b1 s2_a1 s1_r1 s2_r1 +step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ; +step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ; +step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; +ERROR: column "a" of relation "t" contains null values +step s1_r1: ROLLBACK; +step s2_r1: ROLLBACK; + +starting permutation: s1_b1 s2_b2 s2_d1 s1_d1 s2_r1 s1_a1 s1_q1 s1_r1 +step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ; +step s2_b2: BEGIN; +step s2_d1: DROP INDEX t_ab_idx; +step s1_d1: DELETE FROM t; <waiting ...> +step s2_r1: ROLLBACK; +step s1_d1: <... completed> +step s1_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; +step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated + FROM pg_constraint WHERE conname = 't1_nn'; + +conname|conrelid|contype|convalidated +-------+--------+-------+------------ +t1_nn |t |n |t +(1 row) + +step s1_r1: ROLLBACK; + +starting permutation: s1_b2 s2_b1 s1_d1 s2_d1 s1_s0 s1_a1 s1_c1 s2_c1 s1_q1 +step s1_b2: BEGIN; +step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ; +step s1_d1: DELETE FROM t; +step s2_d1: DROP INDEX t_ab_idx; <waiting ...> +step s1_s0: SAVEPOINT s0; +step s1_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; +step s1_c1: COMMIT; +step s2_d1: <... completed> +step s2_c1: COMMIT; +step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated + FROM pg_constraint WHERE conname = 't1_nn'; + +conname|conrelid|contype|convalidated +-------+--------+-------+------------ +t1_nn |t |n |t +(1 row) + diff --git a/src/test/isolation/isolation_schedule b/src/test/isolation/isolation_schedule index 01ff1c6586f..7ce6bbcaf89 100644 --- a/src/test/isolation/isolation_schedule +++ b/src/test/isolation/isolation_schedule @@ -58,6 +58,7 @@ test: merge-delete test: merge-update test: merge-match-recheck test: merge-join +test: indexscan-check-notnull test: delete-abort-savept test: delete-abort-savept-2 test: aborted-keyrevoke diff --git a/src/test/isolation/specs/indexscan-check-notnull.spec b/src/test/isolation/specs/indexscan-check-notnull.spec new file mode 100644 index 00000000000..05b4488550c --- /dev/null +++ b/src/test/isolation/specs/indexscan-check-notnull.spec @@ -0,0 +1,45 @@ + +# +# using indexscan to check a column not-null constraint +# is satisfied or not. +# + +setup +{ + CREATE TABLE t (a int, b int); + CREATE INDEX t_ab_idx on t(a,b); + INSERT INTO t values (null, 1); + INSERT INTO t SELECT x, x*10 FROM generate_series(1,3) g(x); +} + +teardown +{ + DROP TABLE t; +} + +session s1 +step s1_b1 { BEGIN ISOLATION LEVEL REPEATABLE READ; } +step s1_b2 { BEGIN; } +step s1_d1 { DELETE FROM t;} +step s1_s0 { SAVEPOINT s0;} +step s1_a1 { ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;} +step s1_q1 { SELECT conname, conrelid::regclass, contype, convalidated + FROM pg_constraint WHERE conname = 't1_nn'; + } +step s1_r1 { ROLLBACK; } +step s1_c1 { COMMIT; } + +session s2 +step s2_b1 { BEGIN ISOLATION LEVEL REPEATABLE READ; } +step s2_b2 { BEGIN; } +step s2_a1 { ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;} +step s2_d1 { DROP INDEX t_ab_idx;} +step s2_r1 { ROLLBACK; } +step s2_c1 { COMMIT; } + +permutation s1_b1 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1 +permutation s1_b2 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1 +permutation s1_b1 s2_b2 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1 +permutation s1_b1 s2_b1 s2_a1 s1_r1 s2_r1 +permutation s1_b1 s2_b2 s2_d1 s1_d1 s2_r1 s1_a1 s1_q1 s1_r1 +permutation s1_b2 s2_b1 s1_d1 s2_d1 s1_s0 s1_a1 s1_c1 s2_c1 s1_q1 diff --git a/src/test/modules/test_misc/meson.build b/src/test/modules/test_misc/meson.build index 6e8db1621a7..56faf359b29 100644 --- a/src/test/modules/test_misc/meson.build +++ b/src/test/modules/test_misc/meson.build @@ -19,6 +19,7 @@ tests += { 't/008_replslot_single_user.pl', 't/009_log_temp_files.pl', 't/010_index_concurrently_upsert.pl', + 't/011_indexscan_validate_notnull.pl', ], # The injection points are cluster-wide, so disable installcheck 'runningcheck': false, diff --git a/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl b/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl new file mode 100644 index 00000000000..a3f3cb409b6 --- /dev/null +++ b/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl @@ -0,0 +1,163 @@ +# Copyright (c) 2025, PostgreSQL Global Development Group + +# Verify that indexscan mechanism can speedup ALTER TABLE ADD NOT NULL + + +use strict; +use warnings FATAL => 'all'; +use PostgreSQL::Test::Cluster; +use PostgreSQL::Test::Utils; +use Test::More; + +# Initialize a test cluster +my $node = PostgreSQL::Test::Cluster->new('primary'); +$node->init(); +# Turn message level up to DEBUG1 so that we get the messages we want to see +$node->append_conf('postgresql.conf', 'client_min_messages = DEBUG1'); +$node->start; + +# Run a SQL command and return psql's stderr (including debug messages) +sub run_sql_command +{ + my $sql = shift; + my $stderr; + + $node->psql( + 'postgres', + $sql, + stderr => \$stderr, + on_error_die => 1, + on_error_stop => 1); + return $stderr; +} + +# Check whether result of run_sql_command shows that we did a verify pass +sub is_table_verified +{ + my $output = shift; + return index($output, 'DEBUG: verifying table') != -1; +} + +# Check whether result of run_sql_command shows that we did a verify pass +sub is_indexscan_veritify_notnull +{ + my $output = shift; + return index($output, 'DEBUG: all new not-null constraints on relation') != -1; +} + +my $output; + +note "test alter table SET NOT NULL using indexscan with partitioned table"; + +run_sql_command( + 'CREATE TABLE tp (a int, b int, c int, d int ) PARTITION BY range(a); + CREATE TABLE tpp1 partition of tp for values from ( 1 ) to (10); + CREATE TABLE tpp2 partition of tp for values from ( 10 ) to (21); + INSERT INTO tp select g, g + 10, g + 15, g + random(min=>1::int, max=>10::int) from generate_series(1,19) g; + CREATE INDEX ON tp(b); '); + +$output = run_sql_command('ALTER TABLE tp ALTER COLUMN b SET NOT NULL;'); +ok(is_indexscan_veritify_notnull($output), + 'column b will use indexscan to verify not-null status, no need scan table'); +ok( $output =~ + m/all new not-null constraints on relation "tpp1" have been validated by using index scan/, + 'all newly added constraints proved by indexscan'); + +run_sql_command( + 'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;'); + +# use indexes on partitions to fast vertifing not-null should be ok +$output = run_sql_command('ALTER TABLE tpp1 ALTER COLUMN b SET NOT NULL;'); +ok(is_indexscan_veritify_notnull($output), 'use indexscan to validate column b not-null will not scan table'); +ok(!is_table_verified($output), 'no table scan for pp1'); +ok( $output =~ + m/all new not-null constraints on relation "tpp1" have been validated by using index scan/, + 'all newly added constraints proved by indexscan'); + +$output = run_sql_command('ALTER TABLE tpp2 ALTER COLUMN b SET NOT NULL;'); +ok(is_indexscan_veritify_notnull($output), 'use indexscan to validate column b not-null, will not scan table'); +ok(!is_table_verified($output), 'no table scan for tpp2'); +ok( $output =~ + m/all new not-null constraints on relation "tpp2" have been validated by using index scan/, + 'all newly added constraints proved by indexscan'); + +run_sql_command( + 'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;'); + +# table rewrite then can not use indexscan to verify not-null constraint +$output = run_sql_command( + 'ALTER TABLE tp ALTER COLUMN b SET NOT NULL, ALTER COLUMN b SET DATA TYPE bigint;' +); +ok(!is_table_verified($output), 'no table scan for tp'); +ok(!is_indexscan_veritify_notnull($output), 'table tp will rewrite, can not use indexscan to verify not-null constraints on it'); + +# test using indexscan with multiple not-null constraints +run_sql_command( + 'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL; + CREATE INDEX ON tp(c); + CREATE INDEX ON tp(d); '); + +# one column can use indexscan, another can not, so can not use indexscan to verify not-null +$output = run_sql_command( + 'ALTER TABLE tp ALTER COLUMN a SET NOT NULL, ADD CONSTRAINT c_nn NOT NULL c'); +ok(is_table_verified($output), 'table scan for tp'); +ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to verify not-null constraints on table tp'); + +# all columns have index on it +# use indexscan to verify multiple not-null constraints should just fine +$output = run_sql_command( + 'ALTER TABLE tp ALTER COLUMN d SET NOT NULL, ADD CONSTRAINT c_nn NOT NULL c, ALTER COLUMN b SET NOT NULL;'); +ok(!is_table_verified($output), 'no table scan for tp'); +ok(is_indexscan_veritify_notnull($output), + 'using indexscan to verify not-null constraints on column b, c, d, no need table scan'); + +# test with non-partitioned table and other non-Btree index. +run_sql_command( + 'CREATE TABLE t1(f1 INT, f2 int, f3 int,f4 int, f5 int); + INSERT INTO t1 select g, g+1, g+2, g+3, g+4 from generate_series(1, 100) g; + CREATE INDEX t1_f1_f2_idx ON t1(f1,f2); + CREATE UNIQUE INDEX t1_f3idx ON t1(f3); + CREATE INDEX t1_f3f4idx ON t1(f3) include(f4); + CREATE INDEX hash_f5_idx ON t1 USING hash (f5 int4_ops); '); + +# ALTER TABLE VALIDATE CONSTRAINT can not use indexscan, +# because it only hold ShareUpdateExclusiveLock lock. +run_sql_command('ALTER TABLE t1 ADD CONSTRAINT nn_t1_f2 NOT NULL f2 NOT VALID;'); + +$output = run_sql_command( + 'ALTER TABLE t1 VALIDATE CONSTRAINT nn_t1_f2;' +); +ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan for ALTER TABLE VALIDATE CONSTRAINT command'); +run_sql_command('ALTER TABLE t1 DROP CONSTRAINT nn_t1_f2;'); + +$output = run_sql_command( + 'ALTER TABLE t1 ALTER COLUMN f1 SET NOT NULL, ALTER f1 type bigint;' +); +ok(!is_indexscan_veritify_notnull($output), 'table t1 will rewrite, can not use indexscan to validate not-null constraints on t1'); + +run_sql_command('ALTER TABLE t1 ALTER COLUMN f1 DROP NOT NULL;'); +run_sql_command('ALTER TABLE t1 ADD CONSTRAINT nn NOT NULL f1, ALTER f1 type bigint;'); + +# can use indexscan mechanism to fast add multiple not-null constraints +$output = run_sql_command( + 'ALTER TABLE t1 ALTER COLUMN f2 SET NOT NULL, ALTER COLUMN f1 SET NOT NULL;' +); +ok( $output =~ + m/all new not-null constraints on relation "t1" have been validated by using index scan/, + 'all not-null constraints are validated by indexscan'); + +# using indexscan mechanism to fast add a not-null can only apply to key columns, not include column +$output = run_sql_command( + 'ALTER TABLE t1 ADD CONSTRAINT nnf4 NOT NULL f4;' +); +ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to validate not-null constraint on t1'); + +# if index is not btree index then cannot use indexscan mechanism to fast add not-null constraint +$output = run_sql_command( + 'ALTER TABLE t1 ADD CONSTRAINT nn_f5 NOT NULL f5;' +); +ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to validate not-null constraints on t1'); + +$node->stop('fast'); + +done_testing(); -- 2.47.3 --xpkr6zhfzd3fjt76-- ^ permalink raw reply [nested|flat] 11+ messages in thread
* [PATCH v8] using indexscan to speedup add not null constraints @ 2025-10-20 05:29 jian he <[email protected]> 0 siblings, 0 replies; 11+ messages in thread From: jian he @ 2025-10-20 05:29 UTC (permalink / raw) This patch tries to use index_beginscan() / index_getnext() / index_endscan() mentioned in [1] to speedup adding not-null constraints to the existing table. The main logic happens in phase3 ATRewriteTable 1. collect all not-null constraints. 2. For each not-null constraint, check whether there is a corresponding index available for validation. If not, then can not use indexscan to verify not-null constraints. 3. If any of the following conditions are true * table scan or rewrite is required, * table wasn't locked with `AccessExclusiveLock` * the NOT NULL constraint applies to a virtual generated column then index scan cannot be used for fast validation. 4. If all conditions are satisfied, attempt to use indexscan to verify whether the column contains any NULL values. concurrency concern: ALTER TABLE SET NOT NULL will take an ACCESS EXCLUSIVE lock, so there is less variant of racing issue can occur? to prove accurate, I wrote some isolation tests. see[2] performance: demo: case when: %20 percent values are NULL and have been deleted from heap but they still on the index. drop table if exists t; create unlogged table t(a int, b int) with (autovacuum_enabled = off, vacuum_index_cleanup=off); insert into t select case when g % 5 = 0 then null else g end, g+1 from generate_series(1,1_000_000) g; create index t_idx_a on t(a); delete from t where a is null; alter table t alter column a drop not null; alter table t add constraint t1 not null a; the above two statement running several times: patch Time:: 1.084 ms master Time: 12.045 ms references: [1] https://postgr.es/m/CA%2BTgmoa5NKz8iGW_9v7wz%3D-%2BzQFu%3DE4SZoaTaU1znLaEXRYp-Q%40mail.gmail.com [2] https://postgr.es/m/900056D1-32DF-4927-8251-3E0C0DC407FD%40anarazel.de discussion: https://postgr.es/m/CACJufxFiW=4k1is=F1J=r-Cx1RuByXQPUrWB331U47rSnGz+hw@mail.gmail.com commitfest entry: https://commitfest.postgresql.org/patch/5444 --- src/backend/commands/tablecmds.c | 116 +++++++++- src/backend/executor/execIndexing.c | 213 ++++++++++++++++++ src/include/executor/executor.h | 2 + .../expected/indexscan-check-notnull.out | 97 ++++++++ src/test/isolation/isolation_schedule | 1 + .../specs/indexscan-check-notnull.spec | 45 ++++ src/test/modules/test_misc/meson.build | 1 + .../t/011_indexscan_validate_notnull.pl | 163 ++++++++++++++ 8 files changed, 632 insertions(+), 6 deletions(-) create mode 100644 src/test/isolation/expected/indexscan-check-notnull.out create mode 100644 src/test/isolation/specs/indexscan-check-notnull.spec create mode 100644 src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c index f976c0e5c7e..2af06630b35 100644 --- a/src/backend/commands/tablecmds.c +++ b/src/backend/commands/tablecmds.c @@ -210,16 +210,19 @@ typedef struct AlteredTableInfo List *changedStatisticsDefs; /* string definitions of same */ } AlteredTableInfo; -/* Struct describing one new constraint to check in Phase 3 scan */ -/* Note: new not-null constraints are handled elsewhere */ +/* + * Struct describing one new constraint to check in Phase 3 scan. Note: new + * not-null constraints are handled here too. +*/ typedef struct NewConstraint { char *name; /* Constraint name, or NULL if none */ - ConstrType contype; /* CHECK or FOREIGN */ + ConstrType contype; /* CHECK or FOREIGN or NOT NULL */ Oid refrelid; /* PK rel, if FOREIGN */ Oid refindid; /* OID of PK's index, if FOREIGN */ bool conwithperiod; /* Whether the new FOREIGN KEY uses PERIOD */ Oid conid; /* OID of pg_constraint entry, if FOREIGN */ + int attnum; /* NOT NULL constraint attribute number */ Node *qual; /* Check expr or CONSTR_FOREIGN Constraint */ ExprState *qualstate; /* Execution state for CHECK expr */ } NewConstraint; @@ -6217,6 +6220,9 @@ ATRewriteTable(AlteredTableInfo *tab, Oid OIDNewHeap) needscan = true; con->qualstate = ExecPrepareExpr((Expr *) expand_generated_columns_in_expr(con->qual, oldrel, 1), estate); break; + case CONSTR_NOTNULL: + /* Nothing to do here */ + break; case CONSTR_FOREIGN: /* Nothing to do here */ break; @@ -6270,10 +6276,69 @@ ATRewriteTable(AlteredTableInfo *tab, Oid OIDNewHeap) wholeatt->attnum); } } - if (notnull_attrs || notnull_virtual_attrs) - needscan = true; } + /*- + * If we have to verify new not-null constraints and don't have any other + * reason to fully scan the table, then we can use indexes to test for + * absence of NULL values instead of scanning. The following conditions + * must be met: + * - we're operating on a regular table + * - we hold AccessExclusiveLock on the table + * - no not-null constraint covers a virtual generated column, + * because no indexes can be created on them + */ + if (!needscan && + newrel == NULL && + tab->verify_new_notnull && + notnull_virtual_attrs == NIL && + oldrel->rd_rel->relkind == RELKIND_RELATION && + CheckRelationLockedByMe(oldrel, AccessExclusiveLock, false)) + { + List *notnull_attnums = NIL; + + Assert(!tab->rewrite); + + foreach(l, tab->constraints) + { + Form_pg_attribute attr; + NewConstraint *con = lfirst(l); + + if (con->contype != CONSTR_NOTNULL) + continue; + + attr = TupleDescAttr(newTupDesc, con->attnum - 1); + + Assert(attr->attnotnull); + Assert(attr->attnum == con->attnum); + + if (attr->attgenerated == ATTRIBUTE_GENERATED_VIRTUAL) + { + needscan = true; + break; + } + + notnull_attnums = lappend_int(notnull_attnums, attr->attnum); + } + + /* + * Validate new NOT NULL constraints, unless we need a scan for other + * reasons, because we can validate them cheaply there, and doing it + * also here would be a waste of cycles. + */ + if (notnull_attnums != NIL && !needscan) + { + if (!index_check_notnull(oldrel, notnull_attnums)) + needscan = true; + else + ereport(DEBUG1, + errmsg_internal("all new not-null constraints on relation \"%s\" have been validated by using index scan", + RelationGetRelationName(oldrel))); + } + } + else if (notnull_attrs || notnull_virtual_attrs) + needscan = true; + if (newrel || needscan) { ExprContext *econtext; @@ -7949,6 +8014,7 @@ ATExecSetNotNull(List **wqueue, Relation rel, char *conName, char *colName, CookedConstraint *ccon; List *cooked; bool is_no_inherit = false; + AlteredTableInfo *tab = NULL; /* Guard against stack overflow due to overly deep inheritance tree. */ check_stack_depth(); @@ -8073,10 +8139,32 @@ ATExecSetNotNull(List **wqueue, Relation rel, char *conName, char *colName, constraint->is_no_inherit = is_no_inherit; constraint->conname = conName; + tab = ATGetQueueEntry(wqueue, rel); + /* and do it */ cooked = AddRelationNewConstraints(rel, NIL, list_make1(constraint), false, !recursing, false, NULL); ccon = linitial(cooked); + + Assert(ccon->contype == CONSTR_NOTNULL); + + /* + * We may use indexscan to vertify not-null constraint in Phase3. Add the + * to-be-validated not-null constraint to Phase 3's queue. + */ + if (!ccon->skip_validation) + { + NewConstraint *newcon; + + newcon = (NewConstraint *) palloc0(sizeof(NewConstraint)); + + newcon->name = ccon->name; + newcon->contype = ccon->contype; + newcon->attnum = ccon->attnum; + + tab->constraints = lappend(tab->constraints, newcon); + } + ObjectAddressSet(address, ConstraintRelationId, ccon->conoid); InvokeObjectPostAlterHook(RelationRelationId, @@ -9983,13 +10071,15 @@ ATAddCheckNNConstraint(List **wqueue, AlteredTableInfo *tab, Relation rel, { CookedConstraint *ccon = (CookedConstraint *) lfirst(lcon); - if (!ccon->skip_validation && ccon->contype != CONSTR_NOTNULL) + if (!ccon->skip_validation) { NewConstraint *newcon; newcon = palloc0_object(NewConstraint); newcon->name = ccon->name; newcon->contype = ccon->contype; + if (ccon->contype == CONSTR_NOTNULL) + newcon->attnum = ccon->attnum; newcon->qual = ccon->expr; tab->constraints = lappend(tab->constraints, newcon); @@ -13258,6 +13348,7 @@ QueueNNConstraintValidation(List **wqueue, Relation conrel, Relation rel, List *children = NIL; AttrNumber attnum; char *colname; + NewConstraint *newcon; con = (Form_pg_constraint) GETSTRUCT(contuple); Assert(con->contype == CONSTRAINT_NOTNULL); @@ -13321,7 +13412,20 @@ QueueNNConstraintValidation(List **wqueue, Relation conrel, Relation rel, /* Set attnotnull appropriately without queueing another validation */ set_attnotnull(NULL, rel, attnum, true, false); + /* + * Queue validation for phase 3. + * + * ALTER TABLE SET NOT NULL will add NOT NULL constraint to + * AlteredTableInfo->constraints, for consistency, do the same here. + */ + newcon = (NewConstraint *) palloc0(sizeof(NewConstraint)); + newcon->name = colname; + newcon->contype = CONSTR_NOTNULL; + newcon->attnum = attnum; + + /* Find or create work queue entry for this table */ tab = ATGetQueueEntry(wqueue, rel); + tab->constraints = lappend(tab->constraints, newcon); tab->verify_new_notnull = true; /* diff --git a/src/backend/executor/execIndexing.c b/src/backend/executor/execIndexing.c index 6ae0f959592..88694ce0335 100644 --- a/src/backend/executor/execIndexing.c +++ b/src/backend/executor/execIndexing.c @@ -108,12 +108,15 @@ #include "access/genam.h" #include "access/relscan.h" +#include "access/table.h" #include "access/tableam.h" #include "access/xact.h" #include "catalog/index.h" +#include "catalog/pg_am_d.h" #include "executor/executor.h" #include "nodes/nodeFuncs.h" #include "storage/lmgr.h" +#include "utils/fmgroids.h" #include "utils/injection_point.h" #include "utils/multirangetypes.h" #include "utils/rangetypes.h" @@ -146,6 +149,7 @@ static bool index_expression_changed_walker(Node *node, Bitmapset *allUpdatedCols); static void ExecWithoutOverlapsNotEmpty(Relation rel, NameData attname, Datum attval, char typtype, Oid atttypid); +static bool index_check_notnull_internal(Relation relation, List *attnums, List *idxs); /* ---------------------------------------------------------------- * ExecOpenIndices @@ -1178,3 +1182,212 @@ ExecWithoutOverlapsNotEmpty(Relation rel, NameData attname, Datum attval, char t errmsg("empty WITHOUT OVERLAPS value found in column \"%s\" in relation \"%s\"", NameStr(attname), RelationGetRelationName(rel)))); } + +/* + * notnull_attnums: list of attribute numbers of all new not-null constraints. + * + * First check whether the relation has a suitable index for each not-null + * attribute, then using indexscan mechanism to verify that *all* attributes on + * notnull_attnums are indeed not null. + * + * Returning true means all new not-null constraints have been verified, no + * need an extra scan to verify newly added not-null constraints. + */ +bool +index_check_notnull(Relation relation, List *notnull_attnums) +{ + Relation pg_index; + Relation index_rel; + SysScanDesc indscan; + ScanKeyData skey; + HeapTuple htup; + TupleDesc tupdesc; + Form_pg_attribute attr; + List *idxs = NIL; + List *attnums = NIL; + + tupdesc = RelationGetDescr(relation); + + /* Prepare to scan pg_index for entries having indrelid = this rel */ + ScanKeyInit(&skey, + Anum_pg_index_indrelid, + BTEqualStrategyNumber, F_OIDEQ, + ObjectIdGetDatum(RelationGetRelid(relation))); + + pg_index = table_open(IndexRelationId, AccessShareLock); + indscan = systable_beginscan(pg_index, IndexIndrelidIndexId, true, + NULL, 1, &skey); + + while (HeapTupleIsValid(htup = systable_getnext(indscan))) + { + Form_pg_index index = (Form_pg_index) GETSTRUCT(htup); + + /* + * we can only use non-deferred, validated, and alive btree index to + * validate not-null constraints + */ + if (!index->indimmediate || !index->indisvalid || !index->indislive) + continue; + + /* can not use expression index or partial index too */ + if (!heap_attisnull(htup, Anum_pg_index_indexprs, NULL) || + !heap_attisnull(htup, Anum_pg_index_indpred, NULL)) + continue; + + index_rel = index_open(index->indexrelid, AccessShareLock); + + /* can only apply to btree index */ + if (index_rel->rd_rel->relam != BTREE_AM_OID) + { + index_close(index_rel, AccessShareLock); + continue; + } + + /* collect index attnums while loop */ + for (int i = 0; i < index->indnkeyatts; i++) + { + attr = TupleDescAttr(tupdesc, (index->indkey.values[i] - 1)); + + if (attr->attisdropped) + continue; + + if (list_member_int(notnull_attnums, attr->attnum) && + !list_member_int(attnums, attr->attnum)) + { + attnums = lappend_int(attnums, attr->attnum); + idxs = lappend_oid(idxs, index->indexrelid); + } + } + index_close(index_rel, NoLock); + } + systable_endscan(indscan); + table_close(pg_index, AccessShareLock); + + if (attnums == NIL) + return false; + + /* + * every not-null constraint requires an index for indexscan. If no such + * index exists, we need to use regular table scan to validate not-null + * constraints. + */ + foreach_int(attno, notnull_attnums) + { + if (!list_member_int(attnums, attno)) + return false; + } + + return index_check_notnull_internal(relation, attnums, idxs); +} + +/* + * Use indexscan mechanism to fast verify each attribute in "attnums" are + * not-null or not. + */ +static bool +index_check_notnull_internal(Relation relation, List *attnums, List *idxs) +{ + EState *estate; + ExprContext *econtext; + TupleTableSlot *existing_slot; + bool all_not_null = true; + ListCell *lc, + *lc2; + + /* + * Need an EState for slot to hold the current tuple. + */ + estate = CreateExecutorState(); + econtext = GetPerTupleExprContext(estate); + + forboth(lc, attnums, lc2, idxs) + { + SnapshotData DirtySnapshot; + IndexScanDesc index_scan; + ScanKeyData scankeys[INDEX_MAX_KEYS]; + IndexInfo *indexInfo; + AttrNumber sk_attno = -1; + Relation index; + int indnkeyatts; + + AttrNumber attno = lfirst_int(lc); + Oid indexoid = lfirst_oid(lc2); + + existing_slot = table_slot_create(relation, NULL); + + /* Arrange for econtext's scan tuple to be the tuple under test */ + econtext->ecxt_scantuple = existing_slot; + + index = index_open(indexoid, NoLock); + + indexInfo = BuildIndexInfo(index); + indnkeyatts = IndexRelationGetNumberOfKeyAttributes(index); + + /* + * Search the tuples that are in the index for any violations, + * including tuples that aren't visible yet. + */ + InitDirtySnapshot(DirtySnapshot); + + for (int i = 0; i < indnkeyatts; i++) + { + if (indexInfo->ii_IndexAttrNumbers[i] == attno) + { + sk_attno = i + 1; + break; + } + } + + if (sk_attno == -1) + elog(ERROR, "cache lookup failed for attribute number %d on index %u", indexoid, attno); + + for (int i = 0; i < indnkeyatts; i++) + { + /* set up an IS NULL scan key so that we ignore not nulls */ + ScanKeyEntryInitialize(&scankeys[i], + SK_ISNULL | SK_SEARCHNULL, + sk_attno, /* index col to scan */ + InvalidStrategy, /* no strategy */ + InvalidOid, /* no strategy subtype */ + InvalidOid, /* no collation */ + InvalidOid, /* no reg proc for this */ + (Datum) 0); /* constant */ + } + + index_scan = index_beginscan(relation, index, &DirtySnapshot, NULL, indnkeyatts, 0); + index_rescan(index_scan, scankeys, indnkeyatts, NULL, 0); + + while (index_getnext_slot(index_scan, ForwardScanDirection, existing_slot)) + { + Datum values[INDEX_MAX_KEYS]; + bool nulls[INDEX_MAX_KEYS]; + + /* + * Extract the index column values and isnull flags from the + * existing tuple. + */ + FormIndexDatum(indexInfo, existing_slot, estate, values, nulls); + + if (nulls[sk_attno - 1]) + { + all_not_null = false; + break; + } + } + + index_endscan(index_scan); + index_close(index, NoLock); + ExecDropSingleTupleTableSlot(existing_slot); + + /* exit earlier */ + if (!all_not_null) + { + FreeExecutorState(estate); + return false; + } + } + + FreeExecutorState(estate); + + return true; +} diff --git a/src/include/executor/executor.h b/src/include/executor/executor.h index 5929aabc353..7f24caeeafb 100644 --- a/src/include/executor/executor.h +++ b/src/include/executor/executor.h @@ -756,6 +756,8 @@ extern void check_exclusion_constraint(Relation heap, Relation index, const Datum *values, const bool *isnull, EState *estate, bool newIndex); +extern bool index_check_notnull(Relation relation, List *notnull_attnums); + /* * prototypes from functions in execReplication.c */ diff --git a/src/test/isolation/expected/indexscan-check-notnull.out b/src/test/isolation/expected/indexscan-check-notnull.out new file mode 100644 index 00000000000..c6a652e2518 --- /dev/null +++ b/src/test/isolation/expected/indexscan-check-notnull.out @@ -0,0 +1,97 @@ +Parsed test spec with 2 sessions + +starting permutation: s1_b1 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1 +step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ; +step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ; +step s1_d1: DELETE FROM t; +step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...> +step s1_c1: COMMIT; +step s2_a1: <... completed> +step s2_c1: COMMIT; +step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated + FROM pg_constraint WHERE conname = 't1_nn'; + +conname|conrelid|contype|convalidated +-------+--------+-------+------------ +t1_nn |t |n |t +(1 row) + + +starting permutation: s1_b2 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1 +step s1_b2: BEGIN; +step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ; +step s1_d1: DELETE FROM t; +step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...> +step s1_c1: COMMIT; +step s2_a1: <... completed> +step s2_c1: COMMIT; +step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated + FROM pg_constraint WHERE conname = 't1_nn'; + +conname|conrelid|contype|convalidated +-------+--------+-------+------------ +t1_nn |t |n |t +(1 row) + + +starting permutation: s1_b1 s2_b2 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1 +step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ; +step s2_b2: BEGIN; +step s1_d1: DELETE FROM t; +step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...> +step s1_c1: COMMIT; +step s2_a1: <... completed> +step s2_c1: COMMIT; +step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated + FROM pg_constraint WHERE conname = 't1_nn'; + +conname|conrelid|contype|convalidated +-------+--------+-------+------------ +t1_nn |t |n |t +(1 row) + + +starting permutation: s1_b1 s2_b1 s2_a1 s1_r1 s2_r1 +step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ; +step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ; +step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; +ERROR: column "a" of relation "t" contains null values +step s1_r1: ROLLBACK; +step s2_r1: ROLLBACK; + +starting permutation: s1_b1 s2_b2 s2_d1 s1_d1 s2_r1 s1_a1 s1_q1 s1_r1 +step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ; +step s2_b2: BEGIN; +step s2_d1: DROP INDEX t_ab_idx; +step s1_d1: DELETE FROM t; <waiting ...> +step s2_r1: ROLLBACK; +step s1_d1: <... completed> +step s1_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; +step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated + FROM pg_constraint WHERE conname = 't1_nn'; + +conname|conrelid|contype|convalidated +-------+--------+-------+------------ +t1_nn |t |n |t +(1 row) + +step s1_r1: ROLLBACK; + +starting permutation: s1_b2 s2_b1 s1_d1 s2_d1 s1_s0 s1_a1 s1_c1 s2_c1 s1_q1 +step s1_b2: BEGIN; +step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ; +step s1_d1: DELETE FROM t; +step s2_d1: DROP INDEX t_ab_idx; <waiting ...> +step s1_s0: SAVEPOINT s0; +step s1_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; +step s1_c1: COMMIT; +step s2_d1: <... completed> +step s2_c1: COMMIT; +step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated + FROM pg_constraint WHERE conname = 't1_nn'; + +conname|conrelid|contype|convalidated +-------+--------+-------+------------ +t1_nn |t |n |t +(1 row) + diff --git a/src/test/isolation/isolation_schedule b/src/test/isolation/isolation_schedule index 01ff1c6586f..7ce6bbcaf89 100644 --- a/src/test/isolation/isolation_schedule +++ b/src/test/isolation/isolation_schedule @@ -58,6 +58,7 @@ test: merge-delete test: merge-update test: merge-match-recheck test: merge-join +test: indexscan-check-notnull test: delete-abort-savept test: delete-abort-savept-2 test: aborted-keyrevoke diff --git a/src/test/isolation/specs/indexscan-check-notnull.spec b/src/test/isolation/specs/indexscan-check-notnull.spec new file mode 100644 index 00000000000..05b4488550c --- /dev/null +++ b/src/test/isolation/specs/indexscan-check-notnull.spec @@ -0,0 +1,45 @@ + +# +# using indexscan to check a column not-null constraint +# is satisfied or not. +# + +setup +{ + CREATE TABLE t (a int, b int); + CREATE INDEX t_ab_idx on t(a,b); + INSERT INTO t values (null, 1); + INSERT INTO t SELECT x, x*10 FROM generate_series(1,3) g(x); +} + +teardown +{ + DROP TABLE t; +} + +session s1 +step s1_b1 { BEGIN ISOLATION LEVEL REPEATABLE READ; } +step s1_b2 { BEGIN; } +step s1_d1 { DELETE FROM t;} +step s1_s0 { SAVEPOINT s0;} +step s1_a1 { ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;} +step s1_q1 { SELECT conname, conrelid::regclass, contype, convalidated + FROM pg_constraint WHERE conname = 't1_nn'; + } +step s1_r1 { ROLLBACK; } +step s1_c1 { COMMIT; } + +session s2 +step s2_b1 { BEGIN ISOLATION LEVEL REPEATABLE READ; } +step s2_b2 { BEGIN; } +step s2_a1 { ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;} +step s2_d1 { DROP INDEX t_ab_idx;} +step s2_r1 { ROLLBACK; } +step s2_c1 { COMMIT; } + +permutation s1_b1 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1 +permutation s1_b2 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1 +permutation s1_b1 s2_b2 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1 +permutation s1_b1 s2_b1 s2_a1 s1_r1 s2_r1 +permutation s1_b1 s2_b2 s2_d1 s1_d1 s2_r1 s1_a1 s1_q1 s1_r1 +permutation s1_b2 s2_b1 s1_d1 s2_d1 s1_s0 s1_a1 s1_c1 s2_c1 s1_q1 diff --git a/src/test/modules/test_misc/meson.build b/src/test/modules/test_misc/meson.build index 6e8db1621a7..56faf359b29 100644 --- a/src/test/modules/test_misc/meson.build +++ b/src/test/modules/test_misc/meson.build @@ -19,6 +19,7 @@ tests += { 't/008_replslot_single_user.pl', 't/009_log_temp_files.pl', 't/010_index_concurrently_upsert.pl', + 't/011_indexscan_validate_notnull.pl', ], # The injection points are cluster-wide, so disable installcheck 'runningcheck': false, diff --git a/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl b/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl new file mode 100644 index 00000000000..a3f3cb409b6 --- /dev/null +++ b/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl @@ -0,0 +1,163 @@ +# Copyright (c) 2025, PostgreSQL Global Development Group + +# Verify that indexscan mechanism can speedup ALTER TABLE ADD NOT NULL + + +use strict; +use warnings FATAL => 'all'; +use PostgreSQL::Test::Cluster; +use PostgreSQL::Test::Utils; +use Test::More; + +# Initialize a test cluster +my $node = PostgreSQL::Test::Cluster->new('primary'); +$node->init(); +# Turn message level up to DEBUG1 so that we get the messages we want to see +$node->append_conf('postgresql.conf', 'client_min_messages = DEBUG1'); +$node->start; + +# Run a SQL command and return psql's stderr (including debug messages) +sub run_sql_command +{ + my $sql = shift; + my $stderr; + + $node->psql( + 'postgres', + $sql, + stderr => \$stderr, + on_error_die => 1, + on_error_stop => 1); + return $stderr; +} + +# Check whether result of run_sql_command shows that we did a verify pass +sub is_table_verified +{ + my $output = shift; + return index($output, 'DEBUG: verifying table') != -1; +} + +# Check whether result of run_sql_command shows that we did a verify pass +sub is_indexscan_veritify_notnull +{ + my $output = shift; + return index($output, 'DEBUG: all new not-null constraints on relation') != -1; +} + +my $output; + +note "test alter table SET NOT NULL using indexscan with partitioned table"; + +run_sql_command( + 'CREATE TABLE tp (a int, b int, c int, d int ) PARTITION BY range(a); + CREATE TABLE tpp1 partition of tp for values from ( 1 ) to (10); + CREATE TABLE tpp2 partition of tp for values from ( 10 ) to (21); + INSERT INTO tp select g, g + 10, g + 15, g + random(min=>1::int, max=>10::int) from generate_series(1,19) g; + CREATE INDEX ON tp(b); '); + +$output = run_sql_command('ALTER TABLE tp ALTER COLUMN b SET NOT NULL;'); +ok(is_indexscan_veritify_notnull($output), + 'column b will use indexscan to verify not-null status, no need scan table'); +ok( $output =~ + m/all new not-null constraints on relation "tpp1" have been validated by using index scan/, + 'all newly added constraints proved by indexscan'); + +run_sql_command( + 'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;'); + +# use indexes on partitions to fast vertifing not-null should be ok +$output = run_sql_command('ALTER TABLE tpp1 ALTER COLUMN b SET NOT NULL;'); +ok(is_indexscan_veritify_notnull($output), 'use indexscan to validate column b not-null will not scan table'); +ok(!is_table_verified($output), 'no table scan for pp1'); +ok( $output =~ + m/all new not-null constraints on relation "tpp1" have been validated by using index scan/, + 'all newly added constraints proved by indexscan'); + +$output = run_sql_command('ALTER TABLE tpp2 ALTER COLUMN b SET NOT NULL;'); +ok(is_indexscan_veritify_notnull($output), 'use indexscan to validate column b not-null, will not scan table'); +ok(!is_table_verified($output), 'no table scan for tpp2'); +ok( $output =~ + m/all new not-null constraints on relation "tpp2" have been validated by using index scan/, + 'all newly added constraints proved by indexscan'); + +run_sql_command( + 'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;'); + +# table rewrite then can not use indexscan to verify not-null constraint +$output = run_sql_command( + 'ALTER TABLE tp ALTER COLUMN b SET NOT NULL, ALTER COLUMN b SET DATA TYPE bigint;' +); +ok(!is_table_verified($output), 'no table scan for tp'); +ok(!is_indexscan_veritify_notnull($output), 'table tp will rewrite, can not use indexscan to verify not-null constraints on it'); + +# test using indexscan with multiple not-null constraints +run_sql_command( + 'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL; + CREATE INDEX ON tp(c); + CREATE INDEX ON tp(d); '); + +# one column can use indexscan, another can not, so can not use indexscan to verify not-null +$output = run_sql_command( + 'ALTER TABLE tp ALTER COLUMN a SET NOT NULL, ADD CONSTRAINT c_nn NOT NULL c'); +ok(is_table_verified($output), 'table scan for tp'); +ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to verify not-null constraints on table tp'); + +# all columns have index on it +# use indexscan to verify multiple not-null constraints should just fine +$output = run_sql_command( + 'ALTER TABLE tp ALTER COLUMN d SET NOT NULL, ADD CONSTRAINT c_nn NOT NULL c, ALTER COLUMN b SET NOT NULL;'); +ok(!is_table_verified($output), 'no table scan for tp'); +ok(is_indexscan_veritify_notnull($output), + 'using indexscan to verify not-null constraints on column b, c, d, no need table scan'); + +# test with non-partitioned table and other non-Btree index. +run_sql_command( + 'CREATE TABLE t1(f1 INT, f2 int, f3 int,f4 int, f5 int); + INSERT INTO t1 select g, g+1, g+2, g+3, g+4 from generate_series(1, 100) g; + CREATE INDEX t1_f1_f2_idx ON t1(f1,f2); + CREATE UNIQUE INDEX t1_f3idx ON t1(f3); + CREATE INDEX t1_f3f4idx ON t1(f3) include(f4); + CREATE INDEX hash_f5_idx ON t1 USING hash (f5 int4_ops); '); + +# ALTER TABLE VALIDATE CONSTRAINT can not use indexscan, +# because it only hold ShareUpdateExclusiveLock lock. +run_sql_command('ALTER TABLE t1 ADD CONSTRAINT nn_t1_f2 NOT NULL f2 NOT VALID;'); + +$output = run_sql_command( + 'ALTER TABLE t1 VALIDATE CONSTRAINT nn_t1_f2;' +); +ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan for ALTER TABLE VALIDATE CONSTRAINT command'); +run_sql_command('ALTER TABLE t1 DROP CONSTRAINT nn_t1_f2;'); + +$output = run_sql_command( + 'ALTER TABLE t1 ALTER COLUMN f1 SET NOT NULL, ALTER f1 type bigint;' +); +ok(!is_indexscan_veritify_notnull($output), 'table t1 will rewrite, can not use indexscan to validate not-null constraints on t1'); + +run_sql_command('ALTER TABLE t1 ALTER COLUMN f1 DROP NOT NULL;'); +run_sql_command('ALTER TABLE t1 ADD CONSTRAINT nn NOT NULL f1, ALTER f1 type bigint;'); + +# can use indexscan mechanism to fast add multiple not-null constraints +$output = run_sql_command( + 'ALTER TABLE t1 ALTER COLUMN f2 SET NOT NULL, ALTER COLUMN f1 SET NOT NULL;' +); +ok( $output =~ + m/all new not-null constraints on relation "t1" have been validated by using index scan/, + 'all not-null constraints are validated by indexscan'); + +# using indexscan mechanism to fast add a not-null can only apply to key columns, not include column +$output = run_sql_command( + 'ALTER TABLE t1 ADD CONSTRAINT nnf4 NOT NULL f4;' +); +ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to validate not-null constraint on t1'); + +# if index is not btree index then cannot use indexscan mechanism to fast add not-null constraint +$output = run_sql_command( + 'ALTER TABLE t1 ADD CONSTRAINT nn_f5 NOT NULL f5;' +); +ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to validate not-null constraints on t1'); + +$node->stop('fast'); + +done_testing(); -- 2.47.3 --xpkr6zhfzd3fjt76-- ^ permalink raw reply [nested|flat] 11+ messages in thread
end of thread, other threads:[~2025-10-20 05:29 UTC | newest] Thread overview: 11+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2019-07-01 06:08 [PATCH 3/5] Adjust catcachebench for later patches Kyotaro Horiguchi <[email protected]> 2023-08-31 14:59 [PATCH v9 3/4] add support for syncfs in frontend support functions Nathan Bossart <[email protected]> 2023-08-31 14:59 [PATCH v9 3/4] add support for syncfs in frontend support functions Nathan Bossart <[email protected]> 2023-08-31 14:59 [PATCH v8 3/4] add support for syncfs in frontend support functions Nathan Bossart <[email protected]> 2023-08-31 14:59 [PATCH v9 3/4] add support for syncfs in frontend support functions Nathan Bossart <[email protected]> 2023-08-31 14:59 [PATCH v8 3/4] add support for syncfs in frontend support functions Nathan Bossart <[email protected]> 2023-08-31 14:59 [PATCH v9 3/4] add support for syncfs in frontend support functions Nathan Bossart <[email protected]> 2023-08-31 14:59 [PATCH v9 3/4] add support for syncfs in frontend support functions Nathan Bossart <[email protected]> 2024-03-28 10:30 [PATCH v15 2/8] Row pattern recognition patch (parse/analysis). Tatsuo Ishii <[email protected]> 2025-10-20 05:29 [PATCH v8] using indexscan to speedup add not null constraints jian he <[email protected]> 2025-10-20 05:29 [PATCH v8] using indexscan to speedup add not null constraints jian he <[email protected]>
This inbox is served by agora; see mirroring instructions for how to clone and mirror all data and code used for this inbox