fd.h File Reference

#include <dirent.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	PG_TEMP_FILES_DIR   "pgsql_tmp"
#define	PG_TEMP_FILE_PREFIX   "pgsql_tmp"

Typedefs
typedef char *	FileName
typedef int	File

Functions
File	PathNameOpenFile (FileName fileName, int fileFlags, int fileMode)
File	OpenTemporaryFile (bool interXact)
void	FileClose (File file)
int	FilePrefetch (File file, off_t offset, int amount, uint32 wait_event_info)
int	FileRead (File file, char *buffer, int amount, uint32 wait_event_info)
int	FileWrite (File file, char *buffer, int amount, uint32 wait_event_info)
int	FileSync (File file, uint32 wait_event_info)
off_t	FileSeek (File file, off_t offset, int whence)
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)
int	FileGetRawMode (File file)
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)
int	FreeDir (DIR *dir)
int	OpenTransientFile (FileName fileName, int fileFlags, int fileMode)
int	CloseTransientFile (int fd)
int	BasicOpenFile (FileName fileName, int fileFlags, int fileMode)
void	InitFileAccess (void)
void	set_max_safe_fds (void)
void	closeAllVfds (void)
void	SetTempTablespaces (Oid *tableSpaces, int numSpaces)
bool	TempTablespacesAreSet (void)
Oid	GetNextTempTableSpace (void)
void	AtEOXact_Files (void)
void	AtEOSubXact_Files (bool isCommit, SubTransactionId mySubid, SubTransactionId parentSubid)
void	RemovePgTempFiles (void)
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 amount)
void	fsync_fname (const char *fname, bool isdir)
int	durable_rename (const char *oldfile, const char *newfile, int loglevel)
int	durable_unlink (const char *fname, int loglevel)
int	durable_link_or_rename (const char *oldfile, const char *newfile, int loglevel)
void	SyncDataDirectory (void)

Variables
int	max_files_per_process
int	max_safe_fds

Macro Definition Documentation

#define PG_TEMP_FILE_PREFIX   "pgsql_tmp"

Definition at line 128 of file fd.h.

Referenced by OpenTemporaryFileInTablespace(), process_source_file(), RemovePgTempFilesInDir(), and sendDir().

#define PG_TEMP_FILES_DIR   "pgsql_tmp"

Definition at line 127 of file fd.h.

Referenced by OpenTemporaryFileInTablespace(), process_source_file(), and RemovePgTempFiles().

Typedef Documentation

typedef int File

Definition at line 51 of file fd.h.

typedef char* FileName

Definition at line 49 of file fd.h.

Function Documentation

DIR* AllocateDir

(

const char *

dirname

)

Definition at line 2335 of file fd.c.

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

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

{
    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;
}

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

Definition at line 2094 of file fd.c.

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

Referenced by AlterSystemSetConfigFile(), BeginCopyFrom(), BeginCopyTo(), checkDataDir(), do_pg_start_backup(), do_pg_stop_backup(), entry_reset(), existsTimeLineHistory(), ExportSnapshot(), fill_hba_view(), gc_qtexts(), ImportSnapshot(), load_hba(), load_ident(), load_relcache_init_file(), parse_extension_control_file(), ParseTzFile(), perform_base_backup(), pg_backup_start_time(), pg_current_logfile(), pg_file_write(), pgss_shmem_shutdown(), pgss_shmem_startup(), pgstat_read_db_statsfile(), pgstat_read_db_statsfile_timestamp(), pgstat_read_statsfiles(), pgstat_write_db_statsfile(), pgstat_write_statsfiles(), read_backup_label(), read_binary_file(), read_tablespace_map(), read_whole_file(), readRecoveryCommandFile(), readTimeLineHistory(), sendFile(), tokenize_inc_file(), tsearch_readline_begin(), ValidatePgVersion(), write_relcache_init_file(), XLogArchiveForceDone(), and XLogArchiveNotify().

{
    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;
}

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

Definition at line 2586 of file fd.c.

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

Referenced by AbortSubTransaction(), and CommitSubTransaction().

{
    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--]);
            }
        }
    }
}

void AtEOXact_Files

(

void

)

Definition at line 2617 of file fd.c.

References CleanupTempFiles(), NULL, numTempTableSpaces, and tempTableSpaces.

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

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

int BasicOpenFile	(	FileName	fileName,
		int	fileFlags,
		int	fileMode
	)

Definition at line 936 of file fd.c.

References ereport, errcode(), errmsg(), fd(), LOG, and ReleaseLruFile().

Referenced by AlterSystemSetConfigFile(), GetNewRelFileNode(), LruInsert(), OpenTransientFile(), PathNameOpenFile(), ReadControlFile(), UpdateControlFile(), WriteControlFile(), XLogFileInit(), XLogFileOpen(), XLogFileRead(), and XLogRead().

{
    int         fd;

tryAgain:
    fd = open(fileName, fileFlags, fileMode);

    if (fd >= 0)
        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 */
}

void closeAllVfds

(

void

)

Definition at line 2499 of file fd.c.

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

Referenced by standard_ProcessUtility().

{
    Index       i;

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

int ClosePipeStream

(

FILE *

file

)

Definition at line 2470 of file fd.c.

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

Referenced by ClosePipeToProgram(), and pg_import_system_collations().

{
    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);
}

int CloseTransientFile

(

int

fd

)

Definition at line 2305 of file fd.c.

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

Referenced by be_lo_export(), CheckPointLogicalRewriteHeap(), CheckPointReplicationOrigin(), copy_file(), dsm_impl_mmap(), durable_rename(), fsync_fname_ext(), heap_xlog_logical_rewrite(), lo_import_internal(), load_relmap_file(), mdunlinkfork(), qtext_load_file(), qtext_store(), ReadTwoPhaseFile(), RecreateTwoPhaseFile(), ReorderBufferIterTXNFinish(), ReorderBufferRestoreChanges(), ReorderBufferSerializeChange(), ReorderBufferSerializeTXN(), RestoreSlotFromDisk(), SaveSlotToPath(), SendTimeLineHistory(), SimpleLruDoesPhysicalPageExist(), SimpleLruFlush(), SlruInternalWritePage(), SlruPhysicalReadPage(), SlruPhysicalWritePage(), SnapBuildRestore(), SnapBuildSerialize(), StartupReplicationOrigin(), write_relmap_file(), writeTimeLineHistory(), writeTimeLineHistoryFile(), and XLogFileCopy().

{
    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);
}

int durable_link_or_rename	(	const char *	oldfile,
		const char *	newfile,
		int	loglevel
	)

Definition at line 712 of file fd.c.

References ereport, errcode_for_file_access(), errmsg(), fsync_fname_ext(), fsync_parent_path(), link(), and unlink().

Referenced by InstallXLogFileSegment(), writeTimeLineHistory(), and writeTimeLineHistoryFile().

{
    /*
     * Ensure that, if we crash directly after the rename/link, a file with
     * valid contents is moved into place.
     */
    if (fsync_fname_ext(oldfile, false, false, elevel) != 0)
        return -1;

#if HAVE_WORKING_LINK
    if (link(oldfile, newfile) < 0)
    {
        ereport(elevel,
                (errcode_for_file_access(),
                 errmsg("could not link file \"%s\" to \"%s\": %m",
                        oldfile, newfile)));
        return -1;
    }
    unlink(oldfile);
#else
    /* XXX: Add racy file existence check? */
    if (rename(oldfile, newfile) < 0)
    {
        ereport(elevel,
                (errcode_for_file_access(),
                 errmsg("could not rename file \"%s\" to \"%s\": %m",
                        oldfile, newfile)));
        return -1;
    }
#endif

    /*
     * Make change persistent in case of an OS crash, both the new entry and
     * its parent directory need to be flushed.
     */
    if (fsync_fname_ext(newfile, false, false, elevel) != 0)
        return -1;

    /* Same for parent directory */
    if (fsync_parent_path(newfile, elevel) != 0)
        return -1;

    return 0;
}

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

Definition at line 593 of file fd.c.

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

Referenced by AlterSystemSetConfigFile(), CancelBackup(), CheckPointReplicationOrigin(), dir_close(), exitArchiveRecovery(), KeepFileRestoredFromArchive(), pgarch_archiveDone(), pgss_shmem_shutdown(), StartupXLOG(), and XLogArchiveForceDone().

{
    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((char *) newfile, PG_BINARY | O_RDWR, 0);
    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;
        }
        CloseTransientFile(fd);
    }

    /* 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;
}

int durable_unlink	(	const char *	fname,
		int	loglevel
	)

Definition at line 676 of file fd.c.

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

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

{
    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;
}

void FileClose

(

File

file

)

Definition at line 1493 of file fd.c.

References Assert, close, Delete(), DO_DB, elog, ereport, errmsg(), vfd::fd, FD_TEMPORARY, vfd::fdstate, FileIsNotOpen, FileIsValid, vfd::fileName, vfd::fileSize, FreeVfd(), LOG, log_temp_files, nfile, pgstat_report_tempfile(), ResourceOwnerForgetFile(), vfd::resowner, temporary_files_size, unlink(), and VFD_CLOSED.

Referenced by BufFileClose(), CleanupTempFiles(), logical_end_heap_rewrite(), mdclose(), mdtruncate(), and ResourceOwnerReleaseInternal().

{
    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))
            elog(LOG, "could not close file \"%s\": %m", vfdP->fileName);

        --nfile;
        vfdP->fd = VFD_CLOSED;

        /* remove the file from the lru ring */
        Delete(file);
    }

    /*
     * Delete the file if it was temporary, and make a log entry if wanted
     */
    if (vfdP->fdstate & FD_TEMPORARY)
    {
        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_TEMPORARY;

        /* Subtract its size from current usage (do first in case of error) */
        temporary_files_size -= vfdP->fileSize;
        vfdP->fileSize = 0;

        /* 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))
            elog(LOG, "could not unlink file \"%s\": %m", vfdP->fileName);

        /* and last report the stat results */
        if (stat_errno == 0)
        {
            pgstat_report_tempfile(filestats.st_size);

            if (log_temp_files >= 0)
            {
                if ((filestats.st_size / 1024) >= log_temp_files)
                    ereport(LOG,
                            (errmsg("temporary file: path \"%s\", size %lu",
                                    vfdP->fileName,
                                    (unsigned long) filestats.st_size)));
            }
        }
        else
        {
            errno = stat_errno;
            elog(LOG, "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);
}

int FileGetRawDesc

(

File

file

)

Definition at line 1990 of file fd.c.

References Assert, vfd::fd, and FileIsValid.

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

int FileGetRawFlags

(

File

file

)

Definition at line 2000 of file fd.c.

References Assert, vfd::fileFlags, and FileIsValid.

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

int FileGetRawMode

(

File

file

)

Definition at line 2010 of file fd.c.

References Assert, FileIsValid, and vfd::fileMode.

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

char* FilePathName

(

File

file

)

Definition at line 1974 of file fd.c.

References Assert, FileIsValid, and vfd::fileName.

Referenced by _mdnblocks(), mdextend(), mdimmedsync(), mdread(), mdsync(), mdtruncate(), mdwrite(), and register_dirty_segment().

{
    Assert(FileIsValid(file));

    return VfdCache[file].fileName;
}

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

Definition at line 1590 of file fd.c.

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

Referenced by mdprefetch().

{
#if defined(USE_POSIX_FADVISE) && defined(POSIX_FADV_WILLNEED)
    int         returnCode;

    Assert(FileIsValid(file));

    DO_DB(elog(LOG, "FilePrefetch: %d (%s) " INT64_FORMAT " %d",
               file, VfdCache[file].fileName,
               (int64) offset, amount));

    returnCode = FileAccess(file);
    if (returnCode < 0)
        return returnCode;

    pgstat_report_wait_start(wait_event_info);
    returnCode = posix_fadvise(VfdCache[file].fd, offset, amount,
                               POSIX_FADV_WILLNEED);
    pgstat_report_wait_end();

    return returnCode;
#else
    Assert(FileIsValid(file));
    return 0;
#endif
}

int FileRead	(	File	file,
		char *	buffer,
		int	amount,
		uint32	wait_event_info
	)

Definition at line 1645 of file fd.c.

References _dosmaperr(), Assert, DO_DB, EINTR, elog, error(), vfd::fd, FileAccess(), FileIsValid, FilePosIsUnknown, FileUnknownPos, INT64_FORMAT, LOG, pg_usleep(), pgstat_report_wait_end(), pgstat_report_wait_start(), read, and vfd::seekPos.

Referenced by BufFileLoadBuffer(), and mdread().

{
    int         returnCode;
    Vfd        *vfdP;

    Assert(FileIsValid(file));

    DO_DB(elog(LOG, "FileRead: %d (%s) " INT64_FORMAT " %d %p",
               file, VfdCache[file].fileName,
               (int64) VfdCache[file].seekPos,
               amount, buffer));

    returnCode = FileAccess(file);
    if (returnCode < 0)
        return returnCode;

    vfdP = &VfdCache[file];

retry:
    pgstat_report_wait_start(wait_event_info);
    returnCode = read(vfdP->fd, buffer, amount);
    pgstat_report_wait_end();

    if (returnCode >= 0)
    {
        /* if seekPos is unknown, leave it that way */
        if (!FilePosIsUnknown(vfdP->seekPos))
            vfdP->seekPos += returnCode;
    }
    else
    {
        /*
         * 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;

        /* Trouble, so assume we don't know the file position anymore */
        vfdP->seekPos = FileUnknownPos;
    }

    return returnCode;
}

off_t FileSeek	(	File	file,
		off_t	offset,
		int	whence
	)

Definition at line 1851 of file fd.c.

References Assert, DO_DB, elog, ERROR, vfd::fd, FileAccess(), FileIsNotOpen, FileIsValid, FilePosIsUnknown, INT64_FORMAT, LOG, and vfd::seekPos.

Referenced by _mdnblocks(), BufFileDumpBuffer(), BufFileLoadBuffer(), mdextend(), mdread(), and mdwrite().

{
    Vfd        *vfdP;

    Assert(FileIsValid(file));

    DO_DB(elog(LOG, "FileSeek: %d (%s) " INT64_FORMAT " " INT64_FORMAT " %d",
               file, VfdCache[file].fileName,
               (int64) VfdCache[file].seekPos,
               (int64) offset, whence));

    vfdP = &VfdCache[file];

    if (FileIsNotOpen(file))
    {
        switch (whence)
        {
            case SEEK_SET:
                if (offset < 0)
                {
                    errno = EINVAL;
                    return (off_t) -1;
                }
                vfdP->seekPos = offset;
                break;
            case SEEK_CUR:
                if (FilePosIsUnknown(vfdP->seekPos) ||
                    vfdP->seekPos + offset < 0)
                {
                    errno = EINVAL;
                    return (off_t) -1;
                }
                vfdP->seekPos += offset;
                break;
            case SEEK_END:
                if (FileAccess(file) < 0)
                    return (off_t) -1;
                vfdP->seekPos = lseek(vfdP->fd, offset, whence);
                break;
            default:
                elog(ERROR, "invalid whence: %d", whence);
                break;
        }
    }
    else
    {
        switch (whence)
        {
            case SEEK_SET:
                if (offset < 0)
                {
                    errno = EINVAL;
                    return (off_t) -1;
                }
                if (vfdP->seekPos != offset)
                    vfdP->seekPos = lseek(vfdP->fd, offset, whence);
                break;
            case SEEK_CUR:
                if (offset != 0 || FilePosIsUnknown(vfdP->seekPos))
                    vfdP->seekPos = lseek(vfdP->fd, offset, whence);
                break;
            case SEEK_END:
                vfdP->seekPos = lseek(vfdP->fd, offset, whence);
                break;
            default:
                elog(ERROR, "invalid whence: %d", whence);
                break;
        }
    }

    return vfdP->seekPos;
}

int FileSync	(	File	file,
		uint32	wait_event_info
	)

Definition at line 1830 of file fd.c.

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

Referenced by logical_end_heap_rewrite(), mdimmedsync(), mdsync(), and register_dirty_segment().

{
    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;
}

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

Definition at line 1939 of file fd.c.

References Assert, DO_DB, elog, fd(), FD_TEMPORARY, FileAccess(), FileIsValid, vfd::fileSize, ftruncate, LOG, pgstat_report_wait_end(), pgstat_report_wait_start(), and temporary_files_size.

Referenced by mdtruncate().

{
    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 = 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_TEMPORARY);
        temporary_files_size -= VfdCache[file].fileSize - offset;
        VfdCache[file].fileSize = offset;
    }

    return returnCode;
}

int FileWrite	(	File	file,
		char *	buffer,
		int	amount,
		uint32	wait_event_info
	)

Definition at line 1709 of file fd.c.

References _dosmaperr(), Assert, DO_DB, EINTR, elog, ereport, errcode(), errmsg(), ERROR, error(), vfd::fd, FD_TEMPORARY, vfd::fdstate, FileAccess(), FileIsValid, vfd::fileName, FilePosIsUnknown, vfd::fileSize, FileUnknownPos, INT64_FORMAT, LOG, pg_usleep(), pgstat_report_wait_end(), pgstat_report_wait_start(), vfd::seekPos, temp_file_limit, temporary_files_size, and write.

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

{
    int         returnCode;
    Vfd        *vfdP;

    Assert(FileIsValid(file));

    DO_DB(elog(LOG, "FileWrite: %d (%s) " INT64_FORMAT " %d %p",
               file, VfdCache[file].fileName,
               (int64) VfdCache[file].seekPos,
               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_TEMPORARY))
    {
        off_t       newPos;

        /*
         * Normally we should know the seek position, but if for some reason
         * we have lost track of it, try again to get it.  Here, it's fine to
         * throw an error if we still can't get it.
         */
        if (FilePosIsUnknown(vfdP->seekPos))
        {
            vfdP->seekPos = lseek(vfdP->fd, (off_t) 0, SEEK_CUR);
            if (FilePosIsUnknown(vfdP->seekPos))
                elog(ERROR, "could not seek file \"%s\": %m", vfdP->fileName);
        }

        newPos = vfdP->seekPos + amount;
        if (newPos > vfdP->fileSize)
        {
            uint64      newTotal = temporary_files_size;

            newTotal += newPos - 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 = write(vfdP->fd, buffer, amount);
    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)
    {
        /* if seekPos is unknown, leave it that way */
        if (!FilePosIsUnknown(vfdP->seekPos))
            vfdP->seekPos += returnCode;

        /*
         * Maintain fileSize and temporary_files_size if it's a temp file.
         *
         * If seekPos is -1 (unknown), this will do nothing; but we could only
         * get here in that state if we're not enforcing temporary_files_size,
         * so we don't care.
         */
        if (vfdP->fdstate & FD_TEMPORARY)
        {
            off_t       newPos = vfdP->seekPos;

            if (newPos > vfdP->fileSize)
            {
                temporary_files_size += newPos - vfdP->fileSize;
                vfdP->fileSize = newPos;
            }
        }
    }
    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;

        /* Trouble, so assume we don't know the file position anymore */
        vfdP->seekPos = FileUnknownPos;
    }

    return returnCode;
}

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

Definition at line 1618 of file fd.c.

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

Referenced by mdwriteback().

{
    int         returnCode;

    Assert(FileIsValid(file));

    DO_DB(elog(LOG, "FileWriteback: %d (%s) " INT64_FORMAT " " INT64_FORMAT,
               file, VfdCache[file].fileName,
               (int64) offset, (int64) nbytes));

    /*
     * Caution: do not call pg_flush_data with nbytes = 0, it could trash the
     * file's seek position.  We prefer to define that as a no-op here.
     */
    if (nbytes <= 0)
        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();
}

int FreeDir

(

DIR *

dir

)

Definition at line 2444 of file fd.c.

References 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(), dsm_cleanup_for_mmap(), get_ext_ver_list(), getInstallationPaths(), movedb(), ParseTzFile(), perform_base_backup(), pg_available_extension_versions(), pg_available_extensions(), pg_logdir_ls(), pg_ls_dir(), pg_ls_dir_files(), pg_start_backup(), pg_tablespace_databases(), pg_tzenumerate_end(), pg_tzenumerate_next(), pgarch_readyXlog(), pgstat_reset_remove_files(), RelationCacheInitFileRemove(), RelationCacheInitFileRemoveInDir(), RemoveNonParentXlogFiles(), RemoveOldXlogFiles(), RemovePgTempFiles(), RemovePgTempFilesInDir(), RemovePgTempRelationFiles(), RemovePgTempRelationFilesInDbspace(), ResetUnloggedRelations(), ResetUnloggedRelationsInDbspaceDir(), ResetUnloggedRelationsInTablespaceDir(), restoreTwoPhaseData(), scan_directory_ci(), SendBaseBackup(), sendDir(), SlruScanDirectory(), StartupReorderBuffer(), StartupReplicationSlots(), UpdateLogicalMappings(), and walkdir().

{
    int         i;

    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);
}

int FreeFile

(

FILE *

file

)

Definition at line 2277 of file fd.c.

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

Referenced by AlterSystemSetConfigFile(), checkDataDir(), do_pg_start_backup(), do_pg_stop_backup(), EndCopy(), entry_reset(), existsTimeLineHistory(), ExportSnapshot(), fill_hba_view(), gc_qtexts(), ImportSnapshot(), load_hba(), load_ident(), load_relcache_init_file(), parse_extension_control_file(), ParseTzFile(), perform_base_backup(), pg_backup_start_time(), pg_current_logfile(), pg_file_write(), pgss_shmem_shutdown(), pgss_shmem_startup(), pgstat_read_db_statsfile(), pgstat_read_db_statsfile_timestamp(), pgstat_read_statsfiles(), pgstat_write_db_statsfile(), pgstat_write_statsfiles(), read_backup_label(), read_binary_file(), read_tablespace_map(), read_whole_file(), readRecoveryCommandFile(), readTimeLineHistory(), sendFile(), tokenize_inc_file(), tsearch_readline_end(), ValidatePgVersion(), write_relcache_init_file(), XLogArchiveForceDone(), and XLogArchiveNotify().

{
    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);
}

void fsync_fname	(	const char *	fname,
		bool	isdir
	)

Definition at line 567 of file fd.c.

References ERROR, and fsync_fname_ext().

Referenced by _CloseArchive(), BaseBackup(), CheckPointCLOG(), CheckPointCommitTs(), CheckPointTwoPhase(), copydir(), CreateSlotOnDisk(), dir_close(), dir_finish(), dir_open_for_write(), main(), ReceiveTarFile(), ReplicationSlotDropPtr(), ResetUnloggedRelationsInDbspaceDir(), RestoreSlotFromDisk(), SaveSlotToPath(), ShutdownCLOG(), ShutdownCommitTs(), SnapBuildRestore(), SnapBuildSerialize(), StartupReplicationSlots(), and tar_finish().

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

Oid GetNextTempTableSpace

(

void

)

Definition at line 2565 of file fd.c.

References InvalidOid, nextTempTableSpace, numTempTableSpaces, and tempTableSpaces.

Referenced by GetDefaultTablespace(), and OpenTemporaryFile().

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

void InitFileAccess

(

void

)

Definition at line 764 of file fd.c.

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

Referenced by BaseInit().

{
    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;

    /* register proc-exit hook to ensure temp files are dropped at exit */
    on_proc_exit(AtProcExit_Files, 0);
}

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

Definition at line 2184 of file fd.c.

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

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

{
    FILE       *file;

    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(stdout);
    fflush(stderr);
    errno = 0;
    if ((file = popen(command, mode)) != 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)
    {
        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;
}

File OpenTemporaryFile

(

bool

interXact

)

Definition at line 1371 of file fd.c.

References CurrentResourceOwner, DEFAULTTABLESPACE_OID, FD_TEMPORARY, FD_XACT_TEMPORARY, vfd::fdstate, GetNextTempTableSpace(), have_xact_temporary_files, MyDatabaseTableSpace, numTempTableSpaces, OidIsValid, OpenTemporaryFileInTablespace(), ResourceOwnerEnlargeFiles(), ResourceOwnerRememberFile(), and vfd::resowner.

Referenced by BufFileCreateTemp(), and extendBufFile().

{
    File        file = 0;

    /*
     * 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 */
    VfdCache[file].fdstate |= FD_TEMPORARY;

    /* Register it with the current resource owner */
    if (!interXact)
    {
        VfdCache[file].fdstate |= FD_XACT_TEMPORARY;

        ResourceOwnerEnlargeFiles(CurrentResourceOwner);
        ResourceOwnerRememberFile(CurrentResourceOwner, file);
        VfdCache[file].resowner = CurrentResourceOwner;

        /* ensure cleanup happens at eoxact */
        have_xact_temporary_files = true;
    }

    return file;
}

int OpenTransientFile	(	FileName	fileName,
		int	fileFlags,
		int	fileMode
	)

Definition at line 2144 of file fd.c.

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

Referenced by ApplyLogicalMappingFile(), be_lo_export(), CheckPointLogicalRewriteHeap(), CheckPointReplicationOrigin(), copy_file(), dsm_impl_mmap(), durable_rename(), fsync_fname_ext(), heap_xlog_logical_rewrite(), lo_import_internal(), load_relmap_file(), mdunlinkfork(), qtext_load_file(), qtext_store(), ReadTwoPhaseFile(), RecreateTwoPhaseFile(), ReorderBufferRestoreChanges(), ReorderBufferSerializeTXN(), RestoreSlotFromDisk(), SaveSlotToPath(), SendTimeLineHistory(), SimpleLruDoesPhysicalPageExist(), SlruPhysicalReadPage(), SlruPhysicalWritePage(), SnapBuildRestore(), SnapBuildSerialize(), StartupReplicationOrigin(), write_relmap_file(), writeTimeLineHistory(), writeTimeLineHistoryFile(), and XLogFileCopy().

{
    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 = BasicOpenFile(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 */
}

File PathNameOpenFile	(	FileName	fileName,
		int	fileFlags,
		int	fileMode
	)

Definition at line 1303 of file fd.c.

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

Referenced by _mdfd_openseg(), logical_rewrite_log_mapping(), mdcreate(), mdopen(), and OpenTemporaryFileInTablespace().

{
    char       *fnamecopy;
    File        file;
    Vfd        *vfdP;

    DO_DB(elog(LOG, "PathNameOpenFile: %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();

    vfdP->fd = BasicOpenFile(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));

    Insert(file);

    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->seekPos = 0;
    vfdP->fileSize = 0;
    vfdP->fdstate = 0x0;
    vfdP->resowner = NULL;

    return file;
}

int pg_fdatasync

(

int

fd

)

Definition at line 385 of file fd.c.

References enableFsync, and fsync.

Referenced by issue_xlog_fsync().

{
    if (enableFsync)
    {
#ifdef HAVE_FDATASYNC
        return fdatasync(fd);
#else
        return fsync(fd);
#endif
    }
    else
        return 0;
}

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

Definition at line 407 of file fd.c.

References enableFsync, ereport, errcode_for_file_access(), errmsg(), FATAL, MAP_FAILED, NULL, and WARNING.

Referenced by copy_file(), and FileWriteback().

{
    /*
     * 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;

        /*
         * 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);

        /* don't error out, this is just a performance optimization */
        if (rc != 0)
        {
            ereport(WARNING,
                    (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(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
}

int pg_fsync

(

int

fd

)

Definition at line 333 of file fd.c.

References pg_fsync_no_writethrough(), pg_fsync_writethrough(), sync_method, and SYNC_METHOD_FSYNC_WRITETHROUGH.

Referenced by AddToDataDirLockFile(), assign_xlog_sync_method(), BootStrapXLOG(), CheckPointLogicalRewriteHeap(), CreateLockFile(), do_pg_start_backup(), durable_rename(), FileSync(), fsync_fname_ext(), heap_xlog_logical_rewrite(), RecreateTwoPhaseFile(), RestoreSlotFromDisk(), SaveSlotToPath(), SimpleLruFlush(), SlruPhysicalWritePage(), SnapBuildSerialize(), UpdateControlFile(), write_auto_conf_file(), write_relmap_file(), WriteControlFile(), writeTimeLineHistory(), writeTimeLineHistoryFile(), XLogFileCopy(), and XLogFileInit().

{
    /* #if is to skip the sync_method test if there's no need for it */
#if defined(HAVE_FSYNC_WRITETHROUGH) && !defined(FSYNC_WRITETHROUGH_IS_FSYNC)
    if (sync_method == SYNC_METHOD_FSYNC_WRITETHROUGH)
        return pg_fsync_writethrough(fd);
    else
#endif
        return pg_fsync_no_writethrough(fd);
}

int pg_fsync_no_writethrough

(

int

fd

)

Definition at line 350 of file fd.c.

References enableFsync, and fsync.

Referenced by issue_xlog_fsync(), and pg_fsync().

{
    if (enableFsync)
        return fsync(fd);
    else
        return 0;
}

int pg_fsync_writethrough

(

int

fd

)

Definition at line 362 of file fd.c.

References enableFsync.

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

{
    if (enableFsync)
    {
#ifdef WIN32
        return _commit(fd);
#elif defined(F_FULLFSYNC)
        return (fcntl(fd, F_FULLFSYNC, 0) == -1) ? -1 : 0;
#else
        errno = ENOSYS;
        return -1;
#endif
    }
    else
        return 0;
}

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

Definition at line 2401 of file fd.c.

References ERROR, and ReadDirExtended().

Referenced by calculate_database_size(), calculate_tablespace_size(), CheckPointLogicalRewriteHeap(), CheckPointSnapBuild(), CleanupBackupHistory(), copydir(), db_dir_size(), DeleteAllExportedSnapshotFiles(), destroy_tablespace_directories(), directory_is_empty(), do_pg_start_backup(), dsm_cleanup_for_mmap(), get_ext_ver_list(), movedb(), perform_base_backup(), pg_available_extension_versions(), pg_available_extensions(), pg_logdir_ls(), pg_ls_dir(), pg_ls_dir_files(), pg_tablespace_databases(), pg_tzenumerate_next(), pgarch_readyXlog(), pgstat_reset_remove_files(), RelationCacheInitFileRemove(), RelationCacheInitFileRemoveInDir(), RemoveNonParentXlogFiles(), RemoveOldXlogFiles(), RemovePgTempFiles(), RemovePgTempFilesInDir(), RemovePgTempRelationFiles(), RemovePgTempRelationFilesInDbspace(), ResetUnloggedRelations(), ResetUnloggedRelationsInDbspaceDir(), ResetUnloggedRelationsInTablespaceDir(), restoreTwoPhaseData(), scan_directory_ci(), sendDir(), SlruScanDirectory(), StartupReorderBuffer(), StartupReplicationSlots(), and UpdateLogicalMappings().

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

void RemovePgTempFiles

(

void

)

Definition at line 2706 of file fd.c.

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

Referenced by PostmasterMain().

{
    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);
    RemovePgTempRelationFiles("base");

    /*
     * Cycle through temp directories for all non-default tablespaces.
     */
    spc_dir = AllocateDir("pg_tblspc");

    while ((spc_de = ReadDir(spc_dir, "pg_tblspc")) != 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);

        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.
     */
#ifdef EXEC_BACKEND
    RemovePgTempFilesInDir(PG_TEMP_FILES_DIR);
#endif
}

void set_max_safe_fds

(

void

)

Definition at line 881 of file fd.c.

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().

{
    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, we need 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);
}

void SetTempTablespaces	(	Oid *	tableSpaces,
		int	numSpaces
	)

Definition at line 2525 of file fd.c.

References Assert, nextTempTableSpace, numTempTableSpaces, random(), and tempTableSpaces.

Referenced by assign_temp_tablespaces(), and PrepareTempTablespaces().

{
    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 = random() % numSpaces;
    else
        nextTempTableSpace = 0;
}

void SyncDataDirectory

(

void

)

Definition at line 2933 of file fd.c.

References datadir_fsync_fname(), DEBUG1, enableFsync, ereport, errcode_for_file_access(), errmsg(), LOG, lstat, and walkdir().

Referenced by StartupXLOG().

{
    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;

#ifndef WIN32
    {
        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;
    }
#else
    if (pgwin32_is_junction("pg_wal"))
        xlog_is_symlink = true;
#endif

    /*
     * 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.
     */
#ifdef PG_FLUSH_DATA_WORKS
    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

    /*
     * 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);
}

bool TempTablespacesAreSet

(

void

)

Definition at line 2553 of file fd.c.

References numTempTableSpaces.

Referenced by PrepareTempTablespaces().

{
    return (numTempTableSpaces >= 0);
}

Variable Documentation

int max_files_per_process

Definition at line 126 of file fd.c.

Referenced by set_max_safe_fds().

int max_safe_fds

Definition at line 139 of file fd.c.

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