fd.h File Reference

#include <dirent.h>
#include <fcntl.h>

Include dependency graph for fd.h:

This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Macros
#define	IO_DIRECT_DATA   0x01
#define	IO_DIRECT_WAL   0x02
#define	IO_DIRECT_WAL_INIT   0x04
#define	FILE_POSSIBLY_DELETED(err)   ((err) == ENOENT)
#define	PG_O_DIRECT   0

Typedefs
typedef int	File

Functions
File	PathNameOpenFile (const char *fileName, int fileFlags)
File	PathNameOpenFilePerm (const char *fileName, int fileFlags, mode_t fileMode)
File	OpenTemporaryFile (bool interXact)
void	FileClose (File file)
int	FilePrefetch (File file, off_t offset, off_t amount, uint32 wait_event_info)
int	FileRead (File file, void *buffer, size_t amount, off_t offset, uint32 wait_event_info)
int	FileWrite (File file, const void *buffer, size_t amount, off_t offset, uint32 wait_event_info)
int	FileSync (File file, uint32 wait_event_info)
int	FileZero (File file, off_t offset, off_t amount, uint32 wait_event_info)
int	FileFallocate (File file, off_t offset, off_t amount, uint32 wait_event_info)
off_t	FileSize (File file)
int	FileTruncate (File file, off_t offset, uint32 wait_event_info)
void	FileWriteback (File file, off_t offset, off_t nbytes, uint32 wait_event_info)
char *	FilePathName (File file)
int	FileGetRawDesc (File file)
int	FileGetRawFlags (File file)
mode_t	FileGetRawMode (File file)
File	PathNameCreateTemporaryFile (const char *path, bool error_on_failure)
File	PathNameOpenTemporaryFile (const char *path, int mode)
bool	PathNameDeleteTemporaryFile (const char *path, bool error_on_failure)
void	PathNameCreateTemporaryDir (const char *basedir, const char *directory)
void	PathNameDeleteTemporaryDir (const char *dirname)
void	TempTablespacePath (char *path, Oid tablespace)
FILE *	AllocateFile (const char *name, const char *mode)
int	FreeFile (FILE *file)
FILE *	OpenPipeStream (const char *command, const char *mode)
int	ClosePipeStream (FILE *file)
DIR *	AllocateDir (const char *dirname)
struct dirent *	ReadDir (DIR *dir, const char *dirname)
struct dirent *	ReadDirExtended (DIR *dir, const char *dirname, int elevel)
int	FreeDir (DIR *dir)
int	OpenTransientFile (const char *fileName, int fileFlags)
int	OpenTransientFilePerm (const char *fileName, int fileFlags, mode_t fileMode)
int	CloseTransientFile (int fd)
int	BasicOpenFile (const char *fileName, int fileFlags)
int	BasicOpenFilePerm (const char *fileName, int fileFlags, mode_t fileMode)
bool	AcquireExternalFD (void)
void	ReserveExternalFD (void)
void	ReleaseExternalFD (void)
int	MakePGDirectory (const char *directoryName)
void	InitFileAccess (void)
void	InitTemporaryFileAccess (void)
void	set_max_safe_fds (void)
void	closeAllVfds (void)
void	SetTempTablespaces (Oid *tableSpaces, int numSpaces)
bool	TempTablespacesAreSet (void)
int	GetTempTablespaces (Oid *tableSpaces, int numSpaces)
Oid	GetNextTempTableSpace (void)
void	AtEOXact_Files (bool isCommit)
void	AtEOSubXact_Files (bool isCommit, SubTransactionId mySubid, SubTransactionId parentSubid)
void	RemovePgTempFiles (void)
void	RemovePgTempFilesInDir (const char *tmpdirname, bool missing_ok, bool unlink_all)
bool	looks_like_temp_rel_name (const char *name)
int	pg_fsync (int fd)
int	pg_fsync_no_writethrough (int fd)
int	pg_fsync_writethrough (int fd)
int	pg_fdatasync (int fd)
void	pg_flush_data (int fd, off_t offset, off_t nbytes)
int	pg_truncate (const char *path, off_t length)
void	fsync_fname (const char *fname, bool isdir)
int	fsync_fname_ext (const char *fname, bool isdir, bool ignore_perm, int elevel)
int	durable_rename (const char *oldfile, const char *newfile, int elevel)
int	durable_unlink (const char *fname, int elevel)
void	SyncDataDirectory (void)
int	data_sync_elevel (int elevel)

Variables
PGDLLIMPORT int	max_files_per_process
PGDLLIMPORT bool	data_sync_retry
PGDLLIMPORT int	recovery_init_sync_method
PGDLLIMPORT int	io_direct_flags
PGDLLIMPORT int	max_safe_fds

Macro Definition Documentation

FILE_POSSIBLY_DELETED

#define FILE_POSSIBLY_DELETED

(

err

)

((err) == ENOENT)

Definition at line 76 of file fd.h.

IO_DIRECT_DATA

#define IO_DIRECT_DATA   0x01

Definition at line 52 of file fd.h.

IO_DIRECT_WAL

#define IO_DIRECT_WAL   0x02

Definition at line 53 of file fd.h.

IO_DIRECT_WAL_INIT

#define IO_DIRECT_WAL_INIT   0x04

Definition at line 54 of file fd.h.

PG_O_DIRECT

#define PG_O_DIRECT   0

Definition at line 95 of file fd.h.

Typedef Documentation

File

typedef int File

Definition at line 49 of file fd.h.

Function Documentation

AcquireExternalFD()

bool AcquireExternalFD

(

void

)

Definition at line 1138 of file fd.c.

{
    /*
     * We don't want more than max_safe_fds / 3 FDs to be consumed for
     * "external" FDs.
     */
    if (numExternalFDs < max_safe_fds / 3)
    {
        ReserveExternalFD();
        return true;
    }
    errno = EMFILE;
    return false;
}

References max_safe_fds, numExternalFDs, and ReserveExternalFD().

Referenced by CreateWaitEventSet(), and libpqsrv_connect_prepare().

AllocateDir()

DIR* AllocateDir

(

const char *

dirname

)

Definition at line 2788 of file fd.c.

{
    DIR        *dir;
 
    DO_DB(elog(LOG, "AllocateDir: Allocated %d (%s)",
               numAllocatedDescs, dirname));
 
    /* Can we allocate another non-virtual FD? */
    if (!reserveAllocatedDesc())
        ereport(ERROR,
                (errcode(ERRCODE_INSUFFICIENT_RESOURCES),
                 errmsg("exceeded maxAllocatedDescs (%d) while trying to open directory \"%s\"",
                        maxAllocatedDescs, dirname)));
 
    /* Close excess kernel FDs. */
    ReleaseLruFiles();
 
TryAgain:
    if ((dir = opendir(dirname)) != NULL)
    {
        AllocateDesc *desc = &allocatedDescs[numAllocatedDescs];
 
        desc->kind = AllocateDescDir;
        desc->desc.dir = dir;
        desc->create_subid = GetCurrentSubTransactionId();
        numAllocatedDescs++;
        return desc->desc.dir;
    }
 
    if (errno == EMFILE || errno == ENFILE)
    {
        int         save_errno = errno;
 
        ereport(LOG,
                (errcode(ERRCODE_INSUFFICIENT_RESOURCES),
                 errmsg("out of file descriptors: %m; release and retry")));
        errno = 0;
        if (ReleaseLruFile())
            goto TryAgain;
        errno = save_errno;
    }
 
    return NULL;
}

References allocatedDescs, AllocateDescDir, AllocateDesc::create_subid, AllocateDesc::desc, AllocateDesc::dir, DO_DB, elog(), ereport, errcode(), errmsg(), ERROR, GetCurrentSubTransactionId(), AllocateDesc::kind, LOG, maxAllocatedDescs, numAllocatedDescs, opendir(), ReleaseLruFile(), ReleaseLruFiles(), and reserveAllocatedDesc().

Referenced by calculate_database_size(), calculate_tablespace_size(), CheckPointLogicalRewriteHeap(), CheckPointSnapBuild(), CheckTablespaceDirectory(), CleanupBackupHistory(), copydir(), db_dir_size(), DeleteAllExportedSnapshotFiles(), destroy_tablespace_directories(), directory_is_empty(), do_pg_backup_start(), dsm_cleanup_for_mmap(), extension_file_exists(), get_ext_ver_list(), GetConfFilesInDir(), getInstallationPaths(), movedb(), ParseTzFile(), perform_base_backup(), pg_available_extension_versions(), pg_available_extensions(), pg_logdir_ls_internal(), pg_ls_dir(), pg_ls_dir_files(), pg_tablespace_databases(), pg_tzenumerate_next(), pg_tzenumerate_start(), pgarch_readyXlog(), RelationCacheInitFileRemove(), RelationCacheInitFileRemoveInDir(), RemoveNonParentXlogFiles(), RemoveOldXlogFiles(), RemovePgTempFiles(), RemovePgTempFilesInDir(), RemovePgTempRelationFiles(), RemovePgTempRelationFilesInDbspace(), RemoveTempXlogFiles(), ReorderBufferCleanupSerializedTXNs(), ResetUnloggedRelations(), ResetUnloggedRelationsInDbspaceDir(), ResetUnloggedRelationsInTablespaceDir(), restoreTwoPhaseData(), scan_directory_ci(), sendDir(), SlruScanDirectory(), StartupReorderBuffer(), StartupReplicationSlots(), SyncDataDirectory(), UpdateLogicalMappings(), and walkdir().

AllocateFile()

FILE* AllocateFile	(	const char *	name,
		const char *	mode
	)

Definition at line 2528 of file fd.c.

{
    FILE       *file;
 
    DO_DB(elog(LOG, "AllocateFile: Allocated %d (%s)",
               numAllocatedDescs, name));
 
    /* Can we allocate another non-virtual FD? */
    if (!reserveAllocatedDesc())
        ereport(ERROR,
                (errcode(ERRCODE_INSUFFICIENT_RESOURCES),
                 errmsg("exceeded maxAllocatedDescs (%d) while trying to open file \"%s\"",
                        maxAllocatedDescs, name)));
 
    /* Close excess kernel FDs. */
    ReleaseLruFiles();
 
TryAgain:
    if ((file = fopen(name, mode)) != NULL)
    {
        AllocateDesc *desc = &allocatedDescs[numAllocatedDescs];
 
        desc->kind = AllocateDescFile;
        desc->desc.file = file;
        desc->create_subid = GetCurrentSubTransactionId();
        numAllocatedDescs++;
        return desc->desc.file;
    }
 
    if (errno == EMFILE || errno == ENFILE)
    {
        int         save_errno = errno;
 
        ereport(LOG,
                (errcode(ERRCODE_INSUFFICIENT_RESOURCES),
                 errmsg("out of file descriptors: %m; release and retry")));
        errno = 0;
        if (ReleaseLruFile())
            goto TryAgain;
        errno = save_errno;
    }
 
    return NULL;
}

References allocatedDescs, AllocateDescFile, AllocateDesc::create_subid, AllocateDesc::desc, DO_DB, elog(), ereport, errcode(), errmsg(), ERROR, AllocateDesc::file, GetCurrentSubTransactionId(), AllocateDesc::kind, LOG, maxAllocatedDescs, mode, name, numAllocatedDescs, ReleaseLruFile(), ReleaseLruFiles(), and reserveAllocatedDesc().

Referenced by AlterSystemSetConfigFile(), apw_dump_now(), apw_load_buffers(), BeginCopyFrom(), BeginCopyTo(), checkControlFile(), do_pg_backup_stop(), entry_reset(), existsTimeLineHistory(), ExportSnapshot(), gc_qtexts(), GetHugePageSize(), ImportSnapshot(), load_dh_file(), load_relcache_init_file(), open_auth_file(), parse_extension_control_file(), ParseTzFile(), pg_current_logfile(), pg_file_write_internal(), pg_promote(), pgss_shmem_shutdown(), pgss_shmem_startup(), pgstat_read_statsfile(), pgstat_write_statsfile(), read_backup_label(), read_binary_file(), read_tablespace_map(), read_whole_file(), readTimeLineHistory(), tsearch_readline_begin(), ValidatePgVersion(), write_relcache_init_file(), XLogArchiveForceDone(), and XLogArchiveNotify().

AtEOSubXact_Files()

void AtEOSubXact_Files	(	bool	isCommit,
		SubTransactionId	mySubid,
		SubTransactionId	parentSubid
	)

Definition at line 3077 of file fd.c.

{
    Index       i;
 
    for (i = 0; i < numAllocatedDescs; i++)
    {
        if (allocatedDescs[i].create_subid == mySubid)
        {
            if (isCommit)
                allocatedDescs[i].create_subid = parentSubid;
            else
            {
                /* have to recheck the item after FreeDesc (ugly) */
                FreeDesc(&allocatedDescs[i--]);
            }
        }
    }
}

References allocatedDescs, AllocateDesc::create_subid, FreeDesc(), i, and numAllocatedDescs.

Referenced by AbortSubTransaction(), basic_archive_file(), and CommitSubTransaction().

AtEOXact_Files()

void AtEOXact_Files

(

bool

isCommit

)

Definition at line 3110 of file fd.c.

{
    CleanupTempFiles(isCommit, false);
    tempTableSpaces = NULL;
    numTempTableSpaces = -1;
}

References CleanupTempFiles(), numTempTableSpaces, and tempTableSpaces.

Referenced by AbortTransaction(), AutoVacLauncherMain(), BackgroundWriterMain(), CheckpointerMain(), CommitTransaction(), PrepareTransaction(), and WalWriterMain().

BasicOpenFile()

int BasicOpenFile	(	const char *	fileName,
		int	fileFlags
	)

Definition at line 1039 of file fd.c.

{
    return BasicOpenFilePerm(fileName, fileFlags, pg_file_create_mode);
}

References BasicOpenFilePerm(), and pg_file_create_mode.

Referenced by AlterSystemSetConfigFile(), ReadControlFile(), update_controlfile(), wal_segment_open(), WalSndSegmentOpen(), WriteControlFile(), XLogFileInit(), XLogFileInitInternal(), XLogFileOpen(), and XLogFileRead().

BasicOpenFilePerm()

int BasicOpenFilePerm	(	const char *	fileName,
		int	fileFlags,
		mode_t	fileMode
	)

Definition at line 1061 of file fd.c.

{
    int         fd;
 
tryAgain:
#ifdef PG_O_DIRECT_USE_F_NOCACHE
 
    /*
     * The value we defined to stand in for O_DIRECT when simulating it with
     * F_NOCACHE had better not collide with any of the standard flags.
     */
    StaticAssertStmt((PG_O_DIRECT &
                      (O_APPEND |
                       O_CLOEXEC |
                       O_CREAT |
                       O_DSYNC |
                       O_EXCL |
                       O_RDWR |
                       O_RDONLY |
                       O_SYNC |
                       O_TRUNC |
                       O_WRONLY)) == 0,
                     "PG_O_DIRECT value collides with standard flag");
    fd = open(fileName, fileFlags & ~PG_O_DIRECT, fileMode);
#else
    fd = open(fileName, fileFlags, fileMode);
#endif
 
    if (fd >= 0)
    {
#ifdef PG_O_DIRECT_USE_F_NOCACHE
        if (fileFlags & PG_O_DIRECT)
        {
            if (fcntl(fd, F_NOCACHE, 1) < 0)
            {
                int         save_errno = errno;
 
                close(fd);
                errno = save_errno;
                return -1;
            }
        }
#endif
 
        return fd;              /* success! */
    }
 
    if (errno == EMFILE || errno == ENFILE)
    {
        int         save_errno = errno;
 
        ereport(LOG,
                (errcode(ERRCODE_INSUFFICIENT_RESOURCES),
                 errmsg("out of file descriptors: %m; release and retry")));
        errno = 0;
        if (ReleaseLruFile())
            goto tryAgain;
        errno = save_errno;
    }
 
    return -1;                  /* failure */
}

References close, ereport, errcode(), errmsg(), fd(), LOG, O_CLOEXEC, O_DSYNC, PG_O_DIRECT, ReleaseLruFile(), and StaticAssertStmt.

Referenced by BasicOpenFile(), LruInsert(), OpenTransientFilePerm(), PathNameOpenFilePerm(), and readRecoverySignalFile().

closeAllVfds()

void closeAllVfds

(

void

)

Definition at line 2965 of file fd.c.

{
    Index       i;
 
    if (SizeVfdCache > 0)
    {
        Assert(FileIsNotOpen(0));   /* Make sure ring not corrupted */
        for (i = 1; i < SizeVfdCache; i++)
        {
            if (!FileIsNotOpen(i))
                LruDelete(i);
        }
    }
}

References Assert(), FileIsNotOpen, i, LruDelete(), and SizeVfdCache.

Referenced by standard_ProcessUtility().

ClosePipeStream()

int ClosePipeStream

(

FILE *

file

)

Definition at line 2936 of file fd.c.

{
    int         i;
 
    DO_DB(elog(LOG, "ClosePipeStream: Allocated %d", numAllocatedDescs));
 
    /* Remove file from list of allocated files, if it's present */
    for (i = numAllocatedDescs; --i >= 0;)
    {
        AllocateDesc *desc = &allocatedDescs[i];
 
        if (desc->kind == AllocateDescPipe && desc->desc.file == file)
            return FreeDesc(desc);
    }
 
    /* Only get here if someone passes us a file not in allocatedDescs */
    elog(WARNING, "file passed to ClosePipeStream was not obtained from OpenPipeStream");
 
    return pclose(file);
}

References allocatedDescs, AllocateDescPipe, AllocateDesc::desc, DO_DB, elog(), AllocateDesc::file, FreeDesc(), i, AllocateDesc::kind, LOG, numAllocatedDescs, and WARNING.

Referenced by ClosePipeFromProgram(), ClosePipeToProgram(), pg_import_system_collations(), run_ssl_passphrase_command(), and shell_finish_command().

CloseTransientFile()

int CloseTransientFile

(

int

fd

)

Definition at line 2754 of file fd.c.

{
    int         i;
 
    DO_DB(elog(LOG, "CloseTransientFile: Allocated %d", numAllocatedDescs));
 
    /* Remove fd from list of allocated files, if it's present */
    for (i = numAllocatedDescs; --i >= 0;)
    {
        AllocateDesc *desc = &allocatedDescs[i];
 
        if (desc->kind == AllocateDescRawFD && desc->desc.fd == fd)
            return FreeDesc(desc);
    }
 
    /* Only get here if someone passes us a file not in allocatedDescs */
    elog(WARNING, "fd passed to CloseTransientFile was not obtained from OpenTransientFile");
 
    return close(fd);
}

References allocatedDescs, AllocateDescRawFD, close, AllocateDesc::desc, DO_DB, elog(), AllocateDesc::fd, fd(), FreeDesc(), i, AllocateDesc::kind, LOG, numAllocatedDescs, and WARNING.

Referenced by ApplyLogicalMappingFile(), be_lo_export(), CheckPointLogicalRewriteHeap(), CheckPointReplicationOrigin(), compare_files(), copy_file(), CreateDirAndVersionFile(), dsm_impl_mmap(), durable_rename(), fsync_fname_ext(), get_controlfile(), heap_xlog_logical_rewrite(), lo_import_internal(), perform_base_backup(), pg_truncate(), qtext_load_file(), qtext_store(), read_relmap_file(), ReadTwoPhaseFile(), RecreateTwoPhaseFile(), ReorderBufferSerializeChange(), ReorderBufferSerializeTXN(), RestoreSlotFromDisk(), SaveSlotToPath(), sendFile(), SendTimeLineHistory(), SimpleLruDoesPhysicalPageExist(), SimpleLruWriteAll(), SlruInternalWritePage(), SlruPhysicalReadPage(), SlruPhysicalWritePage(), SlruSyncFileTag(), SnapBuildRestore(), SnapBuildRestoreContents(), SnapBuildSerialize(), StartupReplicationOrigin(), write_relmap_file(), writeTimeLineHistory(), writeTimeLineHistoryFile(), and XLogFileCopy().

data_sync_elevel()

int data_sync_elevel

(

int

elevel

)

Definition at line 3881 of file fd.c.

{
    return data_sync_retry ? elevel : PANIC;
}

References data_sync_retry, and PANIC.

Referenced by CheckPointLogicalRewriteHeap(), FileClose(), fsync_fname(), heap_xlog_logical_rewrite(), logical_end_heap_rewrite(), LruDelete(), mdimmedsync(), pg_flush_data(), ProcessSyncRequests(), register_dirty_segment(), SlruReportIOError(), writeTimeLineHistory(), writeTimeLineHistoryFile(), and XLogFileCopy().

durable_rename()

int durable_rename	(	const char *	oldfile,
		const char *	newfile,
		int	elevel
	)

Definition at line 734 of file fd.c.

{
    int         fd;
 
    /*
     * First fsync the old and target path (if it exists), to ensure that they
     * are properly persistent on disk. Syncing the target file is not
     * strictly necessary, but it makes it easier to reason about crashes;
     * because it's then guaranteed that either source or target file exists
     * after a crash.
     */
    if (fsync_fname_ext(oldfile, false, false, elevel) != 0)
        return -1;
 
    fd = OpenTransientFile(newfile, PG_BINARY | O_RDWR);
    if (fd < 0)
    {
        if (errno != ENOENT)
        {
            ereport(elevel,
                    (errcode_for_file_access(),
                     errmsg("could not open file \"%s\": %m", newfile)));
            return -1;
        }
    }
    else
    {
        if (pg_fsync(fd) != 0)
        {
            int         save_errno;
 
            /* close file upon error, might not be in transaction context */
            save_errno = errno;
            CloseTransientFile(fd);
            errno = save_errno;
 
            ereport(elevel,
                    (errcode_for_file_access(),
                     errmsg("could not fsync file \"%s\": %m", newfile)));
            return -1;
        }
 
        if (CloseTransientFile(fd) != 0)
        {
            ereport(elevel,
                    (errcode_for_file_access(),
                     errmsg("could not close file \"%s\": %m", newfile)));
            return -1;
        }
    }
 
    /* Time to do the real deal... */
    if (rename(oldfile, newfile) < 0)
    {
        ereport(elevel,
                (errcode_for_file_access(),
                 errmsg("could not rename file \"%s\" to \"%s\": %m",
                        oldfile, newfile)));
        return -1;
    }
 
    /*
     * To guarantee renaming the file is persistent, fsync the file with its
     * new name, and its containing directory.
     */
    if (fsync_fname_ext(newfile, false, false, elevel) != 0)
        return -1;
 
    if (fsync_parent_path(newfile, elevel) != 0)
        return -1;
 
    return 0;
}

References CloseTransientFile(), ereport, errcode_for_file_access(), errmsg(), fd(), fsync_fname_ext(), fsync_parent_path(), OpenTransientFile(), PG_BINARY, and pg_fsync().

Referenced by AlterSystemSetConfigFile(), apw_dump_now(), BaseBackup(), basic_archive_file_internal(), bbsink_server_end_manifest(), CheckPointReplicationOrigin(), CleanupAfterArchiveRecovery(), dir_close(), InitWalRecovery(), InstallXLogFileSegment(), KeepFileRestoredFromArchive(), pgss_shmem_shutdown(), StartupXLOG(), write_relmap_file(), writeTimeLineHistory(), writeTimeLineHistoryFile(), and XLogArchiveForceDone().

durable_unlink()

int durable_unlink	(	const char *	fname,
		int	elevel
	)

Definition at line 824 of file fd.c.

{
    if (unlink(fname) < 0)
    {
        ereport(elevel,
                (errcode_for_file_access(),
                 errmsg("could not remove file \"%s\": %m",
                        fname)));
        return -1;
    }
 
    /*
     * To guarantee that the removal of the file is persistent, fsync its
     * parent directory.
     */
    if (fsync_parent_path(fname, elevel) != 0)
        return -1;
 
    return 0;
}

References ereport, errcode_for_file_access(), errmsg(), and fsync_parent_path().

Referenced by InstallXLogFileSegment(), RemoveXlogFile(), and StartupXLOG().

FileClose()

void FileClose

(

File

file

)

Definition at line 1930 of file fd.c.

{
    Vfd        *vfdP;
 
    Assert(FileIsValid(file));
 
    DO_DB(elog(LOG, "FileClose: %d (%s)",
               file, VfdCache[file].fileName));
 
    vfdP = &VfdCache[file];
 
    if (!FileIsNotOpen(file))
    {
        /* close the file */
        if (close(vfdP->fd) != 0)
        {
            /*
             * We may need to panic on failure to close non-temporary files;
             * see LruDelete.
             */
            elog(vfdP->fdstate & FD_TEMP_FILE_LIMIT ? LOG : data_sync_elevel(LOG),
                 "could not close file \"%s\": %m", vfdP->fileName);
        }
 
        --nfile;
        vfdP->fd = VFD_CLOSED;
 
        /* remove the file from the lru ring */
        Delete(file);
    }
 
    if (vfdP->fdstate & FD_TEMP_FILE_LIMIT)
    {
        /* Subtract its size from current usage (do first in case of error) */
        temporary_files_size -= vfdP->fileSize;
        vfdP->fileSize = 0;
    }
 
    /*
     * Delete the file if it was temporary, and make a log entry if wanted
     */
    if (vfdP->fdstate & FD_DELETE_AT_CLOSE)
    {
        struct stat filestats;
        int         stat_errno;
 
        /*
         * If we get an error, as could happen within the ereport/elog calls,
         * we'll come right back here during transaction abort.  Reset the
         * flag to ensure that we can't get into an infinite loop.  This code
         * is arranged to ensure that the worst-case consequence is failing to
         * emit log message(s), not failing to attempt the unlink.
         */
        vfdP->fdstate &= ~FD_DELETE_AT_CLOSE;
 
 
        /* first try the stat() */
        if (stat(vfdP->fileName, &filestats))
            stat_errno = errno;
        else
            stat_errno = 0;
 
        /* in any case do the unlink */
        if (unlink(vfdP->fileName))
            ereport(LOG,
                    (errcode_for_file_access(),
                     errmsg("could not delete file \"%s\": %m", vfdP->fileName)));
 
        /* and last report the stat results */
        if (stat_errno == 0)
            ReportTemporaryFileUsage(vfdP->fileName, filestats.st_size);
        else
        {
            errno = stat_errno;
            ereport(LOG,
                    (errcode_for_file_access(),
                     errmsg("could not stat file \"%s\": %m", vfdP->fileName)));
        }
    }
 
    /* Unregister it from the resource owner */
    if (vfdP->resowner)
        ResourceOwnerForgetFile(vfdP->resowner, file);
 
    /*
     * Return the Vfd slot to the free list
     */
    FreeVfd(file);
}

References Assert(), close, data_sync_elevel(), Delete(), DO_DB, elog(), ereport, errcode_for_file_access(), errmsg(), vfd::fd, FD_DELETE_AT_CLOSE, FD_TEMP_FILE_LIMIT, vfd::fdstate, FileIsNotOpen, FileIsValid, vfd::fileName, vfd::fileSize, FreeVfd(), LOG, nfile, ReportTemporaryFileUsage(), ResourceOwnerForgetFile(), vfd::resowner, stat::st_size, stat, temporary_files_size, VFD_CLOSED, and VfdCache.

Referenced by bbsink_server_end_archive(), bbsink_server_end_manifest(), BufFileClose(), BufFileTruncateFileSet(), CleanupTempFiles(), logical_end_heap_rewrite(), mdclose(), mdimmedsync(), mdsyncfiletag(), mdtruncate(), ReorderBufferIterTXNFinish(), ReorderBufferRestoreChanges(), and ResourceOwnerReleaseInternal().

FileFallocate()

int FileFallocate	(	File	file,
		off_t	offset,
		off_t	amount,
		uint32	wait_event_info
	)

Definition at line 2314 of file fd.c.

{
#ifdef HAVE_POSIX_FALLOCATE
    int         returnCode;
 
    Assert(FileIsValid(file));
 
    DO_DB(elog(LOG, "FileFallocate: %d (%s) " INT64_FORMAT " " INT64_FORMAT,
               file, VfdCache[file].fileName,
               (int64) offset, (int64) amount));
 
    returnCode = FileAccess(file);
    if (returnCode < 0)
        return -1;
 
retry:
    pgstat_report_wait_start(wait_event_info);
    returnCode = posix_fallocate(VfdCache[file].fd, offset, amount);
    pgstat_report_wait_end();
 
    if (returnCode == 0)
        return 0;
    else if (returnCode == EINTR)
        goto retry;
 
    /* for compatibility with %m printing etc */
    errno = returnCode;
 
    /*
     * Return in cases of a "real" failure, if fallocate is not supported,
     * fall through to the FileZero() backed implementation.
     */
    if (returnCode != EINVAL && returnCode != EOPNOTSUPP)
        return -1;
#endif
 
    return FileZero(file, offset, amount, wait_event_info);
}

References Assert(), DO_DB, EINTR, elog(), EOPNOTSUPP, fd(), FileAccess(), FileIsValid, FileZero(), INT64_FORMAT, LOG, pgstat_report_wait_end(), pgstat_report_wait_start(), and VfdCache.

Referenced by mdzeroextend().

FileGetRawDesc()

int FileGetRawDesc

(

File

file

)

Definition at line 2422 of file fd.c.

{
    Assert(FileIsValid(file));
    return VfdCache[file].fd;
}

References Assert(), vfd::fd, FileIsValid, and VfdCache.

FileGetRawFlags()

int FileGetRawFlags

(

File

file

)

Definition at line 2432 of file fd.c.

{
    Assert(FileIsValid(file));
    return VfdCache[file].fileFlags;
}

References Assert(), vfd::fileFlags, FileIsValid, and VfdCache.

FileGetRawMode()

mode_t FileGetRawMode

(

File

file

)

Definition at line 2442 of file fd.c.

{
    Assert(FileIsValid(file));
    return VfdCache[file].fileMode;
}

References Assert(), FileIsValid, vfd::fileMode, and VfdCache.

FilePathName()

char* FilePathName

(

File

file

)

Definition at line 2406 of file fd.c.

{
    Assert(FileIsValid(file));
 
    return VfdCache[file].fileName;
}

References Assert(), FileIsValid, vfd::fileName, and VfdCache.

Referenced by _mdnblocks(), bbsink_server_archive_contents(), bbsink_server_end_archive(), bbsink_server_manifest_contents(), BufFileDumpBuffer(), BufFileLoadBuffer(), BufFileSeek(), BufFileSize(), BufFileTruncateFileSet(), mdextend(), mdimmedsync(), mdread(), mdsyncfiletag(), mdtruncate(), mdwrite(), mdzeroextend(), and register_dirty_segment().

FilePrefetch()

int FilePrefetch	(	File	file,
		off_t	offset,
		off_t	amount,
		uint32	wait_event_info
	)

Definition at line 2030 of file fd.c.

{
#if defined(USE_POSIX_FADVISE) && defined(POSIX_FADV_WILLNEED)
    int         returnCode;
 
    Assert(FileIsValid(file));
 
    DO_DB(elog(LOG, "FilePrefetch: %d (%s) " INT64_FORMAT " " INT64_FORMAT,
               file, VfdCache[file].fileName,
               (int64) offset, (int64) amount));
 
    returnCode = FileAccess(file);
    if (returnCode < 0)
        return returnCode;
 
retry:
    pgstat_report_wait_start(wait_event_info);
    returnCode = posix_fadvise(VfdCache[file].fd, offset, amount,
                               POSIX_FADV_WILLNEED);
    pgstat_report_wait_end();
 
    if (returnCode == EINTR)
        goto retry;
 
    return returnCode;
#else
    Assert(FileIsValid(file));
    return 0;
#endif
}

References Assert(), DO_DB, EINTR, elog(), fd(), FileAccess(), FileIsValid, INT64_FORMAT, LOG, pgstat_report_wait_end(), pgstat_report_wait_start(), and VfdCache.

Referenced by mdprefetch().

FileRead()

int FileRead	(	File	file,
		void *	buffer,
		size_t	amount,
		off_t	offset,
		uint32	wait_event_info
	)

Definition at line 2088 of file fd.c.

{
    int         returnCode;
    Vfd        *vfdP;
 
    Assert(FileIsValid(file));
 
    DO_DB(elog(LOG, "FileRead: %d (%s) " INT64_FORMAT " %zu %p",
               file, VfdCache[file].fileName,
               (int64) offset,
               amount, buffer));
 
    returnCode = FileAccess(file);
    if (returnCode < 0)
        return returnCode;
 
    vfdP = &VfdCache[file];
 
retry:
    pgstat_report_wait_start(wait_event_info);
    returnCode = pg_pread(vfdP->fd, buffer, amount, offset);
    pgstat_report_wait_end();
 
    if (returnCode < 0)
    {
        /*
         * Windows may run out of kernel buffers and return "Insufficient
         * system resources" error.  Wait a bit and retry to solve it.
         *
         * It is rumored that EINTR is also possible on some Unix filesystems,
         * in which case immediate retry is indicated.
         */
#ifdef WIN32
        DWORD       error = GetLastError();
 
        switch (error)
        {
            case ERROR_NO_SYSTEM_RESOURCES:
                pg_usleep(1000L);
                errno = EINTR;
                break;
            default:
                _dosmaperr(error);
                break;
        }
#endif
        /* OK to retry if interrupted */
        if (errno == EINTR)
            goto retry;
    }
 
    return returnCode;
}

References _dosmaperr(), Assert(), DO_DB, EINTR, elog(), error(), vfd::fd, FileAccess(), FileIsValid, INT64_FORMAT, LOG, pg_pread, pg_usleep(), pgstat_report_wait_end(), pgstat_report_wait_start(), and VfdCache.

Referenced by BufFileLoadBuffer(), mdread(), and ReorderBufferRestoreChanges().

FileSize()

off_t FileSize

(

File

file

)

Definition at line 2354 of file fd.c.

{
    Assert(FileIsValid(file));
 
    DO_DB(elog(LOG, "FileSize %d (%s)",
               file, VfdCache[file].fileName));
 
    if (FileIsNotOpen(file))
    {
        if (FileAccess(file) < 0)
            return (off_t) -1;
    }
 
    return lseek(VfdCache[file].fd, 0, SEEK_END);
}

References Assert(), DO_DB, elog(), fd(), FileAccess(), FileIsNotOpen, FileIsValid, LOG, and VfdCache.

Referenced by _mdnblocks(), BufFileSeek(), and BufFileSize().

FileSync()

int FileSync	(	File	file,
		uint32	wait_event_info
	)

Definition at line 2242 of file fd.c.

{
    int         returnCode;
 
    Assert(FileIsValid(file));
 
    DO_DB(elog(LOG, "FileSync: %d (%s)",
               file, VfdCache[file].fileName));
 
    returnCode = FileAccess(file);
    if (returnCode < 0)
        return returnCode;
 
    pgstat_report_wait_start(wait_event_info);
    returnCode = pg_fsync(VfdCache[file].fd);
    pgstat_report_wait_end();
 
    return returnCode;
}

References Assert(), DO_DB, elog(), fd(), FileAccess(), FileIsValid, LOG, pg_fsync(), pgstat_report_wait_end(), pgstat_report_wait_start(), and VfdCache.

Referenced by bbsink_server_end_archive(), logical_end_heap_rewrite(), mdimmedsync(), mdsyncfiletag(), and register_dirty_segment().

FileTruncate()

int FileTruncate	(	File	file,
		off_t	offset,
		uint32	wait_event_info
	)

Definition at line 2371 of file fd.c.

{
    int         returnCode;
 
    Assert(FileIsValid(file));
 
    DO_DB(elog(LOG, "FileTruncate %d (%s)",
               file, VfdCache[file].fileName));
 
    returnCode = FileAccess(file);
    if (returnCode < 0)
        return returnCode;
 
    pgstat_report_wait_start(wait_event_info);
    returnCode = pg_ftruncate(VfdCache[file].fd, offset);
    pgstat_report_wait_end();
 
    if (returnCode == 0 && VfdCache[file].fileSize > offset)
    {
        /* adjust our state for truncation of a temp file */
        Assert(VfdCache[file].fdstate & FD_TEMP_FILE_LIMIT);
        temporary_files_size -= VfdCache[file].fileSize - offset;
        VfdCache[file].fileSize = offset;
    }
 
    return returnCode;
}

References Assert(), DO_DB, elog(), fd(), FD_TEMP_FILE_LIMIT, FileAccess(), FileIsValid, vfd::fileSize, LOG, pg_ftruncate(), pgstat_report_wait_end(), pgstat_report_wait_start(), temporary_files_size, and VfdCache.

Referenced by BufFileTruncateFileSet(), and mdtruncate().

FileWrite()

int FileWrite	(	File	file,
		const void *	buffer,
		size_t	amount,
		off_t	offset,
		uint32	wait_event_info
	)

Definition at line 2144 of file fd.c.

{
    int         returnCode;
    Vfd        *vfdP;
 
    Assert(FileIsValid(file));
 
    DO_DB(elog(LOG, "FileWrite: %d (%s) " INT64_FORMAT " %zu %p",
               file, VfdCache[file].fileName,
               (int64) offset,
               amount, buffer));
 
    returnCode = FileAccess(file);
    if (returnCode < 0)
        return returnCode;
 
    vfdP = &VfdCache[file];
 
    /*
     * If enforcing temp_file_limit and it's a temp file, check to see if the
     * write would overrun temp_file_limit, and throw error if so.  Note: it's
     * really a modularity violation to throw error here; we should set errno
     * and return -1.  However, there's no way to report a suitable error
     * message if we do that.  All current callers would just throw error
     * immediately anyway, so this is safe at present.
     */
    if (temp_file_limit >= 0 && (vfdP->fdstate & FD_TEMP_FILE_LIMIT))
    {
        off_t       past_write = offset + amount;
 
        if (past_write > vfdP->fileSize)
        {
            uint64      newTotal = temporary_files_size;
 
            newTotal += past_write - vfdP->fileSize;
            if (newTotal > (uint64) temp_file_limit * (uint64) 1024)
                ereport(ERROR,
                        (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
                         errmsg("temporary file size exceeds temp_file_limit (%dkB)",
                                temp_file_limit)));
        }
    }
 
retry:
    errno = 0;
    pgstat_report_wait_start(wait_event_info);
    returnCode = pg_pwrite(VfdCache[file].fd, buffer, amount, offset);
    pgstat_report_wait_end();
 
    /* if write didn't set errno, assume problem is no disk space */
    if (returnCode != amount && errno == 0)
        errno = ENOSPC;
 
    if (returnCode >= 0)
    {
        /*
         * Maintain fileSize and temporary_files_size if it's a temp file.
         */
        if (vfdP->fdstate & FD_TEMP_FILE_LIMIT)
        {
            off_t       past_write = offset + amount;
 
            if (past_write > vfdP->fileSize)
            {
                temporary_files_size += past_write - vfdP->fileSize;
                vfdP->fileSize = past_write;
            }
        }
    }
    else
    {
        /*
         * See comments in FileRead()
         */
#ifdef WIN32
        DWORD       error = GetLastError();
 
        switch (error)
        {
            case ERROR_NO_SYSTEM_RESOURCES:
                pg_usleep(1000L);
                errno = EINTR;
                break;
            default:
                _dosmaperr(error);
                break;
        }
#endif
        /* OK to retry if interrupted */
        if (errno == EINTR)
            goto retry;
    }
 
    return returnCode;
}

References _dosmaperr(), Assert(), DO_DB, EINTR, elog(), ereport, errcode(), errmsg(), ERROR, error(), fd(), FD_TEMP_FILE_LIMIT, vfd::fdstate, FileAccess(), FileIsValid, vfd::fileSize, INT64_FORMAT, LOG, pg_pwrite, pg_usleep(), pgstat_report_wait_end(), pgstat_report_wait_start(), temp_file_limit, temporary_files_size, and VfdCache.

Referenced by bbsink_server_archive_contents(), bbsink_server_manifest_contents(), BufFileDumpBuffer(), logical_heap_rewrite_flush_mappings(), mdextend(), and mdwrite().

FileWriteback()

void FileWriteback	(	File	file,
		off_t	offset,
		off_t	nbytes,
		uint32	wait_event_info
	)

Definition at line 2062 of file fd.c.

{
    int         returnCode;
 
    Assert(FileIsValid(file));
 
    DO_DB(elog(LOG, "FileWriteback: %d (%s) " INT64_FORMAT " " INT64_FORMAT,
               file, VfdCache[file].fileName,
               (int64) offset, (int64) nbytes));
 
    if (nbytes <= 0)
        return;
 
    if (VfdCache[file].fileFlags & PG_O_DIRECT)
        return;
 
    returnCode = FileAccess(file);
    if (returnCode < 0)
        return;
 
    pgstat_report_wait_start(wait_event_info);
    pg_flush_data(VfdCache[file].fd, offset, nbytes);
    pgstat_report_wait_end();
}

References Assert(), DO_DB, elog(), fd(), FileAccess(), FileIsValid, INT64_FORMAT, LOG, pg_flush_data(), PG_O_DIRECT, pgstat_report_wait_end(), pgstat_report_wait_start(), and VfdCache.

Referenced by mdwriteback().

FileZero()

int FileZero	(	File	file,
		off_t	offset,
		off_t	amount,
		uint32	wait_event_info
	)

Definition at line 2269 of file fd.c.

{
    int         returnCode;
    ssize_t     written;
 
    Assert(FileIsValid(file));
 
    DO_DB(elog(LOG, "FileZero: %d (%s) " INT64_FORMAT " " INT64_FORMAT,
               file, VfdCache[file].fileName,
               (int64) offset, (int64) amount));
 
    returnCode = FileAccess(file);
    if (returnCode < 0)
        return returnCode;
 
    pgstat_report_wait_start(wait_event_info);
    written = pg_pwrite_zeros(VfdCache[file].fd, amount, offset);
    pgstat_report_wait_end();
 
    if (written < 0)
        return -1;
    else if (written != amount)
    {
        /* if errno is unset, assume problem is no disk space */
        if (errno == 0)
            errno = ENOSPC;
        return -1;
    }
 
    return 0;
}

References Assert(), DO_DB, elog(), fd(), FileAccess(), FileIsValid, INT64_FORMAT, LOG, pg_pwrite_zeros(), pgstat_report_wait_end(), pgstat_report_wait_start(), and VfdCache.

Referenced by FileFallocate(), and mdzeroextend().

FreeDir()

int FreeDir

(

DIR *

dir

)

Definition at line 2906 of file fd.c.

{
    int         i;
 
    /* Nothing to do if AllocateDir failed */
    if (dir == NULL)
        return 0;
 
    DO_DB(elog(LOG, "FreeDir: Allocated %d", numAllocatedDescs));
 
    /* Remove dir from list of allocated dirs, if it's present */
    for (i = numAllocatedDescs; --i >= 0;)
    {
        AllocateDesc *desc = &allocatedDescs[i];
 
        if (desc->kind == AllocateDescDir && desc->desc.dir == dir)
            return FreeDesc(desc);
    }
 
    /* Only get here if someone passes us a dir not in allocatedDescs */
    elog(WARNING, "dir passed to FreeDir was not obtained from AllocateDir");
 
    return closedir(dir);
}

References allocatedDescs, AllocateDescDir, closedir(), AllocateDesc::desc, AllocateDesc::dir, DO_DB, elog(), FreeDesc(), i, AllocateDesc::kind, LOG, numAllocatedDescs, and WARNING.

Referenced by calculate_database_size(), calculate_tablespace_size(), CheckPointLogicalRewriteHeap(), CheckPointSnapBuild(), CleanupBackupHistory(), copydir(), db_dir_size(), DeleteAllExportedSnapshotFiles(), destroy_tablespace_directories(), directory_is_empty(), do_pg_backup_start(), dsm_cleanup_for_mmap(), extension_file_exists(), get_ext_ver_list(), GetConfFilesInDir(), getInstallationPaths(), movedb(), ParseTzFile(), perform_base_backup(), pg_available_extension_versions(), pg_available_extensions(), pg_logdir_ls_internal(), pg_ls_dir(), pg_ls_dir_files(), pg_tablespace_databases(), pg_tzenumerate_end(), pg_tzenumerate_next(), pgarch_readyXlog(), RelationCacheInitFileRemove(), RelationCacheInitFileRemoveInDir(), RemoveNonParentXlogFiles(), RemoveOldXlogFiles(), RemovePgTempFiles(), RemovePgTempFilesInDir(), RemovePgTempRelationFiles(), RemovePgTempRelationFilesInDbspace(), RemoveTempXlogFiles(), ReorderBufferCleanupSerializedTXNs(), ResetUnloggedRelations(), ResetUnloggedRelationsInDbspaceDir(), ResetUnloggedRelationsInTablespaceDir(), restoreTwoPhaseData(), scan_directory_ci(), sendDir(), SlruScanDirectory(), StartupReorderBuffer(), StartupReplicationSlots(), SyncDataDirectory(), UpdateLogicalMappings(), and walkdir().

FreeFile()

int FreeFile

(

FILE *

file

)

Definition at line 2726 of file fd.c.

{
    int         i;
 
    DO_DB(elog(LOG, "FreeFile: Allocated %d", numAllocatedDescs));
 
    /* Remove file from list of allocated files, if it's present */
    for (i = numAllocatedDescs; --i >= 0;)
    {
        AllocateDesc *desc = &allocatedDescs[i];
 
        if (desc->kind == AllocateDescFile && desc->desc.file == file)
            return FreeDesc(desc);
    }
 
    /* Only get here if someone passes us a file not in allocatedDescs */
    elog(WARNING, "file passed to FreeFile was not obtained from AllocateFile");
 
    return fclose(file);
}

References allocatedDescs, AllocateDescFile, AllocateDesc::desc, DO_DB, elog(), AllocateDesc::file, FreeDesc(), i, AllocateDesc::kind, LOG, numAllocatedDescs, and WARNING.

Referenced by AlterSystemSetConfigFile(), apw_dump_now(), apw_load_buffers(), checkControlFile(), do_pg_backup_stop(), EndCopy(), EndCopyFrom(), entry_reset(), existsTimeLineHistory(), ExportSnapshot(), free_auth_file(), gc_qtexts(), GetHugePageSize(), ImportSnapshot(), load_dh_file(), load_relcache_init_file(), parse_extension_control_file(), ParseTzFile(), pg_current_logfile(), pg_file_write_internal(), pg_promote(), pgss_shmem_shutdown(), pgss_shmem_startup(), pgstat_read_statsfile(), pgstat_write_statsfile(), read_backup_label(), read_binary_file(), read_tablespace_map(), read_whole_file(), readTimeLineHistory(), tsearch_readline_end(), ValidatePgVersion(), write_relcache_init_file(), XLogArchiveForceDone(), and XLogArchiveNotify().

fsync_fname()

void fsync_fname	(	const char *	fname,
		bool	isdir
	)

Definition at line 708 of file fd.c.

{
    fsync_fname_ext(fname, isdir, false, data_sync_elevel(ERROR));
}

References data_sync_elevel(), ERROR, and fsync_fname_ext().

Referenced by _CloseArchive(), basic_archive_file_internal(), CheckPointLogicalRewriteHeap(), CheckPointTwoPhase(), copydir(), CreateSlotOnDisk(), dir_close(), dir_finish(), dir_open_for_write(), main(), ReplicationSlotDropPtr(), ResetUnloggedRelationsInDbspaceDir(), RestoreSlotFromDisk(), SaveSlotToPath(), SimpleLruWriteAll(), SnapBuildRestore(), SnapBuildSerialize(), StartupReplicationSlots(), and tar_finish().

fsync_fname_ext()

int fsync_fname_ext	(	const char *	fname,
		bool	isdir,
		bool	ignore_perm,
		int	elevel
	)

Definition at line 3742 of file fd.c.

{
    int         fd;
    int         flags;
    int         returncode;
 
    /*
     * Some OSs require directories to be opened read-only whereas other
     * systems don't allow us to fsync files opened read-only; so we need both
     * cases here.  Using O_RDWR will cause us to fail to fsync files that are
     * not writable by our userid, but we assume that's OK.
     */
    flags = PG_BINARY;
    if (!isdir)
        flags |= O_RDWR;
    else
        flags |= O_RDONLY;
 
    fd = OpenTransientFile(fname, flags);
 
    /*
     * Some OSs don't allow us to open directories at all (Windows returns
     * EACCES), just ignore the error in that case.  If desired also silently
     * ignoring errors about unreadable files. Log others.
     */
    if (fd < 0 && isdir && (errno == EISDIR || errno == EACCES))
        return 0;
    else if (fd < 0 && ignore_perm && errno == EACCES)
        return 0;
    else if (fd < 0)
    {
        ereport(elevel,
                (errcode_for_file_access(),
                 errmsg("could not open file \"%s\": %m", fname)));
        return -1;
    }
 
    returncode = pg_fsync(fd);
 
    /*
     * Some OSes don't allow us to fsync directories at all, so we can ignore
     * those errors. Anything else needs to be logged.
     */
    if (returncode != 0 && !(isdir && (errno == EBADF || errno == EINVAL)))
    {
        int         save_errno;
 
        /* close file upon error, might not be in transaction context */
        save_errno = errno;
        (void) CloseTransientFile(fd);
        errno = save_errno;
 
        ereport(elevel,
                (errcode_for_file_access(),
                 errmsg("could not fsync file \"%s\": %m", fname)));
        return -1;
    }
 
    if (CloseTransientFile(fd) != 0)
    {
        ereport(elevel,
                (errcode_for_file_access(),
                 errmsg("could not close file \"%s\": %m", fname)));
        return -1;
    }
 
    return 0;
}

References CloseTransientFile(), ereport, errcode_for_file_access(), errmsg(), fd(), OpenTransientFile(), PG_BINARY, and pg_fsync().

Referenced by datadir_fsync_fname(), durable_rename(), fsync_fname(), fsync_parent_path(), and pg_file_sync().

GetNextTempTableSpace()

Oid GetNextTempTableSpace

(

void

)

Definition at line 3056 of file fd.c.

{
    if (numTempTableSpaces > 0)
    {
        /* Advance nextTempTableSpace counter with wraparound */
        if (++nextTempTableSpace >= numTempTableSpaces)
            nextTempTableSpace = 0;
        return tempTableSpaces[nextTempTableSpace];
    }
    return InvalidOid;
}

References InvalidOid, nextTempTableSpace, numTempTableSpaces, and tempTableSpaces.

Referenced by GetDefaultTablespace(), and OpenTemporaryFile().

GetTempTablespaces()

int GetTempTablespaces	(	Oid *	tableSpaces,
		int	numSpaces
	)

Definition at line 3038 of file fd.c.

{
    int         i;
 
    Assert(TempTablespacesAreSet());
    for (i = 0; i < numTempTableSpaces && i < numSpaces; ++i)
        tableSpaces[i] = tempTableSpaces[i];
 
    return i;
}

References Assert(), i, numTempTableSpaces, tempTableSpaces, and TempTablespacesAreSet().

Referenced by FileSetInit().

InitFileAccess()

void InitFileAccess

(

void

)

Definition at line 855 of file fd.c.

{
    Assert(SizeVfdCache == 0);  /* call me only once */
 
    /* initialize cache header entry */
    VfdCache = (Vfd *) malloc(sizeof(Vfd));
    if (VfdCache == NULL)
        ereport(FATAL,
                (errcode(ERRCODE_OUT_OF_MEMORY),
                 errmsg("out of memory")));
 
    MemSet((char *) &(VfdCache[0]), 0, sizeof(Vfd));
    VfdCache->fd = VFD_CLOSED;
 
    SizeVfdCache = 1;
}

References Assert(), ereport, errcode(), errmsg(), FATAL, vfd::fd, malloc, MemSet, SizeVfdCache, VFD_CLOSED, and VfdCache.

Referenced by BaseInit().

InitTemporaryFileAccess()

void InitTemporaryFileAccess

(

void

)

Definition at line 885 of file fd.c.

{
    Assert(SizeVfdCache != 0);  /* InitFileAccess() needs to have run */
    Assert(!temporary_files_allowed);   /* call me only once */
 
    /*
     * Register before-shmem-exit hook to ensure temp files are dropped while
     * we can still report stats.
     */
    before_shmem_exit(BeforeShmemExit_Files, 0);
 
#ifdef USE_ASSERT_CHECKING
    temporary_files_allowed = true;
#endif
}

References Assert(), before_shmem_exit(), BeforeShmemExit_Files(), and SizeVfdCache.

Referenced by BaseInit().

looks_like_temp_rel_name()

bool looks_like_temp_rel_name

(

const char *

name

)

Definition at line 3394 of file fd.c.

{
    int         pos;
    int         savepos;
 
    /* Must start with "t". */
    if (name[0] != 't')
        return false;
 
    /* Followed by a non-empty string of digits and then an underscore. */
    for (pos = 1; isdigit((unsigned char) name[pos]); ++pos)
        ;
    if (pos == 1 || name[pos] != '_')
        return false;
 
    /* Followed by another nonempty string of digits. */
    for (savepos = ++pos; isdigit((unsigned char) name[pos]); ++pos)
        ;
    if (savepos == pos)
        return false;
 
    /* We might have _forkname or .segment or both. */
    if (name[pos] == '_')
    {
        int         forkchar = forkname_chars(&name[pos + 1], NULL);
 
        if (forkchar <= 0)
            return false;
        pos += forkchar + 1;
    }
    if (name[pos] == '.')
    {
        int         segchar;
 
        for (segchar = 1; isdigit((unsigned char) name[pos + segchar]); ++segchar)
            ;
        if (segchar <= 1)
            return false;
        pos += segchar;
    }
 
    /* Now we should be at the end. */
    if (name[pos] != '\0')
        return false;
    return true;
}

References forkname_chars(), and name.

Referenced by RemovePgTempRelationFilesInDbspace(), and sendDir().

MakePGDirectory()

int MakePGDirectory

(

const char *

directoryName

)

Definition at line 3858 of file fd.c.

{
    return mkdir(directoryName, pg_dir_create_mode);
}

References mkdir, and pg_dir_create_mode.

Referenced by bbsink_server_new(), copydir(), create_tablespace_directories(), CreateDirAndVersionFile(), CreateSlotOnDisk(), OpenTemporaryFileInTablespace(), PathNameCreateTemporaryDir(), SysLogger_Start(), SysLoggerMain(), TablespaceCreateDbspace(), test_slru_shmem_startup(), and ValidateXLOGDirectoryStructure().

OpenPipeStream()

FILE* OpenPipeStream	(	const char *	command,
		const char *	mode
	)

Definition at line 2631 of file fd.c.

{
    FILE       *file;
    int         save_errno;
 
    DO_DB(elog(LOG, "OpenPipeStream: Allocated %d (%s)",
               numAllocatedDescs, command));
 
    /* Can we allocate another non-virtual FD? */
    if (!reserveAllocatedDesc())
        ereport(ERROR,
                (errcode(ERRCODE_INSUFFICIENT_RESOURCES),
                 errmsg("exceeded maxAllocatedDescs (%d) while trying to execute command \"%s\"",
                        maxAllocatedDescs, command)));
 
    /* Close excess kernel FDs. */
    ReleaseLruFiles();
 
TryAgain:
    fflush(NULL);
    pqsignal(SIGPIPE, SIG_DFL);
    errno = 0;
    file = popen(command, mode);
    save_errno = errno;
    pqsignal(SIGPIPE, SIG_IGN);
    errno = save_errno;
    if (file != NULL)
    {
        AllocateDesc *desc = &allocatedDescs[numAllocatedDescs];
 
        desc->kind = AllocateDescPipe;
        desc->desc.file = file;
        desc->create_subid = GetCurrentSubTransactionId();
        numAllocatedDescs++;
        return desc->desc.file;
    }
 
    if (errno == EMFILE || errno == ENFILE)
    {
        ereport(LOG,
                (errcode(ERRCODE_INSUFFICIENT_RESOURCES),
                 errmsg("out of file descriptors: %m; release and retry")));
        if (ReleaseLruFile())
            goto TryAgain;
        errno = save_errno;
    }
 
    return NULL;
}

References allocatedDescs, AllocateDescPipe, AllocateDesc::create_subid, AllocateDesc::desc, DO_DB, elog(), ereport, errcode(), errmsg(), ERROR, fflush(), AllocateDesc::file, GetCurrentSubTransactionId(), AllocateDesc::kind, LOG, maxAllocatedDescs, mode, numAllocatedDescs, pqsignal(), ReleaseLruFile(), ReleaseLruFiles(), reserveAllocatedDesc(), SIG_DFL, SIG_IGN, and SIGPIPE.

Referenced by BeginCopyFrom(), BeginCopyTo(), pg_import_system_collations(), run_ssl_passphrase_command(), and shell_run_command().

OpenTemporaryFile()

File OpenTemporaryFile

(

bool

interXact

)

Definition at line 1676 of file fd.c.

{
    File        file = 0;
 
    Assert(temporary_files_allowed);    /* check temp file access is up */
 
    /*
     * Make sure the current resource owner has space for this File before we
     * open it, if we'll be registering it below.
     */
    if (!interXact)
        ResourceOwnerEnlargeFiles(CurrentResourceOwner);
 
    /*
     * If some temp tablespace(s) have been given to us, try to use the next
     * one.  If a given tablespace can't be found, we silently fall back to
     * the database's default tablespace.
     *
     * BUT: if the temp file is slated to outlive the current transaction,
     * force it into the database's default tablespace, so that it will not
     * pose a threat to possible tablespace drop attempts.
     */
    if (numTempTableSpaces > 0 && !interXact)
    {
        Oid         tblspcOid = GetNextTempTableSpace();
 
        if (OidIsValid(tblspcOid))
            file = OpenTemporaryFileInTablespace(tblspcOid, false);
    }
 
    /*
     * If not, or if tablespace is bad, create in database's default
     * tablespace.  MyDatabaseTableSpace should normally be set before we get
     * here, but just in case it isn't, fall back to pg_default tablespace.
     */
    if (file <= 0)
        file = OpenTemporaryFileInTablespace(MyDatabaseTableSpace ?
                                             MyDatabaseTableSpace :
                                             DEFAULTTABLESPACE_OID,
                                             true);
 
    /* Mark it for deletion at close and temporary file size limit */
    VfdCache[file].fdstate |= FD_DELETE_AT_CLOSE | FD_TEMP_FILE_LIMIT;
 
    /* Register it with the current resource owner */
    if (!interXact)
        RegisterTemporaryFile(file);
 
    return file;
}

References Assert(), CurrentResourceOwner, FD_DELETE_AT_CLOSE, FD_TEMP_FILE_LIMIT, vfd::fdstate, GetNextTempTableSpace(), MyDatabaseTableSpace, numTempTableSpaces, OidIsValid, OpenTemporaryFileInTablespace(), RegisterTemporaryFile(), ResourceOwnerEnlargeFiles(), and VfdCache.

Referenced by BufFileCreateTemp(), and extendBufFile().

OpenTransientFile()

int OpenTransientFile	(	const char *	fileName,
		int	fileFlags
	)

Definition at line 2578 of file fd.c.

{
    return OpenTransientFilePerm(fileName, fileFlags, pg_file_create_mode);
}

References OpenTransientFilePerm(), and pg_file_create_mode.

Referenced by ApplyLogicalMappingFile(), CheckPointLogicalRewriteHeap(), CheckPointReplicationOrigin(), compare_files(), copy_file(), CreateDirAndVersionFile(), dsm_impl_mmap(), durable_rename(), fsync_fname_ext(), get_controlfile(), heap_xlog_logical_rewrite(), lo_import_internal(), perform_base_backup(), pg_truncate(), qtext_load_file(), qtext_store(), read_relmap_file(), ReadTwoPhaseFile(), RecreateTwoPhaseFile(), ReorderBufferSerializeTXN(), RestoreSlotFromDisk(), SaveSlotToPath(), sendFile(), SendTimeLineHistory(), SimpleLruDoesPhysicalPageExist(), SlruPhysicalReadPage(), SlruPhysicalWritePage(), SlruSyncFileTag(), SnapBuildRestore(), SnapBuildSerialize(), StartupReplicationOrigin(), write_relmap_file(), writeTimeLineHistory(), writeTimeLineHistoryFile(), and XLogFileCopy().

OpenTransientFilePerm()

int OpenTransientFilePerm	(	const char *	fileName,
		int	fileFlags,
		mode_t	fileMode
	)

Definition at line 2587 of file fd.c.

{
    int         fd;
 
    DO_DB(elog(LOG, "OpenTransientFile: Allocated %d (%s)",
               numAllocatedDescs, fileName));
 
    /* Can we allocate another non-virtual FD? */
    if (!reserveAllocatedDesc())
        ereport(ERROR,
                (errcode(ERRCODE_INSUFFICIENT_RESOURCES),
                 errmsg("exceeded maxAllocatedDescs (%d) while trying to open file \"%s\"",
                        maxAllocatedDescs, fileName)));
 
    /* Close excess kernel FDs. */
    ReleaseLruFiles();
 
    fd = BasicOpenFilePerm(fileName, fileFlags, fileMode);
 
    if (fd >= 0)
    {
        AllocateDesc *desc = &allocatedDescs[numAllocatedDescs];
 
        desc->kind = AllocateDescRawFD;
        desc->desc.fd = fd;
        desc->create_subid = GetCurrentSubTransactionId();
        numAllocatedDescs++;
 
        return fd;
    }
 
    return -1;                  /* failure */
}

References allocatedDescs, AllocateDescRawFD, BasicOpenFilePerm(), AllocateDesc::create_subid, AllocateDesc::desc, DO_DB, elog(), ereport, errcode(), errmsg(), ERROR, AllocateDesc::fd, fd(), GetCurrentSubTransactionId(), AllocateDesc::kind, LOG, maxAllocatedDescs, numAllocatedDescs, ReleaseLruFiles(), and reserveAllocatedDesc().

Referenced by be_lo_export(), and OpenTransientFile().

PathNameCreateTemporaryDir()

void PathNameCreateTemporaryDir	(	const char *	basedir,
		const char *	directory
	)

Definition at line 1612 of file fd.c.

{
    if (MakePGDirectory(directory) < 0)
    {
        if (errno == EEXIST)
            return;
 
        /*
         * Failed.  Try to create basedir first in case it's missing. Tolerate
         * EEXIST to close a race against another process following the same
         * algorithm.
         */
        if (MakePGDirectory(basedir) < 0 && errno != EEXIST)
            ereport(ERROR,
                    (errcode_for_file_access(),
                     errmsg("cannot create temporary directory \"%s\": %m",
                            basedir)));
 
        /* Try again. */
        if (MakePGDirectory(directory) < 0 && errno != EEXIST)
            ereport(ERROR,
                    (errcode_for_file_access(),
                     errmsg("cannot create temporary subdirectory \"%s\": %m",
                            directory)));
    }
}

References basedir, directory, ereport, errcode_for_file_access(), errmsg(), ERROR, and MakePGDirectory().

Referenced by FileSetCreate().

PathNameCreateTemporaryFile()

File PathNameCreateTemporaryFile	(	const char *	path,
		bool	error_on_failure
	)

Definition at line 1813 of file fd.c.

{
    File        file;
 
    Assert(temporary_files_allowed);    /* check temp file access is up */
 
    ResourceOwnerEnlargeFiles(CurrentResourceOwner);
 
    /*
     * Open the file.  Note: we don't use O_EXCL, in case there is an orphaned
     * temp file that can be reused.
     */
    file = PathNameOpenFile(path, O_RDWR | O_CREAT | O_TRUNC | PG_BINARY);
    if (file <= 0)
    {
        if (error_on_failure)
            ereport(ERROR,
                    (errcode_for_file_access(),
                     errmsg("could not create temporary file \"%s\": %m",
                            path)));
        else
            return file;
    }
 
    /* Mark it for temp_file_limit accounting. */
    VfdCache[file].fdstate |= FD_TEMP_FILE_LIMIT;
 
    /* Register it for automatic close. */
    RegisterTemporaryFile(file);
 
    return file;
}

References Assert(), CurrentResourceOwner, ereport, errcode_for_file_access(), errmsg(), ERROR, FD_TEMP_FILE_LIMIT, vfd::fdstate, PathNameOpenFile(), PG_BINARY, RegisterTemporaryFile(), ResourceOwnerEnlargeFiles(), and VfdCache.

Referenced by FileSetCreate().

PathNameDeleteTemporaryDir()

void PathNameDeleteTemporaryDir

(

const char *

dirname

)

Definition at line 1643 of file fd.c.

{
    struct stat statbuf;
 
    /* Silently ignore missing directory. */
    if (stat(dirname, &statbuf) != 0 && errno == ENOENT)
        return;
 
    /*
     * Currently, walkdir doesn't offer a way for our passed in function to
     * maintain state.  Perhaps it should, so that we could tell the caller
     * whether this operation succeeded or failed.  Since this operation is
     * used in a cleanup path, we wouldn't actually behave differently: we'll
     * just log failures.
     */
    walkdir(dirname, unlink_if_exists_fname, false, LOG);
}

References LOG, stat, unlink_if_exists_fname(), and walkdir().

Referenced by FileSetDeleteAll().

PathNameDeleteTemporaryFile()

bool PathNameDeleteTemporaryFile	(	const char *	path,
		bool	error_on_failure
	)

Definition at line 1884 of file fd.c.

{
    struct stat filestats;
    int         stat_errno;
 
    /* Get the final size for pgstat reporting. */
    if (stat(path, &filestats) != 0)
        stat_errno = errno;
    else
        stat_errno = 0;
 
    /*
     * Unlike FileClose's automatic file deletion code, we tolerate
     * non-existence to support BufFileDeleteFileSet which doesn't know how
     * many segments it has to delete until it runs out.
     */
    if (stat_errno == ENOENT)
        return false;
 
    if (unlink(path) < 0)
    {
        if (errno != ENOENT)
            ereport(error_on_failure ? ERROR : LOG,
                    (errcode_for_file_access(),
                     errmsg("could not unlink temporary file \"%s\": %m",
                            path)));
        return false;
    }
 
    if (stat_errno == 0)
        ReportTemporaryFileUsage(path, filestats.st_size);
    else
    {
        errno = stat_errno;
        ereport(LOG,
                (errcode_for_file_access(),
                 errmsg("could not stat file \"%s\": %m", path)));
    }
 
    return true;
}

References ereport, errcode_for_file_access(), errmsg(), ERROR, LOG, ReportTemporaryFileUsage(), stat::st_size, and stat.

Referenced by FileSetDelete(), and unlink_if_exists_fname().

PathNameOpenFile()

File PathNameOpenFile	(	const char *	fileName,
		int	fileFlags
	)

Definition at line 1527 of file fd.c.

{
    return PathNameOpenFilePerm(fileName, fileFlags, pg_file_create_mode);
}

References PathNameOpenFilePerm(), and pg_file_create_mode.

Referenced by _mdfd_openseg(), bbsink_server_begin_archive(), bbsink_server_begin_manifest(), logical_rewrite_log_mapping(), mdcreate(), mdopenfork(), mdsyncfiletag(), OpenTemporaryFileInTablespace(), PathNameCreateTemporaryFile(), PathNameOpenTemporaryFile(), and ReorderBufferRestoreChanges().

PathNameOpenFilePerm()

File PathNameOpenFilePerm	(	const char *	fileName,
		int	fileFlags,
		mode_t	fileMode
	)

Definition at line 1540 of file fd.c.

{
    char       *fnamecopy;
    File        file;
    Vfd        *vfdP;
 
    DO_DB(elog(LOG, "PathNameOpenFilePerm: %s %x %o",
               fileName, fileFlags, fileMode));
 
    /*
     * We need a malloc'd copy of the file name; fail cleanly if no room.
     */
    fnamecopy = strdup(fileName);
    if (fnamecopy == NULL)
        ereport(ERROR,
                (errcode(ERRCODE_OUT_OF_MEMORY),
                 errmsg("out of memory")));
 
    file = AllocateVfd();
    vfdP = &VfdCache[file];
 
    /* Close excess kernel FDs. */
    ReleaseLruFiles();
 
    /*
     * Descriptors managed by VFDs are implicitly marked O_CLOEXEC.  The
     * client shouldn't be expected to know which kernel descriptors are
     * currently open, so it wouldn't make sense for them to be inherited by
     * executed subprograms.
     */
    fileFlags |= O_CLOEXEC;
 
    vfdP->fd = BasicOpenFilePerm(fileName, fileFlags, fileMode);
 
    if (vfdP->fd < 0)
    {
        int         save_errno = errno;
 
        FreeVfd(file);
        free(fnamecopy);
        errno = save_errno;
        return -1;
    }
    ++nfile;
    DO_DB(elog(LOG, "PathNameOpenFile: success %d",
               vfdP->fd));
 
    vfdP->fileName = fnamecopy;
    /* Saved flags are adjusted to be OK for re-opening file */
    vfdP->fileFlags = fileFlags & ~(O_CREAT | O_TRUNC | O_EXCL);
    vfdP->fileMode = fileMode;
    vfdP->fileSize = 0;
    vfdP->fdstate = 0x0;
    vfdP->resowner = NULL;
 
    Insert(file);
 
    return file;
}

References AllocateVfd(), BasicOpenFilePerm(), DO_DB, elog(), ereport, errcode(), errmsg(), ERROR, vfd::fd, vfd::fdstate, vfd::fileFlags, vfd::fileMode, vfd::fileName, vfd::fileSize, free, FreeVfd(), Insert(), LOG, nfile, O_CLOEXEC, ReleaseLruFiles(), vfd::resowner, and VfdCache.

Referenced by PathNameOpenFile().

PathNameOpenTemporaryFile()

File PathNameOpenTemporaryFile	(	const char *	path,
		int	mode
	)

Definition at line 1853 of file fd.c.

{
    File        file;
 
    Assert(temporary_files_allowed);    /* check temp file access is up */
 
    ResourceOwnerEnlargeFiles(CurrentResourceOwner);
 
    file = PathNameOpenFile(path, mode | PG_BINARY);
 
    /* If no such file, then we don't raise an error. */
    if (file <= 0 && errno != ENOENT)
        ereport(ERROR,
                (errcode_for_file_access(),
                 errmsg("could not open temporary file \"%s\": %m",
                        path)));
 
    if (file > 0)
    {
        /* Register it for automatic close. */
        RegisterTemporaryFile(file);
    }
 
    return file;
}

References Assert(), CurrentResourceOwner, ereport, errcode_for_file_access(), errmsg(), ERROR, mode, PathNameOpenFile(), PG_BINARY, RegisterTemporaryFile(), and ResourceOwnerEnlargeFiles().

Referenced by FileSetOpen().

pg_fdatasync()

int pg_fdatasync

(

int

fd

)

Definition at line 455 of file fd.c.

{
    int         rc;
 
    if (!enableFsync)
        return 0;
 
retry:
    rc = fdatasync(fd);
 
    if (rc == -1 && errno == EINTR)
        goto retry;
 
    return rc;
}

References EINTR, enableFsync, fd(), and fdatasync().

Referenced by issue_xlog_fsync().

pg_flush_data()

void pg_flush_data	(	int	fd,
		off_t	offset,
		off_t	nbytes
	)

Definition at line 477 of file fd.c.

{
    /*
     * Right now file flushing is primarily used to avoid making later
     * fsync()/fdatasync() calls have less impact. Thus don't trigger flushes
     * if fsyncs are disabled - that's a decision we might want to make
     * configurable at some point.
     */
    if (!enableFsync)
        return;
 
    /*
     * We compile all alternatives that are supported on the current platform,
     * to find portability problems more easily.
     */
#if defined(HAVE_SYNC_FILE_RANGE)
    {
        int         rc;
        static bool not_implemented_by_kernel = false;
 
        if (not_implemented_by_kernel)
            return;
 
retry:
 
        /*
         * sync_file_range(SYNC_FILE_RANGE_WRITE), currently linux specific,
         * tells the OS that writeback for the specified blocks should be
         * started, but that we don't want to wait for completion.  Note that
         * this call might block if too much dirty data exists in the range.
         * This is the preferable method on OSs supporting it, as it works
         * reliably when available (contrast to msync()) and doesn't flush out
         * clean data (like FADV_DONTNEED).
         */
        rc = sync_file_range(fd, offset, nbytes,
                             SYNC_FILE_RANGE_WRITE);
        if (rc != 0)
        {
            int         elevel;
 
            if (rc == EINTR)
                goto retry;
 
            /*
             * For systems that don't have an implementation of
             * sync_file_range() such as Windows WSL, generate only one
             * warning and then suppress all further attempts by this process.
             */
            if (errno == ENOSYS)
            {
                elevel = WARNING;
                not_implemented_by_kernel = true;
            }
            else
                elevel = data_sync_elevel(WARNING);
 
            ereport(elevel,
                    (errcode_for_file_access(),
                     errmsg("could not flush dirty data: %m")));
        }
 
        return;
    }
#endif
#if !defined(WIN32) && defined(MS_ASYNC)
    {
        void       *p;
        static int  pagesize = 0;
 
        /*
         * On several OSs msync(MS_ASYNC) on a mmap'ed file triggers
         * writeback. On linux it only does so if MS_SYNC is specified, but
         * then it does the writeback synchronously. Luckily all common linux
         * systems have sync_file_range().  This is preferable over
         * FADV_DONTNEED because it doesn't flush out clean data.
         *
         * We map the file (mmap()), tell the kernel to sync back the contents
         * (msync()), and then remove the mapping again (munmap()).
         */
 
        /* mmap() needs actual length if we want to map whole file */
        if (offset == 0 && nbytes == 0)
        {
            nbytes = lseek(fd, 0, SEEK_END);
            if (nbytes < 0)
            {
                ereport(WARNING,
                        (errcode_for_file_access(),
                         errmsg("could not determine dirty data size: %m")));
                return;
            }
        }
 
        /*
         * Some platforms reject partial-page mmap() attempts.  To deal with
         * that, just truncate the request to a page boundary.  If any extra
         * bytes don't get flushed, well, it's only a hint anyway.
         */
 
        /* fetch pagesize only once */
        if (pagesize == 0)
            pagesize = sysconf(_SC_PAGESIZE);
 
        /* align length to pagesize, dropping any fractional page */
        if (pagesize > 0)
            nbytes = (nbytes / pagesize) * pagesize;
 
        /* fractional-page request is a no-op */
        if (nbytes <= 0)
            return;
 
        /*
         * mmap could well fail, particularly on 32-bit platforms where there
         * may simply not be enough address space.  If so, silently fall
         * through to the next implementation.
         */
        if (nbytes <= (off_t) SSIZE_MAX)
            p = mmap(NULL, nbytes, PROT_READ, MAP_SHARED, fd, offset);
        else
            p = MAP_FAILED;
 
        if (p != MAP_FAILED)
        {
            int         rc;
 
            rc = msync(p, (size_t) nbytes, MS_ASYNC);
            if (rc != 0)
            {
                ereport(data_sync_elevel(WARNING),
                        (errcode_for_file_access(),
                         errmsg("could not flush dirty data: %m")));
                /* NB: need to fall through to munmap()! */
            }
 
            rc = munmap(p, (size_t) nbytes);
            if (rc != 0)
            {
                /* FATAL error because mapping would remain */
                ereport(FATAL,
                        (errcode_for_file_access(),
                         errmsg("could not munmap() while flushing data: %m")));
            }
 
            return;
        }
    }
#endif
#if defined(USE_POSIX_FADVISE) && defined(POSIX_FADV_DONTNEED)
    {
        int         rc;
 
        /*
         * Signal the kernel that the passed in range should not be cached
         * anymore. This has the, desired, side effect of writing out dirty
         * data, and the, undesired, side effect of likely discarding useful
         * clean cached blocks.  For the latter reason this is the least
         * preferable method.
         */
 
        rc = posix_fadvise(fd, offset, nbytes, POSIX_FADV_DONTNEED);
 
        if (rc != 0)
        {
            /* don't error out, this is just a performance optimization */
            ereport(WARNING,
                    (errcode_for_file_access(),
                     errmsg("could not flush dirty data: %m")));
        }
 
        return;
    }
#endif
}

References data_sync_elevel(), EINTR, enableFsync, ereport, errcode_for_file_access(), errmsg(), FATAL, fd(), MAP_FAILED, and WARNING.

Referenced by copy_file(), and FileWriteback().

pg_fsync()

int pg_fsync

(

int

fd

)

Definition at line 361 of file fd.c.

{
#if !defined(WIN32) && defined(USE_ASSERT_CHECKING)
    struct stat st;
 
    /*
     * Some operating system implementations of fsync() have requirements
     * about the file access modes that were used when their file descriptor
     * argument was opened, and these requirements differ depending on whether
     * the file descriptor is for a directory.
     *
     * For any file descriptor that may eventually be handed to fsync(), we
     * should have opened it with access modes that are compatible with
     * fsync() on all supported systems, otherwise the code may not be
     * portable, even if it runs ok on the current system.
     *
     * We assert here that a descriptor for a file was opened with write
     * permissions (either O_RDWR or O_WRONLY) and for a directory without
     * write permissions (O_RDONLY).
     *
     * Ignore any fstat errors and let the follow-up fsync() do its work.
     * Doing this sanity check here counts for the case where fsync() is
     * disabled.
     */
    if (fstat(fd, &st) == 0)
    {
        int         desc_flags = fcntl(fd, F_GETFL);
 
        /*
         * O_RDONLY is historically 0, so just make sure that for directories
         * no write flags are used.
         */
        if (S_ISDIR(st.st_mode))
            Assert((desc_flags & (O_RDWR | O_WRONLY)) == 0);
        else
            Assert((desc_flags & (O_RDWR | O_WRONLY)) != 0);
    }
    errno = 0;
#endif
 
    /* #if is to skip the sync_method test if there's no need for it */
#if defined(HAVE_FSYNC_WRITETHROUGH)
    if (sync_method == SYNC_METHOD_FSYNC_WRITETHROUGH)
        return pg_fsync_writethrough(fd);
    else
#endif
        return pg_fsync_no_writethrough(fd);
}

References Assert(), fd(), fstat, pg_fsync_no_writethrough(), pg_fsync_writethrough(), S_ISDIR, stat::st_mode, sync_method, and SYNC_METHOD_FSYNC_WRITETHROUGH.

Referenced by AddToDataDirLockFile(), assign_xlog_sync_method(), BootStrapXLOG(), CheckPointLogicalRewriteHeap(), CreateLockFile(), durable_rename(), FileSync(), fsync_fname_ext(), heap_xlog_logical_rewrite(), readRecoverySignalFile(), RecreateTwoPhaseFile(), RestoreSlotFromDisk(), SaveSlotToPath(), SlruPhysicalWritePage(), SlruSyncFileTag(), SnapBuildSerialize(), update_controlfile(), write_auto_conf_file(), WriteControlFile(), writeTimeLineHistory(), writeTimeLineHistoryFile(), XLogFileCopy(), and XLogFileInitInternal().

pg_fsync_no_writethrough()

int pg_fsync_no_writethrough

(

int

fd

)

Definition at line 416 of file fd.c.

{
    int         rc;
 
    if (!enableFsync)
        return 0;
 
retry:
    rc = fsync(fd);
 
    if (rc == -1 && errno == EINTR)
        goto retry;
 
    return rc;
}

References EINTR, enableFsync, fd(), and fsync.

Referenced by issue_xlog_fsync(), and pg_fsync().

pg_fsync_writethrough()

int pg_fsync_writethrough

(

int

fd

)

Definition at line 436 of file fd.c.

{
    if (enableFsync)
    {
#if defined(F_FULLFSYNC)
        return (fcntl(fd, F_FULLFSYNC, 0) == -1) ? -1 : 0;
#else
        errno = ENOSYS;
        return -1;
#endif
    }
    else
        return 0;
}

References enableFsync, and fd().

Referenced by issue_xlog_fsync(), pg_fsync(), and test_sync().

pg_truncate()

int pg_truncate	(	const char *	path,
		off_t	length
	)

Definition at line 672 of file fd.c.

{
    int         ret;
#ifdef WIN32
    int         save_errno;
    int         fd;
 
    fd = OpenTransientFile(path, O_RDWR | PG_BINARY);
    if (fd >= 0)
    {
        ret = pg_ftruncate(fd, length);
        save_errno = errno;
        CloseTransientFile(fd);
        errno = save_errno;
    }
    else
        ret = -1;
#else
 
retry:
    ret = truncate(path, length);
 
    if (ret == -1 && errno == EINTR)
        goto retry;
#endif
 
    return ret;
}

References CloseTransientFile(), EINTR, fd(), OpenTransientFile(), PG_BINARY, and pg_ftruncate().

Referenced by do_truncate().

ReadDir()

struct dirent* ReadDir	(	DIR *	dir,
		const char *	dirname
	)

Definition at line 2854 of file fd.c.

{
    return ReadDirExtended(dir, dirname, ERROR);
}

References ERROR, and ReadDirExtended().

Referenced by calculate_database_size(), calculate_tablespace_size(), CheckPointLogicalRewriteHeap(), CheckPointSnapBuild(), CheckTablespaceDirectory(), CleanupBackupHistory(), copydir(), db_dir_size(), destroy_tablespace_directories(), directory_is_empty(), do_pg_backup_start(), dsm_cleanup_for_mmap(), extension_file_exists(), get_ext_ver_list(), GetConfFilesInDir(), movedb(), perform_base_backup(), pg_available_extension_versions(), pg_available_extensions(), pg_logdir_ls_internal(), pg_ls_dir(), pg_ls_dir_files(), pg_tablespace_databases(), pg_tzenumerate_next(), pgarch_readyXlog(), RemoveNonParentXlogFiles(), RemoveOldXlogFiles(), RemoveTempXlogFiles(), ResetUnloggedRelations(), ResetUnloggedRelationsInDbspaceDir(), ResetUnloggedRelationsInTablespaceDir(), restoreTwoPhaseData(), sendDir(), SlruScanDirectory(), StartupReorderBuffer(), StartupReplicationSlots(), and UpdateLogicalMappings().

ReadDirExtended()

struct dirent* ReadDirExtended	(	DIR *	dir,
		const char *	dirname,
		int	elevel
	)

Definition at line 2869 of file fd.c.

{
    struct dirent *dent;
 
    /* Give a generic message for AllocateDir failure, if caller didn't */
    if (dir == NULL)
    {
        ereport(elevel,
                (errcode_for_file_access(),
                 errmsg("could not open directory \"%s\": %m",
                        dirname)));
        return NULL;
    }
 
    errno = 0;
    if ((dent = readdir(dir)) != NULL)
        return dent;
 
    if (errno)
        ereport(elevel,
                (errcode_for_file_access(),
                 errmsg("could not read directory \"%s\": %m",
                        dirname)));
    return NULL;
}

References ereport, errcode_for_file_access(), errmsg(), and readdir().

Referenced by DeleteAllExportedSnapshotFiles(), ReadDir(), RelationCacheInitFileRemove(), RelationCacheInitFileRemoveInDir(), RemovePgTempFiles(), RemovePgTempFilesInDir(), RemovePgTempRelationFiles(), RemovePgTempRelationFilesInDbspace(), ReorderBufferCleanupSerializedTXNs(), scan_directory_ci(), SyncDataDirectory(), and walkdir().

ReleaseExternalFD()

void ReleaseExternalFD

(

void

)

Definition at line 1191 of file fd.c.

{
    Assert(numExternalFDs > 0);
    numExternalFDs--;
}

References Assert(), and numExternalFDs.

Referenced by ClosePostmasterPorts(), CreateWaitEventSet(), dsm_impl_posix(), FreeWaitEventSet(), FreeWaitEventSetAfterFork(), InitializeLatchSupport(), libpqsrv_connect_internal(), libpqsrv_disconnect(), and XLogFileClose().

RemovePgTempFiles()

void RemovePgTempFiles

(

void

)

Definition at line 3219 of file fd.c.

{
    char        temp_path[MAXPGPATH + 10 + sizeof(TABLESPACE_VERSION_DIRECTORY) + sizeof(PG_TEMP_FILES_DIR)];
    DIR        *spc_dir;
    struct dirent *spc_de;
 
    /*
     * First process temp files in pg_default ($PGDATA/base)
     */
    snprintf(temp_path, sizeof(temp_path), "base/%s", PG_TEMP_FILES_DIR);
    RemovePgTempFilesInDir(temp_path, true, false);
    RemovePgTempRelationFiles("base");
 
    /*
     * Cycle through temp directories for all non-default tablespaces.
     */
    spc_dir = AllocateDir("pg_tblspc");
 
    while ((spc_de = ReadDirExtended(spc_dir, "pg_tblspc", LOG)) != NULL)
    {
        if (strcmp(spc_de->d_name, ".") == 0 ||
            strcmp(spc_de->d_name, "..") == 0)
            continue;
 
        snprintf(temp_path, sizeof(temp_path), "pg_tblspc/%s/%s/%s",
                 spc_de->d_name, TABLESPACE_VERSION_DIRECTORY, PG_TEMP_FILES_DIR);
        RemovePgTempFilesInDir(temp_path, true, false);
 
        snprintf(temp_path, sizeof(temp_path), "pg_tblspc/%s/%s",
                 spc_de->d_name, TABLESPACE_VERSION_DIRECTORY);
        RemovePgTempRelationFiles(temp_path);
    }
 
    FreeDir(spc_dir);
 
    /*
     * In EXEC_BACKEND case there is a pgsql_tmp directory at the top level of
     * DataDir as well.  However, that is *not* cleaned here because doing so
     * would create a race condition.  It's done separately, earlier in
     * postmaster startup.
     */
}

References AllocateDir(), dirent::d_name, FreeDir(), LOG, MAXPGPATH, PG_TEMP_FILES_DIR, ReadDirExtended(), RemovePgTempFilesInDir(), RemovePgTempRelationFiles(), snprintf, and TABLESPACE_VERSION_DIRECTORY.

Referenced by PostmasterMain(), and PostmasterStateMachine().

RemovePgTempFilesInDir()

void RemovePgTempFilesInDir	(	const char *	tmpdirname,
		bool	missing_ok,
		bool	unlink_all
	)

Definition at line 3278 of file fd.c.

{
    DIR        *temp_dir;
    struct dirent *temp_de;
    char        rm_path[MAXPGPATH * 2];
 
    temp_dir = AllocateDir(tmpdirname);
 
    if (temp_dir == NULL && errno == ENOENT && missing_ok)
        return;
 
    while ((temp_de = ReadDirExtended(temp_dir, tmpdirname, LOG)) != NULL)
    {
        if (strcmp(temp_de->d_name, ".") == 0 ||
            strcmp(temp_de->d_name, "..") == 0)
            continue;
 
        snprintf(rm_path, sizeof(rm_path), "%s/%s",
                 tmpdirname, temp_de->d_name);
 
        if (unlink_all ||
            strncmp(temp_de->d_name,
                    PG_TEMP_FILE_PREFIX,
                    strlen(PG_TEMP_FILE_PREFIX)) == 0)
        {
            PGFileType  type = get_dirent_type(rm_path, temp_de, false, LOG);
 
            if (type == PGFILETYPE_ERROR)
                continue;
            else if (type == PGFILETYPE_DIR)
            {
                /* recursively remove contents, then directory itself */
                RemovePgTempFilesInDir(rm_path, false, true);
 
                if (rmdir(rm_path) < 0)
                    ereport(LOG,
                            (errcode_for_file_access(),
                             errmsg("could not remove directory \"%s\": %m",
                                    rm_path)));
            }
            else
            {
                if (unlink(rm_path) < 0)
                    ereport(LOG,
                            (errcode_for_file_access(),
                             errmsg("could not remove file \"%s\": %m",
                                    rm_path)));
            }
        }
        else
            ereport(LOG,
                    (errmsg("unexpected file found in temporary-files directory: \"%s\"",
                            rm_path)));
    }
 
    FreeDir(temp_dir);
}

References AllocateDir(), dirent::d_name, ereport, errcode_for_file_access(), errmsg(), FreeDir(), get_dirent_type(), LOG, MAXPGPATH, PG_TEMP_FILE_PREFIX, PGFILETYPE_DIR, PGFILETYPE_ERROR, ReadDirExtended(), snprintf, and type.

Referenced by PostmasterMain(), and RemovePgTempFiles().

ReserveExternalFD()

void ReserveExternalFD

(

void

)

Definition at line 1173 of file fd.c.

{
    /*
     * Release VFDs if needed to stay safe.  Because we do this before
     * incrementing numExternalFDs, the final state will be as desired, i.e.,
     * nfile + numAllocatedDescs + numExternalFDs <= max_safe_fds.
     */
    ReleaseLruFiles();
 
    numExternalFDs++;
}

References numExternalFDs, and ReleaseLruFiles().

Referenced by AcquireExternalFD(), BackendInitialize(), dsm_impl_posix(), InitializeLatchSupport(), InitPostmasterDeathWatchHandle(), and XLogWrite().

set_max_safe_fds()

void set_max_safe_fds

(

void

)

Definition at line 996 of file fd.c.

{
    int         usable_fds;
    int         already_open;
 
    /*----------
     * We want to set max_safe_fds to
     *          MIN(usable_fds, max_files_per_process - already_open)
     * less the slop factor for files that are opened without consulting
     * fd.c.  This ensures that we won't exceed either max_files_per_process
     * or the experimentally-determined EMFILE limit.
     *----------
     */
    count_usable_fds(max_files_per_process,
                     &usable_fds, &already_open);
 
    max_safe_fds = Min(usable_fds, max_files_per_process - already_open);
 
    /*
     * Take off the FDs reserved for system() etc.
     */
    max_safe_fds -= NUM_RESERVED_FDS;
 
    /*
     * Make sure we still have enough to get by.
     */
    if (max_safe_fds < FD_MINFREE)
        ereport(FATAL,
                (errcode(ERRCODE_INSUFFICIENT_RESOURCES),
                 errmsg("insufficient file descriptors available to start server process"),
                 errdetail("System allows %d, server needs at least %d.",
                           max_safe_fds + NUM_RESERVED_FDS,
                           FD_MINFREE + NUM_RESERVED_FDS)));
 
    elog(DEBUG2, "max_safe_fds = %d, usable_fds = %d, already_open = %d",
         max_safe_fds, usable_fds, already_open);
}

References count_usable_fds(), DEBUG2, elog(), ereport, errcode(), errdetail(), errmsg(), FATAL, FD_MINFREE, max_files_per_process, max_safe_fds, Min, and NUM_RESERVED_FDS.

Referenced by PostmasterMain().

SetTempTablespaces()

void SetTempTablespaces	(	Oid *	tableSpaces,
		int	numSpaces
	)

Definition at line 2994 of file fd.c.

{
    Assert(numSpaces >= 0);
    tempTableSpaces = tableSpaces;
    numTempTableSpaces = numSpaces;
 
    /*
     * Select a random starting point in the list.  This is to minimize
     * conflicts between backends that are most likely sharing the same list
     * of temp tablespaces.  Note that if we create multiple temp files in the
     * same transaction, we'll advance circularly through the list --- this
     * ensures that large temporary sort files are nicely spread across all
     * available tablespaces.
     */
    if (numSpaces > 1)
        nextTempTableSpace = pg_prng_uint64_range(&pg_global_prng_state,
                                                  0, numSpaces - 1);
    else
        nextTempTableSpace = 0;
}

References Assert(), nextTempTableSpace, numTempTableSpaces, pg_global_prng_state, pg_prng_uint64_range(), and tempTableSpaces.

Referenced by assign_temp_tablespaces(), and PrepareTempTablespaces().

SyncDataDirectory()

void SyncDataDirectory

(

void

)

Definition at line 3489 of file fd.c.

{
    bool        xlog_is_symlink;
 
    /* We can skip this whole thing if fsync is disabled. */
    if (!enableFsync)
        return;
 
    /*
     * If pg_wal is a symlink, we'll need to recurse into it separately,
     * because the first walkdir below will ignore it.
     */
    xlog_is_symlink = false;
 
    {
        struct stat st;
 
        if (lstat("pg_wal", &st) < 0)
            ereport(LOG,
                    (errcode_for_file_access(),
                     errmsg("could not stat file \"%s\": %m",
                            "pg_wal")));
        else if (S_ISLNK(st.st_mode))
            xlog_is_symlink = true;
    }
 
#ifdef HAVE_SYNCFS
    if (recovery_init_sync_method == DATA_DIR_SYNC_METHOD_SYNCFS)
    {
        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.
         */
 
        /* Prepare to report progress syncing the data directory via syncfs. */
        begin_startup_progress_phase();
 
        /* Sync the top level pgdata directory. */
        do_syncfs(".");
        /* If any tablespaces are configured, sync each of those. */
        dir = AllocateDir("pg_tblspc");
        while ((de = ReadDirExtended(dir, "pg_tblspc", LOG)))
        {
            char        path[MAXPGPATH];
 
            if (strcmp(de->d_name, ".") == 0 || strcmp(de->d_name, "..") == 0)
                continue;
 
            snprintf(path, MAXPGPATH, "pg_tblspc/%s", de->d_name);
            do_syncfs(path);
        }
        FreeDir(dir);
        /* If pg_wal is a symlink, process that too. */
        if (xlog_is_symlink)
            do_syncfs("pg_wal");
        return;
    }
#endif                          /* !HAVE_SYNCFS */
 
#ifdef PG_FLUSH_DATA_WORKS
    /* Prepare to report progress of the pre-fsync phase. */
    begin_startup_progress_phase();
 
    /*
     * If possible, hint to the kernel that we're soon going to fsync the data
     * directory and its contents.  Errors in this step are even less
     * interesting than normal, so log them only at DEBUG1.
     */
    walkdir(".", pre_sync_fname, false, DEBUG1);
    if (xlog_is_symlink)
        walkdir("pg_wal", pre_sync_fname, false, DEBUG1);
    walkdir("pg_tblspc", pre_sync_fname, true, DEBUG1);
#endif
 
    /* Prepare to report progress syncing the data directory via fsync. */
    begin_startup_progress_phase();
 
    /*
     * 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(".", datadir_fsync_fname, false, LOG);
    if (xlog_is_symlink)
        walkdir("pg_wal", datadir_fsync_fname, false, LOG);
    walkdir("pg_tblspc", datadir_fsync_fname, true, LOG);
}

References AllocateDir(), begin_startup_progress_phase(), dirent::d_name, DATA_DIR_SYNC_METHOD_SYNCFS, datadir_fsync_fname(), DEBUG1, enableFsync, ereport, errcode_for_file_access(), errmsg(), FreeDir(), LOG, lstat, MAXPGPATH, ReadDirExtended(), recovery_init_sync_method, S_ISLNK, snprintf, stat::st_mode, and walkdir().

Referenced by StartupXLOG().

TempTablespacePath()

void TempTablespacePath	(	char *	path,
		Oid	tablespace
	)

Definition at line 1731 of file fd.c.

{
    /*
     * Identify the tempfile directory for this tablespace.
     *
     * If someone tries to specify pg_global, use pg_default instead.
     */
    if (tablespace == InvalidOid ||
        tablespace == DEFAULTTABLESPACE_OID ||
        tablespace == GLOBALTABLESPACE_OID)
        snprintf(path, MAXPGPATH, "base/%s", PG_TEMP_FILES_DIR);
    else
    {
        /* All other tablespaces are accessed via symlinks */
        snprintf(path, MAXPGPATH, "pg_tblspc/%u/%s/%s",
                 tablespace, TABLESPACE_VERSION_DIRECTORY,
                 PG_TEMP_FILES_DIR);
    }
}

References InvalidOid, MAXPGPATH, PG_TEMP_FILES_DIR, snprintf, tablespace, and TABLESPACE_VERSION_DIRECTORY.

Referenced by FileSetCreate(), FileSetPath(), OpenTemporaryFileInTablespace(), and pg_ls_tmpdir().

TempTablespacesAreSet()

bool TempTablespacesAreSet

(

void

)

Definition at line 3023 of file fd.c.

{
    return (numTempTableSpaces >= 0);
}

References numTempTableSpaces.

Referenced by GetTempTablespaces(), and PrepareTempTablespaces().

Variable Documentation

data_sync_retry

PGDLLIMPORT bool data_sync_retry

extern

Definition at line 162 of file fd.c.

Referenced by data_sync_elevel().

io_direct_flags

PGDLLIMPORT int io_direct_flags

extern

Definition at line 168 of file fd.c.

Referenced by _mdfd_open_flags(), assign_debug_io_direct(), get_sync_bit(), mdprefetch(), mdwriteback(), PrefetchLocalBuffer(), PrefetchSharedBuffer(), ScheduleBufferTagForWriteback(), XLogFileClose(), XLogFileInitInternal(), and XLogPrefetcherNextBlock().

max_files_per_process

PGDLLIMPORT int max_files_per_process

extern

Definition at line 146 of file fd.c.

Referenced by set_max_safe_fds().

max_safe_fds

PGDLLIMPORT int max_safe_fds

extern

Definition at line 159 of file fd.c.

Referenced by AcquireExternalFD(), ReleaseLruFiles(), reserveAllocatedDesc(), and set_max_safe_fds().

recovery_init_sync_method

PGDLLIMPORT int recovery_init_sync_method

extern

Definition at line 165 of file fd.c.

Referenced by SyncDataDirectory().