public inbox for [email protected]help / color / mirror / Atom feed
[PATCH 03/20] Support multiple compression algs/levels/opts.. 23+ messages / 2 participants [nested] [flat]
* [PATCH 03/20] Support multiple compression algs/levels/opts.. @ 2020-12-22 06:23 Justin Pryzby <[email protected]> 0 siblings, 0 replies; 23+ messages in thread From: Justin Pryzby @ 2020-12-22 06:23 UTC (permalink / raw) The existing implementation abtracts compressed and noncompressed I/O. This preliminary commit is intended to also allow for multiple compression algorithms. --- src/bin/pg_dump/compress_io.c | 220 +++++++++++--------------- src/bin/pg_dump/compress_io.h | 19 +-- src/bin/pg_dump/pg_backup.h | 23 ++- src/bin/pg_dump/pg_backup_archiver.c | 45 +++--- src/bin/pg_dump/pg_backup_archiver.h | 12 +- src/bin/pg_dump/pg_backup_custom.c | 6 +- src/bin/pg_dump/pg_backup_directory.c | 17 +- src/bin/pg_dump/pg_backup_tar.c | 33 ++-- src/bin/pg_dump/pg_dump.c | 115 +++++++++++--- 9 files changed, 272 insertions(+), 218 deletions(-) diff --git a/src/bin/pg_dump/compress_io.c b/src/bin/pg_dump/compress_io.c index 6a428978d4..db16fd33f2 100644 --- a/src/bin/pg_dump/compress_io.c +++ b/src/bin/pg_dump/compress_io.c @@ -74,12 +74,9 @@ struct CompressorState #endif }; -static void ParseCompressionOption(int compression, CompressionAlgorithm *alg, - int *level); - /* Routines that support zlib compressed data I/O */ #ifdef HAVE_LIBZ -static void InitCompressorZlib(CompressorState *cs, int level); +static void InitCompressorZlib(CompressorState *cs, Compress *compress); static void DeflateCompressorZlib(ArchiveHandle *AH, CompressorState *cs, bool flush); static void ReadDataFromArchiveZlib(ArchiveHandle *AH, ReadFunc readF); @@ -93,58 +90,36 @@ static void ReadDataFromArchiveNone(ArchiveHandle *AH, ReadFunc readF); static void WriteDataToArchiveNone(ArchiveHandle *AH, CompressorState *cs, const char *data, size_t dLen); -/* - * Interprets a numeric 'compression' value. The algorithm implied by the - * value (zlib or none at the moment), is returned in *alg, and the - * zlib compression level in *level. - */ -static void -ParseCompressionOption(int compression, CompressionAlgorithm *alg, int *level) -{ - if (compression == Z_DEFAULT_COMPRESSION || - (compression > 0 && compression <= 9)) - *alg = COMPR_ALG_LIBZ; - else if (compression == 0) - *alg = COMPR_ALG_NONE; - else - { - fatal("invalid compression code: %d", compression); - *alg = COMPR_ALG_NONE; /* keep compiler quiet */ - } - - /* The level is just the passed-in value. */ - if (level) - *level = compression; -} - /* Public interface routines */ /* Allocate a new compressor */ CompressorState * -AllocateCompressor(int compression, WriteFunc writeF) +AllocateCompressor(Compress *compression, WriteFunc writeF) { CompressorState *cs; - CompressionAlgorithm alg; - int level; - - ParseCompressionOption(compression, &alg, &level); - -#ifndef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - fatal("not built with zlib support"); -#endif cs = (CompressorState *) pg_malloc0(sizeof(CompressorState)); cs->writeF = writeF; - cs->comprAlg = alg; + cs->comprAlg = compression->alg; /* * Perform compression algorithm specific initialization. */ + Assert (compression->alg != COMPR_ALG_DEFAULT); + switch (compression->alg) + { #ifdef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - InitCompressorZlib(cs, level); + case COMPR_ALG_LIBZ: + InitCompressorZlib(cs, compression); + break; #endif + case COMPR_ALG_NONE: + /* Do nothing */ + break; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } return cs; } @@ -154,21 +129,21 @@ AllocateCompressor(int compression, WriteFunc writeF) * out with ahwrite(). */ void -ReadDataFromArchive(ArchiveHandle *AH, int compression, ReadFunc readF) +ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF) { - CompressionAlgorithm alg; - - ParseCompressionOption(compression, &alg, NULL); - - if (alg == COMPR_ALG_NONE) - ReadDataFromArchiveNone(AH, readF); - if (alg == COMPR_ALG_LIBZ) + switch (AH->compression.alg) { + case COMPR_ALG_NONE: + ReadDataFromArchiveNone(AH, readF); + break; #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: ReadDataFromArchiveZlib(AH, readF); -#else - fatal("not built with zlib support"); + break; #endif + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -181,16 +156,18 @@ WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, { switch (cs->comprAlg) { - case COMPR_ALG_LIBZ: #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: WriteDataToArchiveZlib(AH, cs, data, dLen); -#else - fatal("not built with zlib support"); -#endif break; +#endif case COMPR_ALG_NONE: WriteDataToArchiveNone(AH, cs, data, dLen); break; + + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -215,7 +192,7 @@ EndCompressor(ArchiveHandle *AH, CompressorState *cs) */ static void -InitCompressorZlib(CompressorState *cs, int level) +InitCompressorZlib(CompressorState *cs, Compress *compress) { z_streamp zp; @@ -232,7 +209,7 @@ InitCompressorZlib(CompressorState *cs, int level) cs->zlibOut = (char *) pg_malloc(ZLIB_OUT_SIZE + 1); cs->zlibOutSize = ZLIB_OUT_SIZE; - if (deflateInit(zp, level) != Z_OK) + if (deflateInit(zp, compress->level) != Z_OK) fatal("could not initialize compression library: %s", zp->msg); @@ -424,9 +401,7 @@ struct cfp #endif }; -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix); -#endif /* free() without changing errno; useful in several places below */ static void @@ -442,34 +417,31 @@ free_keep_errno(void *p) * Open a file for reading. 'path' is the file to open, and 'mode' should * be either "r" or "rb". * - * If the file at 'path' does not exist, we append the ".gz" suffix (if 'path' - * doesn't already have it) and try again. So if you pass "foo" as 'path', + * If the file at 'path' does not exist, we search with compressed suffix (if 'path' + * doesn't already have one) and try again. So if you pass "foo" as 'path', * this will open either "foo" or "foo.gz". * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_read(const char *path, const char *mode) +cfopen_read(const char *path, const char *mode, Compress *compression) { cfp *fp; -#ifdef HAVE_LIBZ if (hasSuffix(path, ".gz")) - fp = cfopen(path, mode, 1); + fp = cfopen(path, mode, compression); else -#endif { - fp = cfopen(path, mode, 0); -#ifdef HAVE_LIBZ + fp = cfopen(path, mode, compression); if (fp == NULL) { char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); - fp = cfopen(fname, mode, 1); + fname = psprintf("%s%s", path, suffix); + fp = cfopen(fname, mode, compression); free_keep_errno(fname); } -#endif } return fp; } @@ -479,31 +451,26 @@ cfopen_read(const char *path, const char *mode) * be a filemode as accepted by fopen() and gzopen() that indicates writing * ("w", "wb", "a", or "ab"). * - * If 'compression' is non-zero, a gzip compressed stream is opened, and - * 'compression' indicates the compression level used. The ".gz" suffix - * is automatically added to 'path' in that case. + * Use compression if specified. + * The appropriate suffix is automatically added to 'path' in that case. * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_write(const char *path, const char *mode, int compression) +cfopen_write(const char *path, const char *mode, Compress *compression) { cfp *fp; - if (compression == 0) - fp = cfopen(path, mode, 0); + if (compression->alg == COMPR_ALG_NONE) + fp = cfopen(path, mode, compression); else { -#ifdef HAVE_LIBZ char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); + fname = psprintf("%s%s", path, suffix); fp = cfopen(fname, mode, compression); free_keep_errno(fname); -#else - fatal("not built with zlib support"); - fp = NULL; /* keep compiler quiet */ -#endif } return fp; } @@ -515,20 +482,21 @@ cfopen_write(const char *path, const char *mode, int compression) * On failure, return NULL with an error code in errno. */ cfp * -cfopen(const char *path, const char *mode, int compression) +cfopen(const char *path, const char *mode, Compress *compression) { - cfp *fp = pg_malloc(sizeof(cfp)); + cfp *fp = pg_malloc0(sizeof(cfp)); - if (compression != 0) + switch (compression->alg) { #ifdef HAVE_LIBZ - if (compression != Z_DEFAULT_COMPRESSION) + case COMPR_ALG_LIBZ: + if (compression->level != Z_DEFAULT_COMPRESSION) { /* user has specified a compression level, so tell zlib to use it */ char mode_compression[32]; snprintf(mode_compression, sizeof(mode_compression), "%s%d", - mode, compression); + mode, compression->level); fp->compressedfp = gzopen(path, mode_compression); } else @@ -537,30 +505,27 @@ cfopen(const char *path, const char *mode, int compression) fp->compressedfp = gzopen(path, mode); } - fp->uncompressedfp = NULL; if (fp->compressedfp == NULL) { free_keep_errno(fp); fp = NULL; } -#else - fatal("not built with zlib support"); -#endif - } - else - { -#ifdef HAVE_LIBZ - fp->compressedfp = NULL; + return fp; #endif + + case COMPR_ALG_NONE: fp->uncompressedfp = fopen(path, mode); if (fp->uncompressedfp == NULL) { free_keep_errno(fp); fp = NULL; } - } + return fp; - return fp; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } } @@ -584,14 +549,13 @@ cfread(void *ptr, int size, cfp *fp) fatal("could not read from input file: %s", errnum == Z_ERRNO ? strerror(errno) : errmsg); } + return ret; } - else #endif - { - ret = fread(ptr, 1, size, fp->uncompressedfp); - if (ret != size && !feof(fp->uncompressedfp)) - READ_ERROR_EXIT(fp->uncompressedfp); - } + + ret = fread(ptr, 1, size, fp->uncompressedfp); + if (ret != size && !feof(fp->uncompressedfp)) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -601,9 +565,8 @@ cfwrite(const void *ptr, int size, cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzwrite(fp->compressedfp, ptr, size); - else #endif - return fwrite(ptr, 1, size, fp->uncompressedfp); + return fwrite(ptr, 1, size, fp->uncompressedfp); } int @@ -622,15 +585,12 @@ cfgetc(cfp *fp) else fatal("could not read from input file: end of file"); } + return ret; } - else #endif - { - ret = fgetc(fp->uncompressedfp); - if (ret == EOF) - READ_ERROR_EXIT(fp->uncompressedfp); - } - + ret = fgetc(fp->uncompressedfp); + if (ret == EOF) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -640,9 +600,8 @@ cfgets(cfp *fp, char *buf, int len) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzgets(fp->compressedfp, buf, len); - else #endif - return fgets(buf, len, fp->uncompressedfp); + return fgets(buf, len, fp->uncompressedfp); } int @@ -660,15 +619,13 @@ cfclose(cfp *fp) { result = gzclose(fp->compressedfp); fp->compressedfp = NULL; + return result; } - else #endif - { - result = fclose(fp->uncompressedfp); - fp->uncompressedfp = NULL; - } - free_keep_errno(fp); + result = fclose(fp->uncompressedfp); + fp->uncompressedfp = NULL; + free_keep_errno(fp); return result; } @@ -678,9 +635,9 @@ cfeof(cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzeof(fp->compressedfp); - else #endif - return feof(fp->uncompressedfp); + + return feof(fp->uncompressedfp); } const char * @@ -699,7 +656,6 @@ get_cfp_error(cfp *fp) return strerror(errno); } -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix) { @@ -714,4 +670,18 @@ hasSuffix(const char *filename, const char *suffix) suffixlen) == 0; } -#endif +/* + * Return a string for the given AH's compression. + * The string is statically allocated. + */ +const char * +compress_suffix(Compress *compression) +{ + switch (compression->alg) + { + case COMPR_ALG_LIBZ: + return ".gz"; + default: + return ""; + } +} diff --git a/src/bin/pg_dump/compress_io.h b/src/bin/pg_dump/compress_io.h index d2e6e1b854..2c073676eb 100644 --- a/src/bin/pg_dump/compress_io.h +++ b/src/bin/pg_dump/compress_io.h @@ -21,12 +21,6 @@ #define ZLIB_OUT_SIZE 4096 #define ZLIB_IN_SIZE 4096 -typedef enum -{ - COMPR_ALG_NONE, - COMPR_ALG_LIBZ -} CompressionAlgorithm; - /* Prototype for callback function to WriteDataToArchive() */ typedef void (*WriteFunc) (ArchiveHandle *AH, const char *buf, size_t len); @@ -46,8 +40,8 @@ typedef size_t (*ReadFunc) (ArchiveHandle *AH, char **buf, size_t *buflen); /* struct definition appears in compress_io.c */ typedef struct CompressorState CompressorState; -extern CompressorState *AllocateCompressor(int compression, WriteFunc writeF); -extern void ReadDataFromArchive(ArchiveHandle *AH, int compression, +extern CompressorState *AllocateCompressor(Compress *compression, WriteFunc writeF); +extern void ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF); extern void WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, const void *data, size_t dLen); @@ -56,9 +50,9 @@ extern void EndCompressor(ArchiveHandle *AH, CompressorState *cs); typedef struct cfp cfp; -extern cfp *cfopen(const char *path, const char *mode, int compression); -extern cfp *cfopen_read(const char *path, const char *mode); -extern cfp *cfopen_write(const char *path, const char *mode, int compression); +extern cfp *cfopen(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_read(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_write(const char *path, const char *mode, Compress *compression); extern int cfread(void *ptr, int size, cfp *fp); extern int cfwrite(const void *ptr, int size, cfp *fp); extern int cfgetc(cfp *fp); @@ -67,4 +61,7 @@ extern int cfclose(cfp *fp); extern int cfeof(cfp *fp); extern const char *get_cfp_error(cfp *fp); +/* also used by tar */ +extern const char * compress_suffix(Compress *compression); + #endif diff --git a/src/bin/pg_dump/pg_backup.h b/src/bin/pg_dump/pg_backup.h index 9d0056a569..f2390b7937 100644 --- a/src/bin/pg_dump/pg_backup.h +++ b/src/bin/pg_dump/pg_backup.h @@ -72,6 +72,25 @@ typedef struct _connParams char *override_dbname; } ConnParams; +typedef enum +{ + COMPR_ALG_DEFAULT = -1, + COMPR_ALG_NONE, + COMPR_ALG_LIBZ, +} CompressionAlgorithm; +/* Should be called "method" or "library" ? */ + +typedef struct Compress { + CompressionAlgorithm alg; + int level; + /* Is a nondefault level set ? This is useful since different compression + * methods have different "default" levels. For now we assume the levels + * are all integer, though. + */ + bool level_set; +} Compress; + + typedef struct _restoreOptions { int createDB; /* Issue commands to create the database */ @@ -125,7 +144,7 @@ typedef struct _restoreOptions int noDataForFailedTables; int exit_on_error; - int compression; + Compress compression; int suppressDumpWarnings; /* Suppress output of WARNING entries * to stderr */ bool single_txn; @@ -281,7 +300,7 @@ extern Archive *OpenArchive(const char *FileSpec, const ArchiveFormat fmt); /* Create a new archive */ extern Archive *CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker); /* The --list option */ diff --git a/src/bin/pg_dump/pg_backup_archiver.c b/src/bin/pg_dump/pg_backup_archiver.c index 1f82c6499b..3eb6c55600 100644 --- a/src/bin/pg_dump/pg_backup_archiver.c +++ b/src/bin/pg_dump/pg_backup_archiver.c @@ -70,7 +70,7 @@ typedef struct _parallelReadyList static ArchiveHandle *_allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr); static void _getObjectDescription(PQExpBuffer buf, TocEntry *te); static void _printTocEntry(ArchiveHandle *AH, TocEntry *te, bool isData); @@ -98,7 +98,7 @@ static int _discoverArchiveFormat(ArchiveHandle *AH); static int RestoringToDB(ArchiveHandle *AH); static void dump_lo_buf(ArchiveHandle *AH); static void dumpTimestamp(ArchiveHandle *AH, const char *msg, time_t tim); -static void SetOutput(ArchiveHandle *AH, const char *filename, int compression); +static void SetOutput(ArchiveHandle *AH, const char *filename, Compress *compress); static OutputContext SaveOutput(ArchiveHandle *AH); static void RestoreOutput(ArchiveHandle *AH, OutputContext savedContext); @@ -238,7 +238,7 @@ setupRestoreWorker(Archive *AHX) /* Public */ Archive * CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker) { @@ -253,7 +253,9 @@ CreateArchive(const char *FileSpec, const ArchiveFormat fmt, Archive * OpenArchive(const char *FileSpec, const ArchiveFormat fmt) { - ArchiveHandle *AH = _allocAH(FileSpec, fmt, 0, true, archModeRead, setupRestoreWorker); + Compress compress = {0}; + ArchiveHandle *AH = _allocAH(FileSpec, fmt, &compress, true, archModeRead, + setupRestoreWorker); return (Archive *) AH; } @@ -382,7 +384,7 @@ RestoreArchive(Archive *AHX) * Make sure we won't need (de)compression we haven't got */ #ifndef HAVE_LIBZ - if (AH->compression != 0 && AH->PrintTocDataPtr != NULL) + if (AH->compression.alg != COMPR_ALG_NONE && AH->PrintTocDataPtr != NULL) { for (te = AH->toc->next; te != AH->toc; te = te->next) { @@ -457,8 +459,8 @@ RestoreArchive(Archive *AHX) * Setup the output file if necessary. */ sav = SaveOutput(AH); - if (ropt->filename || ropt->compression) - SetOutput(AH, ropt->filename, ropt->compression); + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) + SetOutput(AH, ropt->filename, &ropt->compression); ahprintf(AH, "--\n-- PostgreSQL database dump\n--\n\n"); @@ -738,7 +740,7 @@ RestoreArchive(Archive *AHX) */ AH->stage = STAGE_FINALIZING; - if (ropt->filename || ropt->compression) + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) RestoreOutput(AH, sav); if (ropt->useDB) @@ -1123,8 +1125,9 @@ PrintTOCSummary(Archive *AHX) char stamp_str[64]; sav = SaveOutput(AH); + Assert(ropt->compression.alg == COMPR_ALG_NONE); if (ropt->filename) - SetOutput(AH, ropt->filename, 0 /* no compression */ ); + SetOutput(AH, ropt->filename, &ropt->compression); if (strftime(stamp_str, sizeof(stamp_str), PGDUMP_STRFTIME_FMT, localtime(&AH->createDate)) == 0) @@ -1133,7 +1136,7 @@ PrintTOCSummary(Archive *AHX) ahprintf(AH, ";\n; Archive created at %s\n", stamp_str); ahprintf(AH, "; dbname: %s\n; TOC Entries: %d\n; Compression: %d\n", sanitize_line(AH->archdbname, false), - AH->tocCount, AH->compression); + AH->tocCount, AH->compression.alg); switch (AH->format) { @@ -1487,7 +1490,7 @@ archprintf(Archive *AH, const char *fmt,...) *******************************/ static void -SetOutput(ArchiveHandle *AH, const char *filename, int compression) +SetOutput(ArchiveHandle *AH, const char *filename, Compress *compression) { int fn; @@ -1510,12 +1513,12 @@ SetOutput(ArchiveHandle *AH, const char *filename, int compression) /* If compression explicitly requested, use gzopen */ #ifdef HAVE_LIBZ - if (compression != 0) + if (compression->alg != COMPR_ALG_NONE) { char fmode[14]; /* Don't use PG_BINARY_x since this is zlib */ - sprintf(fmode, "wb%d", compression); + sprintf(fmode, "wb%d", compression->level); if (fn >= 0) AH->OF = gzdopen(dup(fn), fmode); else @@ -2259,7 +2262,7 @@ _discoverArchiveFormat(ArchiveHandle *AH) */ static ArchiveHandle * _allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr) { ArchiveHandle *AH; @@ -2310,7 +2313,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, AH->toc->prev = AH->toc; AH->mode = mode; - AH->compression = compression; + AH->compression = *compression; AH->dosync = dosync; memset(&(AH->sqlparse), 0, sizeof(AH->sqlparse)); @@ -2325,7 +2328,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, * Force stdin/stdout into binary mode if that is what we are using. */ #ifdef WIN32 - if ((fmt != archNull || compression != 0) && + if ((fmt != archNull || compression->alg != COMPR_ALG_NONE) && (AH->fSpec == NULL || strcmp(AH->fSpec, "") == 0)) { if (mode == archModeWrite) @@ -3741,7 +3744,7 @@ WriteHead(ArchiveHandle *AH) AH->WriteBytePtr(AH, AH->intSize); AH->WriteBytePtr(AH, AH->offSize); AH->WriteBytePtr(AH, AH->format); - WriteInt(AH, AH->compression); + WriteInt(AH, AH->compression.alg); crtm = *localtime(&AH->createDate); WriteInt(AH, crtm.tm_sec); WriteInt(AH, crtm.tm_min); @@ -3816,15 +3819,15 @@ ReadHead(ArchiveHandle *AH) if (AH->version >= K_VERS_1_2) { if (AH->version < K_VERS_1_4) - AH->compression = AH->ReadBytePtr(AH); + AH->compression.alg = AH->ReadBytePtr(AH); else - AH->compression = ReadInt(AH); + AH->compression.alg = ReadInt(AH); } else - AH->compression = Z_DEFAULT_COMPRESSION; + AH->compression.alg = Z_DEFAULT_COMPRESSION; #ifndef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) pg_log_warning("archive is compressed, but this installation does not support compression -- no data will be available"); #endif diff --git a/src/bin/pg_dump/pg_backup_archiver.h b/src/bin/pg_dump/pg_backup_archiver.h index a8ea5c7eae..6e033d040e 100644 --- a/src/bin/pg_dump/pg_backup_archiver.h +++ b/src/bin/pg_dump/pg_backup_archiver.h @@ -47,7 +47,8 @@ #define GZWRITE(p, s, n, fh) (fwrite(p, s, n, fh) * (s)) #define GZREAD(p, s, n, fh) fread(p, s, n, fh) #define GZEOF(fh) feof(fh) -/* this is just the redefinition of a libz constant */ +/* this is just the redefinition of a libz constant, in case zlib isn't + * available */ #define Z_DEFAULT_COMPRESSION (-1) typedef struct _z_stream @@ -329,14 +330,7 @@ struct _archiveHandle DumpId *tableDataId; /* TABLE DATA ids, indexed by table dumpId */ struct _tocEntry *currToc; /* Used when dumping data */ - int compression; /*--------- - * Compression requested on open(). - * Possible values for compression: - * -1 Z_DEFAULT_COMPRESSION - * 0 COMPRESSION_NONE - * 1-9 levels for gzip compression - *--------- - */ + Compress compression; /* Compression requested on open */ bool dosync; /* data requested to be synced on sight */ ArchiveMode mode; /* File mode - r or w */ void *formatData; /* Header data specific to file format */ diff --git a/src/bin/pg_dump/pg_backup_custom.c b/src/bin/pg_dump/pg_backup_custom.c index 77d402c323..55a887a236 100644 --- a/src/bin/pg_dump/pg_backup_custom.c +++ b/src/bin/pg_dump/pg_backup_custom.c @@ -298,7 +298,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) _WriteByte(AH, BLK_DATA); /* Block type */ WriteInt(AH, te->dumpId); /* For sanity check */ - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -377,7 +377,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) WriteInt(AH, oid); - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -566,7 +566,7 @@ _PrintTocData(ArchiveHandle *AH, TocEntry *te) static void _PrintData(ArchiveHandle *AH) { - ReadDataFromArchive(AH, AH->compression, _CustomReadFunc); + ReadDataFromArchive(AH, _CustomReadFunc); } static void diff --git a/src/bin/pg_dump/pg_backup_directory.c b/src/bin/pg_dump/pg_backup_directory.c index 650b542fce..8bf869c6ca 100644 --- a/src/bin/pg_dump/pg_backup_directory.c +++ b/src/bin/pg_dump/pg_backup_directory.c @@ -202,7 +202,7 @@ InitArchiveFmt_Directory(ArchiveHandle *AH) setFilePath(AH, fname, "toc.dat"); - tocFH = cfopen_read(fname, PG_BINARY_R); + tocFH = cfopen_read(fname, PG_BINARY_R, &AH->compression); if (tocFH == NULL) fatal("could not open input file \"%s\": %m", fname); @@ -327,7 +327,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) setFilePath(AH, fname, tctx->filename); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -388,7 +388,7 @@ _PrintFileData(ArchiveHandle *AH, char *filename) if (!filename) return; - cfp = cfopen_read(filename, PG_BINARY_R); + cfp = cfopen_read(filename, PG_BINARY_R, &AH->compression); if (!cfp) fatal("could not open input file \"%s\": %m", filename); @@ -435,12 +435,13 @@ _LoadBlobs(ArchiveHandle *AH) lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; char line[MAXPGPATH]; + Compress nocompression = {0}; StartRestoreBlobs(AH); setFilePath(AH, fname, "blobs.toc"); - ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R); + ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R, &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open large object TOC file \"%s\" for input: %m", @@ -573,6 +574,7 @@ _CloseArchive(ArchiveHandle *AH) { cfp *tocFH; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "toc.dat"); @@ -580,7 +582,7 @@ _CloseArchive(ArchiveHandle *AH) ctx->pstate = ParallelBackupStart(AH); /* The TOC is always created uncompressed */ - tocFH = cfopen_write(fname, PG_BINARY_W, 0); + tocFH = cfopen_write(fname, PG_BINARY_W, &nocompression); if (tocFH == NULL) fatal("could not open output file \"%s\": %m", fname); ctx->dataFH = tocFH; @@ -639,11 +641,12 @@ _StartBlobs(ArchiveHandle *AH, TocEntry *te) { lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "blobs.toc"); /* The blob TOC file is never compressed */ - ctx->blobsTocFH = cfopen_write(fname, "ab", 0); + ctx->blobsTocFH = cfopen_write(fname, "ab", &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -661,7 +664,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) snprintf(fname, MAXPGPATH, "%s/blob_%u.dat", ctx->directory, oid); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); diff --git a/src/bin/pg_dump/pg_backup_tar.c b/src/bin/pg_dump/pg_backup_tar.c index 61c9c87a9f..4ba79ab924 100644 --- a/src/bin/pg_dump/pg_backup_tar.c +++ b/src/bin/pg_dump/pg_backup_tar.c @@ -39,6 +39,7 @@ #include "pg_backup_archiver.h" #include "pg_backup_tar.h" #include "pg_backup_utils.h" +#include "compress_io.h" #include "pgtar.h" static void _ArchiveEntry(ArchiveHandle *AH, TocEntry *te); @@ -196,10 +197,10 @@ InitArchiveFmt_Tar(ArchiveHandle *AH) /* * We don't support compression because reading the files back is not - * possible since gzdopen uses buffered IO which totally screws file + * possible since gzdopen uses buffered IO which totally screws file XXX * positioning. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) fatal("compression is not supported by tar archive format"); } else @@ -254,14 +255,8 @@ _ArchiveEntry(ArchiveHandle *AH, TocEntry *te) ctx = (lclTocEntry *) pg_malloc0(sizeof(lclTocEntry)); if (te->dataDumper != NULL) { -#ifdef HAVE_LIBZ - if (AH->compression == 0) - sprintf(fn, "%d.dat", te->dumpId); - else - sprintf(fn, "%d.dat.gz", te->dumpId); -#else - sprintf(fn, "%d.dat", te->dumpId); -#endif + const char *suffix = compress_suffix(&AH->compression); + sprintf(fn, "%d.dat%s", te->dumpId, suffix); ctx->filename = pg_strdup(fn); } else @@ -352,7 +347,7 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression == 0) + if (AH->compression.alg == COMPR_ALG_NONE) tm->nFH = ctx->tarFH; else fatal("compression is not supported by tar archive format"); @@ -413,9 +408,9 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) { - sprintf(fmode, "wb%d", AH->compression); + sprintf(fmode, "wb%d", AH->compression.level); tm->zFH = gzdopen(dup(fileno(tm->tmpFH)), fmode); if (tm->zFH == NULL) fatal("could not open temporary file"); @@ -443,7 +438,7 @@ tarClose(ArchiveHandle *AH, TAR_MEMBER *th) /* * Close the GZ file since we dup'd. This will flush the buffers. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) if (GZCLOSE(th->zFH) != 0) fatal("could not close tar member"); @@ -868,7 +863,7 @@ _CloseArchive(ArchiveHandle *AH) memcpy(ropt, AH->public.ropt, sizeof(RestoreOptions)); ropt->filename = NULL; ropt->dropSchema = 1; - ropt->compression = 0; + ropt->compression.alg = COMPR_ALG_NONE; ropt->superuser = NULL; ropt->suppressDumpWarnings = true; @@ -952,16 +947,12 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) lclContext *ctx = (lclContext *) AH->formatData; lclTocEntry *tctx = (lclTocEntry *) te->formatData; char fname[255]; - char *sfx; + const char *sfx; if (oid == 0) fatal("invalid OID for large object (%u)", oid); - if (AH->compression != 0) - sfx = ".gz"; - else - sfx = ""; - + sfx = compress_suffix(&AH->compression); sprintf(fname, "blob_%u.dat%s", oid, sfx); tarPrintf(ctx->blobToc, "%u %s\n", oid, fname); diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c index 1ab98a2286..4cbc79aedc 100644 --- a/src/bin/pg_dump/pg_dump.c +++ b/src/bin/pg_dump/pg_dump.c @@ -59,6 +59,7 @@ #include "getopt_long.h" #include "libpq/libpq-fs.h" #include "parallel.h" +#include "compress_io.h" #include "pg_backup_db.h" #include "pg_backup_utils.h" #include "pg_dump.h" @@ -297,6 +298,82 @@ static void setupDumpWorker(Archive *AHX); static TableInfo *getRootTableInfo(TableInfo *tbinfo); +/* Parse the string into compression options */ +static void +parse_compression(const char *optarg, Compress *compress) +{ + if (optarg[0] == '0' && optarg[1] == '\0') + compress->alg = COMPR_ALG_NONE; + else if ((optarg[0] > '0' && optarg[0] <= '9') || + optarg[0] == '-') + { + compress->alg = COMPR_ALG_LIBZ; + compress->level_set = true; + compress->level = atoi(optarg); + if (optarg[1] != '\0') + { + pg_log_error("compression level must be in range 0..9"); + exit_nicely(1); + } + } + else + { + /* Parse a more flexible string like level=3 alg=zlib opts=long */ + for (;;) + { + char *eq = strchr(optarg, '='); + int len; + + if (eq == NULL) + { + pg_log_error("compression options must be key=value: %s", optarg); + exit_nicely(1); + } + + len = eq - optarg; + if (strncmp(optarg, "alg", len) == 0) + { + if (strchr(eq, ' ')) + len = strchr(eq, ' ') - eq - 1; + else + len = strlen(eq) - len; + if (strncmp(1+eq, "zlib", len) == 0 || + strncmp(1+eq, "libz", len) == 0) + compress->alg = COMPR_ALG_LIBZ; + else + { + pg_log_error("unknown compression algorithm: %s", 1+eq); + exit_nicely(1); + } + } + else if (strncmp(optarg, "level", len) == 0) + { + compress->level = atoi(1+eq); + compress->level_set = true; + } + else + { + pg_log_error("unknown compression setting: %s", optarg); + exit_nicely(1); + } + + optarg = strchr(eq, ' '); + if (!optarg++) + break; + } + + if (!compress->level_set) + { + const int default_compress_level[] = { + 0, /* COMPR_ALG_NONE */ + Z_DEFAULT_COMPRESSION, /* COMPR_ALG_ZLIB */ + }; + + compress->level = default_compress_level[compress->alg]; + } + } +} + int main(int argc, char **argv) { @@ -319,7 +396,7 @@ main(int argc, char **argv) char *use_role = NULL; long rowsPerInsert; int numWorkers = 1; - int compressLevel = -1; + Compress compress = { .alg = COMPR_ALG_DEFAULT }; int plainText = 0; ArchiveFormat archiveFormat = archUnknown; ArchiveMode archiveMode; @@ -532,12 +609,7 @@ main(int argc, char **argv) break; case 'Z': /* Compression Level */ - compressLevel = atoi(optarg); - if (compressLevel < 0 || compressLevel > 9) - { - pg_log_error("compression level must be in range 0..9"); - exit_nicely(1); - } + parse_compression(optarg, &compress); break; case 0: @@ -679,20 +751,28 @@ main(int argc, char **argv) plainText = 1; /* Custom and directory formats are compressed by default, others not */ - if (compressLevel == -1) + if (compress.alg == COMPR_ALG_DEFAULT) { -#ifdef HAVE_LIBZ if (archiveFormat == archCustom || archiveFormat == archDirectory) - compressLevel = Z_DEFAULT_COMPRESSION; - else + { +#ifdef HAVE_LIBZ + compress.alg = COMPR_ALG_LIBZ; + compress.level = Z_DEFAULT_COMPRESSION; #endif - compressLevel = 0; + } + else + { + compress.alg = COMPR_ALG_NONE; + compress.level = 0; + } } #ifndef HAVE_LIBZ - if (compressLevel != 0) + if (compress.alg == COMPR_ALG_LIBZ) + { pg_log_warning("requested compression not available in this installation -- archive will be uncompressed"); - compressLevel = 0; + compress.alg = 0; + } #endif /* @@ -723,7 +803,7 @@ main(int argc, char **argv) fatal("option --index-collation-versions-unknown only works in binary upgrade mode"); /* Open the output file */ - fout = CreateArchive(filename, archiveFormat, compressLevel, dosync, + fout = CreateArchive(filename, archiveFormat, &compress, dosync, archiveMode, setupDumpWorker); /* Make dump options accessible right away */ @@ -957,10 +1037,7 @@ main(int argc, char **argv) ropt->sequence_data = dopt.sequence_data; ropt->binary_upgrade = dopt.binary_upgrade; - if (compressLevel == -1) - ropt->compression = 0; - else - ropt->compression = compressLevel; + ropt->compression = compress; ropt->suppressDumpWarnings = true; /* We've already shown them */ -- 2.17.0 --GRPZ8SYKNexpdSJ7 Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="0004-struct-compressLibs.patch" ^ permalink raw reply [nested|flat] 23+ messages in thread
* [PATCH 03/20] Support multiple compression algs/levels/opts.. @ 2020-12-22 06:23 Justin Pryzby <[email protected]> 0 siblings, 0 replies; 23+ messages in thread From: Justin Pryzby @ 2020-12-22 06:23 UTC (permalink / raw) The existing implementation abtracts compressed and noncompressed I/O. This preliminary commit is intended to also allow for multiple compression algorithms. --- src/bin/pg_dump/compress_io.c | 220 +++++++++++--------------- src/bin/pg_dump/compress_io.h | 19 +-- src/bin/pg_dump/pg_backup.h | 23 ++- src/bin/pg_dump/pg_backup_archiver.c | 45 +++--- src/bin/pg_dump/pg_backup_archiver.h | 12 +- src/bin/pg_dump/pg_backup_custom.c | 6 +- src/bin/pg_dump/pg_backup_directory.c | 17 +- src/bin/pg_dump/pg_backup_tar.c | 33 ++-- src/bin/pg_dump/pg_dump.c | 115 +++++++++++--- 9 files changed, 272 insertions(+), 218 deletions(-) diff --git a/src/bin/pg_dump/compress_io.c b/src/bin/pg_dump/compress_io.c index 6a428978d4..db16fd33f2 100644 --- a/src/bin/pg_dump/compress_io.c +++ b/src/bin/pg_dump/compress_io.c @@ -74,12 +74,9 @@ struct CompressorState #endif }; -static void ParseCompressionOption(int compression, CompressionAlgorithm *alg, - int *level); - /* Routines that support zlib compressed data I/O */ #ifdef HAVE_LIBZ -static void InitCompressorZlib(CompressorState *cs, int level); +static void InitCompressorZlib(CompressorState *cs, Compress *compress); static void DeflateCompressorZlib(ArchiveHandle *AH, CompressorState *cs, bool flush); static void ReadDataFromArchiveZlib(ArchiveHandle *AH, ReadFunc readF); @@ -93,58 +90,36 @@ static void ReadDataFromArchiveNone(ArchiveHandle *AH, ReadFunc readF); static void WriteDataToArchiveNone(ArchiveHandle *AH, CompressorState *cs, const char *data, size_t dLen); -/* - * Interprets a numeric 'compression' value. The algorithm implied by the - * value (zlib or none at the moment), is returned in *alg, and the - * zlib compression level in *level. - */ -static void -ParseCompressionOption(int compression, CompressionAlgorithm *alg, int *level) -{ - if (compression == Z_DEFAULT_COMPRESSION || - (compression > 0 && compression <= 9)) - *alg = COMPR_ALG_LIBZ; - else if (compression == 0) - *alg = COMPR_ALG_NONE; - else - { - fatal("invalid compression code: %d", compression); - *alg = COMPR_ALG_NONE; /* keep compiler quiet */ - } - - /* The level is just the passed-in value. */ - if (level) - *level = compression; -} - /* Public interface routines */ /* Allocate a new compressor */ CompressorState * -AllocateCompressor(int compression, WriteFunc writeF) +AllocateCompressor(Compress *compression, WriteFunc writeF) { CompressorState *cs; - CompressionAlgorithm alg; - int level; - - ParseCompressionOption(compression, &alg, &level); - -#ifndef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - fatal("not built with zlib support"); -#endif cs = (CompressorState *) pg_malloc0(sizeof(CompressorState)); cs->writeF = writeF; - cs->comprAlg = alg; + cs->comprAlg = compression->alg; /* * Perform compression algorithm specific initialization. */ + Assert (compression->alg != COMPR_ALG_DEFAULT); + switch (compression->alg) + { #ifdef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - InitCompressorZlib(cs, level); + case COMPR_ALG_LIBZ: + InitCompressorZlib(cs, compression); + break; #endif + case COMPR_ALG_NONE: + /* Do nothing */ + break; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } return cs; } @@ -154,21 +129,21 @@ AllocateCompressor(int compression, WriteFunc writeF) * out with ahwrite(). */ void -ReadDataFromArchive(ArchiveHandle *AH, int compression, ReadFunc readF) +ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF) { - CompressionAlgorithm alg; - - ParseCompressionOption(compression, &alg, NULL); - - if (alg == COMPR_ALG_NONE) - ReadDataFromArchiveNone(AH, readF); - if (alg == COMPR_ALG_LIBZ) + switch (AH->compression.alg) { + case COMPR_ALG_NONE: + ReadDataFromArchiveNone(AH, readF); + break; #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: ReadDataFromArchiveZlib(AH, readF); -#else - fatal("not built with zlib support"); + break; #endif + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -181,16 +156,18 @@ WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, { switch (cs->comprAlg) { - case COMPR_ALG_LIBZ: #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: WriteDataToArchiveZlib(AH, cs, data, dLen); -#else - fatal("not built with zlib support"); -#endif break; +#endif case COMPR_ALG_NONE: WriteDataToArchiveNone(AH, cs, data, dLen); break; + + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -215,7 +192,7 @@ EndCompressor(ArchiveHandle *AH, CompressorState *cs) */ static void -InitCompressorZlib(CompressorState *cs, int level) +InitCompressorZlib(CompressorState *cs, Compress *compress) { z_streamp zp; @@ -232,7 +209,7 @@ InitCompressorZlib(CompressorState *cs, int level) cs->zlibOut = (char *) pg_malloc(ZLIB_OUT_SIZE + 1); cs->zlibOutSize = ZLIB_OUT_SIZE; - if (deflateInit(zp, level) != Z_OK) + if (deflateInit(zp, compress->level) != Z_OK) fatal("could not initialize compression library: %s", zp->msg); @@ -424,9 +401,7 @@ struct cfp #endif }; -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix); -#endif /* free() without changing errno; useful in several places below */ static void @@ -442,34 +417,31 @@ free_keep_errno(void *p) * Open a file for reading. 'path' is the file to open, and 'mode' should * be either "r" or "rb". * - * If the file at 'path' does not exist, we append the ".gz" suffix (if 'path' - * doesn't already have it) and try again. So if you pass "foo" as 'path', + * If the file at 'path' does not exist, we search with compressed suffix (if 'path' + * doesn't already have one) and try again. So if you pass "foo" as 'path', * this will open either "foo" or "foo.gz". * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_read(const char *path, const char *mode) +cfopen_read(const char *path, const char *mode, Compress *compression) { cfp *fp; -#ifdef HAVE_LIBZ if (hasSuffix(path, ".gz")) - fp = cfopen(path, mode, 1); + fp = cfopen(path, mode, compression); else -#endif { - fp = cfopen(path, mode, 0); -#ifdef HAVE_LIBZ + fp = cfopen(path, mode, compression); if (fp == NULL) { char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); - fp = cfopen(fname, mode, 1); + fname = psprintf("%s%s", path, suffix); + fp = cfopen(fname, mode, compression); free_keep_errno(fname); } -#endif } return fp; } @@ -479,31 +451,26 @@ cfopen_read(const char *path, const char *mode) * be a filemode as accepted by fopen() and gzopen() that indicates writing * ("w", "wb", "a", or "ab"). * - * If 'compression' is non-zero, a gzip compressed stream is opened, and - * 'compression' indicates the compression level used. The ".gz" suffix - * is automatically added to 'path' in that case. + * Use compression if specified. + * The appropriate suffix is automatically added to 'path' in that case. * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_write(const char *path, const char *mode, int compression) +cfopen_write(const char *path, const char *mode, Compress *compression) { cfp *fp; - if (compression == 0) - fp = cfopen(path, mode, 0); + if (compression->alg == COMPR_ALG_NONE) + fp = cfopen(path, mode, compression); else { -#ifdef HAVE_LIBZ char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); + fname = psprintf("%s%s", path, suffix); fp = cfopen(fname, mode, compression); free_keep_errno(fname); -#else - fatal("not built with zlib support"); - fp = NULL; /* keep compiler quiet */ -#endif } return fp; } @@ -515,20 +482,21 @@ cfopen_write(const char *path, const char *mode, int compression) * On failure, return NULL with an error code in errno. */ cfp * -cfopen(const char *path, const char *mode, int compression) +cfopen(const char *path, const char *mode, Compress *compression) { - cfp *fp = pg_malloc(sizeof(cfp)); + cfp *fp = pg_malloc0(sizeof(cfp)); - if (compression != 0) + switch (compression->alg) { #ifdef HAVE_LIBZ - if (compression != Z_DEFAULT_COMPRESSION) + case COMPR_ALG_LIBZ: + if (compression->level != Z_DEFAULT_COMPRESSION) { /* user has specified a compression level, so tell zlib to use it */ char mode_compression[32]; snprintf(mode_compression, sizeof(mode_compression), "%s%d", - mode, compression); + mode, compression->level); fp->compressedfp = gzopen(path, mode_compression); } else @@ -537,30 +505,27 @@ cfopen(const char *path, const char *mode, int compression) fp->compressedfp = gzopen(path, mode); } - fp->uncompressedfp = NULL; if (fp->compressedfp == NULL) { free_keep_errno(fp); fp = NULL; } -#else - fatal("not built with zlib support"); -#endif - } - else - { -#ifdef HAVE_LIBZ - fp->compressedfp = NULL; + return fp; #endif + + case COMPR_ALG_NONE: fp->uncompressedfp = fopen(path, mode); if (fp->uncompressedfp == NULL) { free_keep_errno(fp); fp = NULL; } - } + return fp; - return fp; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } } @@ -584,14 +549,13 @@ cfread(void *ptr, int size, cfp *fp) fatal("could not read from input file: %s", errnum == Z_ERRNO ? strerror(errno) : errmsg); } + return ret; } - else #endif - { - ret = fread(ptr, 1, size, fp->uncompressedfp); - if (ret != size && !feof(fp->uncompressedfp)) - READ_ERROR_EXIT(fp->uncompressedfp); - } + + ret = fread(ptr, 1, size, fp->uncompressedfp); + if (ret != size && !feof(fp->uncompressedfp)) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -601,9 +565,8 @@ cfwrite(const void *ptr, int size, cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzwrite(fp->compressedfp, ptr, size); - else #endif - return fwrite(ptr, 1, size, fp->uncompressedfp); + return fwrite(ptr, 1, size, fp->uncompressedfp); } int @@ -622,15 +585,12 @@ cfgetc(cfp *fp) else fatal("could not read from input file: end of file"); } + return ret; } - else #endif - { - ret = fgetc(fp->uncompressedfp); - if (ret == EOF) - READ_ERROR_EXIT(fp->uncompressedfp); - } - + ret = fgetc(fp->uncompressedfp); + if (ret == EOF) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -640,9 +600,8 @@ cfgets(cfp *fp, char *buf, int len) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzgets(fp->compressedfp, buf, len); - else #endif - return fgets(buf, len, fp->uncompressedfp); + return fgets(buf, len, fp->uncompressedfp); } int @@ -660,15 +619,13 @@ cfclose(cfp *fp) { result = gzclose(fp->compressedfp); fp->compressedfp = NULL; + return result; } - else #endif - { - result = fclose(fp->uncompressedfp); - fp->uncompressedfp = NULL; - } - free_keep_errno(fp); + result = fclose(fp->uncompressedfp); + fp->uncompressedfp = NULL; + free_keep_errno(fp); return result; } @@ -678,9 +635,9 @@ cfeof(cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzeof(fp->compressedfp); - else #endif - return feof(fp->uncompressedfp); + + return feof(fp->uncompressedfp); } const char * @@ -699,7 +656,6 @@ get_cfp_error(cfp *fp) return strerror(errno); } -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix) { @@ -714,4 +670,18 @@ hasSuffix(const char *filename, const char *suffix) suffixlen) == 0; } -#endif +/* + * Return a string for the given AH's compression. + * The string is statically allocated. + */ +const char * +compress_suffix(Compress *compression) +{ + switch (compression->alg) + { + case COMPR_ALG_LIBZ: + return ".gz"; + default: + return ""; + } +} diff --git a/src/bin/pg_dump/compress_io.h b/src/bin/pg_dump/compress_io.h index d2e6e1b854..2c073676eb 100644 --- a/src/bin/pg_dump/compress_io.h +++ b/src/bin/pg_dump/compress_io.h @@ -21,12 +21,6 @@ #define ZLIB_OUT_SIZE 4096 #define ZLIB_IN_SIZE 4096 -typedef enum -{ - COMPR_ALG_NONE, - COMPR_ALG_LIBZ -} CompressionAlgorithm; - /* Prototype for callback function to WriteDataToArchive() */ typedef void (*WriteFunc) (ArchiveHandle *AH, const char *buf, size_t len); @@ -46,8 +40,8 @@ typedef size_t (*ReadFunc) (ArchiveHandle *AH, char **buf, size_t *buflen); /* struct definition appears in compress_io.c */ typedef struct CompressorState CompressorState; -extern CompressorState *AllocateCompressor(int compression, WriteFunc writeF); -extern void ReadDataFromArchive(ArchiveHandle *AH, int compression, +extern CompressorState *AllocateCompressor(Compress *compression, WriteFunc writeF); +extern void ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF); extern void WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, const void *data, size_t dLen); @@ -56,9 +50,9 @@ extern void EndCompressor(ArchiveHandle *AH, CompressorState *cs); typedef struct cfp cfp; -extern cfp *cfopen(const char *path, const char *mode, int compression); -extern cfp *cfopen_read(const char *path, const char *mode); -extern cfp *cfopen_write(const char *path, const char *mode, int compression); +extern cfp *cfopen(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_read(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_write(const char *path, const char *mode, Compress *compression); extern int cfread(void *ptr, int size, cfp *fp); extern int cfwrite(const void *ptr, int size, cfp *fp); extern int cfgetc(cfp *fp); @@ -67,4 +61,7 @@ extern int cfclose(cfp *fp); extern int cfeof(cfp *fp); extern const char *get_cfp_error(cfp *fp); +/* also used by tar */ +extern const char * compress_suffix(Compress *compression); + #endif diff --git a/src/bin/pg_dump/pg_backup.h b/src/bin/pg_dump/pg_backup.h index 9d0056a569..f2390b7937 100644 --- a/src/bin/pg_dump/pg_backup.h +++ b/src/bin/pg_dump/pg_backup.h @@ -72,6 +72,25 @@ typedef struct _connParams char *override_dbname; } ConnParams; +typedef enum +{ + COMPR_ALG_DEFAULT = -1, + COMPR_ALG_NONE, + COMPR_ALG_LIBZ, +} CompressionAlgorithm; +/* Should be called "method" or "library" ? */ + +typedef struct Compress { + CompressionAlgorithm alg; + int level; + /* Is a nondefault level set ? This is useful since different compression + * methods have different "default" levels. For now we assume the levels + * are all integer, though. + */ + bool level_set; +} Compress; + + typedef struct _restoreOptions { int createDB; /* Issue commands to create the database */ @@ -125,7 +144,7 @@ typedef struct _restoreOptions int noDataForFailedTables; int exit_on_error; - int compression; + Compress compression; int suppressDumpWarnings; /* Suppress output of WARNING entries * to stderr */ bool single_txn; @@ -281,7 +300,7 @@ extern Archive *OpenArchive(const char *FileSpec, const ArchiveFormat fmt); /* Create a new archive */ extern Archive *CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker); /* The --list option */ diff --git a/src/bin/pg_dump/pg_backup_archiver.c b/src/bin/pg_dump/pg_backup_archiver.c index 1f82c6499b..3eb6c55600 100644 --- a/src/bin/pg_dump/pg_backup_archiver.c +++ b/src/bin/pg_dump/pg_backup_archiver.c @@ -70,7 +70,7 @@ typedef struct _parallelReadyList static ArchiveHandle *_allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr); static void _getObjectDescription(PQExpBuffer buf, TocEntry *te); static void _printTocEntry(ArchiveHandle *AH, TocEntry *te, bool isData); @@ -98,7 +98,7 @@ static int _discoverArchiveFormat(ArchiveHandle *AH); static int RestoringToDB(ArchiveHandle *AH); static void dump_lo_buf(ArchiveHandle *AH); static void dumpTimestamp(ArchiveHandle *AH, const char *msg, time_t tim); -static void SetOutput(ArchiveHandle *AH, const char *filename, int compression); +static void SetOutput(ArchiveHandle *AH, const char *filename, Compress *compress); static OutputContext SaveOutput(ArchiveHandle *AH); static void RestoreOutput(ArchiveHandle *AH, OutputContext savedContext); @@ -238,7 +238,7 @@ setupRestoreWorker(Archive *AHX) /* Public */ Archive * CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker) { @@ -253,7 +253,9 @@ CreateArchive(const char *FileSpec, const ArchiveFormat fmt, Archive * OpenArchive(const char *FileSpec, const ArchiveFormat fmt) { - ArchiveHandle *AH = _allocAH(FileSpec, fmt, 0, true, archModeRead, setupRestoreWorker); + Compress compress = {0}; + ArchiveHandle *AH = _allocAH(FileSpec, fmt, &compress, true, archModeRead, + setupRestoreWorker); return (Archive *) AH; } @@ -382,7 +384,7 @@ RestoreArchive(Archive *AHX) * Make sure we won't need (de)compression we haven't got */ #ifndef HAVE_LIBZ - if (AH->compression != 0 && AH->PrintTocDataPtr != NULL) + if (AH->compression.alg != COMPR_ALG_NONE && AH->PrintTocDataPtr != NULL) { for (te = AH->toc->next; te != AH->toc; te = te->next) { @@ -457,8 +459,8 @@ RestoreArchive(Archive *AHX) * Setup the output file if necessary. */ sav = SaveOutput(AH); - if (ropt->filename || ropt->compression) - SetOutput(AH, ropt->filename, ropt->compression); + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) + SetOutput(AH, ropt->filename, &ropt->compression); ahprintf(AH, "--\n-- PostgreSQL database dump\n--\n\n"); @@ -738,7 +740,7 @@ RestoreArchive(Archive *AHX) */ AH->stage = STAGE_FINALIZING; - if (ropt->filename || ropt->compression) + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) RestoreOutput(AH, sav); if (ropt->useDB) @@ -1123,8 +1125,9 @@ PrintTOCSummary(Archive *AHX) char stamp_str[64]; sav = SaveOutput(AH); + Assert(ropt->compression.alg == COMPR_ALG_NONE); if (ropt->filename) - SetOutput(AH, ropt->filename, 0 /* no compression */ ); + SetOutput(AH, ropt->filename, &ropt->compression); if (strftime(stamp_str, sizeof(stamp_str), PGDUMP_STRFTIME_FMT, localtime(&AH->createDate)) == 0) @@ -1133,7 +1136,7 @@ PrintTOCSummary(Archive *AHX) ahprintf(AH, ";\n; Archive created at %s\n", stamp_str); ahprintf(AH, "; dbname: %s\n; TOC Entries: %d\n; Compression: %d\n", sanitize_line(AH->archdbname, false), - AH->tocCount, AH->compression); + AH->tocCount, AH->compression.alg); switch (AH->format) { @@ -1487,7 +1490,7 @@ archprintf(Archive *AH, const char *fmt,...) *******************************/ static void -SetOutput(ArchiveHandle *AH, const char *filename, int compression) +SetOutput(ArchiveHandle *AH, const char *filename, Compress *compression) { int fn; @@ -1510,12 +1513,12 @@ SetOutput(ArchiveHandle *AH, const char *filename, int compression) /* If compression explicitly requested, use gzopen */ #ifdef HAVE_LIBZ - if (compression != 0) + if (compression->alg != COMPR_ALG_NONE) { char fmode[14]; /* Don't use PG_BINARY_x since this is zlib */ - sprintf(fmode, "wb%d", compression); + sprintf(fmode, "wb%d", compression->level); if (fn >= 0) AH->OF = gzdopen(dup(fn), fmode); else @@ -2259,7 +2262,7 @@ _discoverArchiveFormat(ArchiveHandle *AH) */ static ArchiveHandle * _allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr) { ArchiveHandle *AH; @@ -2310,7 +2313,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, AH->toc->prev = AH->toc; AH->mode = mode; - AH->compression = compression; + AH->compression = *compression; AH->dosync = dosync; memset(&(AH->sqlparse), 0, sizeof(AH->sqlparse)); @@ -2325,7 +2328,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, * Force stdin/stdout into binary mode if that is what we are using. */ #ifdef WIN32 - if ((fmt != archNull || compression != 0) && + if ((fmt != archNull || compression->alg != COMPR_ALG_NONE) && (AH->fSpec == NULL || strcmp(AH->fSpec, "") == 0)) { if (mode == archModeWrite) @@ -3741,7 +3744,7 @@ WriteHead(ArchiveHandle *AH) AH->WriteBytePtr(AH, AH->intSize); AH->WriteBytePtr(AH, AH->offSize); AH->WriteBytePtr(AH, AH->format); - WriteInt(AH, AH->compression); + WriteInt(AH, AH->compression.alg); crtm = *localtime(&AH->createDate); WriteInt(AH, crtm.tm_sec); WriteInt(AH, crtm.tm_min); @@ -3816,15 +3819,15 @@ ReadHead(ArchiveHandle *AH) if (AH->version >= K_VERS_1_2) { if (AH->version < K_VERS_1_4) - AH->compression = AH->ReadBytePtr(AH); + AH->compression.alg = AH->ReadBytePtr(AH); else - AH->compression = ReadInt(AH); + AH->compression.alg = ReadInt(AH); } else - AH->compression = Z_DEFAULT_COMPRESSION; + AH->compression.alg = Z_DEFAULT_COMPRESSION; #ifndef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) pg_log_warning("archive is compressed, but this installation does not support compression -- no data will be available"); #endif diff --git a/src/bin/pg_dump/pg_backup_archiver.h b/src/bin/pg_dump/pg_backup_archiver.h index a8ea5c7eae..6e033d040e 100644 --- a/src/bin/pg_dump/pg_backup_archiver.h +++ b/src/bin/pg_dump/pg_backup_archiver.h @@ -47,7 +47,8 @@ #define GZWRITE(p, s, n, fh) (fwrite(p, s, n, fh) * (s)) #define GZREAD(p, s, n, fh) fread(p, s, n, fh) #define GZEOF(fh) feof(fh) -/* this is just the redefinition of a libz constant */ +/* this is just the redefinition of a libz constant, in case zlib isn't + * available */ #define Z_DEFAULT_COMPRESSION (-1) typedef struct _z_stream @@ -329,14 +330,7 @@ struct _archiveHandle DumpId *tableDataId; /* TABLE DATA ids, indexed by table dumpId */ struct _tocEntry *currToc; /* Used when dumping data */ - int compression; /*--------- - * Compression requested on open(). - * Possible values for compression: - * -1 Z_DEFAULT_COMPRESSION - * 0 COMPRESSION_NONE - * 1-9 levels for gzip compression - *--------- - */ + Compress compression; /* Compression requested on open */ bool dosync; /* data requested to be synced on sight */ ArchiveMode mode; /* File mode - r or w */ void *formatData; /* Header data specific to file format */ diff --git a/src/bin/pg_dump/pg_backup_custom.c b/src/bin/pg_dump/pg_backup_custom.c index 77d402c323..55a887a236 100644 --- a/src/bin/pg_dump/pg_backup_custom.c +++ b/src/bin/pg_dump/pg_backup_custom.c @@ -298,7 +298,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) _WriteByte(AH, BLK_DATA); /* Block type */ WriteInt(AH, te->dumpId); /* For sanity check */ - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -377,7 +377,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) WriteInt(AH, oid); - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -566,7 +566,7 @@ _PrintTocData(ArchiveHandle *AH, TocEntry *te) static void _PrintData(ArchiveHandle *AH) { - ReadDataFromArchive(AH, AH->compression, _CustomReadFunc); + ReadDataFromArchive(AH, _CustomReadFunc); } static void diff --git a/src/bin/pg_dump/pg_backup_directory.c b/src/bin/pg_dump/pg_backup_directory.c index 650b542fce..8bf869c6ca 100644 --- a/src/bin/pg_dump/pg_backup_directory.c +++ b/src/bin/pg_dump/pg_backup_directory.c @@ -202,7 +202,7 @@ InitArchiveFmt_Directory(ArchiveHandle *AH) setFilePath(AH, fname, "toc.dat"); - tocFH = cfopen_read(fname, PG_BINARY_R); + tocFH = cfopen_read(fname, PG_BINARY_R, &AH->compression); if (tocFH == NULL) fatal("could not open input file \"%s\": %m", fname); @@ -327,7 +327,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) setFilePath(AH, fname, tctx->filename); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -388,7 +388,7 @@ _PrintFileData(ArchiveHandle *AH, char *filename) if (!filename) return; - cfp = cfopen_read(filename, PG_BINARY_R); + cfp = cfopen_read(filename, PG_BINARY_R, &AH->compression); if (!cfp) fatal("could not open input file \"%s\": %m", filename); @@ -435,12 +435,13 @@ _LoadBlobs(ArchiveHandle *AH) lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; char line[MAXPGPATH]; + Compress nocompression = {0}; StartRestoreBlobs(AH); setFilePath(AH, fname, "blobs.toc"); - ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R); + ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R, &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open large object TOC file \"%s\" for input: %m", @@ -573,6 +574,7 @@ _CloseArchive(ArchiveHandle *AH) { cfp *tocFH; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "toc.dat"); @@ -580,7 +582,7 @@ _CloseArchive(ArchiveHandle *AH) ctx->pstate = ParallelBackupStart(AH); /* The TOC is always created uncompressed */ - tocFH = cfopen_write(fname, PG_BINARY_W, 0); + tocFH = cfopen_write(fname, PG_BINARY_W, &nocompression); if (tocFH == NULL) fatal("could not open output file \"%s\": %m", fname); ctx->dataFH = tocFH; @@ -639,11 +641,12 @@ _StartBlobs(ArchiveHandle *AH, TocEntry *te) { lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "blobs.toc"); /* The blob TOC file is never compressed */ - ctx->blobsTocFH = cfopen_write(fname, "ab", 0); + ctx->blobsTocFH = cfopen_write(fname, "ab", &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -661,7 +664,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) snprintf(fname, MAXPGPATH, "%s/blob_%u.dat", ctx->directory, oid); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); diff --git a/src/bin/pg_dump/pg_backup_tar.c b/src/bin/pg_dump/pg_backup_tar.c index 61c9c87a9f..4ba79ab924 100644 --- a/src/bin/pg_dump/pg_backup_tar.c +++ b/src/bin/pg_dump/pg_backup_tar.c @@ -39,6 +39,7 @@ #include "pg_backup_archiver.h" #include "pg_backup_tar.h" #include "pg_backup_utils.h" +#include "compress_io.h" #include "pgtar.h" static void _ArchiveEntry(ArchiveHandle *AH, TocEntry *te); @@ -196,10 +197,10 @@ InitArchiveFmt_Tar(ArchiveHandle *AH) /* * We don't support compression because reading the files back is not - * possible since gzdopen uses buffered IO which totally screws file + * possible since gzdopen uses buffered IO which totally screws file XXX * positioning. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) fatal("compression is not supported by tar archive format"); } else @@ -254,14 +255,8 @@ _ArchiveEntry(ArchiveHandle *AH, TocEntry *te) ctx = (lclTocEntry *) pg_malloc0(sizeof(lclTocEntry)); if (te->dataDumper != NULL) { -#ifdef HAVE_LIBZ - if (AH->compression == 0) - sprintf(fn, "%d.dat", te->dumpId); - else - sprintf(fn, "%d.dat.gz", te->dumpId); -#else - sprintf(fn, "%d.dat", te->dumpId); -#endif + const char *suffix = compress_suffix(&AH->compression); + sprintf(fn, "%d.dat%s", te->dumpId, suffix); ctx->filename = pg_strdup(fn); } else @@ -352,7 +347,7 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression == 0) + if (AH->compression.alg == COMPR_ALG_NONE) tm->nFH = ctx->tarFH; else fatal("compression is not supported by tar archive format"); @@ -413,9 +408,9 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) { - sprintf(fmode, "wb%d", AH->compression); + sprintf(fmode, "wb%d", AH->compression.level); tm->zFH = gzdopen(dup(fileno(tm->tmpFH)), fmode); if (tm->zFH == NULL) fatal("could not open temporary file"); @@ -443,7 +438,7 @@ tarClose(ArchiveHandle *AH, TAR_MEMBER *th) /* * Close the GZ file since we dup'd. This will flush the buffers. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) if (GZCLOSE(th->zFH) != 0) fatal("could not close tar member"); @@ -868,7 +863,7 @@ _CloseArchive(ArchiveHandle *AH) memcpy(ropt, AH->public.ropt, sizeof(RestoreOptions)); ropt->filename = NULL; ropt->dropSchema = 1; - ropt->compression = 0; + ropt->compression.alg = COMPR_ALG_NONE; ropt->superuser = NULL; ropt->suppressDumpWarnings = true; @@ -952,16 +947,12 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) lclContext *ctx = (lclContext *) AH->formatData; lclTocEntry *tctx = (lclTocEntry *) te->formatData; char fname[255]; - char *sfx; + const char *sfx; if (oid == 0) fatal("invalid OID for large object (%u)", oid); - if (AH->compression != 0) - sfx = ".gz"; - else - sfx = ""; - + sfx = compress_suffix(&AH->compression); sprintf(fname, "blob_%u.dat%s", oid, sfx); tarPrintf(ctx->blobToc, "%u %s\n", oid, fname); diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c index 1ab98a2286..4cbc79aedc 100644 --- a/src/bin/pg_dump/pg_dump.c +++ b/src/bin/pg_dump/pg_dump.c @@ -59,6 +59,7 @@ #include "getopt_long.h" #include "libpq/libpq-fs.h" #include "parallel.h" +#include "compress_io.h" #include "pg_backup_db.h" #include "pg_backup_utils.h" #include "pg_dump.h" @@ -297,6 +298,82 @@ static void setupDumpWorker(Archive *AHX); static TableInfo *getRootTableInfo(TableInfo *tbinfo); +/* Parse the string into compression options */ +static void +parse_compression(const char *optarg, Compress *compress) +{ + if (optarg[0] == '0' && optarg[1] == '\0') + compress->alg = COMPR_ALG_NONE; + else if ((optarg[0] > '0' && optarg[0] <= '9') || + optarg[0] == '-') + { + compress->alg = COMPR_ALG_LIBZ; + compress->level_set = true; + compress->level = atoi(optarg); + if (optarg[1] != '\0') + { + pg_log_error("compression level must be in range 0..9"); + exit_nicely(1); + } + } + else + { + /* Parse a more flexible string like level=3 alg=zlib opts=long */ + for (;;) + { + char *eq = strchr(optarg, '='); + int len; + + if (eq == NULL) + { + pg_log_error("compression options must be key=value: %s", optarg); + exit_nicely(1); + } + + len = eq - optarg; + if (strncmp(optarg, "alg", len) == 0) + { + if (strchr(eq, ' ')) + len = strchr(eq, ' ') - eq - 1; + else + len = strlen(eq) - len; + if (strncmp(1+eq, "zlib", len) == 0 || + strncmp(1+eq, "libz", len) == 0) + compress->alg = COMPR_ALG_LIBZ; + else + { + pg_log_error("unknown compression algorithm: %s", 1+eq); + exit_nicely(1); + } + } + else if (strncmp(optarg, "level", len) == 0) + { + compress->level = atoi(1+eq); + compress->level_set = true; + } + else + { + pg_log_error("unknown compression setting: %s", optarg); + exit_nicely(1); + } + + optarg = strchr(eq, ' '); + if (!optarg++) + break; + } + + if (!compress->level_set) + { + const int default_compress_level[] = { + 0, /* COMPR_ALG_NONE */ + Z_DEFAULT_COMPRESSION, /* COMPR_ALG_ZLIB */ + }; + + compress->level = default_compress_level[compress->alg]; + } + } +} + int main(int argc, char **argv) { @@ -319,7 +396,7 @@ main(int argc, char **argv) char *use_role = NULL; long rowsPerInsert; int numWorkers = 1; - int compressLevel = -1; + Compress compress = { .alg = COMPR_ALG_DEFAULT }; int plainText = 0; ArchiveFormat archiveFormat = archUnknown; ArchiveMode archiveMode; @@ -532,12 +609,7 @@ main(int argc, char **argv) break; case 'Z': /* Compression Level */ - compressLevel = atoi(optarg); - if (compressLevel < 0 || compressLevel > 9) - { - pg_log_error("compression level must be in range 0..9"); - exit_nicely(1); - } + parse_compression(optarg, &compress); break; case 0: @@ -679,20 +751,28 @@ main(int argc, char **argv) plainText = 1; /* Custom and directory formats are compressed by default, others not */ - if (compressLevel == -1) + if (compress.alg == COMPR_ALG_DEFAULT) { -#ifdef HAVE_LIBZ if (archiveFormat == archCustom || archiveFormat == archDirectory) - compressLevel = Z_DEFAULT_COMPRESSION; - else + { +#ifdef HAVE_LIBZ + compress.alg = COMPR_ALG_LIBZ; + compress.level = Z_DEFAULT_COMPRESSION; #endif - compressLevel = 0; + } + else + { + compress.alg = COMPR_ALG_NONE; + compress.level = 0; + } } #ifndef HAVE_LIBZ - if (compressLevel != 0) + if (compress.alg == COMPR_ALG_LIBZ) + { pg_log_warning("requested compression not available in this installation -- archive will be uncompressed"); - compressLevel = 0; + compress.alg = 0; + } #endif /* @@ -723,7 +803,7 @@ main(int argc, char **argv) fatal("option --index-collation-versions-unknown only works in binary upgrade mode"); /* Open the output file */ - fout = CreateArchive(filename, archiveFormat, compressLevel, dosync, + fout = CreateArchive(filename, archiveFormat, &compress, dosync, archiveMode, setupDumpWorker); /* Make dump options accessible right away */ @@ -957,10 +1037,7 @@ main(int argc, char **argv) ropt->sequence_data = dopt.sequence_data; ropt->binary_upgrade = dopt.binary_upgrade; - if (compressLevel == -1) - ropt->compression = 0; - else - ropt->compression = compressLevel; + ropt->compression = compress; ropt->suppressDumpWarnings = true; /* We've already shown them */ -- 2.17.0 --GRPZ8SYKNexpdSJ7 Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="0004-struct-compressLibs.patch" ^ permalink raw reply [nested|flat] 23+ messages in thread
* [PATCH 03/20] Support multiple compression algs/levels/opts.. @ 2020-12-22 06:23 Justin Pryzby <[email protected]> 0 siblings, 0 replies; 23+ messages in thread From: Justin Pryzby @ 2020-12-22 06:23 UTC (permalink / raw) The existing implementation abtracts compressed and noncompressed I/O. This preliminary commit is intended to also allow for multiple compression algorithms. --- src/bin/pg_dump/compress_io.c | 220 +++++++++++--------------- src/bin/pg_dump/compress_io.h | 19 +-- src/bin/pg_dump/pg_backup.h | 23 ++- src/bin/pg_dump/pg_backup_archiver.c | 45 +++--- src/bin/pg_dump/pg_backup_archiver.h | 12 +- src/bin/pg_dump/pg_backup_custom.c | 6 +- src/bin/pg_dump/pg_backup_directory.c | 17 +- src/bin/pg_dump/pg_backup_tar.c | 33 ++-- src/bin/pg_dump/pg_dump.c | 115 +++++++++++--- 9 files changed, 272 insertions(+), 218 deletions(-) diff --git a/src/bin/pg_dump/compress_io.c b/src/bin/pg_dump/compress_io.c index 6a428978d4..db16fd33f2 100644 --- a/src/bin/pg_dump/compress_io.c +++ b/src/bin/pg_dump/compress_io.c @@ -74,12 +74,9 @@ struct CompressorState #endif }; -static void ParseCompressionOption(int compression, CompressionAlgorithm *alg, - int *level); - /* Routines that support zlib compressed data I/O */ #ifdef HAVE_LIBZ -static void InitCompressorZlib(CompressorState *cs, int level); +static void InitCompressorZlib(CompressorState *cs, Compress *compress); static void DeflateCompressorZlib(ArchiveHandle *AH, CompressorState *cs, bool flush); static void ReadDataFromArchiveZlib(ArchiveHandle *AH, ReadFunc readF); @@ -93,58 +90,36 @@ static void ReadDataFromArchiveNone(ArchiveHandle *AH, ReadFunc readF); static void WriteDataToArchiveNone(ArchiveHandle *AH, CompressorState *cs, const char *data, size_t dLen); -/* - * Interprets a numeric 'compression' value. The algorithm implied by the - * value (zlib or none at the moment), is returned in *alg, and the - * zlib compression level in *level. - */ -static void -ParseCompressionOption(int compression, CompressionAlgorithm *alg, int *level) -{ - if (compression == Z_DEFAULT_COMPRESSION || - (compression > 0 && compression <= 9)) - *alg = COMPR_ALG_LIBZ; - else if (compression == 0) - *alg = COMPR_ALG_NONE; - else - { - fatal("invalid compression code: %d", compression); - *alg = COMPR_ALG_NONE; /* keep compiler quiet */ - } - - /* The level is just the passed-in value. */ - if (level) - *level = compression; -} - /* Public interface routines */ /* Allocate a new compressor */ CompressorState * -AllocateCompressor(int compression, WriteFunc writeF) +AllocateCompressor(Compress *compression, WriteFunc writeF) { CompressorState *cs; - CompressionAlgorithm alg; - int level; - - ParseCompressionOption(compression, &alg, &level); - -#ifndef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - fatal("not built with zlib support"); -#endif cs = (CompressorState *) pg_malloc0(sizeof(CompressorState)); cs->writeF = writeF; - cs->comprAlg = alg; + cs->comprAlg = compression->alg; /* * Perform compression algorithm specific initialization. */ + Assert (compression->alg != COMPR_ALG_DEFAULT); + switch (compression->alg) + { #ifdef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - InitCompressorZlib(cs, level); + case COMPR_ALG_LIBZ: + InitCompressorZlib(cs, compression); + break; #endif + case COMPR_ALG_NONE: + /* Do nothing */ + break; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } return cs; } @@ -154,21 +129,21 @@ AllocateCompressor(int compression, WriteFunc writeF) * out with ahwrite(). */ void -ReadDataFromArchive(ArchiveHandle *AH, int compression, ReadFunc readF) +ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF) { - CompressionAlgorithm alg; - - ParseCompressionOption(compression, &alg, NULL); - - if (alg == COMPR_ALG_NONE) - ReadDataFromArchiveNone(AH, readF); - if (alg == COMPR_ALG_LIBZ) + switch (AH->compression.alg) { + case COMPR_ALG_NONE: + ReadDataFromArchiveNone(AH, readF); + break; #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: ReadDataFromArchiveZlib(AH, readF); -#else - fatal("not built with zlib support"); + break; #endif + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -181,16 +156,18 @@ WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, { switch (cs->comprAlg) { - case COMPR_ALG_LIBZ: #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: WriteDataToArchiveZlib(AH, cs, data, dLen); -#else - fatal("not built with zlib support"); -#endif break; +#endif case COMPR_ALG_NONE: WriteDataToArchiveNone(AH, cs, data, dLen); break; + + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -215,7 +192,7 @@ EndCompressor(ArchiveHandle *AH, CompressorState *cs) */ static void -InitCompressorZlib(CompressorState *cs, int level) +InitCompressorZlib(CompressorState *cs, Compress *compress) { z_streamp zp; @@ -232,7 +209,7 @@ InitCompressorZlib(CompressorState *cs, int level) cs->zlibOut = (char *) pg_malloc(ZLIB_OUT_SIZE + 1); cs->zlibOutSize = ZLIB_OUT_SIZE; - if (deflateInit(zp, level) != Z_OK) + if (deflateInit(zp, compress->level) != Z_OK) fatal("could not initialize compression library: %s", zp->msg); @@ -424,9 +401,7 @@ struct cfp #endif }; -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix); -#endif /* free() without changing errno; useful in several places below */ static void @@ -442,34 +417,31 @@ free_keep_errno(void *p) * Open a file for reading. 'path' is the file to open, and 'mode' should * be either "r" or "rb". * - * If the file at 'path' does not exist, we append the ".gz" suffix (if 'path' - * doesn't already have it) and try again. So if you pass "foo" as 'path', + * If the file at 'path' does not exist, we search with compressed suffix (if 'path' + * doesn't already have one) and try again. So if you pass "foo" as 'path', * this will open either "foo" or "foo.gz". * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_read(const char *path, const char *mode) +cfopen_read(const char *path, const char *mode, Compress *compression) { cfp *fp; -#ifdef HAVE_LIBZ if (hasSuffix(path, ".gz")) - fp = cfopen(path, mode, 1); + fp = cfopen(path, mode, compression); else -#endif { - fp = cfopen(path, mode, 0); -#ifdef HAVE_LIBZ + fp = cfopen(path, mode, compression); if (fp == NULL) { char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); - fp = cfopen(fname, mode, 1); + fname = psprintf("%s%s", path, suffix); + fp = cfopen(fname, mode, compression); free_keep_errno(fname); } -#endif } return fp; } @@ -479,31 +451,26 @@ cfopen_read(const char *path, const char *mode) * be a filemode as accepted by fopen() and gzopen() that indicates writing * ("w", "wb", "a", or "ab"). * - * If 'compression' is non-zero, a gzip compressed stream is opened, and - * 'compression' indicates the compression level used. The ".gz" suffix - * is automatically added to 'path' in that case. + * Use compression if specified. + * The appropriate suffix is automatically added to 'path' in that case. * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_write(const char *path, const char *mode, int compression) +cfopen_write(const char *path, const char *mode, Compress *compression) { cfp *fp; - if (compression == 0) - fp = cfopen(path, mode, 0); + if (compression->alg == COMPR_ALG_NONE) + fp = cfopen(path, mode, compression); else { -#ifdef HAVE_LIBZ char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); + fname = psprintf("%s%s", path, suffix); fp = cfopen(fname, mode, compression); free_keep_errno(fname); -#else - fatal("not built with zlib support"); - fp = NULL; /* keep compiler quiet */ -#endif } return fp; } @@ -515,20 +482,21 @@ cfopen_write(const char *path, const char *mode, int compression) * On failure, return NULL with an error code in errno. */ cfp * -cfopen(const char *path, const char *mode, int compression) +cfopen(const char *path, const char *mode, Compress *compression) { - cfp *fp = pg_malloc(sizeof(cfp)); + cfp *fp = pg_malloc0(sizeof(cfp)); - if (compression != 0) + switch (compression->alg) { #ifdef HAVE_LIBZ - if (compression != Z_DEFAULT_COMPRESSION) + case COMPR_ALG_LIBZ: + if (compression->level != Z_DEFAULT_COMPRESSION) { /* user has specified a compression level, so tell zlib to use it */ char mode_compression[32]; snprintf(mode_compression, sizeof(mode_compression), "%s%d", - mode, compression); + mode, compression->level); fp->compressedfp = gzopen(path, mode_compression); } else @@ -537,30 +505,27 @@ cfopen(const char *path, const char *mode, int compression) fp->compressedfp = gzopen(path, mode); } - fp->uncompressedfp = NULL; if (fp->compressedfp == NULL) { free_keep_errno(fp); fp = NULL; } -#else - fatal("not built with zlib support"); -#endif - } - else - { -#ifdef HAVE_LIBZ - fp->compressedfp = NULL; + return fp; #endif + + case COMPR_ALG_NONE: fp->uncompressedfp = fopen(path, mode); if (fp->uncompressedfp == NULL) { free_keep_errno(fp); fp = NULL; } - } + return fp; - return fp; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } } @@ -584,14 +549,13 @@ cfread(void *ptr, int size, cfp *fp) fatal("could not read from input file: %s", errnum == Z_ERRNO ? strerror(errno) : errmsg); } + return ret; } - else #endif - { - ret = fread(ptr, 1, size, fp->uncompressedfp); - if (ret != size && !feof(fp->uncompressedfp)) - READ_ERROR_EXIT(fp->uncompressedfp); - } + + ret = fread(ptr, 1, size, fp->uncompressedfp); + if (ret != size && !feof(fp->uncompressedfp)) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -601,9 +565,8 @@ cfwrite(const void *ptr, int size, cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzwrite(fp->compressedfp, ptr, size); - else #endif - return fwrite(ptr, 1, size, fp->uncompressedfp); + return fwrite(ptr, 1, size, fp->uncompressedfp); } int @@ -622,15 +585,12 @@ cfgetc(cfp *fp) else fatal("could not read from input file: end of file"); } + return ret; } - else #endif - { - ret = fgetc(fp->uncompressedfp); - if (ret == EOF) - READ_ERROR_EXIT(fp->uncompressedfp); - } - + ret = fgetc(fp->uncompressedfp); + if (ret == EOF) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -640,9 +600,8 @@ cfgets(cfp *fp, char *buf, int len) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzgets(fp->compressedfp, buf, len); - else #endif - return fgets(buf, len, fp->uncompressedfp); + return fgets(buf, len, fp->uncompressedfp); } int @@ -660,15 +619,13 @@ cfclose(cfp *fp) { result = gzclose(fp->compressedfp); fp->compressedfp = NULL; + return result; } - else #endif - { - result = fclose(fp->uncompressedfp); - fp->uncompressedfp = NULL; - } - free_keep_errno(fp); + result = fclose(fp->uncompressedfp); + fp->uncompressedfp = NULL; + free_keep_errno(fp); return result; } @@ -678,9 +635,9 @@ cfeof(cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzeof(fp->compressedfp); - else #endif - return feof(fp->uncompressedfp); + + return feof(fp->uncompressedfp); } const char * @@ -699,7 +656,6 @@ get_cfp_error(cfp *fp) return strerror(errno); } -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix) { @@ -714,4 +670,18 @@ hasSuffix(const char *filename, const char *suffix) suffixlen) == 0; } -#endif +/* + * Return a string for the given AH's compression. + * The string is statically allocated. + */ +const char * +compress_suffix(Compress *compression) +{ + switch (compression->alg) + { + case COMPR_ALG_LIBZ: + return ".gz"; + default: + return ""; + } +} diff --git a/src/bin/pg_dump/compress_io.h b/src/bin/pg_dump/compress_io.h index d2e6e1b854..2c073676eb 100644 --- a/src/bin/pg_dump/compress_io.h +++ b/src/bin/pg_dump/compress_io.h @@ -21,12 +21,6 @@ #define ZLIB_OUT_SIZE 4096 #define ZLIB_IN_SIZE 4096 -typedef enum -{ - COMPR_ALG_NONE, - COMPR_ALG_LIBZ -} CompressionAlgorithm; - /* Prototype for callback function to WriteDataToArchive() */ typedef void (*WriteFunc) (ArchiveHandle *AH, const char *buf, size_t len); @@ -46,8 +40,8 @@ typedef size_t (*ReadFunc) (ArchiveHandle *AH, char **buf, size_t *buflen); /* struct definition appears in compress_io.c */ typedef struct CompressorState CompressorState; -extern CompressorState *AllocateCompressor(int compression, WriteFunc writeF); -extern void ReadDataFromArchive(ArchiveHandle *AH, int compression, +extern CompressorState *AllocateCompressor(Compress *compression, WriteFunc writeF); +extern void ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF); extern void WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, const void *data, size_t dLen); @@ -56,9 +50,9 @@ extern void EndCompressor(ArchiveHandle *AH, CompressorState *cs); typedef struct cfp cfp; -extern cfp *cfopen(const char *path, const char *mode, int compression); -extern cfp *cfopen_read(const char *path, const char *mode); -extern cfp *cfopen_write(const char *path, const char *mode, int compression); +extern cfp *cfopen(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_read(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_write(const char *path, const char *mode, Compress *compression); extern int cfread(void *ptr, int size, cfp *fp); extern int cfwrite(const void *ptr, int size, cfp *fp); extern int cfgetc(cfp *fp); @@ -67,4 +61,7 @@ extern int cfclose(cfp *fp); extern int cfeof(cfp *fp); extern const char *get_cfp_error(cfp *fp); +/* also used by tar */ +extern const char * compress_suffix(Compress *compression); + #endif diff --git a/src/bin/pg_dump/pg_backup.h b/src/bin/pg_dump/pg_backup.h index 9d0056a569..f2390b7937 100644 --- a/src/bin/pg_dump/pg_backup.h +++ b/src/bin/pg_dump/pg_backup.h @@ -72,6 +72,25 @@ typedef struct _connParams char *override_dbname; } ConnParams; +typedef enum +{ + COMPR_ALG_DEFAULT = -1, + COMPR_ALG_NONE, + COMPR_ALG_LIBZ, +} CompressionAlgorithm; +/* Should be called "method" or "library" ? */ + +typedef struct Compress { + CompressionAlgorithm alg; + int level; + /* Is a nondefault level set ? This is useful since different compression + * methods have different "default" levels. For now we assume the levels + * are all integer, though. + */ + bool level_set; +} Compress; + + typedef struct _restoreOptions { int createDB; /* Issue commands to create the database */ @@ -125,7 +144,7 @@ typedef struct _restoreOptions int noDataForFailedTables; int exit_on_error; - int compression; + Compress compression; int suppressDumpWarnings; /* Suppress output of WARNING entries * to stderr */ bool single_txn; @@ -281,7 +300,7 @@ extern Archive *OpenArchive(const char *FileSpec, const ArchiveFormat fmt); /* Create a new archive */ extern Archive *CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker); /* The --list option */ diff --git a/src/bin/pg_dump/pg_backup_archiver.c b/src/bin/pg_dump/pg_backup_archiver.c index 1f82c6499b..3eb6c55600 100644 --- a/src/bin/pg_dump/pg_backup_archiver.c +++ b/src/bin/pg_dump/pg_backup_archiver.c @@ -70,7 +70,7 @@ typedef struct _parallelReadyList static ArchiveHandle *_allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr); static void _getObjectDescription(PQExpBuffer buf, TocEntry *te); static void _printTocEntry(ArchiveHandle *AH, TocEntry *te, bool isData); @@ -98,7 +98,7 @@ static int _discoverArchiveFormat(ArchiveHandle *AH); static int RestoringToDB(ArchiveHandle *AH); static void dump_lo_buf(ArchiveHandle *AH); static void dumpTimestamp(ArchiveHandle *AH, const char *msg, time_t tim); -static void SetOutput(ArchiveHandle *AH, const char *filename, int compression); +static void SetOutput(ArchiveHandle *AH, const char *filename, Compress *compress); static OutputContext SaveOutput(ArchiveHandle *AH); static void RestoreOutput(ArchiveHandle *AH, OutputContext savedContext); @@ -238,7 +238,7 @@ setupRestoreWorker(Archive *AHX) /* Public */ Archive * CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker) { @@ -253,7 +253,9 @@ CreateArchive(const char *FileSpec, const ArchiveFormat fmt, Archive * OpenArchive(const char *FileSpec, const ArchiveFormat fmt) { - ArchiveHandle *AH = _allocAH(FileSpec, fmt, 0, true, archModeRead, setupRestoreWorker); + Compress compress = {0}; + ArchiveHandle *AH = _allocAH(FileSpec, fmt, &compress, true, archModeRead, + setupRestoreWorker); return (Archive *) AH; } @@ -382,7 +384,7 @@ RestoreArchive(Archive *AHX) * Make sure we won't need (de)compression we haven't got */ #ifndef HAVE_LIBZ - if (AH->compression != 0 && AH->PrintTocDataPtr != NULL) + if (AH->compression.alg != COMPR_ALG_NONE && AH->PrintTocDataPtr != NULL) { for (te = AH->toc->next; te != AH->toc; te = te->next) { @@ -457,8 +459,8 @@ RestoreArchive(Archive *AHX) * Setup the output file if necessary. */ sav = SaveOutput(AH); - if (ropt->filename || ropt->compression) - SetOutput(AH, ropt->filename, ropt->compression); + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) + SetOutput(AH, ropt->filename, &ropt->compression); ahprintf(AH, "--\n-- PostgreSQL database dump\n--\n\n"); @@ -738,7 +740,7 @@ RestoreArchive(Archive *AHX) */ AH->stage = STAGE_FINALIZING; - if (ropt->filename || ropt->compression) + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) RestoreOutput(AH, sav); if (ropt->useDB) @@ -1123,8 +1125,9 @@ PrintTOCSummary(Archive *AHX) char stamp_str[64]; sav = SaveOutput(AH); + Assert(ropt->compression.alg == COMPR_ALG_NONE); if (ropt->filename) - SetOutput(AH, ropt->filename, 0 /* no compression */ ); + SetOutput(AH, ropt->filename, &ropt->compression); if (strftime(stamp_str, sizeof(stamp_str), PGDUMP_STRFTIME_FMT, localtime(&AH->createDate)) == 0) @@ -1133,7 +1136,7 @@ PrintTOCSummary(Archive *AHX) ahprintf(AH, ";\n; Archive created at %s\n", stamp_str); ahprintf(AH, "; dbname: %s\n; TOC Entries: %d\n; Compression: %d\n", sanitize_line(AH->archdbname, false), - AH->tocCount, AH->compression); + AH->tocCount, AH->compression.alg); switch (AH->format) { @@ -1487,7 +1490,7 @@ archprintf(Archive *AH, const char *fmt,...) *******************************/ static void -SetOutput(ArchiveHandle *AH, const char *filename, int compression) +SetOutput(ArchiveHandle *AH, const char *filename, Compress *compression) { int fn; @@ -1510,12 +1513,12 @@ SetOutput(ArchiveHandle *AH, const char *filename, int compression) /* If compression explicitly requested, use gzopen */ #ifdef HAVE_LIBZ - if (compression != 0) + if (compression->alg != COMPR_ALG_NONE) { char fmode[14]; /* Don't use PG_BINARY_x since this is zlib */ - sprintf(fmode, "wb%d", compression); + sprintf(fmode, "wb%d", compression->level); if (fn >= 0) AH->OF = gzdopen(dup(fn), fmode); else @@ -2259,7 +2262,7 @@ _discoverArchiveFormat(ArchiveHandle *AH) */ static ArchiveHandle * _allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr) { ArchiveHandle *AH; @@ -2310,7 +2313,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, AH->toc->prev = AH->toc; AH->mode = mode; - AH->compression = compression; + AH->compression = *compression; AH->dosync = dosync; memset(&(AH->sqlparse), 0, sizeof(AH->sqlparse)); @@ -2325,7 +2328,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, * Force stdin/stdout into binary mode if that is what we are using. */ #ifdef WIN32 - if ((fmt != archNull || compression != 0) && + if ((fmt != archNull || compression->alg != COMPR_ALG_NONE) && (AH->fSpec == NULL || strcmp(AH->fSpec, "") == 0)) { if (mode == archModeWrite) @@ -3741,7 +3744,7 @@ WriteHead(ArchiveHandle *AH) AH->WriteBytePtr(AH, AH->intSize); AH->WriteBytePtr(AH, AH->offSize); AH->WriteBytePtr(AH, AH->format); - WriteInt(AH, AH->compression); + WriteInt(AH, AH->compression.alg); crtm = *localtime(&AH->createDate); WriteInt(AH, crtm.tm_sec); WriteInt(AH, crtm.tm_min); @@ -3816,15 +3819,15 @@ ReadHead(ArchiveHandle *AH) if (AH->version >= K_VERS_1_2) { if (AH->version < K_VERS_1_4) - AH->compression = AH->ReadBytePtr(AH); + AH->compression.alg = AH->ReadBytePtr(AH); else - AH->compression = ReadInt(AH); + AH->compression.alg = ReadInt(AH); } else - AH->compression = Z_DEFAULT_COMPRESSION; + AH->compression.alg = Z_DEFAULT_COMPRESSION; #ifndef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) pg_log_warning("archive is compressed, but this installation does not support compression -- no data will be available"); #endif diff --git a/src/bin/pg_dump/pg_backup_archiver.h b/src/bin/pg_dump/pg_backup_archiver.h index a8ea5c7eae..6e033d040e 100644 --- a/src/bin/pg_dump/pg_backup_archiver.h +++ b/src/bin/pg_dump/pg_backup_archiver.h @@ -47,7 +47,8 @@ #define GZWRITE(p, s, n, fh) (fwrite(p, s, n, fh) * (s)) #define GZREAD(p, s, n, fh) fread(p, s, n, fh) #define GZEOF(fh) feof(fh) -/* this is just the redefinition of a libz constant */ +/* this is just the redefinition of a libz constant, in case zlib isn't + * available */ #define Z_DEFAULT_COMPRESSION (-1) typedef struct _z_stream @@ -329,14 +330,7 @@ struct _archiveHandle DumpId *tableDataId; /* TABLE DATA ids, indexed by table dumpId */ struct _tocEntry *currToc; /* Used when dumping data */ - int compression; /*--------- - * Compression requested on open(). - * Possible values for compression: - * -1 Z_DEFAULT_COMPRESSION - * 0 COMPRESSION_NONE - * 1-9 levels for gzip compression - *--------- - */ + Compress compression; /* Compression requested on open */ bool dosync; /* data requested to be synced on sight */ ArchiveMode mode; /* File mode - r or w */ void *formatData; /* Header data specific to file format */ diff --git a/src/bin/pg_dump/pg_backup_custom.c b/src/bin/pg_dump/pg_backup_custom.c index 77d402c323..55a887a236 100644 --- a/src/bin/pg_dump/pg_backup_custom.c +++ b/src/bin/pg_dump/pg_backup_custom.c @@ -298,7 +298,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) _WriteByte(AH, BLK_DATA); /* Block type */ WriteInt(AH, te->dumpId); /* For sanity check */ - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -377,7 +377,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) WriteInt(AH, oid); - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -566,7 +566,7 @@ _PrintTocData(ArchiveHandle *AH, TocEntry *te) static void _PrintData(ArchiveHandle *AH) { - ReadDataFromArchive(AH, AH->compression, _CustomReadFunc); + ReadDataFromArchive(AH, _CustomReadFunc); } static void diff --git a/src/bin/pg_dump/pg_backup_directory.c b/src/bin/pg_dump/pg_backup_directory.c index 650b542fce..8bf869c6ca 100644 --- a/src/bin/pg_dump/pg_backup_directory.c +++ b/src/bin/pg_dump/pg_backup_directory.c @@ -202,7 +202,7 @@ InitArchiveFmt_Directory(ArchiveHandle *AH) setFilePath(AH, fname, "toc.dat"); - tocFH = cfopen_read(fname, PG_BINARY_R); + tocFH = cfopen_read(fname, PG_BINARY_R, &AH->compression); if (tocFH == NULL) fatal("could not open input file \"%s\": %m", fname); @@ -327,7 +327,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) setFilePath(AH, fname, tctx->filename); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -388,7 +388,7 @@ _PrintFileData(ArchiveHandle *AH, char *filename) if (!filename) return; - cfp = cfopen_read(filename, PG_BINARY_R); + cfp = cfopen_read(filename, PG_BINARY_R, &AH->compression); if (!cfp) fatal("could not open input file \"%s\": %m", filename); @@ -435,12 +435,13 @@ _LoadBlobs(ArchiveHandle *AH) lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; char line[MAXPGPATH]; + Compress nocompression = {0}; StartRestoreBlobs(AH); setFilePath(AH, fname, "blobs.toc"); - ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R); + ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R, &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open large object TOC file \"%s\" for input: %m", @@ -573,6 +574,7 @@ _CloseArchive(ArchiveHandle *AH) { cfp *tocFH; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "toc.dat"); @@ -580,7 +582,7 @@ _CloseArchive(ArchiveHandle *AH) ctx->pstate = ParallelBackupStart(AH); /* The TOC is always created uncompressed */ - tocFH = cfopen_write(fname, PG_BINARY_W, 0); + tocFH = cfopen_write(fname, PG_BINARY_W, &nocompression); if (tocFH == NULL) fatal("could not open output file \"%s\": %m", fname); ctx->dataFH = tocFH; @@ -639,11 +641,12 @@ _StartBlobs(ArchiveHandle *AH, TocEntry *te) { lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "blobs.toc"); /* The blob TOC file is never compressed */ - ctx->blobsTocFH = cfopen_write(fname, "ab", 0); + ctx->blobsTocFH = cfopen_write(fname, "ab", &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -661,7 +664,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) snprintf(fname, MAXPGPATH, "%s/blob_%u.dat", ctx->directory, oid); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); diff --git a/src/bin/pg_dump/pg_backup_tar.c b/src/bin/pg_dump/pg_backup_tar.c index 61c9c87a9f..4ba79ab924 100644 --- a/src/bin/pg_dump/pg_backup_tar.c +++ b/src/bin/pg_dump/pg_backup_tar.c @@ -39,6 +39,7 @@ #include "pg_backup_archiver.h" #include "pg_backup_tar.h" #include "pg_backup_utils.h" +#include "compress_io.h" #include "pgtar.h" static void _ArchiveEntry(ArchiveHandle *AH, TocEntry *te); @@ -196,10 +197,10 @@ InitArchiveFmt_Tar(ArchiveHandle *AH) /* * We don't support compression because reading the files back is not - * possible since gzdopen uses buffered IO which totally screws file + * possible since gzdopen uses buffered IO which totally screws file XXX * positioning. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) fatal("compression is not supported by tar archive format"); } else @@ -254,14 +255,8 @@ _ArchiveEntry(ArchiveHandle *AH, TocEntry *te) ctx = (lclTocEntry *) pg_malloc0(sizeof(lclTocEntry)); if (te->dataDumper != NULL) { -#ifdef HAVE_LIBZ - if (AH->compression == 0) - sprintf(fn, "%d.dat", te->dumpId); - else - sprintf(fn, "%d.dat.gz", te->dumpId); -#else - sprintf(fn, "%d.dat", te->dumpId); -#endif + const char *suffix = compress_suffix(&AH->compression); + sprintf(fn, "%d.dat%s", te->dumpId, suffix); ctx->filename = pg_strdup(fn); } else @@ -352,7 +347,7 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression == 0) + if (AH->compression.alg == COMPR_ALG_NONE) tm->nFH = ctx->tarFH; else fatal("compression is not supported by tar archive format"); @@ -413,9 +408,9 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) { - sprintf(fmode, "wb%d", AH->compression); + sprintf(fmode, "wb%d", AH->compression.level); tm->zFH = gzdopen(dup(fileno(tm->tmpFH)), fmode); if (tm->zFH == NULL) fatal("could not open temporary file"); @@ -443,7 +438,7 @@ tarClose(ArchiveHandle *AH, TAR_MEMBER *th) /* * Close the GZ file since we dup'd. This will flush the buffers. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) if (GZCLOSE(th->zFH) != 0) fatal("could not close tar member"); @@ -868,7 +863,7 @@ _CloseArchive(ArchiveHandle *AH) memcpy(ropt, AH->public.ropt, sizeof(RestoreOptions)); ropt->filename = NULL; ropt->dropSchema = 1; - ropt->compression = 0; + ropt->compression.alg = COMPR_ALG_NONE; ropt->superuser = NULL; ropt->suppressDumpWarnings = true; @@ -952,16 +947,12 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) lclContext *ctx = (lclContext *) AH->formatData; lclTocEntry *tctx = (lclTocEntry *) te->formatData; char fname[255]; - char *sfx; + const char *sfx; if (oid == 0) fatal("invalid OID for large object (%u)", oid); - if (AH->compression != 0) - sfx = ".gz"; - else - sfx = ""; - + sfx = compress_suffix(&AH->compression); sprintf(fname, "blob_%u.dat%s", oid, sfx); tarPrintf(ctx->blobToc, "%u %s\n", oid, fname); diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c index 1ab98a2286..4cbc79aedc 100644 --- a/src/bin/pg_dump/pg_dump.c +++ b/src/bin/pg_dump/pg_dump.c @@ -59,6 +59,7 @@ #include "getopt_long.h" #include "libpq/libpq-fs.h" #include "parallel.h" +#include "compress_io.h" #include "pg_backup_db.h" #include "pg_backup_utils.h" #include "pg_dump.h" @@ -297,6 +298,82 @@ static void setupDumpWorker(Archive *AHX); static TableInfo *getRootTableInfo(TableInfo *tbinfo); +/* Parse the string into compression options */ +static void +parse_compression(const char *optarg, Compress *compress) +{ + if (optarg[0] == '0' && optarg[1] == '\0') + compress->alg = COMPR_ALG_NONE; + else if ((optarg[0] > '0' && optarg[0] <= '9') || + optarg[0] == '-') + { + compress->alg = COMPR_ALG_LIBZ; + compress->level_set = true; + compress->level = atoi(optarg); + if (optarg[1] != '\0') + { + pg_log_error("compression level must be in range 0..9"); + exit_nicely(1); + } + } + else + { + /* Parse a more flexible string like level=3 alg=zlib opts=long */ + for (;;) + { + char *eq = strchr(optarg, '='); + int len; + + if (eq == NULL) + { + pg_log_error("compression options must be key=value: %s", optarg); + exit_nicely(1); + } + + len = eq - optarg; + if (strncmp(optarg, "alg", len) == 0) + { + if (strchr(eq, ' ')) + len = strchr(eq, ' ') - eq - 1; + else + len = strlen(eq) - len; + if (strncmp(1+eq, "zlib", len) == 0 || + strncmp(1+eq, "libz", len) == 0) + compress->alg = COMPR_ALG_LIBZ; + else + { + pg_log_error("unknown compression algorithm: %s", 1+eq); + exit_nicely(1); + } + } + else if (strncmp(optarg, "level", len) == 0) + { + compress->level = atoi(1+eq); + compress->level_set = true; + } + else + { + pg_log_error("unknown compression setting: %s", optarg); + exit_nicely(1); + } + + optarg = strchr(eq, ' '); + if (!optarg++) + break; + } + + if (!compress->level_set) + { + const int default_compress_level[] = { + 0, /* COMPR_ALG_NONE */ + Z_DEFAULT_COMPRESSION, /* COMPR_ALG_ZLIB */ + }; + + compress->level = default_compress_level[compress->alg]; + } + } +} + int main(int argc, char **argv) { @@ -319,7 +396,7 @@ main(int argc, char **argv) char *use_role = NULL; long rowsPerInsert; int numWorkers = 1; - int compressLevel = -1; + Compress compress = { .alg = COMPR_ALG_DEFAULT }; int plainText = 0; ArchiveFormat archiveFormat = archUnknown; ArchiveMode archiveMode; @@ -532,12 +609,7 @@ main(int argc, char **argv) break; case 'Z': /* Compression Level */ - compressLevel = atoi(optarg); - if (compressLevel < 0 || compressLevel > 9) - { - pg_log_error("compression level must be in range 0..9"); - exit_nicely(1); - } + parse_compression(optarg, &compress); break; case 0: @@ -679,20 +751,28 @@ main(int argc, char **argv) plainText = 1; /* Custom and directory formats are compressed by default, others not */ - if (compressLevel == -1) + if (compress.alg == COMPR_ALG_DEFAULT) { -#ifdef HAVE_LIBZ if (archiveFormat == archCustom || archiveFormat == archDirectory) - compressLevel = Z_DEFAULT_COMPRESSION; - else + { +#ifdef HAVE_LIBZ + compress.alg = COMPR_ALG_LIBZ; + compress.level = Z_DEFAULT_COMPRESSION; #endif - compressLevel = 0; + } + else + { + compress.alg = COMPR_ALG_NONE; + compress.level = 0; + } } #ifndef HAVE_LIBZ - if (compressLevel != 0) + if (compress.alg == COMPR_ALG_LIBZ) + { pg_log_warning("requested compression not available in this installation -- archive will be uncompressed"); - compressLevel = 0; + compress.alg = 0; + } #endif /* @@ -723,7 +803,7 @@ main(int argc, char **argv) fatal("option --index-collation-versions-unknown only works in binary upgrade mode"); /* Open the output file */ - fout = CreateArchive(filename, archiveFormat, compressLevel, dosync, + fout = CreateArchive(filename, archiveFormat, &compress, dosync, archiveMode, setupDumpWorker); /* Make dump options accessible right away */ @@ -957,10 +1037,7 @@ main(int argc, char **argv) ropt->sequence_data = dopt.sequence_data; ropt->binary_upgrade = dopt.binary_upgrade; - if (compressLevel == -1) - ropt->compression = 0; - else - ropt->compression = compressLevel; + ropt->compression = compress; ropt->suppressDumpWarnings = true; /* We've already shown them */ -- 2.17.0 --GRPZ8SYKNexpdSJ7 Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="0004-struct-compressLibs.patch" ^ permalink raw reply [nested|flat] 23+ messages in thread
* [PATCH 03/20] Support multiple compression algs/levels/opts.. @ 2020-12-22 06:23 Justin Pryzby <[email protected]> 0 siblings, 0 replies; 23+ messages in thread From: Justin Pryzby @ 2020-12-22 06:23 UTC (permalink / raw) The existing implementation abtracts compressed and noncompressed I/O. This preliminary commit is intended to also allow for multiple compression algorithms. --- src/bin/pg_dump/compress_io.c | 220 +++++++++++--------------- src/bin/pg_dump/compress_io.h | 19 +-- src/bin/pg_dump/pg_backup.h | 23 ++- src/bin/pg_dump/pg_backup_archiver.c | 45 +++--- src/bin/pg_dump/pg_backup_archiver.h | 12 +- src/bin/pg_dump/pg_backup_custom.c | 6 +- src/bin/pg_dump/pg_backup_directory.c | 17 +- src/bin/pg_dump/pg_backup_tar.c | 33 ++-- src/bin/pg_dump/pg_dump.c | 115 +++++++++++--- 9 files changed, 272 insertions(+), 218 deletions(-) diff --git a/src/bin/pg_dump/compress_io.c b/src/bin/pg_dump/compress_io.c index 6a428978d4..db16fd33f2 100644 --- a/src/bin/pg_dump/compress_io.c +++ b/src/bin/pg_dump/compress_io.c @@ -74,12 +74,9 @@ struct CompressorState #endif }; -static void ParseCompressionOption(int compression, CompressionAlgorithm *alg, - int *level); - /* Routines that support zlib compressed data I/O */ #ifdef HAVE_LIBZ -static void InitCompressorZlib(CompressorState *cs, int level); +static void InitCompressorZlib(CompressorState *cs, Compress *compress); static void DeflateCompressorZlib(ArchiveHandle *AH, CompressorState *cs, bool flush); static void ReadDataFromArchiveZlib(ArchiveHandle *AH, ReadFunc readF); @@ -93,58 +90,36 @@ static void ReadDataFromArchiveNone(ArchiveHandle *AH, ReadFunc readF); static void WriteDataToArchiveNone(ArchiveHandle *AH, CompressorState *cs, const char *data, size_t dLen); -/* - * Interprets a numeric 'compression' value. The algorithm implied by the - * value (zlib or none at the moment), is returned in *alg, and the - * zlib compression level in *level. - */ -static void -ParseCompressionOption(int compression, CompressionAlgorithm *alg, int *level) -{ - if (compression == Z_DEFAULT_COMPRESSION || - (compression > 0 && compression <= 9)) - *alg = COMPR_ALG_LIBZ; - else if (compression == 0) - *alg = COMPR_ALG_NONE; - else - { - fatal("invalid compression code: %d", compression); - *alg = COMPR_ALG_NONE; /* keep compiler quiet */ - } - - /* The level is just the passed-in value. */ - if (level) - *level = compression; -} - /* Public interface routines */ /* Allocate a new compressor */ CompressorState * -AllocateCompressor(int compression, WriteFunc writeF) +AllocateCompressor(Compress *compression, WriteFunc writeF) { CompressorState *cs; - CompressionAlgorithm alg; - int level; - - ParseCompressionOption(compression, &alg, &level); - -#ifndef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - fatal("not built with zlib support"); -#endif cs = (CompressorState *) pg_malloc0(sizeof(CompressorState)); cs->writeF = writeF; - cs->comprAlg = alg; + cs->comprAlg = compression->alg; /* * Perform compression algorithm specific initialization. */ + Assert (compression->alg != COMPR_ALG_DEFAULT); + switch (compression->alg) + { #ifdef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - InitCompressorZlib(cs, level); + case COMPR_ALG_LIBZ: + InitCompressorZlib(cs, compression); + break; #endif + case COMPR_ALG_NONE: + /* Do nothing */ + break; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } return cs; } @@ -154,21 +129,21 @@ AllocateCompressor(int compression, WriteFunc writeF) * out with ahwrite(). */ void -ReadDataFromArchive(ArchiveHandle *AH, int compression, ReadFunc readF) +ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF) { - CompressionAlgorithm alg; - - ParseCompressionOption(compression, &alg, NULL); - - if (alg == COMPR_ALG_NONE) - ReadDataFromArchiveNone(AH, readF); - if (alg == COMPR_ALG_LIBZ) + switch (AH->compression.alg) { + case COMPR_ALG_NONE: + ReadDataFromArchiveNone(AH, readF); + break; #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: ReadDataFromArchiveZlib(AH, readF); -#else - fatal("not built with zlib support"); + break; #endif + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -181,16 +156,18 @@ WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, { switch (cs->comprAlg) { - case COMPR_ALG_LIBZ: #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: WriteDataToArchiveZlib(AH, cs, data, dLen); -#else - fatal("not built with zlib support"); -#endif break; +#endif case COMPR_ALG_NONE: WriteDataToArchiveNone(AH, cs, data, dLen); break; + + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -215,7 +192,7 @@ EndCompressor(ArchiveHandle *AH, CompressorState *cs) */ static void -InitCompressorZlib(CompressorState *cs, int level) +InitCompressorZlib(CompressorState *cs, Compress *compress) { z_streamp zp; @@ -232,7 +209,7 @@ InitCompressorZlib(CompressorState *cs, int level) cs->zlibOut = (char *) pg_malloc(ZLIB_OUT_SIZE + 1); cs->zlibOutSize = ZLIB_OUT_SIZE; - if (deflateInit(zp, level) != Z_OK) + if (deflateInit(zp, compress->level) != Z_OK) fatal("could not initialize compression library: %s", zp->msg); @@ -424,9 +401,7 @@ struct cfp #endif }; -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix); -#endif /* free() without changing errno; useful in several places below */ static void @@ -442,34 +417,31 @@ free_keep_errno(void *p) * Open a file for reading. 'path' is the file to open, and 'mode' should * be either "r" or "rb". * - * If the file at 'path' does not exist, we append the ".gz" suffix (if 'path' - * doesn't already have it) and try again. So if you pass "foo" as 'path', + * If the file at 'path' does not exist, we search with compressed suffix (if 'path' + * doesn't already have one) and try again. So if you pass "foo" as 'path', * this will open either "foo" or "foo.gz". * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_read(const char *path, const char *mode) +cfopen_read(const char *path, const char *mode, Compress *compression) { cfp *fp; -#ifdef HAVE_LIBZ if (hasSuffix(path, ".gz")) - fp = cfopen(path, mode, 1); + fp = cfopen(path, mode, compression); else -#endif { - fp = cfopen(path, mode, 0); -#ifdef HAVE_LIBZ + fp = cfopen(path, mode, compression); if (fp == NULL) { char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); - fp = cfopen(fname, mode, 1); + fname = psprintf("%s%s", path, suffix); + fp = cfopen(fname, mode, compression); free_keep_errno(fname); } -#endif } return fp; } @@ -479,31 +451,26 @@ cfopen_read(const char *path, const char *mode) * be a filemode as accepted by fopen() and gzopen() that indicates writing * ("w", "wb", "a", or "ab"). * - * If 'compression' is non-zero, a gzip compressed stream is opened, and - * 'compression' indicates the compression level used. The ".gz" suffix - * is automatically added to 'path' in that case. + * Use compression if specified. + * The appropriate suffix is automatically added to 'path' in that case. * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_write(const char *path, const char *mode, int compression) +cfopen_write(const char *path, const char *mode, Compress *compression) { cfp *fp; - if (compression == 0) - fp = cfopen(path, mode, 0); + if (compression->alg == COMPR_ALG_NONE) + fp = cfopen(path, mode, compression); else { -#ifdef HAVE_LIBZ char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); + fname = psprintf("%s%s", path, suffix); fp = cfopen(fname, mode, compression); free_keep_errno(fname); -#else - fatal("not built with zlib support"); - fp = NULL; /* keep compiler quiet */ -#endif } return fp; } @@ -515,20 +482,21 @@ cfopen_write(const char *path, const char *mode, int compression) * On failure, return NULL with an error code in errno. */ cfp * -cfopen(const char *path, const char *mode, int compression) +cfopen(const char *path, const char *mode, Compress *compression) { - cfp *fp = pg_malloc(sizeof(cfp)); + cfp *fp = pg_malloc0(sizeof(cfp)); - if (compression != 0) + switch (compression->alg) { #ifdef HAVE_LIBZ - if (compression != Z_DEFAULT_COMPRESSION) + case COMPR_ALG_LIBZ: + if (compression->level != Z_DEFAULT_COMPRESSION) { /* user has specified a compression level, so tell zlib to use it */ char mode_compression[32]; snprintf(mode_compression, sizeof(mode_compression), "%s%d", - mode, compression); + mode, compression->level); fp->compressedfp = gzopen(path, mode_compression); } else @@ -537,30 +505,27 @@ cfopen(const char *path, const char *mode, int compression) fp->compressedfp = gzopen(path, mode); } - fp->uncompressedfp = NULL; if (fp->compressedfp == NULL) { free_keep_errno(fp); fp = NULL; } -#else - fatal("not built with zlib support"); -#endif - } - else - { -#ifdef HAVE_LIBZ - fp->compressedfp = NULL; + return fp; #endif + + case COMPR_ALG_NONE: fp->uncompressedfp = fopen(path, mode); if (fp->uncompressedfp == NULL) { free_keep_errno(fp); fp = NULL; } - } + return fp; - return fp; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } } @@ -584,14 +549,13 @@ cfread(void *ptr, int size, cfp *fp) fatal("could not read from input file: %s", errnum == Z_ERRNO ? strerror(errno) : errmsg); } + return ret; } - else #endif - { - ret = fread(ptr, 1, size, fp->uncompressedfp); - if (ret != size && !feof(fp->uncompressedfp)) - READ_ERROR_EXIT(fp->uncompressedfp); - } + + ret = fread(ptr, 1, size, fp->uncompressedfp); + if (ret != size && !feof(fp->uncompressedfp)) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -601,9 +565,8 @@ cfwrite(const void *ptr, int size, cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzwrite(fp->compressedfp, ptr, size); - else #endif - return fwrite(ptr, 1, size, fp->uncompressedfp); + return fwrite(ptr, 1, size, fp->uncompressedfp); } int @@ -622,15 +585,12 @@ cfgetc(cfp *fp) else fatal("could not read from input file: end of file"); } + return ret; } - else #endif - { - ret = fgetc(fp->uncompressedfp); - if (ret == EOF) - READ_ERROR_EXIT(fp->uncompressedfp); - } - + ret = fgetc(fp->uncompressedfp); + if (ret == EOF) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -640,9 +600,8 @@ cfgets(cfp *fp, char *buf, int len) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzgets(fp->compressedfp, buf, len); - else #endif - return fgets(buf, len, fp->uncompressedfp); + return fgets(buf, len, fp->uncompressedfp); } int @@ -660,15 +619,13 @@ cfclose(cfp *fp) { result = gzclose(fp->compressedfp); fp->compressedfp = NULL; + return result; } - else #endif - { - result = fclose(fp->uncompressedfp); - fp->uncompressedfp = NULL; - } - free_keep_errno(fp); + result = fclose(fp->uncompressedfp); + fp->uncompressedfp = NULL; + free_keep_errno(fp); return result; } @@ -678,9 +635,9 @@ cfeof(cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzeof(fp->compressedfp); - else #endif - return feof(fp->uncompressedfp); + + return feof(fp->uncompressedfp); } const char * @@ -699,7 +656,6 @@ get_cfp_error(cfp *fp) return strerror(errno); } -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix) { @@ -714,4 +670,18 @@ hasSuffix(const char *filename, const char *suffix) suffixlen) == 0; } -#endif +/* + * Return a string for the given AH's compression. + * The string is statically allocated. + */ +const char * +compress_suffix(Compress *compression) +{ + switch (compression->alg) + { + case COMPR_ALG_LIBZ: + return ".gz"; + default: + return ""; + } +} diff --git a/src/bin/pg_dump/compress_io.h b/src/bin/pg_dump/compress_io.h index d2e6e1b854..2c073676eb 100644 --- a/src/bin/pg_dump/compress_io.h +++ b/src/bin/pg_dump/compress_io.h @@ -21,12 +21,6 @@ #define ZLIB_OUT_SIZE 4096 #define ZLIB_IN_SIZE 4096 -typedef enum -{ - COMPR_ALG_NONE, - COMPR_ALG_LIBZ -} CompressionAlgorithm; - /* Prototype for callback function to WriteDataToArchive() */ typedef void (*WriteFunc) (ArchiveHandle *AH, const char *buf, size_t len); @@ -46,8 +40,8 @@ typedef size_t (*ReadFunc) (ArchiveHandle *AH, char **buf, size_t *buflen); /* struct definition appears in compress_io.c */ typedef struct CompressorState CompressorState; -extern CompressorState *AllocateCompressor(int compression, WriteFunc writeF); -extern void ReadDataFromArchive(ArchiveHandle *AH, int compression, +extern CompressorState *AllocateCompressor(Compress *compression, WriteFunc writeF); +extern void ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF); extern void WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, const void *data, size_t dLen); @@ -56,9 +50,9 @@ extern void EndCompressor(ArchiveHandle *AH, CompressorState *cs); typedef struct cfp cfp; -extern cfp *cfopen(const char *path, const char *mode, int compression); -extern cfp *cfopen_read(const char *path, const char *mode); -extern cfp *cfopen_write(const char *path, const char *mode, int compression); +extern cfp *cfopen(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_read(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_write(const char *path, const char *mode, Compress *compression); extern int cfread(void *ptr, int size, cfp *fp); extern int cfwrite(const void *ptr, int size, cfp *fp); extern int cfgetc(cfp *fp); @@ -67,4 +61,7 @@ extern int cfclose(cfp *fp); extern int cfeof(cfp *fp); extern const char *get_cfp_error(cfp *fp); +/* also used by tar */ +extern const char * compress_suffix(Compress *compression); + #endif diff --git a/src/bin/pg_dump/pg_backup.h b/src/bin/pg_dump/pg_backup.h index 9d0056a569..f2390b7937 100644 --- a/src/bin/pg_dump/pg_backup.h +++ b/src/bin/pg_dump/pg_backup.h @@ -72,6 +72,25 @@ typedef struct _connParams char *override_dbname; } ConnParams; +typedef enum +{ + COMPR_ALG_DEFAULT = -1, + COMPR_ALG_NONE, + COMPR_ALG_LIBZ, +} CompressionAlgorithm; +/* Should be called "method" or "library" ? */ + +typedef struct Compress { + CompressionAlgorithm alg; + int level; + /* Is a nondefault level set ? This is useful since different compression + * methods have different "default" levels. For now we assume the levels + * are all integer, though. + */ + bool level_set; +} Compress; + + typedef struct _restoreOptions { int createDB; /* Issue commands to create the database */ @@ -125,7 +144,7 @@ typedef struct _restoreOptions int noDataForFailedTables; int exit_on_error; - int compression; + Compress compression; int suppressDumpWarnings; /* Suppress output of WARNING entries * to stderr */ bool single_txn; @@ -281,7 +300,7 @@ extern Archive *OpenArchive(const char *FileSpec, const ArchiveFormat fmt); /* Create a new archive */ extern Archive *CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker); /* The --list option */ diff --git a/src/bin/pg_dump/pg_backup_archiver.c b/src/bin/pg_dump/pg_backup_archiver.c index 1f82c6499b..3eb6c55600 100644 --- a/src/bin/pg_dump/pg_backup_archiver.c +++ b/src/bin/pg_dump/pg_backup_archiver.c @@ -70,7 +70,7 @@ typedef struct _parallelReadyList static ArchiveHandle *_allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr); static void _getObjectDescription(PQExpBuffer buf, TocEntry *te); static void _printTocEntry(ArchiveHandle *AH, TocEntry *te, bool isData); @@ -98,7 +98,7 @@ static int _discoverArchiveFormat(ArchiveHandle *AH); static int RestoringToDB(ArchiveHandle *AH); static void dump_lo_buf(ArchiveHandle *AH); static void dumpTimestamp(ArchiveHandle *AH, const char *msg, time_t tim); -static void SetOutput(ArchiveHandle *AH, const char *filename, int compression); +static void SetOutput(ArchiveHandle *AH, const char *filename, Compress *compress); static OutputContext SaveOutput(ArchiveHandle *AH); static void RestoreOutput(ArchiveHandle *AH, OutputContext savedContext); @@ -238,7 +238,7 @@ setupRestoreWorker(Archive *AHX) /* Public */ Archive * CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker) { @@ -253,7 +253,9 @@ CreateArchive(const char *FileSpec, const ArchiveFormat fmt, Archive * OpenArchive(const char *FileSpec, const ArchiveFormat fmt) { - ArchiveHandle *AH = _allocAH(FileSpec, fmt, 0, true, archModeRead, setupRestoreWorker); + Compress compress = {0}; + ArchiveHandle *AH = _allocAH(FileSpec, fmt, &compress, true, archModeRead, + setupRestoreWorker); return (Archive *) AH; } @@ -382,7 +384,7 @@ RestoreArchive(Archive *AHX) * Make sure we won't need (de)compression we haven't got */ #ifndef HAVE_LIBZ - if (AH->compression != 0 && AH->PrintTocDataPtr != NULL) + if (AH->compression.alg != COMPR_ALG_NONE && AH->PrintTocDataPtr != NULL) { for (te = AH->toc->next; te != AH->toc; te = te->next) { @@ -457,8 +459,8 @@ RestoreArchive(Archive *AHX) * Setup the output file if necessary. */ sav = SaveOutput(AH); - if (ropt->filename || ropt->compression) - SetOutput(AH, ropt->filename, ropt->compression); + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) + SetOutput(AH, ropt->filename, &ropt->compression); ahprintf(AH, "--\n-- PostgreSQL database dump\n--\n\n"); @@ -738,7 +740,7 @@ RestoreArchive(Archive *AHX) */ AH->stage = STAGE_FINALIZING; - if (ropt->filename || ropt->compression) + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) RestoreOutput(AH, sav); if (ropt->useDB) @@ -1123,8 +1125,9 @@ PrintTOCSummary(Archive *AHX) char stamp_str[64]; sav = SaveOutput(AH); + Assert(ropt->compression.alg == COMPR_ALG_NONE); if (ropt->filename) - SetOutput(AH, ropt->filename, 0 /* no compression */ ); + SetOutput(AH, ropt->filename, &ropt->compression); if (strftime(stamp_str, sizeof(stamp_str), PGDUMP_STRFTIME_FMT, localtime(&AH->createDate)) == 0) @@ -1133,7 +1136,7 @@ PrintTOCSummary(Archive *AHX) ahprintf(AH, ";\n; Archive created at %s\n", stamp_str); ahprintf(AH, "; dbname: %s\n; TOC Entries: %d\n; Compression: %d\n", sanitize_line(AH->archdbname, false), - AH->tocCount, AH->compression); + AH->tocCount, AH->compression.alg); switch (AH->format) { @@ -1487,7 +1490,7 @@ archprintf(Archive *AH, const char *fmt,...) *******************************/ static void -SetOutput(ArchiveHandle *AH, const char *filename, int compression) +SetOutput(ArchiveHandle *AH, const char *filename, Compress *compression) { int fn; @@ -1510,12 +1513,12 @@ SetOutput(ArchiveHandle *AH, const char *filename, int compression) /* If compression explicitly requested, use gzopen */ #ifdef HAVE_LIBZ - if (compression != 0) + if (compression->alg != COMPR_ALG_NONE) { char fmode[14]; /* Don't use PG_BINARY_x since this is zlib */ - sprintf(fmode, "wb%d", compression); + sprintf(fmode, "wb%d", compression->level); if (fn >= 0) AH->OF = gzdopen(dup(fn), fmode); else @@ -2259,7 +2262,7 @@ _discoverArchiveFormat(ArchiveHandle *AH) */ static ArchiveHandle * _allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr) { ArchiveHandle *AH; @@ -2310,7 +2313,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, AH->toc->prev = AH->toc; AH->mode = mode; - AH->compression = compression; + AH->compression = *compression; AH->dosync = dosync; memset(&(AH->sqlparse), 0, sizeof(AH->sqlparse)); @@ -2325,7 +2328,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, * Force stdin/stdout into binary mode if that is what we are using. */ #ifdef WIN32 - if ((fmt != archNull || compression != 0) && + if ((fmt != archNull || compression->alg != COMPR_ALG_NONE) && (AH->fSpec == NULL || strcmp(AH->fSpec, "") == 0)) { if (mode == archModeWrite) @@ -3741,7 +3744,7 @@ WriteHead(ArchiveHandle *AH) AH->WriteBytePtr(AH, AH->intSize); AH->WriteBytePtr(AH, AH->offSize); AH->WriteBytePtr(AH, AH->format); - WriteInt(AH, AH->compression); + WriteInt(AH, AH->compression.alg); crtm = *localtime(&AH->createDate); WriteInt(AH, crtm.tm_sec); WriteInt(AH, crtm.tm_min); @@ -3816,15 +3819,15 @@ ReadHead(ArchiveHandle *AH) if (AH->version >= K_VERS_1_2) { if (AH->version < K_VERS_1_4) - AH->compression = AH->ReadBytePtr(AH); + AH->compression.alg = AH->ReadBytePtr(AH); else - AH->compression = ReadInt(AH); + AH->compression.alg = ReadInt(AH); } else - AH->compression = Z_DEFAULT_COMPRESSION; + AH->compression.alg = Z_DEFAULT_COMPRESSION; #ifndef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) pg_log_warning("archive is compressed, but this installation does not support compression -- no data will be available"); #endif diff --git a/src/bin/pg_dump/pg_backup_archiver.h b/src/bin/pg_dump/pg_backup_archiver.h index a8ea5c7eae..6e033d040e 100644 --- a/src/bin/pg_dump/pg_backup_archiver.h +++ b/src/bin/pg_dump/pg_backup_archiver.h @@ -47,7 +47,8 @@ #define GZWRITE(p, s, n, fh) (fwrite(p, s, n, fh) * (s)) #define GZREAD(p, s, n, fh) fread(p, s, n, fh) #define GZEOF(fh) feof(fh) -/* this is just the redefinition of a libz constant */ +/* this is just the redefinition of a libz constant, in case zlib isn't + * available */ #define Z_DEFAULT_COMPRESSION (-1) typedef struct _z_stream @@ -329,14 +330,7 @@ struct _archiveHandle DumpId *tableDataId; /* TABLE DATA ids, indexed by table dumpId */ struct _tocEntry *currToc; /* Used when dumping data */ - int compression; /*--------- - * Compression requested on open(). - * Possible values for compression: - * -1 Z_DEFAULT_COMPRESSION - * 0 COMPRESSION_NONE - * 1-9 levels for gzip compression - *--------- - */ + Compress compression; /* Compression requested on open */ bool dosync; /* data requested to be synced on sight */ ArchiveMode mode; /* File mode - r or w */ void *formatData; /* Header data specific to file format */ diff --git a/src/bin/pg_dump/pg_backup_custom.c b/src/bin/pg_dump/pg_backup_custom.c index 77d402c323..55a887a236 100644 --- a/src/bin/pg_dump/pg_backup_custom.c +++ b/src/bin/pg_dump/pg_backup_custom.c @@ -298,7 +298,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) _WriteByte(AH, BLK_DATA); /* Block type */ WriteInt(AH, te->dumpId); /* For sanity check */ - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -377,7 +377,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) WriteInt(AH, oid); - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -566,7 +566,7 @@ _PrintTocData(ArchiveHandle *AH, TocEntry *te) static void _PrintData(ArchiveHandle *AH) { - ReadDataFromArchive(AH, AH->compression, _CustomReadFunc); + ReadDataFromArchive(AH, _CustomReadFunc); } static void diff --git a/src/bin/pg_dump/pg_backup_directory.c b/src/bin/pg_dump/pg_backup_directory.c index 650b542fce..8bf869c6ca 100644 --- a/src/bin/pg_dump/pg_backup_directory.c +++ b/src/bin/pg_dump/pg_backup_directory.c @@ -202,7 +202,7 @@ InitArchiveFmt_Directory(ArchiveHandle *AH) setFilePath(AH, fname, "toc.dat"); - tocFH = cfopen_read(fname, PG_BINARY_R); + tocFH = cfopen_read(fname, PG_BINARY_R, &AH->compression); if (tocFH == NULL) fatal("could not open input file \"%s\": %m", fname); @@ -327,7 +327,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) setFilePath(AH, fname, tctx->filename); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -388,7 +388,7 @@ _PrintFileData(ArchiveHandle *AH, char *filename) if (!filename) return; - cfp = cfopen_read(filename, PG_BINARY_R); + cfp = cfopen_read(filename, PG_BINARY_R, &AH->compression); if (!cfp) fatal("could not open input file \"%s\": %m", filename); @@ -435,12 +435,13 @@ _LoadBlobs(ArchiveHandle *AH) lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; char line[MAXPGPATH]; + Compress nocompression = {0}; StartRestoreBlobs(AH); setFilePath(AH, fname, "blobs.toc"); - ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R); + ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R, &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open large object TOC file \"%s\" for input: %m", @@ -573,6 +574,7 @@ _CloseArchive(ArchiveHandle *AH) { cfp *tocFH; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "toc.dat"); @@ -580,7 +582,7 @@ _CloseArchive(ArchiveHandle *AH) ctx->pstate = ParallelBackupStart(AH); /* The TOC is always created uncompressed */ - tocFH = cfopen_write(fname, PG_BINARY_W, 0); + tocFH = cfopen_write(fname, PG_BINARY_W, &nocompression); if (tocFH == NULL) fatal("could not open output file \"%s\": %m", fname); ctx->dataFH = tocFH; @@ -639,11 +641,12 @@ _StartBlobs(ArchiveHandle *AH, TocEntry *te) { lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "blobs.toc"); /* The blob TOC file is never compressed */ - ctx->blobsTocFH = cfopen_write(fname, "ab", 0); + ctx->blobsTocFH = cfopen_write(fname, "ab", &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -661,7 +664,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) snprintf(fname, MAXPGPATH, "%s/blob_%u.dat", ctx->directory, oid); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); diff --git a/src/bin/pg_dump/pg_backup_tar.c b/src/bin/pg_dump/pg_backup_tar.c index 61c9c87a9f..4ba79ab924 100644 --- a/src/bin/pg_dump/pg_backup_tar.c +++ b/src/bin/pg_dump/pg_backup_tar.c @@ -39,6 +39,7 @@ #include "pg_backup_archiver.h" #include "pg_backup_tar.h" #include "pg_backup_utils.h" +#include "compress_io.h" #include "pgtar.h" static void _ArchiveEntry(ArchiveHandle *AH, TocEntry *te); @@ -196,10 +197,10 @@ InitArchiveFmt_Tar(ArchiveHandle *AH) /* * We don't support compression because reading the files back is not - * possible since gzdopen uses buffered IO which totally screws file + * possible since gzdopen uses buffered IO which totally screws file XXX * positioning. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) fatal("compression is not supported by tar archive format"); } else @@ -254,14 +255,8 @@ _ArchiveEntry(ArchiveHandle *AH, TocEntry *te) ctx = (lclTocEntry *) pg_malloc0(sizeof(lclTocEntry)); if (te->dataDumper != NULL) { -#ifdef HAVE_LIBZ - if (AH->compression == 0) - sprintf(fn, "%d.dat", te->dumpId); - else - sprintf(fn, "%d.dat.gz", te->dumpId); -#else - sprintf(fn, "%d.dat", te->dumpId); -#endif + const char *suffix = compress_suffix(&AH->compression); + sprintf(fn, "%d.dat%s", te->dumpId, suffix); ctx->filename = pg_strdup(fn); } else @@ -352,7 +347,7 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression == 0) + if (AH->compression.alg == COMPR_ALG_NONE) tm->nFH = ctx->tarFH; else fatal("compression is not supported by tar archive format"); @@ -413,9 +408,9 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) { - sprintf(fmode, "wb%d", AH->compression); + sprintf(fmode, "wb%d", AH->compression.level); tm->zFH = gzdopen(dup(fileno(tm->tmpFH)), fmode); if (tm->zFH == NULL) fatal("could not open temporary file"); @@ -443,7 +438,7 @@ tarClose(ArchiveHandle *AH, TAR_MEMBER *th) /* * Close the GZ file since we dup'd. This will flush the buffers. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) if (GZCLOSE(th->zFH) != 0) fatal("could not close tar member"); @@ -868,7 +863,7 @@ _CloseArchive(ArchiveHandle *AH) memcpy(ropt, AH->public.ropt, sizeof(RestoreOptions)); ropt->filename = NULL; ropt->dropSchema = 1; - ropt->compression = 0; + ropt->compression.alg = COMPR_ALG_NONE; ropt->superuser = NULL; ropt->suppressDumpWarnings = true; @@ -952,16 +947,12 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) lclContext *ctx = (lclContext *) AH->formatData; lclTocEntry *tctx = (lclTocEntry *) te->formatData; char fname[255]; - char *sfx; + const char *sfx; if (oid == 0) fatal("invalid OID for large object (%u)", oid); - if (AH->compression != 0) - sfx = ".gz"; - else - sfx = ""; - + sfx = compress_suffix(&AH->compression); sprintf(fname, "blob_%u.dat%s", oid, sfx); tarPrintf(ctx->blobToc, "%u %s\n", oid, fname); diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c index 1ab98a2286..4cbc79aedc 100644 --- a/src/bin/pg_dump/pg_dump.c +++ b/src/bin/pg_dump/pg_dump.c @@ -59,6 +59,7 @@ #include "getopt_long.h" #include "libpq/libpq-fs.h" #include "parallel.h" +#include "compress_io.h" #include "pg_backup_db.h" #include "pg_backup_utils.h" #include "pg_dump.h" @@ -297,6 +298,82 @@ static void setupDumpWorker(Archive *AHX); static TableInfo *getRootTableInfo(TableInfo *tbinfo); +/* Parse the string into compression options */ +static void +parse_compression(const char *optarg, Compress *compress) +{ + if (optarg[0] == '0' && optarg[1] == '\0') + compress->alg = COMPR_ALG_NONE; + else if ((optarg[0] > '0' && optarg[0] <= '9') || + optarg[0] == '-') + { + compress->alg = COMPR_ALG_LIBZ; + compress->level_set = true; + compress->level = atoi(optarg); + if (optarg[1] != '\0') + { + pg_log_error("compression level must be in range 0..9"); + exit_nicely(1); + } + } + else + { + /* Parse a more flexible string like level=3 alg=zlib opts=long */ + for (;;) + { + char *eq = strchr(optarg, '='); + int len; + + if (eq == NULL) + { + pg_log_error("compression options must be key=value: %s", optarg); + exit_nicely(1); + } + + len = eq - optarg; + if (strncmp(optarg, "alg", len) == 0) + { + if (strchr(eq, ' ')) + len = strchr(eq, ' ') - eq - 1; + else + len = strlen(eq) - len; + if (strncmp(1+eq, "zlib", len) == 0 || + strncmp(1+eq, "libz", len) == 0) + compress->alg = COMPR_ALG_LIBZ; + else + { + pg_log_error("unknown compression algorithm: %s", 1+eq); + exit_nicely(1); + } + } + else if (strncmp(optarg, "level", len) == 0) + { + compress->level = atoi(1+eq); + compress->level_set = true; + } + else + { + pg_log_error("unknown compression setting: %s", optarg); + exit_nicely(1); + } + + optarg = strchr(eq, ' '); + if (!optarg++) + break; + } + + if (!compress->level_set) + { + const int default_compress_level[] = { + 0, /* COMPR_ALG_NONE */ + Z_DEFAULT_COMPRESSION, /* COMPR_ALG_ZLIB */ + }; + + compress->level = default_compress_level[compress->alg]; + } + } +} + int main(int argc, char **argv) { @@ -319,7 +396,7 @@ main(int argc, char **argv) char *use_role = NULL; long rowsPerInsert; int numWorkers = 1; - int compressLevel = -1; + Compress compress = { .alg = COMPR_ALG_DEFAULT }; int plainText = 0; ArchiveFormat archiveFormat = archUnknown; ArchiveMode archiveMode; @@ -532,12 +609,7 @@ main(int argc, char **argv) break; case 'Z': /* Compression Level */ - compressLevel = atoi(optarg); - if (compressLevel < 0 || compressLevel > 9) - { - pg_log_error("compression level must be in range 0..9"); - exit_nicely(1); - } + parse_compression(optarg, &compress); break; case 0: @@ -679,20 +751,28 @@ main(int argc, char **argv) plainText = 1; /* Custom and directory formats are compressed by default, others not */ - if (compressLevel == -1) + if (compress.alg == COMPR_ALG_DEFAULT) { -#ifdef HAVE_LIBZ if (archiveFormat == archCustom || archiveFormat == archDirectory) - compressLevel = Z_DEFAULT_COMPRESSION; - else + { +#ifdef HAVE_LIBZ + compress.alg = COMPR_ALG_LIBZ; + compress.level = Z_DEFAULT_COMPRESSION; #endif - compressLevel = 0; + } + else + { + compress.alg = COMPR_ALG_NONE; + compress.level = 0; + } } #ifndef HAVE_LIBZ - if (compressLevel != 0) + if (compress.alg == COMPR_ALG_LIBZ) + { pg_log_warning("requested compression not available in this installation -- archive will be uncompressed"); - compressLevel = 0; + compress.alg = 0; + } #endif /* @@ -723,7 +803,7 @@ main(int argc, char **argv) fatal("option --index-collation-versions-unknown only works in binary upgrade mode"); /* Open the output file */ - fout = CreateArchive(filename, archiveFormat, compressLevel, dosync, + fout = CreateArchive(filename, archiveFormat, &compress, dosync, archiveMode, setupDumpWorker); /* Make dump options accessible right away */ @@ -957,10 +1037,7 @@ main(int argc, char **argv) ropt->sequence_data = dopt.sequence_data; ropt->binary_upgrade = dopt.binary_upgrade; - if (compressLevel == -1) - ropt->compression = 0; - else - ropt->compression = compressLevel; + ropt->compression = compress; ropt->suppressDumpWarnings = true; /* We've already shown them */ -- 2.17.0 --GRPZ8SYKNexpdSJ7 Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="0004-struct-compressLibs.patch" ^ permalink raw reply [nested|flat] 23+ messages in thread
* [PATCH 03/20] Support multiple compression algs/levels/opts.. @ 2020-12-22 06:23 Justin Pryzby <[email protected]> 0 siblings, 0 replies; 23+ messages in thread From: Justin Pryzby @ 2020-12-22 06:23 UTC (permalink / raw) The existing implementation abtracts compressed and noncompressed I/O. This preliminary commit is intended to also allow for multiple compression algorithms. --- src/bin/pg_dump/compress_io.c | 220 +++++++++++--------------- src/bin/pg_dump/compress_io.h | 19 +-- src/bin/pg_dump/pg_backup.h | 23 ++- src/bin/pg_dump/pg_backup_archiver.c | 45 +++--- src/bin/pg_dump/pg_backup_archiver.h | 12 +- src/bin/pg_dump/pg_backup_custom.c | 6 +- src/bin/pg_dump/pg_backup_directory.c | 17 +- src/bin/pg_dump/pg_backup_tar.c | 33 ++-- src/bin/pg_dump/pg_dump.c | 115 +++++++++++--- 9 files changed, 272 insertions(+), 218 deletions(-) diff --git a/src/bin/pg_dump/compress_io.c b/src/bin/pg_dump/compress_io.c index 6a428978d4..db16fd33f2 100644 --- a/src/bin/pg_dump/compress_io.c +++ b/src/bin/pg_dump/compress_io.c @@ -74,12 +74,9 @@ struct CompressorState #endif }; -static void ParseCompressionOption(int compression, CompressionAlgorithm *alg, - int *level); - /* Routines that support zlib compressed data I/O */ #ifdef HAVE_LIBZ -static void InitCompressorZlib(CompressorState *cs, int level); +static void InitCompressorZlib(CompressorState *cs, Compress *compress); static void DeflateCompressorZlib(ArchiveHandle *AH, CompressorState *cs, bool flush); static void ReadDataFromArchiveZlib(ArchiveHandle *AH, ReadFunc readF); @@ -93,58 +90,36 @@ static void ReadDataFromArchiveNone(ArchiveHandle *AH, ReadFunc readF); static void WriteDataToArchiveNone(ArchiveHandle *AH, CompressorState *cs, const char *data, size_t dLen); -/* - * Interprets a numeric 'compression' value. The algorithm implied by the - * value (zlib or none at the moment), is returned in *alg, and the - * zlib compression level in *level. - */ -static void -ParseCompressionOption(int compression, CompressionAlgorithm *alg, int *level) -{ - if (compression == Z_DEFAULT_COMPRESSION || - (compression > 0 && compression <= 9)) - *alg = COMPR_ALG_LIBZ; - else if (compression == 0) - *alg = COMPR_ALG_NONE; - else - { - fatal("invalid compression code: %d", compression); - *alg = COMPR_ALG_NONE; /* keep compiler quiet */ - } - - /* The level is just the passed-in value. */ - if (level) - *level = compression; -} - /* Public interface routines */ /* Allocate a new compressor */ CompressorState * -AllocateCompressor(int compression, WriteFunc writeF) +AllocateCompressor(Compress *compression, WriteFunc writeF) { CompressorState *cs; - CompressionAlgorithm alg; - int level; - - ParseCompressionOption(compression, &alg, &level); - -#ifndef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - fatal("not built with zlib support"); -#endif cs = (CompressorState *) pg_malloc0(sizeof(CompressorState)); cs->writeF = writeF; - cs->comprAlg = alg; + cs->comprAlg = compression->alg; /* * Perform compression algorithm specific initialization. */ + Assert (compression->alg != COMPR_ALG_DEFAULT); + switch (compression->alg) + { #ifdef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - InitCompressorZlib(cs, level); + case COMPR_ALG_LIBZ: + InitCompressorZlib(cs, compression); + break; #endif + case COMPR_ALG_NONE: + /* Do nothing */ + break; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } return cs; } @@ -154,21 +129,21 @@ AllocateCompressor(int compression, WriteFunc writeF) * out with ahwrite(). */ void -ReadDataFromArchive(ArchiveHandle *AH, int compression, ReadFunc readF) +ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF) { - CompressionAlgorithm alg; - - ParseCompressionOption(compression, &alg, NULL); - - if (alg == COMPR_ALG_NONE) - ReadDataFromArchiveNone(AH, readF); - if (alg == COMPR_ALG_LIBZ) + switch (AH->compression.alg) { + case COMPR_ALG_NONE: + ReadDataFromArchiveNone(AH, readF); + break; #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: ReadDataFromArchiveZlib(AH, readF); -#else - fatal("not built with zlib support"); + break; #endif + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -181,16 +156,18 @@ WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, { switch (cs->comprAlg) { - case COMPR_ALG_LIBZ: #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: WriteDataToArchiveZlib(AH, cs, data, dLen); -#else - fatal("not built with zlib support"); -#endif break; +#endif case COMPR_ALG_NONE: WriteDataToArchiveNone(AH, cs, data, dLen); break; + + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -215,7 +192,7 @@ EndCompressor(ArchiveHandle *AH, CompressorState *cs) */ static void -InitCompressorZlib(CompressorState *cs, int level) +InitCompressorZlib(CompressorState *cs, Compress *compress) { z_streamp zp; @@ -232,7 +209,7 @@ InitCompressorZlib(CompressorState *cs, int level) cs->zlibOut = (char *) pg_malloc(ZLIB_OUT_SIZE + 1); cs->zlibOutSize = ZLIB_OUT_SIZE; - if (deflateInit(zp, level) != Z_OK) + if (deflateInit(zp, compress->level) != Z_OK) fatal("could not initialize compression library: %s", zp->msg); @@ -424,9 +401,7 @@ struct cfp #endif }; -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix); -#endif /* free() without changing errno; useful in several places below */ static void @@ -442,34 +417,31 @@ free_keep_errno(void *p) * Open a file for reading. 'path' is the file to open, and 'mode' should * be either "r" or "rb". * - * If the file at 'path' does not exist, we append the ".gz" suffix (if 'path' - * doesn't already have it) and try again. So if you pass "foo" as 'path', + * If the file at 'path' does not exist, we search with compressed suffix (if 'path' + * doesn't already have one) and try again. So if you pass "foo" as 'path', * this will open either "foo" or "foo.gz". * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_read(const char *path, const char *mode) +cfopen_read(const char *path, const char *mode, Compress *compression) { cfp *fp; -#ifdef HAVE_LIBZ if (hasSuffix(path, ".gz")) - fp = cfopen(path, mode, 1); + fp = cfopen(path, mode, compression); else -#endif { - fp = cfopen(path, mode, 0); -#ifdef HAVE_LIBZ + fp = cfopen(path, mode, compression); if (fp == NULL) { char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); - fp = cfopen(fname, mode, 1); + fname = psprintf("%s%s", path, suffix); + fp = cfopen(fname, mode, compression); free_keep_errno(fname); } -#endif } return fp; } @@ -479,31 +451,26 @@ cfopen_read(const char *path, const char *mode) * be a filemode as accepted by fopen() and gzopen() that indicates writing * ("w", "wb", "a", or "ab"). * - * If 'compression' is non-zero, a gzip compressed stream is opened, and - * 'compression' indicates the compression level used. The ".gz" suffix - * is automatically added to 'path' in that case. + * Use compression if specified. + * The appropriate suffix is automatically added to 'path' in that case. * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_write(const char *path, const char *mode, int compression) +cfopen_write(const char *path, const char *mode, Compress *compression) { cfp *fp; - if (compression == 0) - fp = cfopen(path, mode, 0); + if (compression->alg == COMPR_ALG_NONE) + fp = cfopen(path, mode, compression); else { -#ifdef HAVE_LIBZ char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); + fname = psprintf("%s%s", path, suffix); fp = cfopen(fname, mode, compression); free_keep_errno(fname); -#else - fatal("not built with zlib support"); - fp = NULL; /* keep compiler quiet */ -#endif } return fp; } @@ -515,20 +482,21 @@ cfopen_write(const char *path, const char *mode, int compression) * On failure, return NULL with an error code in errno. */ cfp * -cfopen(const char *path, const char *mode, int compression) +cfopen(const char *path, const char *mode, Compress *compression) { - cfp *fp = pg_malloc(sizeof(cfp)); + cfp *fp = pg_malloc0(sizeof(cfp)); - if (compression != 0) + switch (compression->alg) { #ifdef HAVE_LIBZ - if (compression != Z_DEFAULT_COMPRESSION) + case COMPR_ALG_LIBZ: + if (compression->level != Z_DEFAULT_COMPRESSION) { /* user has specified a compression level, so tell zlib to use it */ char mode_compression[32]; snprintf(mode_compression, sizeof(mode_compression), "%s%d", - mode, compression); + mode, compression->level); fp->compressedfp = gzopen(path, mode_compression); } else @@ -537,30 +505,27 @@ cfopen(const char *path, const char *mode, int compression) fp->compressedfp = gzopen(path, mode); } - fp->uncompressedfp = NULL; if (fp->compressedfp == NULL) { free_keep_errno(fp); fp = NULL; } -#else - fatal("not built with zlib support"); -#endif - } - else - { -#ifdef HAVE_LIBZ - fp->compressedfp = NULL; + return fp; #endif + + case COMPR_ALG_NONE: fp->uncompressedfp = fopen(path, mode); if (fp->uncompressedfp == NULL) { free_keep_errno(fp); fp = NULL; } - } + return fp; - return fp; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } } @@ -584,14 +549,13 @@ cfread(void *ptr, int size, cfp *fp) fatal("could not read from input file: %s", errnum == Z_ERRNO ? strerror(errno) : errmsg); } + return ret; } - else #endif - { - ret = fread(ptr, 1, size, fp->uncompressedfp); - if (ret != size && !feof(fp->uncompressedfp)) - READ_ERROR_EXIT(fp->uncompressedfp); - } + + ret = fread(ptr, 1, size, fp->uncompressedfp); + if (ret != size && !feof(fp->uncompressedfp)) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -601,9 +565,8 @@ cfwrite(const void *ptr, int size, cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzwrite(fp->compressedfp, ptr, size); - else #endif - return fwrite(ptr, 1, size, fp->uncompressedfp); + return fwrite(ptr, 1, size, fp->uncompressedfp); } int @@ -622,15 +585,12 @@ cfgetc(cfp *fp) else fatal("could not read from input file: end of file"); } + return ret; } - else #endif - { - ret = fgetc(fp->uncompressedfp); - if (ret == EOF) - READ_ERROR_EXIT(fp->uncompressedfp); - } - + ret = fgetc(fp->uncompressedfp); + if (ret == EOF) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -640,9 +600,8 @@ cfgets(cfp *fp, char *buf, int len) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzgets(fp->compressedfp, buf, len); - else #endif - return fgets(buf, len, fp->uncompressedfp); + return fgets(buf, len, fp->uncompressedfp); } int @@ -660,15 +619,13 @@ cfclose(cfp *fp) { result = gzclose(fp->compressedfp); fp->compressedfp = NULL; + return result; } - else #endif - { - result = fclose(fp->uncompressedfp); - fp->uncompressedfp = NULL; - } - free_keep_errno(fp); + result = fclose(fp->uncompressedfp); + fp->uncompressedfp = NULL; + free_keep_errno(fp); return result; } @@ -678,9 +635,9 @@ cfeof(cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzeof(fp->compressedfp); - else #endif - return feof(fp->uncompressedfp); + + return feof(fp->uncompressedfp); } const char * @@ -699,7 +656,6 @@ get_cfp_error(cfp *fp) return strerror(errno); } -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix) { @@ -714,4 +670,18 @@ hasSuffix(const char *filename, const char *suffix) suffixlen) == 0; } -#endif +/* + * Return a string for the given AH's compression. + * The string is statically allocated. + */ +const char * +compress_suffix(Compress *compression) +{ + switch (compression->alg) + { + case COMPR_ALG_LIBZ: + return ".gz"; + default: + return ""; + } +} diff --git a/src/bin/pg_dump/compress_io.h b/src/bin/pg_dump/compress_io.h index d2e6e1b854..2c073676eb 100644 --- a/src/bin/pg_dump/compress_io.h +++ b/src/bin/pg_dump/compress_io.h @@ -21,12 +21,6 @@ #define ZLIB_OUT_SIZE 4096 #define ZLIB_IN_SIZE 4096 -typedef enum -{ - COMPR_ALG_NONE, - COMPR_ALG_LIBZ -} CompressionAlgorithm; - /* Prototype for callback function to WriteDataToArchive() */ typedef void (*WriteFunc) (ArchiveHandle *AH, const char *buf, size_t len); @@ -46,8 +40,8 @@ typedef size_t (*ReadFunc) (ArchiveHandle *AH, char **buf, size_t *buflen); /* struct definition appears in compress_io.c */ typedef struct CompressorState CompressorState; -extern CompressorState *AllocateCompressor(int compression, WriteFunc writeF); -extern void ReadDataFromArchive(ArchiveHandle *AH, int compression, +extern CompressorState *AllocateCompressor(Compress *compression, WriteFunc writeF); +extern void ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF); extern void WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, const void *data, size_t dLen); @@ -56,9 +50,9 @@ extern void EndCompressor(ArchiveHandle *AH, CompressorState *cs); typedef struct cfp cfp; -extern cfp *cfopen(const char *path, const char *mode, int compression); -extern cfp *cfopen_read(const char *path, const char *mode); -extern cfp *cfopen_write(const char *path, const char *mode, int compression); +extern cfp *cfopen(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_read(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_write(const char *path, const char *mode, Compress *compression); extern int cfread(void *ptr, int size, cfp *fp); extern int cfwrite(const void *ptr, int size, cfp *fp); extern int cfgetc(cfp *fp); @@ -67,4 +61,7 @@ extern int cfclose(cfp *fp); extern int cfeof(cfp *fp); extern const char *get_cfp_error(cfp *fp); +/* also used by tar */ +extern const char * compress_suffix(Compress *compression); + #endif diff --git a/src/bin/pg_dump/pg_backup.h b/src/bin/pg_dump/pg_backup.h index 9d0056a569..f2390b7937 100644 --- a/src/bin/pg_dump/pg_backup.h +++ b/src/bin/pg_dump/pg_backup.h @@ -72,6 +72,25 @@ typedef struct _connParams char *override_dbname; } ConnParams; +typedef enum +{ + COMPR_ALG_DEFAULT = -1, + COMPR_ALG_NONE, + COMPR_ALG_LIBZ, +} CompressionAlgorithm; +/* Should be called "method" or "library" ? */ + +typedef struct Compress { + CompressionAlgorithm alg; + int level; + /* Is a nondefault level set ? This is useful since different compression + * methods have different "default" levels. For now we assume the levels + * are all integer, though. + */ + bool level_set; +} Compress; + + typedef struct _restoreOptions { int createDB; /* Issue commands to create the database */ @@ -125,7 +144,7 @@ typedef struct _restoreOptions int noDataForFailedTables; int exit_on_error; - int compression; + Compress compression; int suppressDumpWarnings; /* Suppress output of WARNING entries * to stderr */ bool single_txn; @@ -281,7 +300,7 @@ extern Archive *OpenArchive(const char *FileSpec, const ArchiveFormat fmt); /* Create a new archive */ extern Archive *CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker); /* The --list option */ diff --git a/src/bin/pg_dump/pg_backup_archiver.c b/src/bin/pg_dump/pg_backup_archiver.c index 1f82c6499b..3eb6c55600 100644 --- a/src/bin/pg_dump/pg_backup_archiver.c +++ b/src/bin/pg_dump/pg_backup_archiver.c @@ -70,7 +70,7 @@ typedef struct _parallelReadyList static ArchiveHandle *_allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr); static void _getObjectDescription(PQExpBuffer buf, TocEntry *te); static void _printTocEntry(ArchiveHandle *AH, TocEntry *te, bool isData); @@ -98,7 +98,7 @@ static int _discoverArchiveFormat(ArchiveHandle *AH); static int RestoringToDB(ArchiveHandle *AH); static void dump_lo_buf(ArchiveHandle *AH); static void dumpTimestamp(ArchiveHandle *AH, const char *msg, time_t tim); -static void SetOutput(ArchiveHandle *AH, const char *filename, int compression); +static void SetOutput(ArchiveHandle *AH, const char *filename, Compress *compress); static OutputContext SaveOutput(ArchiveHandle *AH); static void RestoreOutput(ArchiveHandle *AH, OutputContext savedContext); @@ -238,7 +238,7 @@ setupRestoreWorker(Archive *AHX) /* Public */ Archive * CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker) { @@ -253,7 +253,9 @@ CreateArchive(const char *FileSpec, const ArchiveFormat fmt, Archive * OpenArchive(const char *FileSpec, const ArchiveFormat fmt) { - ArchiveHandle *AH = _allocAH(FileSpec, fmt, 0, true, archModeRead, setupRestoreWorker); + Compress compress = {0}; + ArchiveHandle *AH = _allocAH(FileSpec, fmt, &compress, true, archModeRead, + setupRestoreWorker); return (Archive *) AH; } @@ -382,7 +384,7 @@ RestoreArchive(Archive *AHX) * Make sure we won't need (de)compression we haven't got */ #ifndef HAVE_LIBZ - if (AH->compression != 0 && AH->PrintTocDataPtr != NULL) + if (AH->compression.alg != COMPR_ALG_NONE && AH->PrintTocDataPtr != NULL) { for (te = AH->toc->next; te != AH->toc; te = te->next) { @@ -457,8 +459,8 @@ RestoreArchive(Archive *AHX) * Setup the output file if necessary. */ sav = SaveOutput(AH); - if (ropt->filename || ropt->compression) - SetOutput(AH, ropt->filename, ropt->compression); + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) + SetOutput(AH, ropt->filename, &ropt->compression); ahprintf(AH, "--\n-- PostgreSQL database dump\n--\n\n"); @@ -738,7 +740,7 @@ RestoreArchive(Archive *AHX) */ AH->stage = STAGE_FINALIZING; - if (ropt->filename || ropt->compression) + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) RestoreOutput(AH, sav); if (ropt->useDB) @@ -1123,8 +1125,9 @@ PrintTOCSummary(Archive *AHX) char stamp_str[64]; sav = SaveOutput(AH); + Assert(ropt->compression.alg == COMPR_ALG_NONE); if (ropt->filename) - SetOutput(AH, ropt->filename, 0 /* no compression */ ); + SetOutput(AH, ropt->filename, &ropt->compression); if (strftime(stamp_str, sizeof(stamp_str), PGDUMP_STRFTIME_FMT, localtime(&AH->createDate)) == 0) @@ -1133,7 +1136,7 @@ PrintTOCSummary(Archive *AHX) ahprintf(AH, ";\n; Archive created at %s\n", stamp_str); ahprintf(AH, "; dbname: %s\n; TOC Entries: %d\n; Compression: %d\n", sanitize_line(AH->archdbname, false), - AH->tocCount, AH->compression); + AH->tocCount, AH->compression.alg); switch (AH->format) { @@ -1487,7 +1490,7 @@ archprintf(Archive *AH, const char *fmt,...) *******************************/ static void -SetOutput(ArchiveHandle *AH, const char *filename, int compression) +SetOutput(ArchiveHandle *AH, const char *filename, Compress *compression) { int fn; @@ -1510,12 +1513,12 @@ SetOutput(ArchiveHandle *AH, const char *filename, int compression) /* If compression explicitly requested, use gzopen */ #ifdef HAVE_LIBZ - if (compression != 0) + if (compression->alg != COMPR_ALG_NONE) { char fmode[14]; /* Don't use PG_BINARY_x since this is zlib */ - sprintf(fmode, "wb%d", compression); + sprintf(fmode, "wb%d", compression->level); if (fn >= 0) AH->OF = gzdopen(dup(fn), fmode); else @@ -2259,7 +2262,7 @@ _discoverArchiveFormat(ArchiveHandle *AH) */ static ArchiveHandle * _allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr) { ArchiveHandle *AH; @@ -2310,7 +2313,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, AH->toc->prev = AH->toc; AH->mode = mode; - AH->compression = compression; + AH->compression = *compression; AH->dosync = dosync; memset(&(AH->sqlparse), 0, sizeof(AH->sqlparse)); @@ -2325,7 +2328,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, * Force stdin/stdout into binary mode if that is what we are using. */ #ifdef WIN32 - if ((fmt != archNull || compression != 0) && + if ((fmt != archNull || compression->alg != COMPR_ALG_NONE) && (AH->fSpec == NULL || strcmp(AH->fSpec, "") == 0)) { if (mode == archModeWrite) @@ -3741,7 +3744,7 @@ WriteHead(ArchiveHandle *AH) AH->WriteBytePtr(AH, AH->intSize); AH->WriteBytePtr(AH, AH->offSize); AH->WriteBytePtr(AH, AH->format); - WriteInt(AH, AH->compression); + WriteInt(AH, AH->compression.alg); crtm = *localtime(&AH->createDate); WriteInt(AH, crtm.tm_sec); WriteInt(AH, crtm.tm_min); @@ -3816,15 +3819,15 @@ ReadHead(ArchiveHandle *AH) if (AH->version >= K_VERS_1_2) { if (AH->version < K_VERS_1_4) - AH->compression = AH->ReadBytePtr(AH); + AH->compression.alg = AH->ReadBytePtr(AH); else - AH->compression = ReadInt(AH); + AH->compression.alg = ReadInt(AH); } else - AH->compression = Z_DEFAULT_COMPRESSION; + AH->compression.alg = Z_DEFAULT_COMPRESSION; #ifndef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) pg_log_warning("archive is compressed, but this installation does not support compression -- no data will be available"); #endif diff --git a/src/bin/pg_dump/pg_backup_archiver.h b/src/bin/pg_dump/pg_backup_archiver.h index a8ea5c7eae..6e033d040e 100644 --- a/src/bin/pg_dump/pg_backup_archiver.h +++ b/src/bin/pg_dump/pg_backup_archiver.h @@ -47,7 +47,8 @@ #define GZWRITE(p, s, n, fh) (fwrite(p, s, n, fh) * (s)) #define GZREAD(p, s, n, fh) fread(p, s, n, fh) #define GZEOF(fh) feof(fh) -/* this is just the redefinition of a libz constant */ +/* this is just the redefinition of a libz constant, in case zlib isn't + * available */ #define Z_DEFAULT_COMPRESSION (-1) typedef struct _z_stream @@ -329,14 +330,7 @@ struct _archiveHandle DumpId *tableDataId; /* TABLE DATA ids, indexed by table dumpId */ struct _tocEntry *currToc; /* Used when dumping data */ - int compression; /*--------- - * Compression requested on open(). - * Possible values for compression: - * -1 Z_DEFAULT_COMPRESSION - * 0 COMPRESSION_NONE - * 1-9 levels for gzip compression - *--------- - */ + Compress compression; /* Compression requested on open */ bool dosync; /* data requested to be synced on sight */ ArchiveMode mode; /* File mode - r or w */ void *formatData; /* Header data specific to file format */ diff --git a/src/bin/pg_dump/pg_backup_custom.c b/src/bin/pg_dump/pg_backup_custom.c index 77d402c323..55a887a236 100644 --- a/src/bin/pg_dump/pg_backup_custom.c +++ b/src/bin/pg_dump/pg_backup_custom.c @@ -298,7 +298,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) _WriteByte(AH, BLK_DATA); /* Block type */ WriteInt(AH, te->dumpId); /* For sanity check */ - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -377,7 +377,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) WriteInt(AH, oid); - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -566,7 +566,7 @@ _PrintTocData(ArchiveHandle *AH, TocEntry *te) static void _PrintData(ArchiveHandle *AH) { - ReadDataFromArchive(AH, AH->compression, _CustomReadFunc); + ReadDataFromArchive(AH, _CustomReadFunc); } static void diff --git a/src/bin/pg_dump/pg_backup_directory.c b/src/bin/pg_dump/pg_backup_directory.c index 650b542fce..8bf869c6ca 100644 --- a/src/bin/pg_dump/pg_backup_directory.c +++ b/src/bin/pg_dump/pg_backup_directory.c @@ -202,7 +202,7 @@ InitArchiveFmt_Directory(ArchiveHandle *AH) setFilePath(AH, fname, "toc.dat"); - tocFH = cfopen_read(fname, PG_BINARY_R); + tocFH = cfopen_read(fname, PG_BINARY_R, &AH->compression); if (tocFH == NULL) fatal("could not open input file \"%s\": %m", fname); @@ -327,7 +327,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) setFilePath(AH, fname, tctx->filename); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -388,7 +388,7 @@ _PrintFileData(ArchiveHandle *AH, char *filename) if (!filename) return; - cfp = cfopen_read(filename, PG_BINARY_R); + cfp = cfopen_read(filename, PG_BINARY_R, &AH->compression); if (!cfp) fatal("could not open input file \"%s\": %m", filename); @@ -435,12 +435,13 @@ _LoadBlobs(ArchiveHandle *AH) lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; char line[MAXPGPATH]; + Compress nocompression = {0}; StartRestoreBlobs(AH); setFilePath(AH, fname, "blobs.toc"); - ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R); + ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R, &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open large object TOC file \"%s\" for input: %m", @@ -573,6 +574,7 @@ _CloseArchive(ArchiveHandle *AH) { cfp *tocFH; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "toc.dat"); @@ -580,7 +582,7 @@ _CloseArchive(ArchiveHandle *AH) ctx->pstate = ParallelBackupStart(AH); /* The TOC is always created uncompressed */ - tocFH = cfopen_write(fname, PG_BINARY_W, 0); + tocFH = cfopen_write(fname, PG_BINARY_W, &nocompression); if (tocFH == NULL) fatal("could not open output file \"%s\": %m", fname); ctx->dataFH = tocFH; @@ -639,11 +641,12 @@ _StartBlobs(ArchiveHandle *AH, TocEntry *te) { lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "blobs.toc"); /* The blob TOC file is never compressed */ - ctx->blobsTocFH = cfopen_write(fname, "ab", 0); + ctx->blobsTocFH = cfopen_write(fname, "ab", &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -661,7 +664,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) snprintf(fname, MAXPGPATH, "%s/blob_%u.dat", ctx->directory, oid); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); diff --git a/src/bin/pg_dump/pg_backup_tar.c b/src/bin/pg_dump/pg_backup_tar.c index 61c9c87a9f..4ba79ab924 100644 --- a/src/bin/pg_dump/pg_backup_tar.c +++ b/src/bin/pg_dump/pg_backup_tar.c @@ -39,6 +39,7 @@ #include "pg_backup_archiver.h" #include "pg_backup_tar.h" #include "pg_backup_utils.h" +#include "compress_io.h" #include "pgtar.h" static void _ArchiveEntry(ArchiveHandle *AH, TocEntry *te); @@ -196,10 +197,10 @@ InitArchiveFmt_Tar(ArchiveHandle *AH) /* * We don't support compression because reading the files back is not - * possible since gzdopen uses buffered IO which totally screws file + * possible since gzdopen uses buffered IO which totally screws file XXX * positioning. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) fatal("compression is not supported by tar archive format"); } else @@ -254,14 +255,8 @@ _ArchiveEntry(ArchiveHandle *AH, TocEntry *te) ctx = (lclTocEntry *) pg_malloc0(sizeof(lclTocEntry)); if (te->dataDumper != NULL) { -#ifdef HAVE_LIBZ - if (AH->compression == 0) - sprintf(fn, "%d.dat", te->dumpId); - else - sprintf(fn, "%d.dat.gz", te->dumpId); -#else - sprintf(fn, "%d.dat", te->dumpId); -#endif + const char *suffix = compress_suffix(&AH->compression); + sprintf(fn, "%d.dat%s", te->dumpId, suffix); ctx->filename = pg_strdup(fn); } else @@ -352,7 +347,7 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression == 0) + if (AH->compression.alg == COMPR_ALG_NONE) tm->nFH = ctx->tarFH; else fatal("compression is not supported by tar archive format"); @@ -413,9 +408,9 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) { - sprintf(fmode, "wb%d", AH->compression); + sprintf(fmode, "wb%d", AH->compression.level); tm->zFH = gzdopen(dup(fileno(tm->tmpFH)), fmode); if (tm->zFH == NULL) fatal("could not open temporary file"); @@ -443,7 +438,7 @@ tarClose(ArchiveHandle *AH, TAR_MEMBER *th) /* * Close the GZ file since we dup'd. This will flush the buffers. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) if (GZCLOSE(th->zFH) != 0) fatal("could not close tar member"); @@ -868,7 +863,7 @@ _CloseArchive(ArchiveHandle *AH) memcpy(ropt, AH->public.ropt, sizeof(RestoreOptions)); ropt->filename = NULL; ropt->dropSchema = 1; - ropt->compression = 0; + ropt->compression.alg = COMPR_ALG_NONE; ropt->superuser = NULL; ropt->suppressDumpWarnings = true; @@ -952,16 +947,12 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) lclContext *ctx = (lclContext *) AH->formatData; lclTocEntry *tctx = (lclTocEntry *) te->formatData; char fname[255]; - char *sfx; + const char *sfx; if (oid == 0) fatal("invalid OID for large object (%u)", oid); - if (AH->compression != 0) - sfx = ".gz"; - else - sfx = ""; - + sfx = compress_suffix(&AH->compression); sprintf(fname, "blob_%u.dat%s", oid, sfx); tarPrintf(ctx->blobToc, "%u %s\n", oid, fname); diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c index 1ab98a2286..4cbc79aedc 100644 --- a/src/bin/pg_dump/pg_dump.c +++ b/src/bin/pg_dump/pg_dump.c @@ -59,6 +59,7 @@ #include "getopt_long.h" #include "libpq/libpq-fs.h" #include "parallel.h" +#include "compress_io.h" #include "pg_backup_db.h" #include "pg_backup_utils.h" #include "pg_dump.h" @@ -297,6 +298,82 @@ static void setupDumpWorker(Archive *AHX); static TableInfo *getRootTableInfo(TableInfo *tbinfo); +/* Parse the string into compression options */ +static void +parse_compression(const char *optarg, Compress *compress) +{ + if (optarg[0] == '0' && optarg[1] == '\0') + compress->alg = COMPR_ALG_NONE; + else if ((optarg[0] > '0' && optarg[0] <= '9') || + optarg[0] == '-') + { + compress->alg = COMPR_ALG_LIBZ; + compress->level_set = true; + compress->level = atoi(optarg); + if (optarg[1] != '\0') + { + pg_log_error("compression level must be in range 0..9"); + exit_nicely(1); + } + } + else + { + /* Parse a more flexible string like level=3 alg=zlib opts=long */ + for (;;) + { + char *eq = strchr(optarg, '='); + int len; + + if (eq == NULL) + { + pg_log_error("compression options must be key=value: %s", optarg); + exit_nicely(1); + } + + len = eq - optarg; + if (strncmp(optarg, "alg", len) == 0) + { + if (strchr(eq, ' ')) + len = strchr(eq, ' ') - eq - 1; + else + len = strlen(eq) - len; + if (strncmp(1+eq, "zlib", len) == 0 || + strncmp(1+eq, "libz", len) == 0) + compress->alg = COMPR_ALG_LIBZ; + else + { + pg_log_error("unknown compression algorithm: %s", 1+eq); + exit_nicely(1); + } + } + else if (strncmp(optarg, "level", len) == 0) + { + compress->level = atoi(1+eq); + compress->level_set = true; + } + else + { + pg_log_error("unknown compression setting: %s", optarg); + exit_nicely(1); + } + + optarg = strchr(eq, ' '); + if (!optarg++) + break; + } + + if (!compress->level_set) + { + const int default_compress_level[] = { + 0, /* COMPR_ALG_NONE */ + Z_DEFAULT_COMPRESSION, /* COMPR_ALG_ZLIB */ + }; + + compress->level = default_compress_level[compress->alg]; + } + } +} + int main(int argc, char **argv) { @@ -319,7 +396,7 @@ main(int argc, char **argv) char *use_role = NULL; long rowsPerInsert; int numWorkers = 1; - int compressLevel = -1; + Compress compress = { .alg = COMPR_ALG_DEFAULT }; int plainText = 0; ArchiveFormat archiveFormat = archUnknown; ArchiveMode archiveMode; @@ -532,12 +609,7 @@ main(int argc, char **argv) break; case 'Z': /* Compression Level */ - compressLevel = atoi(optarg); - if (compressLevel < 0 || compressLevel > 9) - { - pg_log_error("compression level must be in range 0..9"); - exit_nicely(1); - } + parse_compression(optarg, &compress); break; case 0: @@ -679,20 +751,28 @@ main(int argc, char **argv) plainText = 1; /* Custom and directory formats are compressed by default, others not */ - if (compressLevel == -1) + if (compress.alg == COMPR_ALG_DEFAULT) { -#ifdef HAVE_LIBZ if (archiveFormat == archCustom || archiveFormat == archDirectory) - compressLevel = Z_DEFAULT_COMPRESSION; - else + { +#ifdef HAVE_LIBZ + compress.alg = COMPR_ALG_LIBZ; + compress.level = Z_DEFAULT_COMPRESSION; #endif - compressLevel = 0; + } + else + { + compress.alg = COMPR_ALG_NONE; + compress.level = 0; + } } #ifndef HAVE_LIBZ - if (compressLevel != 0) + if (compress.alg == COMPR_ALG_LIBZ) + { pg_log_warning("requested compression not available in this installation -- archive will be uncompressed"); - compressLevel = 0; + compress.alg = 0; + } #endif /* @@ -723,7 +803,7 @@ main(int argc, char **argv) fatal("option --index-collation-versions-unknown only works in binary upgrade mode"); /* Open the output file */ - fout = CreateArchive(filename, archiveFormat, compressLevel, dosync, + fout = CreateArchive(filename, archiveFormat, &compress, dosync, archiveMode, setupDumpWorker); /* Make dump options accessible right away */ @@ -957,10 +1037,7 @@ main(int argc, char **argv) ropt->sequence_data = dopt.sequence_data; ropt->binary_upgrade = dopt.binary_upgrade; - if (compressLevel == -1) - ropt->compression = 0; - else - ropt->compression = compressLevel; + ropt->compression = compress; ropt->suppressDumpWarnings = true; /* We've already shown them */ -- 2.17.0 --GRPZ8SYKNexpdSJ7 Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="0004-struct-compressLibs.patch" ^ permalink raw reply [nested|flat] 23+ messages in thread
* [PATCH 03/20] Support multiple compression algs/levels/opts.. @ 2020-12-22 06:23 Justin Pryzby <[email protected]> 0 siblings, 0 replies; 23+ messages in thread From: Justin Pryzby @ 2020-12-22 06:23 UTC (permalink / raw) The existing implementation abtracts compressed and noncompressed I/O. This preliminary commit is intended to also allow for multiple compression algorithms. --- src/bin/pg_dump/compress_io.c | 220 +++++++++++--------------- src/bin/pg_dump/compress_io.h | 19 +-- src/bin/pg_dump/pg_backup.h | 23 ++- src/bin/pg_dump/pg_backup_archiver.c | 45 +++--- src/bin/pg_dump/pg_backup_archiver.h | 12 +- src/bin/pg_dump/pg_backup_custom.c | 6 +- src/bin/pg_dump/pg_backup_directory.c | 17 +- src/bin/pg_dump/pg_backup_tar.c | 33 ++-- src/bin/pg_dump/pg_dump.c | 115 +++++++++++--- 9 files changed, 272 insertions(+), 218 deletions(-) diff --git a/src/bin/pg_dump/compress_io.c b/src/bin/pg_dump/compress_io.c index 6a428978d4..db16fd33f2 100644 --- a/src/bin/pg_dump/compress_io.c +++ b/src/bin/pg_dump/compress_io.c @@ -74,12 +74,9 @@ struct CompressorState #endif }; -static void ParseCompressionOption(int compression, CompressionAlgorithm *alg, - int *level); - /* Routines that support zlib compressed data I/O */ #ifdef HAVE_LIBZ -static void InitCompressorZlib(CompressorState *cs, int level); +static void InitCompressorZlib(CompressorState *cs, Compress *compress); static void DeflateCompressorZlib(ArchiveHandle *AH, CompressorState *cs, bool flush); static void ReadDataFromArchiveZlib(ArchiveHandle *AH, ReadFunc readF); @@ -93,58 +90,36 @@ static void ReadDataFromArchiveNone(ArchiveHandle *AH, ReadFunc readF); static void WriteDataToArchiveNone(ArchiveHandle *AH, CompressorState *cs, const char *data, size_t dLen); -/* - * Interprets a numeric 'compression' value. The algorithm implied by the - * value (zlib or none at the moment), is returned in *alg, and the - * zlib compression level in *level. - */ -static void -ParseCompressionOption(int compression, CompressionAlgorithm *alg, int *level) -{ - if (compression == Z_DEFAULT_COMPRESSION || - (compression > 0 && compression <= 9)) - *alg = COMPR_ALG_LIBZ; - else if (compression == 0) - *alg = COMPR_ALG_NONE; - else - { - fatal("invalid compression code: %d", compression); - *alg = COMPR_ALG_NONE; /* keep compiler quiet */ - } - - /* The level is just the passed-in value. */ - if (level) - *level = compression; -} - /* Public interface routines */ /* Allocate a new compressor */ CompressorState * -AllocateCompressor(int compression, WriteFunc writeF) +AllocateCompressor(Compress *compression, WriteFunc writeF) { CompressorState *cs; - CompressionAlgorithm alg; - int level; - - ParseCompressionOption(compression, &alg, &level); - -#ifndef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - fatal("not built with zlib support"); -#endif cs = (CompressorState *) pg_malloc0(sizeof(CompressorState)); cs->writeF = writeF; - cs->comprAlg = alg; + cs->comprAlg = compression->alg; /* * Perform compression algorithm specific initialization. */ + Assert (compression->alg != COMPR_ALG_DEFAULT); + switch (compression->alg) + { #ifdef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - InitCompressorZlib(cs, level); + case COMPR_ALG_LIBZ: + InitCompressorZlib(cs, compression); + break; #endif + case COMPR_ALG_NONE: + /* Do nothing */ + break; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } return cs; } @@ -154,21 +129,21 @@ AllocateCompressor(int compression, WriteFunc writeF) * out with ahwrite(). */ void -ReadDataFromArchive(ArchiveHandle *AH, int compression, ReadFunc readF) +ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF) { - CompressionAlgorithm alg; - - ParseCompressionOption(compression, &alg, NULL); - - if (alg == COMPR_ALG_NONE) - ReadDataFromArchiveNone(AH, readF); - if (alg == COMPR_ALG_LIBZ) + switch (AH->compression.alg) { + case COMPR_ALG_NONE: + ReadDataFromArchiveNone(AH, readF); + break; #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: ReadDataFromArchiveZlib(AH, readF); -#else - fatal("not built with zlib support"); + break; #endif + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -181,16 +156,18 @@ WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, { switch (cs->comprAlg) { - case COMPR_ALG_LIBZ: #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: WriteDataToArchiveZlib(AH, cs, data, dLen); -#else - fatal("not built with zlib support"); -#endif break; +#endif case COMPR_ALG_NONE: WriteDataToArchiveNone(AH, cs, data, dLen); break; + + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -215,7 +192,7 @@ EndCompressor(ArchiveHandle *AH, CompressorState *cs) */ static void -InitCompressorZlib(CompressorState *cs, int level) +InitCompressorZlib(CompressorState *cs, Compress *compress) { z_streamp zp; @@ -232,7 +209,7 @@ InitCompressorZlib(CompressorState *cs, int level) cs->zlibOut = (char *) pg_malloc(ZLIB_OUT_SIZE + 1); cs->zlibOutSize = ZLIB_OUT_SIZE; - if (deflateInit(zp, level) != Z_OK) + if (deflateInit(zp, compress->level) != Z_OK) fatal("could not initialize compression library: %s", zp->msg); @@ -424,9 +401,7 @@ struct cfp #endif }; -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix); -#endif /* free() without changing errno; useful in several places below */ static void @@ -442,34 +417,31 @@ free_keep_errno(void *p) * Open a file for reading. 'path' is the file to open, and 'mode' should * be either "r" or "rb". * - * If the file at 'path' does not exist, we append the ".gz" suffix (if 'path' - * doesn't already have it) and try again. So if you pass "foo" as 'path', + * If the file at 'path' does not exist, we search with compressed suffix (if 'path' + * doesn't already have one) and try again. So if you pass "foo" as 'path', * this will open either "foo" or "foo.gz". * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_read(const char *path, const char *mode) +cfopen_read(const char *path, const char *mode, Compress *compression) { cfp *fp; -#ifdef HAVE_LIBZ if (hasSuffix(path, ".gz")) - fp = cfopen(path, mode, 1); + fp = cfopen(path, mode, compression); else -#endif { - fp = cfopen(path, mode, 0); -#ifdef HAVE_LIBZ + fp = cfopen(path, mode, compression); if (fp == NULL) { char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); - fp = cfopen(fname, mode, 1); + fname = psprintf("%s%s", path, suffix); + fp = cfopen(fname, mode, compression); free_keep_errno(fname); } -#endif } return fp; } @@ -479,31 +451,26 @@ cfopen_read(const char *path, const char *mode) * be a filemode as accepted by fopen() and gzopen() that indicates writing * ("w", "wb", "a", or "ab"). * - * If 'compression' is non-zero, a gzip compressed stream is opened, and - * 'compression' indicates the compression level used. The ".gz" suffix - * is automatically added to 'path' in that case. + * Use compression if specified. + * The appropriate suffix is automatically added to 'path' in that case. * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_write(const char *path, const char *mode, int compression) +cfopen_write(const char *path, const char *mode, Compress *compression) { cfp *fp; - if (compression == 0) - fp = cfopen(path, mode, 0); + if (compression->alg == COMPR_ALG_NONE) + fp = cfopen(path, mode, compression); else { -#ifdef HAVE_LIBZ char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); + fname = psprintf("%s%s", path, suffix); fp = cfopen(fname, mode, compression); free_keep_errno(fname); -#else - fatal("not built with zlib support"); - fp = NULL; /* keep compiler quiet */ -#endif } return fp; } @@ -515,20 +482,21 @@ cfopen_write(const char *path, const char *mode, int compression) * On failure, return NULL with an error code in errno. */ cfp * -cfopen(const char *path, const char *mode, int compression) +cfopen(const char *path, const char *mode, Compress *compression) { - cfp *fp = pg_malloc(sizeof(cfp)); + cfp *fp = pg_malloc0(sizeof(cfp)); - if (compression != 0) + switch (compression->alg) { #ifdef HAVE_LIBZ - if (compression != Z_DEFAULT_COMPRESSION) + case COMPR_ALG_LIBZ: + if (compression->level != Z_DEFAULT_COMPRESSION) { /* user has specified a compression level, so tell zlib to use it */ char mode_compression[32]; snprintf(mode_compression, sizeof(mode_compression), "%s%d", - mode, compression); + mode, compression->level); fp->compressedfp = gzopen(path, mode_compression); } else @@ -537,30 +505,27 @@ cfopen(const char *path, const char *mode, int compression) fp->compressedfp = gzopen(path, mode); } - fp->uncompressedfp = NULL; if (fp->compressedfp == NULL) { free_keep_errno(fp); fp = NULL; } -#else - fatal("not built with zlib support"); -#endif - } - else - { -#ifdef HAVE_LIBZ - fp->compressedfp = NULL; + return fp; #endif + + case COMPR_ALG_NONE: fp->uncompressedfp = fopen(path, mode); if (fp->uncompressedfp == NULL) { free_keep_errno(fp); fp = NULL; } - } + return fp; - return fp; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } } @@ -584,14 +549,13 @@ cfread(void *ptr, int size, cfp *fp) fatal("could not read from input file: %s", errnum == Z_ERRNO ? strerror(errno) : errmsg); } + return ret; } - else #endif - { - ret = fread(ptr, 1, size, fp->uncompressedfp); - if (ret != size && !feof(fp->uncompressedfp)) - READ_ERROR_EXIT(fp->uncompressedfp); - } + + ret = fread(ptr, 1, size, fp->uncompressedfp); + if (ret != size && !feof(fp->uncompressedfp)) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -601,9 +565,8 @@ cfwrite(const void *ptr, int size, cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzwrite(fp->compressedfp, ptr, size); - else #endif - return fwrite(ptr, 1, size, fp->uncompressedfp); + return fwrite(ptr, 1, size, fp->uncompressedfp); } int @@ -622,15 +585,12 @@ cfgetc(cfp *fp) else fatal("could not read from input file: end of file"); } + return ret; } - else #endif - { - ret = fgetc(fp->uncompressedfp); - if (ret == EOF) - READ_ERROR_EXIT(fp->uncompressedfp); - } - + ret = fgetc(fp->uncompressedfp); + if (ret == EOF) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -640,9 +600,8 @@ cfgets(cfp *fp, char *buf, int len) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzgets(fp->compressedfp, buf, len); - else #endif - return fgets(buf, len, fp->uncompressedfp); + return fgets(buf, len, fp->uncompressedfp); } int @@ -660,15 +619,13 @@ cfclose(cfp *fp) { result = gzclose(fp->compressedfp); fp->compressedfp = NULL; + return result; } - else #endif - { - result = fclose(fp->uncompressedfp); - fp->uncompressedfp = NULL; - } - free_keep_errno(fp); + result = fclose(fp->uncompressedfp); + fp->uncompressedfp = NULL; + free_keep_errno(fp); return result; } @@ -678,9 +635,9 @@ cfeof(cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzeof(fp->compressedfp); - else #endif - return feof(fp->uncompressedfp); + + return feof(fp->uncompressedfp); } const char * @@ -699,7 +656,6 @@ get_cfp_error(cfp *fp) return strerror(errno); } -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix) { @@ -714,4 +670,18 @@ hasSuffix(const char *filename, const char *suffix) suffixlen) == 0; } -#endif +/* + * Return a string for the given AH's compression. + * The string is statically allocated. + */ +const char * +compress_suffix(Compress *compression) +{ + switch (compression->alg) + { + case COMPR_ALG_LIBZ: + return ".gz"; + default: + return ""; + } +} diff --git a/src/bin/pg_dump/compress_io.h b/src/bin/pg_dump/compress_io.h index d2e6e1b854..2c073676eb 100644 --- a/src/bin/pg_dump/compress_io.h +++ b/src/bin/pg_dump/compress_io.h @@ -21,12 +21,6 @@ #define ZLIB_OUT_SIZE 4096 #define ZLIB_IN_SIZE 4096 -typedef enum -{ - COMPR_ALG_NONE, - COMPR_ALG_LIBZ -} CompressionAlgorithm; - /* Prototype for callback function to WriteDataToArchive() */ typedef void (*WriteFunc) (ArchiveHandle *AH, const char *buf, size_t len); @@ -46,8 +40,8 @@ typedef size_t (*ReadFunc) (ArchiveHandle *AH, char **buf, size_t *buflen); /* struct definition appears in compress_io.c */ typedef struct CompressorState CompressorState; -extern CompressorState *AllocateCompressor(int compression, WriteFunc writeF); -extern void ReadDataFromArchive(ArchiveHandle *AH, int compression, +extern CompressorState *AllocateCompressor(Compress *compression, WriteFunc writeF); +extern void ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF); extern void WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, const void *data, size_t dLen); @@ -56,9 +50,9 @@ extern void EndCompressor(ArchiveHandle *AH, CompressorState *cs); typedef struct cfp cfp; -extern cfp *cfopen(const char *path, const char *mode, int compression); -extern cfp *cfopen_read(const char *path, const char *mode); -extern cfp *cfopen_write(const char *path, const char *mode, int compression); +extern cfp *cfopen(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_read(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_write(const char *path, const char *mode, Compress *compression); extern int cfread(void *ptr, int size, cfp *fp); extern int cfwrite(const void *ptr, int size, cfp *fp); extern int cfgetc(cfp *fp); @@ -67,4 +61,7 @@ extern int cfclose(cfp *fp); extern int cfeof(cfp *fp); extern const char *get_cfp_error(cfp *fp); +/* also used by tar */ +extern const char * compress_suffix(Compress *compression); + #endif diff --git a/src/bin/pg_dump/pg_backup.h b/src/bin/pg_dump/pg_backup.h index 9d0056a569..f2390b7937 100644 --- a/src/bin/pg_dump/pg_backup.h +++ b/src/bin/pg_dump/pg_backup.h @@ -72,6 +72,25 @@ typedef struct _connParams char *override_dbname; } ConnParams; +typedef enum +{ + COMPR_ALG_DEFAULT = -1, + COMPR_ALG_NONE, + COMPR_ALG_LIBZ, +} CompressionAlgorithm; +/* Should be called "method" or "library" ? */ + +typedef struct Compress { + CompressionAlgorithm alg; + int level; + /* Is a nondefault level set ? This is useful since different compression + * methods have different "default" levels. For now we assume the levels + * are all integer, though. + */ + bool level_set; +} Compress; + + typedef struct _restoreOptions { int createDB; /* Issue commands to create the database */ @@ -125,7 +144,7 @@ typedef struct _restoreOptions int noDataForFailedTables; int exit_on_error; - int compression; + Compress compression; int suppressDumpWarnings; /* Suppress output of WARNING entries * to stderr */ bool single_txn; @@ -281,7 +300,7 @@ extern Archive *OpenArchive(const char *FileSpec, const ArchiveFormat fmt); /* Create a new archive */ extern Archive *CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker); /* The --list option */ diff --git a/src/bin/pg_dump/pg_backup_archiver.c b/src/bin/pg_dump/pg_backup_archiver.c index 1f82c6499b..3eb6c55600 100644 --- a/src/bin/pg_dump/pg_backup_archiver.c +++ b/src/bin/pg_dump/pg_backup_archiver.c @@ -70,7 +70,7 @@ typedef struct _parallelReadyList static ArchiveHandle *_allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr); static void _getObjectDescription(PQExpBuffer buf, TocEntry *te); static void _printTocEntry(ArchiveHandle *AH, TocEntry *te, bool isData); @@ -98,7 +98,7 @@ static int _discoverArchiveFormat(ArchiveHandle *AH); static int RestoringToDB(ArchiveHandle *AH); static void dump_lo_buf(ArchiveHandle *AH); static void dumpTimestamp(ArchiveHandle *AH, const char *msg, time_t tim); -static void SetOutput(ArchiveHandle *AH, const char *filename, int compression); +static void SetOutput(ArchiveHandle *AH, const char *filename, Compress *compress); static OutputContext SaveOutput(ArchiveHandle *AH); static void RestoreOutput(ArchiveHandle *AH, OutputContext savedContext); @@ -238,7 +238,7 @@ setupRestoreWorker(Archive *AHX) /* Public */ Archive * CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker) { @@ -253,7 +253,9 @@ CreateArchive(const char *FileSpec, const ArchiveFormat fmt, Archive * OpenArchive(const char *FileSpec, const ArchiveFormat fmt) { - ArchiveHandle *AH = _allocAH(FileSpec, fmt, 0, true, archModeRead, setupRestoreWorker); + Compress compress = {0}; + ArchiveHandle *AH = _allocAH(FileSpec, fmt, &compress, true, archModeRead, + setupRestoreWorker); return (Archive *) AH; } @@ -382,7 +384,7 @@ RestoreArchive(Archive *AHX) * Make sure we won't need (de)compression we haven't got */ #ifndef HAVE_LIBZ - if (AH->compression != 0 && AH->PrintTocDataPtr != NULL) + if (AH->compression.alg != COMPR_ALG_NONE && AH->PrintTocDataPtr != NULL) { for (te = AH->toc->next; te != AH->toc; te = te->next) { @@ -457,8 +459,8 @@ RestoreArchive(Archive *AHX) * Setup the output file if necessary. */ sav = SaveOutput(AH); - if (ropt->filename || ropt->compression) - SetOutput(AH, ropt->filename, ropt->compression); + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) + SetOutput(AH, ropt->filename, &ropt->compression); ahprintf(AH, "--\n-- PostgreSQL database dump\n--\n\n"); @@ -738,7 +740,7 @@ RestoreArchive(Archive *AHX) */ AH->stage = STAGE_FINALIZING; - if (ropt->filename || ropt->compression) + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) RestoreOutput(AH, sav); if (ropt->useDB) @@ -1123,8 +1125,9 @@ PrintTOCSummary(Archive *AHX) char stamp_str[64]; sav = SaveOutput(AH); + Assert(ropt->compression.alg == COMPR_ALG_NONE); if (ropt->filename) - SetOutput(AH, ropt->filename, 0 /* no compression */ ); + SetOutput(AH, ropt->filename, &ropt->compression); if (strftime(stamp_str, sizeof(stamp_str), PGDUMP_STRFTIME_FMT, localtime(&AH->createDate)) == 0) @@ -1133,7 +1136,7 @@ PrintTOCSummary(Archive *AHX) ahprintf(AH, ";\n; Archive created at %s\n", stamp_str); ahprintf(AH, "; dbname: %s\n; TOC Entries: %d\n; Compression: %d\n", sanitize_line(AH->archdbname, false), - AH->tocCount, AH->compression); + AH->tocCount, AH->compression.alg); switch (AH->format) { @@ -1487,7 +1490,7 @@ archprintf(Archive *AH, const char *fmt,...) *******************************/ static void -SetOutput(ArchiveHandle *AH, const char *filename, int compression) +SetOutput(ArchiveHandle *AH, const char *filename, Compress *compression) { int fn; @@ -1510,12 +1513,12 @@ SetOutput(ArchiveHandle *AH, const char *filename, int compression) /* If compression explicitly requested, use gzopen */ #ifdef HAVE_LIBZ - if (compression != 0) + if (compression->alg != COMPR_ALG_NONE) { char fmode[14]; /* Don't use PG_BINARY_x since this is zlib */ - sprintf(fmode, "wb%d", compression); + sprintf(fmode, "wb%d", compression->level); if (fn >= 0) AH->OF = gzdopen(dup(fn), fmode); else @@ -2259,7 +2262,7 @@ _discoverArchiveFormat(ArchiveHandle *AH) */ static ArchiveHandle * _allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr) { ArchiveHandle *AH; @@ -2310,7 +2313,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, AH->toc->prev = AH->toc; AH->mode = mode; - AH->compression = compression; + AH->compression = *compression; AH->dosync = dosync; memset(&(AH->sqlparse), 0, sizeof(AH->sqlparse)); @@ -2325,7 +2328,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, * Force stdin/stdout into binary mode if that is what we are using. */ #ifdef WIN32 - if ((fmt != archNull || compression != 0) && + if ((fmt != archNull || compression->alg != COMPR_ALG_NONE) && (AH->fSpec == NULL || strcmp(AH->fSpec, "") == 0)) { if (mode == archModeWrite) @@ -3741,7 +3744,7 @@ WriteHead(ArchiveHandle *AH) AH->WriteBytePtr(AH, AH->intSize); AH->WriteBytePtr(AH, AH->offSize); AH->WriteBytePtr(AH, AH->format); - WriteInt(AH, AH->compression); + WriteInt(AH, AH->compression.alg); crtm = *localtime(&AH->createDate); WriteInt(AH, crtm.tm_sec); WriteInt(AH, crtm.tm_min); @@ -3816,15 +3819,15 @@ ReadHead(ArchiveHandle *AH) if (AH->version >= K_VERS_1_2) { if (AH->version < K_VERS_1_4) - AH->compression = AH->ReadBytePtr(AH); + AH->compression.alg = AH->ReadBytePtr(AH); else - AH->compression = ReadInt(AH); + AH->compression.alg = ReadInt(AH); } else - AH->compression = Z_DEFAULT_COMPRESSION; + AH->compression.alg = Z_DEFAULT_COMPRESSION; #ifndef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) pg_log_warning("archive is compressed, but this installation does not support compression -- no data will be available"); #endif diff --git a/src/bin/pg_dump/pg_backup_archiver.h b/src/bin/pg_dump/pg_backup_archiver.h index a8ea5c7eae..6e033d040e 100644 --- a/src/bin/pg_dump/pg_backup_archiver.h +++ b/src/bin/pg_dump/pg_backup_archiver.h @@ -47,7 +47,8 @@ #define GZWRITE(p, s, n, fh) (fwrite(p, s, n, fh) * (s)) #define GZREAD(p, s, n, fh) fread(p, s, n, fh) #define GZEOF(fh) feof(fh) -/* this is just the redefinition of a libz constant */ +/* this is just the redefinition of a libz constant, in case zlib isn't + * available */ #define Z_DEFAULT_COMPRESSION (-1) typedef struct _z_stream @@ -329,14 +330,7 @@ struct _archiveHandle DumpId *tableDataId; /* TABLE DATA ids, indexed by table dumpId */ struct _tocEntry *currToc; /* Used when dumping data */ - int compression; /*--------- - * Compression requested on open(). - * Possible values for compression: - * -1 Z_DEFAULT_COMPRESSION - * 0 COMPRESSION_NONE - * 1-9 levels for gzip compression - *--------- - */ + Compress compression; /* Compression requested on open */ bool dosync; /* data requested to be synced on sight */ ArchiveMode mode; /* File mode - r or w */ void *formatData; /* Header data specific to file format */ diff --git a/src/bin/pg_dump/pg_backup_custom.c b/src/bin/pg_dump/pg_backup_custom.c index 77d402c323..55a887a236 100644 --- a/src/bin/pg_dump/pg_backup_custom.c +++ b/src/bin/pg_dump/pg_backup_custom.c @@ -298,7 +298,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) _WriteByte(AH, BLK_DATA); /* Block type */ WriteInt(AH, te->dumpId); /* For sanity check */ - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -377,7 +377,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) WriteInt(AH, oid); - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -566,7 +566,7 @@ _PrintTocData(ArchiveHandle *AH, TocEntry *te) static void _PrintData(ArchiveHandle *AH) { - ReadDataFromArchive(AH, AH->compression, _CustomReadFunc); + ReadDataFromArchive(AH, _CustomReadFunc); } static void diff --git a/src/bin/pg_dump/pg_backup_directory.c b/src/bin/pg_dump/pg_backup_directory.c index 650b542fce..8bf869c6ca 100644 --- a/src/bin/pg_dump/pg_backup_directory.c +++ b/src/bin/pg_dump/pg_backup_directory.c @@ -202,7 +202,7 @@ InitArchiveFmt_Directory(ArchiveHandle *AH) setFilePath(AH, fname, "toc.dat"); - tocFH = cfopen_read(fname, PG_BINARY_R); + tocFH = cfopen_read(fname, PG_BINARY_R, &AH->compression); if (tocFH == NULL) fatal("could not open input file \"%s\": %m", fname); @@ -327,7 +327,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) setFilePath(AH, fname, tctx->filename); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -388,7 +388,7 @@ _PrintFileData(ArchiveHandle *AH, char *filename) if (!filename) return; - cfp = cfopen_read(filename, PG_BINARY_R); + cfp = cfopen_read(filename, PG_BINARY_R, &AH->compression); if (!cfp) fatal("could not open input file \"%s\": %m", filename); @@ -435,12 +435,13 @@ _LoadBlobs(ArchiveHandle *AH) lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; char line[MAXPGPATH]; + Compress nocompression = {0}; StartRestoreBlobs(AH); setFilePath(AH, fname, "blobs.toc"); - ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R); + ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R, &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open large object TOC file \"%s\" for input: %m", @@ -573,6 +574,7 @@ _CloseArchive(ArchiveHandle *AH) { cfp *tocFH; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "toc.dat"); @@ -580,7 +582,7 @@ _CloseArchive(ArchiveHandle *AH) ctx->pstate = ParallelBackupStart(AH); /* The TOC is always created uncompressed */ - tocFH = cfopen_write(fname, PG_BINARY_W, 0); + tocFH = cfopen_write(fname, PG_BINARY_W, &nocompression); if (tocFH == NULL) fatal("could not open output file \"%s\": %m", fname); ctx->dataFH = tocFH; @@ -639,11 +641,12 @@ _StartBlobs(ArchiveHandle *AH, TocEntry *te) { lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "blobs.toc"); /* The blob TOC file is never compressed */ - ctx->blobsTocFH = cfopen_write(fname, "ab", 0); + ctx->blobsTocFH = cfopen_write(fname, "ab", &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -661,7 +664,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) snprintf(fname, MAXPGPATH, "%s/blob_%u.dat", ctx->directory, oid); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); diff --git a/src/bin/pg_dump/pg_backup_tar.c b/src/bin/pg_dump/pg_backup_tar.c index 61c9c87a9f..4ba79ab924 100644 --- a/src/bin/pg_dump/pg_backup_tar.c +++ b/src/bin/pg_dump/pg_backup_tar.c @@ -39,6 +39,7 @@ #include "pg_backup_archiver.h" #include "pg_backup_tar.h" #include "pg_backup_utils.h" +#include "compress_io.h" #include "pgtar.h" static void _ArchiveEntry(ArchiveHandle *AH, TocEntry *te); @@ -196,10 +197,10 @@ InitArchiveFmt_Tar(ArchiveHandle *AH) /* * We don't support compression because reading the files back is not - * possible since gzdopen uses buffered IO which totally screws file + * possible since gzdopen uses buffered IO which totally screws file XXX * positioning. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) fatal("compression is not supported by tar archive format"); } else @@ -254,14 +255,8 @@ _ArchiveEntry(ArchiveHandle *AH, TocEntry *te) ctx = (lclTocEntry *) pg_malloc0(sizeof(lclTocEntry)); if (te->dataDumper != NULL) { -#ifdef HAVE_LIBZ - if (AH->compression == 0) - sprintf(fn, "%d.dat", te->dumpId); - else - sprintf(fn, "%d.dat.gz", te->dumpId); -#else - sprintf(fn, "%d.dat", te->dumpId); -#endif + const char *suffix = compress_suffix(&AH->compression); + sprintf(fn, "%d.dat%s", te->dumpId, suffix); ctx->filename = pg_strdup(fn); } else @@ -352,7 +347,7 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression == 0) + if (AH->compression.alg == COMPR_ALG_NONE) tm->nFH = ctx->tarFH; else fatal("compression is not supported by tar archive format"); @@ -413,9 +408,9 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) { - sprintf(fmode, "wb%d", AH->compression); + sprintf(fmode, "wb%d", AH->compression.level); tm->zFH = gzdopen(dup(fileno(tm->tmpFH)), fmode); if (tm->zFH == NULL) fatal("could not open temporary file"); @@ -443,7 +438,7 @@ tarClose(ArchiveHandle *AH, TAR_MEMBER *th) /* * Close the GZ file since we dup'd. This will flush the buffers. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) if (GZCLOSE(th->zFH) != 0) fatal("could not close tar member"); @@ -868,7 +863,7 @@ _CloseArchive(ArchiveHandle *AH) memcpy(ropt, AH->public.ropt, sizeof(RestoreOptions)); ropt->filename = NULL; ropt->dropSchema = 1; - ropt->compression = 0; + ropt->compression.alg = COMPR_ALG_NONE; ropt->superuser = NULL; ropt->suppressDumpWarnings = true; @@ -952,16 +947,12 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) lclContext *ctx = (lclContext *) AH->formatData; lclTocEntry *tctx = (lclTocEntry *) te->formatData; char fname[255]; - char *sfx; + const char *sfx; if (oid == 0) fatal("invalid OID for large object (%u)", oid); - if (AH->compression != 0) - sfx = ".gz"; - else - sfx = ""; - + sfx = compress_suffix(&AH->compression); sprintf(fname, "blob_%u.dat%s", oid, sfx); tarPrintf(ctx->blobToc, "%u %s\n", oid, fname); diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c index 1ab98a2286..4cbc79aedc 100644 --- a/src/bin/pg_dump/pg_dump.c +++ b/src/bin/pg_dump/pg_dump.c @@ -59,6 +59,7 @@ #include "getopt_long.h" #include "libpq/libpq-fs.h" #include "parallel.h" +#include "compress_io.h" #include "pg_backup_db.h" #include "pg_backup_utils.h" #include "pg_dump.h" @@ -297,6 +298,82 @@ static void setupDumpWorker(Archive *AHX); static TableInfo *getRootTableInfo(TableInfo *tbinfo); +/* Parse the string into compression options */ +static void +parse_compression(const char *optarg, Compress *compress) +{ + if (optarg[0] == '0' && optarg[1] == '\0') + compress->alg = COMPR_ALG_NONE; + else if ((optarg[0] > '0' && optarg[0] <= '9') || + optarg[0] == '-') + { + compress->alg = COMPR_ALG_LIBZ; + compress->level_set = true; + compress->level = atoi(optarg); + if (optarg[1] != '\0') + { + pg_log_error("compression level must be in range 0..9"); + exit_nicely(1); + } + } + else + { + /* Parse a more flexible string like level=3 alg=zlib opts=long */ + for (;;) + { + char *eq = strchr(optarg, '='); + int len; + + if (eq == NULL) + { + pg_log_error("compression options must be key=value: %s", optarg); + exit_nicely(1); + } + + len = eq - optarg; + if (strncmp(optarg, "alg", len) == 0) + { + if (strchr(eq, ' ')) + len = strchr(eq, ' ') - eq - 1; + else + len = strlen(eq) - len; + if (strncmp(1+eq, "zlib", len) == 0 || + strncmp(1+eq, "libz", len) == 0) + compress->alg = COMPR_ALG_LIBZ; + else + { + pg_log_error("unknown compression algorithm: %s", 1+eq); + exit_nicely(1); + } + } + else if (strncmp(optarg, "level", len) == 0) + { + compress->level = atoi(1+eq); + compress->level_set = true; + } + else + { + pg_log_error("unknown compression setting: %s", optarg); + exit_nicely(1); + } + + optarg = strchr(eq, ' '); + if (!optarg++) + break; + } + + if (!compress->level_set) + { + const int default_compress_level[] = { + 0, /* COMPR_ALG_NONE */ + Z_DEFAULT_COMPRESSION, /* COMPR_ALG_ZLIB */ + }; + + compress->level = default_compress_level[compress->alg]; + } + } +} + int main(int argc, char **argv) { @@ -319,7 +396,7 @@ main(int argc, char **argv) char *use_role = NULL; long rowsPerInsert; int numWorkers = 1; - int compressLevel = -1; + Compress compress = { .alg = COMPR_ALG_DEFAULT }; int plainText = 0; ArchiveFormat archiveFormat = archUnknown; ArchiveMode archiveMode; @@ -532,12 +609,7 @@ main(int argc, char **argv) break; case 'Z': /* Compression Level */ - compressLevel = atoi(optarg); - if (compressLevel < 0 || compressLevel > 9) - { - pg_log_error("compression level must be in range 0..9"); - exit_nicely(1); - } + parse_compression(optarg, &compress); break; case 0: @@ -679,20 +751,28 @@ main(int argc, char **argv) plainText = 1; /* Custom and directory formats are compressed by default, others not */ - if (compressLevel == -1) + if (compress.alg == COMPR_ALG_DEFAULT) { -#ifdef HAVE_LIBZ if (archiveFormat == archCustom || archiveFormat == archDirectory) - compressLevel = Z_DEFAULT_COMPRESSION; - else + { +#ifdef HAVE_LIBZ + compress.alg = COMPR_ALG_LIBZ; + compress.level = Z_DEFAULT_COMPRESSION; #endif - compressLevel = 0; + } + else + { + compress.alg = COMPR_ALG_NONE; + compress.level = 0; + } } #ifndef HAVE_LIBZ - if (compressLevel != 0) + if (compress.alg == COMPR_ALG_LIBZ) + { pg_log_warning("requested compression not available in this installation -- archive will be uncompressed"); - compressLevel = 0; + compress.alg = 0; + } #endif /* @@ -723,7 +803,7 @@ main(int argc, char **argv) fatal("option --index-collation-versions-unknown only works in binary upgrade mode"); /* Open the output file */ - fout = CreateArchive(filename, archiveFormat, compressLevel, dosync, + fout = CreateArchive(filename, archiveFormat, &compress, dosync, archiveMode, setupDumpWorker); /* Make dump options accessible right away */ @@ -957,10 +1037,7 @@ main(int argc, char **argv) ropt->sequence_data = dopt.sequence_data; ropt->binary_upgrade = dopt.binary_upgrade; - if (compressLevel == -1) - ropt->compression = 0; - else - ropt->compression = compressLevel; + ropt->compression = compress; ropt->suppressDumpWarnings = true; /* We've already shown them */ -- 2.17.0 --GRPZ8SYKNexpdSJ7 Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="0004-struct-compressLibs.patch" ^ permalink raw reply [nested|flat] 23+ messages in thread
* [PATCH 03/20] Support multiple compression algs/levels/opts.. @ 2020-12-22 06:23 Justin Pryzby <[email protected]> 0 siblings, 0 replies; 23+ messages in thread From: Justin Pryzby @ 2020-12-22 06:23 UTC (permalink / raw) The existing implementation abtracts compressed and noncompressed I/O. This preliminary commit is intended to also allow for multiple compression algorithms. --- src/bin/pg_dump/compress_io.c | 220 +++++++++++--------------- src/bin/pg_dump/compress_io.h | 19 +-- src/bin/pg_dump/pg_backup.h | 23 ++- src/bin/pg_dump/pg_backup_archiver.c | 45 +++--- src/bin/pg_dump/pg_backup_archiver.h | 12 +- src/bin/pg_dump/pg_backup_custom.c | 6 +- src/bin/pg_dump/pg_backup_directory.c | 17 +- src/bin/pg_dump/pg_backup_tar.c | 33 ++-- src/bin/pg_dump/pg_dump.c | 115 +++++++++++--- 9 files changed, 272 insertions(+), 218 deletions(-) diff --git a/src/bin/pg_dump/compress_io.c b/src/bin/pg_dump/compress_io.c index 6a428978d4..db16fd33f2 100644 --- a/src/bin/pg_dump/compress_io.c +++ b/src/bin/pg_dump/compress_io.c @@ -74,12 +74,9 @@ struct CompressorState #endif }; -static void ParseCompressionOption(int compression, CompressionAlgorithm *alg, - int *level); - /* Routines that support zlib compressed data I/O */ #ifdef HAVE_LIBZ -static void InitCompressorZlib(CompressorState *cs, int level); +static void InitCompressorZlib(CompressorState *cs, Compress *compress); static void DeflateCompressorZlib(ArchiveHandle *AH, CompressorState *cs, bool flush); static void ReadDataFromArchiveZlib(ArchiveHandle *AH, ReadFunc readF); @@ -93,58 +90,36 @@ static void ReadDataFromArchiveNone(ArchiveHandle *AH, ReadFunc readF); static void WriteDataToArchiveNone(ArchiveHandle *AH, CompressorState *cs, const char *data, size_t dLen); -/* - * Interprets a numeric 'compression' value. The algorithm implied by the - * value (zlib or none at the moment), is returned in *alg, and the - * zlib compression level in *level. - */ -static void -ParseCompressionOption(int compression, CompressionAlgorithm *alg, int *level) -{ - if (compression == Z_DEFAULT_COMPRESSION || - (compression > 0 && compression <= 9)) - *alg = COMPR_ALG_LIBZ; - else if (compression == 0) - *alg = COMPR_ALG_NONE; - else - { - fatal("invalid compression code: %d", compression); - *alg = COMPR_ALG_NONE; /* keep compiler quiet */ - } - - /* The level is just the passed-in value. */ - if (level) - *level = compression; -} - /* Public interface routines */ /* Allocate a new compressor */ CompressorState * -AllocateCompressor(int compression, WriteFunc writeF) +AllocateCompressor(Compress *compression, WriteFunc writeF) { CompressorState *cs; - CompressionAlgorithm alg; - int level; - - ParseCompressionOption(compression, &alg, &level); - -#ifndef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - fatal("not built with zlib support"); -#endif cs = (CompressorState *) pg_malloc0(sizeof(CompressorState)); cs->writeF = writeF; - cs->comprAlg = alg; + cs->comprAlg = compression->alg; /* * Perform compression algorithm specific initialization. */ + Assert (compression->alg != COMPR_ALG_DEFAULT); + switch (compression->alg) + { #ifdef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - InitCompressorZlib(cs, level); + case COMPR_ALG_LIBZ: + InitCompressorZlib(cs, compression); + break; #endif + case COMPR_ALG_NONE: + /* Do nothing */ + break; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } return cs; } @@ -154,21 +129,21 @@ AllocateCompressor(int compression, WriteFunc writeF) * out with ahwrite(). */ void -ReadDataFromArchive(ArchiveHandle *AH, int compression, ReadFunc readF) +ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF) { - CompressionAlgorithm alg; - - ParseCompressionOption(compression, &alg, NULL); - - if (alg == COMPR_ALG_NONE) - ReadDataFromArchiveNone(AH, readF); - if (alg == COMPR_ALG_LIBZ) + switch (AH->compression.alg) { + case COMPR_ALG_NONE: + ReadDataFromArchiveNone(AH, readF); + break; #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: ReadDataFromArchiveZlib(AH, readF); -#else - fatal("not built with zlib support"); + break; #endif + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -181,16 +156,18 @@ WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, { switch (cs->comprAlg) { - case COMPR_ALG_LIBZ: #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: WriteDataToArchiveZlib(AH, cs, data, dLen); -#else - fatal("not built with zlib support"); -#endif break; +#endif case COMPR_ALG_NONE: WriteDataToArchiveNone(AH, cs, data, dLen); break; + + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -215,7 +192,7 @@ EndCompressor(ArchiveHandle *AH, CompressorState *cs) */ static void -InitCompressorZlib(CompressorState *cs, int level) +InitCompressorZlib(CompressorState *cs, Compress *compress) { z_streamp zp; @@ -232,7 +209,7 @@ InitCompressorZlib(CompressorState *cs, int level) cs->zlibOut = (char *) pg_malloc(ZLIB_OUT_SIZE + 1); cs->zlibOutSize = ZLIB_OUT_SIZE; - if (deflateInit(zp, level) != Z_OK) + if (deflateInit(zp, compress->level) != Z_OK) fatal("could not initialize compression library: %s", zp->msg); @@ -424,9 +401,7 @@ struct cfp #endif }; -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix); -#endif /* free() without changing errno; useful in several places below */ static void @@ -442,34 +417,31 @@ free_keep_errno(void *p) * Open a file for reading. 'path' is the file to open, and 'mode' should * be either "r" or "rb". * - * If the file at 'path' does not exist, we append the ".gz" suffix (if 'path' - * doesn't already have it) and try again. So if you pass "foo" as 'path', + * If the file at 'path' does not exist, we search with compressed suffix (if 'path' + * doesn't already have one) and try again. So if you pass "foo" as 'path', * this will open either "foo" or "foo.gz". * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_read(const char *path, const char *mode) +cfopen_read(const char *path, const char *mode, Compress *compression) { cfp *fp; -#ifdef HAVE_LIBZ if (hasSuffix(path, ".gz")) - fp = cfopen(path, mode, 1); + fp = cfopen(path, mode, compression); else -#endif { - fp = cfopen(path, mode, 0); -#ifdef HAVE_LIBZ + fp = cfopen(path, mode, compression); if (fp == NULL) { char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); - fp = cfopen(fname, mode, 1); + fname = psprintf("%s%s", path, suffix); + fp = cfopen(fname, mode, compression); free_keep_errno(fname); } -#endif } return fp; } @@ -479,31 +451,26 @@ cfopen_read(const char *path, const char *mode) * be a filemode as accepted by fopen() and gzopen() that indicates writing * ("w", "wb", "a", or "ab"). * - * If 'compression' is non-zero, a gzip compressed stream is opened, and - * 'compression' indicates the compression level used. The ".gz" suffix - * is automatically added to 'path' in that case. + * Use compression if specified. + * The appropriate suffix is automatically added to 'path' in that case. * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_write(const char *path, const char *mode, int compression) +cfopen_write(const char *path, const char *mode, Compress *compression) { cfp *fp; - if (compression == 0) - fp = cfopen(path, mode, 0); + if (compression->alg == COMPR_ALG_NONE) + fp = cfopen(path, mode, compression); else { -#ifdef HAVE_LIBZ char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); + fname = psprintf("%s%s", path, suffix); fp = cfopen(fname, mode, compression); free_keep_errno(fname); -#else - fatal("not built with zlib support"); - fp = NULL; /* keep compiler quiet */ -#endif } return fp; } @@ -515,20 +482,21 @@ cfopen_write(const char *path, const char *mode, int compression) * On failure, return NULL with an error code in errno. */ cfp * -cfopen(const char *path, const char *mode, int compression) +cfopen(const char *path, const char *mode, Compress *compression) { - cfp *fp = pg_malloc(sizeof(cfp)); + cfp *fp = pg_malloc0(sizeof(cfp)); - if (compression != 0) + switch (compression->alg) { #ifdef HAVE_LIBZ - if (compression != Z_DEFAULT_COMPRESSION) + case COMPR_ALG_LIBZ: + if (compression->level != Z_DEFAULT_COMPRESSION) { /* user has specified a compression level, so tell zlib to use it */ char mode_compression[32]; snprintf(mode_compression, sizeof(mode_compression), "%s%d", - mode, compression); + mode, compression->level); fp->compressedfp = gzopen(path, mode_compression); } else @@ -537,30 +505,27 @@ cfopen(const char *path, const char *mode, int compression) fp->compressedfp = gzopen(path, mode); } - fp->uncompressedfp = NULL; if (fp->compressedfp == NULL) { free_keep_errno(fp); fp = NULL; } -#else - fatal("not built with zlib support"); -#endif - } - else - { -#ifdef HAVE_LIBZ - fp->compressedfp = NULL; + return fp; #endif + + case COMPR_ALG_NONE: fp->uncompressedfp = fopen(path, mode); if (fp->uncompressedfp == NULL) { free_keep_errno(fp); fp = NULL; } - } + return fp; - return fp; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } } @@ -584,14 +549,13 @@ cfread(void *ptr, int size, cfp *fp) fatal("could not read from input file: %s", errnum == Z_ERRNO ? strerror(errno) : errmsg); } + return ret; } - else #endif - { - ret = fread(ptr, 1, size, fp->uncompressedfp); - if (ret != size && !feof(fp->uncompressedfp)) - READ_ERROR_EXIT(fp->uncompressedfp); - } + + ret = fread(ptr, 1, size, fp->uncompressedfp); + if (ret != size && !feof(fp->uncompressedfp)) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -601,9 +565,8 @@ cfwrite(const void *ptr, int size, cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzwrite(fp->compressedfp, ptr, size); - else #endif - return fwrite(ptr, 1, size, fp->uncompressedfp); + return fwrite(ptr, 1, size, fp->uncompressedfp); } int @@ -622,15 +585,12 @@ cfgetc(cfp *fp) else fatal("could not read from input file: end of file"); } + return ret; } - else #endif - { - ret = fgetc(fp->uncompressedfp); - if (ret == EOF) - READ_ERROR_EXIT(fp->uncompressedfp); - } - + ret = fgetc(fp->uncompressedfp); + if (ret == EOF) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -640,9 +600,8 @@ cfgets(cfp *fp, char *buf, int len) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzgets(fp->compressedfp, buf, len); - else #endif - return fgets(buf, len, fp->uncompressedfp); + return fgets(buf, len, fp->uncompressedfp); } int @@ -660,15 +619,13 @@ cfclose(cfp *fp) { result = gzclose(fp->compressedfp); fp->compressedfp = NULL; + return result; } - else #endif - { - result = fclose(fp->uncompressedfp); - fp->uncompressedfp = NULL; - } - free_keep_errno(fp); + result = fclose(fp->uncompressedfp); + fp->uncompressedfp = NULL; + free_keep_errno(fp); return result; } @@ -678,9 +635,9 @@ cfeof(cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzeof(fp->compressedfp); - else #endif - return feof(fp->uncompressedfp); + + return feof(fp->uncompressedfp); } const char * @@ -699,7 +656,6 @@ get_cfp_error(cfp *fp) return strerror(errno); } -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix) { @@ -714,4 +670,18 @@ hasSuffix(const char *filename, const char *suffix) suffixlen) == 0; } -#endif +/* + * Return a string for the given AH's compression. + * The string is statically allocated. + */ +const char * +compress_suffix(Compress *compression) +{ + switch (compression->alg) + { + case COMPR_ALG_LIBZ: + return ".gz"; + default: + return ""; + } +} diff --git a/src/bin/pg_dump/compress_io.h b/src/bin/pg_dump/compress_io.h index d2e6e1b854..2c073676eb 100644 --- a/src/bin/pg_dump/compress_io.h +++ b/src/bin/pg_dump/compress_io.h @@ -21,12 +21,6 @@ #define ZLIB_OUT_SIZE 4096 #define ZLIB_IN_SIZE 4096 -typedef enum -{ - COMPR_ALG_NONE, - COMPR_ALG_LIBZ -} CompressionAlgorithm; - /* Prototype for callback function to WriteDataToArchive() */ typedef void (*WriteFunc) (ArchiveHandle *AH, const char *buf, size_t len); @@ -46,8 +40,8 @@ typedef size_t (*ReadFunc) (ArchiveHandle *AH, char **buf, size_t *buflen); /* struct definition appears in compress_io.c */ typedef struct CompressorState CompressorState; -extern CompressorState *AllocateCompressor(int compression, WriteFunc writeF); -extern void ReadDataFromArchive(ArchiveHandle *AH, int compression, +extern CompressorState *AllocateCompressor(Compress *compression, WriteFunc writeF); +extern void ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF); extern void WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, const void *data, size_t dLen); @@ -56,9 +50,9 @@ extern void EndCompressor(ArchiveHandle *AH, CompressorState *cs); typedef struct cfp cfp; -extern cfp *cfopen(const char *path, const char *mode, int compression); -extern cfp *cfopen_read(const char *path, const char *mode); -extern cfp *cfopen_write(const char *path, const char *mode, int compression); +extern cfp *cfopen(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_read(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_write(const char *path, const char *mode, Compress *compression); extern int cfread(void *ptr, int size, cfp *fp); extern int cfwrite(const void *ptr, int size, cfp *fp); extern int cfgetc(cfp *fp); @@ -67,4 +61,7 @@ extern int cfclose(cfp *fp); extern int cfeof(cfp *fp); extern const char *get_cfp_error(cfp *fp); +/* also used by tar */ +extern const char * compress_suffix(Compress *compression); + #endif diff --git a/src/bin/pg_dump/pg_backup.h b/src/bin/pg_dump/pg_backup.h index 9d0056a569..f2390b7937 100644 --- a/src/bin/pg_dump/pg_backup.h +++ b/src/bin/pg_dump/pg_backup.h @@ -72,6 +72,25 @@ typedef struct _connParams char *override_dbname; } ConnParams; +typedef enum +{ + COMPR_ALG_DEFAULT = -1, + COMPR_ALG_NONE, + COMPR_ALG_LIBZ, +} CompressionAlgorithm; +/* Should be called "method" or "library" ? */ + +typedef struct Compress { + CompressionAlgorithm alg; + int level; + /* Is a nondefault level set ? This is useful since different compression + * methods have different "default" levels. For now we assume the levels + * are all integer, though. + */ + bool level_set; +} Compress; + + typedef struct _restoreOptions { int createDB; /* Issue commands to create the database */ @@ -125,7 +144,7 @@ typedef struct _restoreOptions int noDataForFailedTables; int exit_on_error; - int compression; + Compress compression; int suppressDumpWarnings; /* Suppress output of WARNING entries * to stderr */ bool single_txn; @@ -281,7 +300,7 @@ extern Archive *OpenArchive(const char *FileSpec, const ArchiveFormat fmt); /* Create a new archive */ extern Archive *CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker); /* The --list option */ diff --git a/src/bin/pg_dump/pg_backup_archiver.c b/src/bin/pg_dump/pg_backup_archiver.c index 1f82c6499b..3eb6c55600 100644 --- a/src/bin/pg_dump/pg_backup_archiver.c +++ b/src/bin/pg_dump/pg_backup_archiver.c @@ -70,7 +70,7 @@ typedef struct _parallelReadyList static ArchiveHandle *_allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr); static void _getObjectDescription(PQExpBuffer buf, TocEntry *te); static void _printTocEntry(ArchiveHandle *AH, TocEntry *te, bool isData); @@ -98,7 +98,7 @@ static int _discoverArchiveFormat(ArchiveHandle *AH); static int RestoringToDB(ArchiveHandle *AH); static void dump_lo_buf(ArchiveHandle *AH); static void dumpTimestamp(ArchiveHandle *AH, const char *msg, time_t tim); -static void SetOutput(ArchiveHandle *AH, const char *filename, int compression); +static void SetOutput(ArchiveHandle *AH, const char *filename, Compress *compress); static OutputContext SaveOutput(ArchiveHandle *AH); static void RestoreOutput(ArchiveHandle *AH, OutputContext savedContext); @@ -238,7 +238,7 @@ setupRestoreWorker(Archive *AHX) /* Public */ Archive * CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker) { @@ -253,7 +253,9 @@ CreateArchive(const char *FileSpec, const ArchiveFormat fmt, Archive * OpenArchive(const char *FileSpec, const ArchiveFormat fmt) { - ArchiveHandle *AH = _allocAH(FileSpec, fmt, 0, true, archModeRead, setupRestoreWorker); + Compress compress = {0}; + ArchiveHandle *AH = _allocAH(FileSpec, fmt, &compress, true, archModeRead, + setupRestoreWorker); return (Archive *) AH; } @@ -382,7 +384,7 @@ RestoreArchive(Archive *AHX) * Make sure we won't need (de)compression we haven't got */ #ifndef HAVE_LIBZ - if (AH->compression != 0 && AH->PrintTocDataPtr != NULL) + if (AH->compression.alg != COMPR_ALG_NONE && AH->PrintTocDataPtr != NULL) { for (te = AH->toc->next; te != AH->toc; te = te->next) { @@ -457,8 +459,8 @@ RestoreArchive(Archive *AHX) * Setup the output file if necessary. */ sav = SaveOutput(AH); - if (ropt->filename || ropt->compression) - SetOutput(AH, ropt->filename, ropt->compression); + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) + SetOutput(AH, ropt->filename, &ropt->compression); ahprintf(AH, "--\n-- PostgreSQL database dump\n--\n\n"); @@ -738,7 +740,7 @@ RestoreArchive(Archive *AHX) */ AH->stage = STAGE_FINALIZING; - if (ropt->filename || ropt->compression) + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) RestoreOutput(AH, sav); if (ropt->useDB) @@ -1123,8 +1125,9 @@ PrintTOCSummary(Archive *AHX) char stamp_str[64]; sav = SaveOutput(AH); + Assert(ropt->compression.alg == COMPR_ALG_NONE); if (ropt->filename) - SetOutput(AH, ropt->filename, 0 /* no compression */ ); + SetOutput(AH, ropt->filename, &ropt->compression); if (strftime(stamp_str, sizeof(stamp_str), PGDUMP_STRFTIME_FMT, localtime(&AH->createDate)) == 0) @@ -1133,7 +1136,7 @@ PrintTOCSummary(Archive *AHX) ahprintf(AH, ";\n; Archive created at %s\n", stamp_str); ahprintf(AH, "; dbname: %s\n; TOC Entries: %d\n; Compression: %d\n", sanitize_line(AH->archdbname, false), - AH->tocCount, AH->compression); + AH->tocCount, AH->compression.alg); switch (AH->format) { @@ -1487,7 +1490,7 @@ archprintf(Archive *AH, const char *fmt,...) *******************************/ static void -SetOutput(ArchiveHandle *AH, const char *filename, int compression) +SetOutput(ArchiveHandle *AH, const char *filename, Compress *compression) { int fn; @@ -1510,12 +1513,12 @@ SetOutput(ArchiveHandle *AH, const char *filename, int compression) /* If compression explicitly requested, use gzopen */ #ifdef HAVE_LIBZ - if (compression != 0) + if (compression->alg != COMPR_ALG_NONE) { char fmode[14]; /* Don't use PG_BINARY_x since this is zlib */ - sprintf(fmode, "wb%d", compression); + sprintf(fmode, "wb%d", compression->level); if (fn >= 0) AH->OF = gzdopen(dup(fn), fmode); else @@ -2259,7 +2262,7 @@ _discoverArchiveFormat(ArchiveHandle *AH) */ static ArchiveHandle * _allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr) { ArchiveHandle *AH; @@ -2310,7 +2313,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, AH->toc->prev = AH->toc; AH->mode = mode; - AH->compression = compression; + AH->compression = *compression; AH->dosync = dosync; memset(&(AH->sqlparse), 0, sizeof(AH->sqlparse)); @@ -2325,7 +2328,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, * Force stdin/stdout into binary mode if that is what we are using. */ #ifdef WIN32 - if ((fmt != archNull || compression != 0) && + if ((fmt != archNull || compression->alg != COMPR_ALG_NONE) && (AH->fSpec == NULL || strcmp(AH->fSpec, "") == 0)) { if (mode == archModeWrite) @@ -3741,7 +3744,7 @@ WriteHead(ArchiveHandle *AH) AH->WriteBytePtr(AH, AH->intSize); AH->WriteBytePtr(AH, AH->offSize); AH->WriteBytePtr(AH, AH->format); - WriteInt(AH, AH->compression); + WriteInt(AH, AH->compression.alg); crtm = *localtime(&AH->createDate); WriteInt(AH, crtm.tm_sec); WriteInt(AH, crtm.tm_min); @@ -3816,15 +3819,15 @@ ReadHead(ArchiveHandle *AH) if (AH->version >= K_VERS_1_2) { if (AH->version < K_VERS_1_4) - AH->compression = AH->ReadBytePtr(AH); + AH->compression.alg = AH->ReadBytePtr(AH); else - AH->compression = ReadInt(AH); + AH->compression.alg = ReadInt(AH); } else - AH->compression = Z_DEFAULT_COMPRESSION; + AH->compression.alg = Z_DEFAULT_COMPRESSION; #ifndef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) pg_log_warning("archive is compressed, but this installation does not support compression -- no data will be available"); #endif diff --git a/src/bin/pg_dump/pg_backup_archiver.h b/src/bin/pg_dump/pg_backup_archiver.h index a8ea5c7eae..6e033d040e 100644 --- a/src/bin/pg_dump/pg_backup_archiver.h +++ b/src/bin/pg_dump/pg_backup_archiver.h @@ -47,7 +47,8 @@ #define GZWRITE(p, s, n, fh) (fwrite(p, s, n, fh) * (s)) #define GZREAD(p, s, n, fh) fread(p, s, n, fh) #define GZEOF(fh) feof(fh) -/* this is just the redefinition of a libz constant */ +/* this is just the redefinition of a libz constant, in case zlib isn't + * available */ #define Z_DEFAULT_COMPRESSION (-1) typedef struct _z_stream @@ -329,14 +330,7 @@ struct _archiveHandle DumpId *tableDataId; /* TABLE DATA ids, indexed by table dumpId */ struct _tocEntry *currToc; /* Used when dumping data */ - int compression; /*--------- - * Compression requested on open(). - * Possible values for compression: - * -1 Z_DEFAULT_COMPRESSION - * 0 COMPRESSION_NONE - * 1-9 levels for gzip compression - *--------- - */ + Compress compression; /* Compression requested on open */ bool dosync; /* data requested to be synced on sight */ ArchiveMode mode; /* File mode - r or w */ void *formatData; /* Header data specific to file format */ diff --git a/src/bin/pg_dump/pg_backup_custom.c b/src/bin/pg_dump/pg_backup_custom.c index 77d402c323..55a887a236 100644 --- a/src/bin/pg_dump/pg_backup_custom.c +++ b/src/bin/pg_dump/pg_backup_custom.c @@ -298,7 +298,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) _WriteByte(AH, BLK_DATA); /* Block type */ WriteInt(AH, te->dumpId); /* For sanity check */ - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -377,7 +377,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) WriteInt(AH, oid); - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -566,7 +566,7 @@ _PrintTocData(ArchiveHandle *AH, TocEntry *te) static void _PrintData(ArchiveHandle *AH) { - ReadDataFromArchive(AH, AH->compression, _CustomReadFunc); + ReadDataFromArchive(AH, _CustomReadFunc); } static void diff --git a/src/bin/pg_dump/pg_backup_directory.c b/src/bin/pg_dump/pg_backup_directory.c index 650b542fce..8bf869c6ca 100644 --- a/src/bin/pg_dump/pg_backup_directory.c +++ b/src/bin/pg_dump/pg_backup_directory.c @@ -202,7 +202,7 @@ InitArchiveFmt_Directory(ArchiveHandle *AH) setFilePath(AH, fname, "toc.dat"); - tocFH = cfopen_read(fname, PG_BINARY_R); + tocFH = cfopen_read(fname, PG_BINARY_R, &AH->compression); if (tocFH == NULL) fatal("could not open input file \"%s\": %m", fname); @@ -327,7 +327,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) setFilePath(AH, fname, tctx->filename); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -388,7 +388,7 @@ _PrintFileData(ArchiveHandle *AH, char *filename) if (!filename) return; - cfp = cfopen_read(filename, PG_BINARY_R); + cfp = cfopen_read(filename, PG_BINARY_R, &AH->compression); if (!cfp) fatal("could not open input file \"%s\": %m", filename); @@ -435,12 +435,13 @@ _LoadBlobs(ArchiveHandle *AH) lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; char line[MAXPGPATH]; + Compress nocompression = {0}; StartRestoreBlobs(AH); setFilePath(AH, fname, "blobs.toc"); - ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R); + ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R, &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open large object TOC file \"%s\" for input: %m", @@ -573,6 +574,7 @@ _CloseArchive(ArchiveHandle *AH) { cfp *tocFH; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "toc.dat"); @@ -580,7 +582,7 @@ _CloseArchive(ArchiveHandle *AH) ctx->pstate = ParallelBackupStart(AH); /* The TOC is always created uncompressed */ - tocFH = cfopen_write(fname, PG_BINARY_W, 0); + tocFH = cfopen_write(fname, PG_BINARY_W, &nocompression); if (tocFH == NULL) fatal("could not open output file \"%s\": %m", fname); ctx->dataFH = tocFH; @@ -639,11 +641,12 @@ _StartBlobs(ArchiveHandle *AH, TocEntry *te) { lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "blobs.toc"); /* The blob TOC file is never compressed */ - ctx->blobsTocFH = cfopen_write(fname, "ab", 0); + ctx->blobsTocFH = cfopen_write(fname, "ab", &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -661,7 +664,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) snprintf(fname, MAXPGPATH, "%s/blob_%u.dat", ctx->directory, oid); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); diff --git a/src/bin/pg_dump/pg_backup_tar.c b/src/bin/pg_dump/pg_backup_tar.c index 61c9c87a9f..4ba79ab924 100644 --- a/src/bin/pg_dump/pg_backup_tar.c +++ b/src/bin/pg_dump/pg_backup_tar.c @@ -39,6 +39,7 @@ #include "pg_backup_archiver.h" #include "pg_backup_tar.h" #include "pg_backup_utils.h" +#include "compress_io.h" #include "pgtar.h" static void _ArchiveEntry(ArchiveHandle *AH, TocEntry *te); @@ -196,10 +197,10 @@ InitArchiveFmt_Tar(ArchiveHandle *AH) /* * We don't support compression because reading the files back is not - * possible since gzdopen uses buffered IO which totally screws file + * possible since gzdopen uses buffered IO which totally screws file XXX * positioning. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) fatal("compression is not supported by tar archive format"); } else @@ -254,14 +255,8 @@ _ArchiveEntry(ArchiveHandle *AH, TocEntry *te) ctx = (lclTocEntry *) pg_malloc0(sizeof(lclTocEntry)); if (te->dataDumper != NULL) { -#ifdef HAVE_LIBZ - if (AH->compression == 0) - sprintf(fn, "%d.dat", te->dumpId); - else - sprintf(fn, "%d.dat.gz", te->dumpId); -#else - sprintf(fn, "%d.dat", te->dumpId); -#endif + const char *suffix = compress_suffix(&AH->compression); + sprintf(fn, "%d.dat%s", te->dumpId, suffix); ctx->filename = pg_strdup(fn); } else @@ -352,7 +347,7 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression == 0) + if (AH->compression.alg == COMPR_ALG_NONE) tm->nFH = ctx->tarFH; else fatal("compression is not supported by tar archive format"); @@ -413,9 +408,9 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) { - sprintf(fmode, "wb%d", AH->compression); + sprintf(fmode, "wb%d", AH->compression.level); tm->zFH = gzdopen(dup(fileno(tm->tmpFH)), fmode); if (tm->zFH == NULL) fatal("could not open temporary file"); @@ -443,7 +438,7 @@ tarClose(ArchiveHandle *AH, TAR_MEMBER *th) /* * Close the GZ file since we dup'd. This will flush the buffers. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) if (GZCLOSE(th->zFH) != 0) fatal("could not close tar member"); @@ -868,7 +863,7 @@ _CloseArchive(ArchiveHandle *AH) memcpy(ropt, AH->public.ropt, sizeof(RestoreOptions)); ropt->filename = NULL; ropt->dropSchema = 1; - ropt->compression = 0; + ropt->compression.alg = COMPR_ALG_NONE; ropt->superuser = NULL; ropt->suppressDumpWarnings = true; @@ -952,16 +947,12 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) lclContext *ctx = (lclContext *) AH->formatData; lclTocEntry *tctx = (lclTocEntry *) te->formatData; char fname[255]; - char *sfx; + const char *sfx; if (oid == 0) fatal("invalid OID for large object (%u)", oid); - if (AH->compression != 0) - sfx = ".gz"; - else - sfx = ""; - + sfx = compress_suffix(&AH->compression); sprintf(fname, "blob_%u.dat%s", oid, sfx); tarPrintf(ctx->blobToc, "%u %s\n", oid, fname); diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c index 1ab98a2286..4cbc79aedc 100644 --- a/src/bin/pg_dump/pg_dump.c +++ b/src/bin/pg_dump/pg_dump.c @@ -59,6 +59,7 @@ #include "getopt_long.h" #include "libpq/libpq-fs.h" #include "parallel.h" +#include "compress_io.h" #include "pg_backup_db.h" #include "pg_backup_utils.h" #include "pg_dump.h" @@ -297,6 +298,82 @@ static void setupDumpWorker(Archive *AHX); static TableInfo *getRootTableInfo(TableInfo *tbinfo); +/* Parse the string into compression options */ +static void +parse_compression(const char *optarg, Compress *compress) +{ + if (optarg[0] == '0' && optarg[1] == '\0') + compress->alg = COMPR_ALG_NONE; + else if ((optarg[0] > '0' && optarg[0] <= '9') || + optarg[0] == '-') + { + compress->alg = COMPR_ALG_LIBZ; + compress->level_set = true; + compress->level = atoi(optarg); + if (optarg[1] != '\0') + { + pg_log_error("compression level must be in range 0..9"); + exit_nicely(1); + } + } + else + { + /* Parse a more flexible string like level=3 alg=zlib opts=long */ + for (;;) + { + char *eq = strchr(optarg, '='); + int len; + + if (eq == NULL) + { + pg_log_error("compression options must be key=value: %s", optarg); + exit_nicely(1); + } + + len = eq - optarg; + if (strncmp(optarg, "alg", len) == 0) + { + if (strchr(eq, ' ')) + len = strchr(eq, ' ') - eq - 1; + else + len = strlen(eq) - len; + if (strncmp(1+eq, "zlib", len) == 0 || + strncmp(1+eq, "libz", len) == 0) + compress->alg = COMPR_ALG_LIBZ; + else + { + pg_log_error("unknown compression algorithm: %s", 1+eq); + exit_nicely(1); + } + } + else if (strncmp(optarg, "level", len) == 0) + { + compress->level = atoi(1+eq); + compress->level_set = true; + } + else + { + pg_log_error("unknown compression setting: %s", optarg); + exit_nicely(1); + } + + optarg = strchr(eq, ' '); + if (!optarg++) + break; + } + + if (!compress->level_set) + { + const int default_compress_level[] = { + 0, /* COMPR_ALG_NONE */ + Z_DEFAULT_COMPRESSION, /* COMPR_ALG_ZLIB */ + }; + + compress->level = default_compress_level[compress->alg]; + } + } +} + int main(int argc, char **argv) { @@ -319,7 +396,7 @@ main(int argc, char **argv) char *use_role = NULL; long rowsPerInsert; int numWorkers = 1; - int compressLevel = -1; + Compress compress = { .alg = COMPR_ALG_DEFAULT }; int plainText = 0; ArchiveFormat archiveFormat = archUnknown; ArchiveMode archiveMode; @@ -532,12 +609,7 @@ main(int argc, char **argv) break; case 'Z': /* Compression Level */ - compressLevel = atoi(optarg); - if (compressLevel < 0 || compressLevel > 9) - { - pg_log_error("compression level must be in range 0..9"); - exit_nicely(1); - } + parse_compression(optarg, &compress); break; case 0: @@ -679,20 +751,28 @@ main(int argc, char **argv) plainText = 1; /* Custom and directory formats are compressed by default, others not */ - if (compressLevel == -1) + if (compress.alg == COMPR_ALG_DEFAULT) { -#ifdef HAVE_LIBZ if (archiveFormat == archCustom || archiveFormat == archDirectory) - compressLevel = Z_DEFAULT_COMPRESSION; - else + { +#ifdef HAVE_LIBZ + compress.alg = COMPR_ALG_LIBZ; + compress.level = Z_DEFAULT_COMPRESSION; #endif - compressLevel = 0; + } + else + { + compress.alg = COMPR_ALG_NONE; + compress.level = 0; + } } #ifndef HAVE_LIBZ - if (compressLevel != 0) + if (compress.alg == COMPR_ALG_LIBZ) + { pg_log_warning("requested compression not available in this installation -- archive will be uncompressed"); - compressLevel = 0; + compress.alg = 0; + } #endif /* @@ -723,7 +803,7 @@ main(int argc, char **argv) fatal("option --index-collation-versions-unknown only works in binary upgrade mode"); /* Open the output file */ - fout = CreateArchive(filename, archiveFormat, compressLevel, dosync, + fout = CreateArchive(filename, archiveFormat, &compress, dosync, archiveMode, setupDumpWorker); /* Make dump options accessible right away */ @@ -957,10 +1037,7 @@ main(int argc, char **argv) ropt->sequence_data = dopt.sequence_data; ropt->binary_upgrade = dopt.binary_upgrade; - if (compressLevel == -1) - ropt->compression = 0; - else - ropt->compression = compressLevel; + ropt->compression = compress; ropt->suppressDumpWarnings = true; /* We've already shown them */ -- 2.17.0 --GRPZ8SYKNexpdSJ7 Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="0004-struct-compressLibs.patch" ^ permalink raw reply [nested|flat] 23+ messages in thread
* [PATCH 03/20] Support multiple compression algs/levels/opts.. @ 2020-12-22 06:23 Justin Pryzby <[email protected]> 0 siblings, 0 replies; 23+ messages in thread From: Justin Pryzby @ 2020-12-22 06:23 UTC (permalink / raw) The existing implementation abtracts compressed and noncompressed I/O. This preliminary commit is intended to also allow for multiple compression algorithms. --- src/bin/pg_dump/compress_io.c | 220 +++++++++++--------------- src/bin/pg_dump/compress_io.h | 19 +-- src/bin/pg_dump/pg_backup.h | 23 ++- src/bin/pg_dump/pg_backup_archiver.c | 45 +++--- src/bin/pg_dump/pg_backup_archiver.h | 12 +- src/bin/pg_dump/pg_backup_custom.c | 6 +- src/bin/pg_dump/pg_backup_directory.c | 17 +- src/bin/pg_dump/pg_backup_tar.c | 33 ++-- src/bin/pg_dump/pg_dump.c | 115 +++++++++++--- 9 files changed, 272 insertions(+), 218 deletions(-) diff --git a/src/bin/pg_dump/compress_io.c b/src/bin/pg_dump/compress_io.c index 6a428978d4..db16fd33f2 100644 --- a/src/bin/pg_dump/compress_io.c +++ b/src/bin/pg_dump/compress_io.c @@ -74,12 +74,9 @@ struct CompressorState #endif }; -static void ParseCompressionOption(int compression, CompressionAlgorithm *alg, - int *level); - /* Routines that support zlib compressed data I/O */ #ifdef HAVE_LIBZ -static void InitCompressorZlib(CompressorState *cs, int level); +static void InitCompressorZlib(CompressorState *cs, Compress *compress); static void DeflateCompressorZlib(ArchiveHandle *AH, CompressorState *cs, bool flush); static void ReadDataFromArchiveZlib(ArchiveHandle *AH, ReadFunc readF); @@ -93,58 +90,36 @@ static void ReadDataFromArchiveNone(ArchiveHandle *AH, ReadFunc readF); static void WriteDataToArchiveNone(ArchiveHandle *AH, CompressorState *cs, const char *data, size_t dLen); -/* - * Interprets a numeric 'compression' value. The algorithm implied by the - * value (zlib or none at the moment), is returned in *alg, and the - * zlib compression level in *level. - */ -static void -ParseCompressionOption(int compression, CompressionAlgorithm *alg, int *level) -{ - if (compression == Z_DEFAULT_COMPRESSION || - (compression > 0 && compression <= 9)) - *alg = COMPR_ALG_LIBZ; - else if (compression == 0) - *alg = COMPR_ALG_NONE; - else - { - fatal("invalid compression code: %d", compression); - *alg = COMPR_ALG_NONE; /* keep compiler quiet */ - } - - /* The level is just the passed-in value. */ - if (level) - *level = compression; -} - /* Public interface routines */ /* Allocate a new compressor */ CompressorState * -AllocateCompressor(int compression, WriteFunc writeF) +AllocateCompressor(Compress *compression, WriteFunc writeF) { CompressorState *cs; - CompressionAlgorithm alg; - int level; - - ParseCompressionOption(compression, &alg, &level); - -#ifndef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - fatal("not built with zlib support"); -#endif cs = (CompressorState *) pg_malloc0(sizeof(CompressorState)); cs->writeF = writeF; - cs->comprAlg = alg; + cs->comprAlg = compression->alg; /* * Perform compression algorithm specific initialization. */ + Assert (compression->alg != COMPR_ALG_DEFAULT); + switch (compression->alg) + { #ifdef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - InitCompressorZlib(cs, level); + case COMPR_ALG_LIBZ: + InitCompressorZlib(cs, compression); + break; #endif + case COMPR_ALG_NONE: + /* Do nothing */ + break; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } return cs; } @@ -154,21 +129,21 @@ AllocateCompressor(int compression, WriteFunc writeF) * out with ahwrite(). */ void -ReadDataFromArchive(ArchiveHandle *AH, int compression, ReadFunc readF) +ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF) { - CompressionAlgorithm alg; - - ParseCompressionOption(compression, &alg, NULL); - - if (alg == COMPR_ALG_NONE) - ReadDataFromArchiveNone(AH, readF); - if (alg == COMPR_ALG_LIBZ) + switch (AH->compression.alg) { + case COMPR_ALG_NONE: + ReadDataFromArchiveNone(AH, readF); + break; #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: ReadDataFromArchiveZlib(AH, readF); -#else - fatal("not built with zlib support"); + break; #endif + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -181,16 +156,18 @@ WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, { switch (cs->comprAlg) { - case COMPR_ALG_LIBZ: #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: WriteDataToArchiveZlib(AH, cs, data, dLen); -#else - fatal("not built with zlib support"); -#endif break; +#endif case COMPR_ALG_NONE: WriteDataToArchiveNone(AH, cs, data, dLen); break; + + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -215,7 +192,7 @@ EndCompressor(ArchiveHandle *AH, CompressorState *cs) */ static void -InitCompressorZlib(CompressorState *cs, int level) +InitCompressorZlib(CompressorState *cs, Compress *compress) { z_streamp zp; @@ -232,7 +209,7 @@ InitCompressorZlib(CompressorState *cs, int level) cs->zlibOut = (char *) pg_malloc(ZLIB_OUT_SIZE + 1); cs->zlibOutSize = ZLIB_OUT_SIZE; - if (deflateInit(zp, level) != Z_OK) + if (deflateInit(zp, compress->level) != Z_OK) fatal("could not initialize compression library: %s", zp->msg); @@ -424,9 +401,7 @@ struct cfp #endif }; -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix); -#endif /* free() without changing errno; useful in several places below */ static void @@ -442,34 +417,31 @@ free_keep_errno(void *p) * Open a file for reading. 'path' is the file to open, and 'mode' should * be either "r" or "rb". * - * If the file at 'path' does not exist, we append the ".gz" suffix (if 'path' - * doesn't already have it) and try again. So if you pass "foo" as 'path', + * If the file at 'path' does not exist, we search with compressed suffix (if 'path' + * doesn't already have one) and try again. So if you pass "foo" as 'path', * this will open either "foo" or "foo.gz". * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_read(const char *path, const char *mode) +cfopen_read(const char *path, const char *mode, Compress *compression) { cfp *fp; -#ifdef HAVE_LIBZ if (hasSuffix(path, ".gz")) - fp = cfopen(path, mode, 1); + fp = cfopen(path, mode, compression); else -#endif { - fp = cfopen(path, mode, 0); -#ifdef HAVE_LIBZ + fp = cfopen(path, mode, compression); if (fp == NULL) { char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); - fp = cfopen(fname, mode, 1); + fname = psprintf("%s%s", path, suffix); + fp = cfopen(fname, mode, compression); free_keep_errno(fname); } -#endif } return fp; } @@ -479,31 +451,26 @@ cfopen_read(const char *path, const char *mode) * be a filemode as accepted by fopen() and gzopen() that indicates writing * ("w", "wb", "a", or "ab"). * - * If 'compression' is non-zero, a gzip compressed stream is opened, and - * 'compression' indicates the compression level used. The ".gz" suffix - * is automatically added to 'path' in that case. + * Use compression if specified. + * The appropriate suffix is automatically added to 'path' in that case. * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_write(const char *path, const char *mode, int compression) +cfopen_write(const char *path, const char *mode, Compress *compression) { cfp *fp; - if (compression == 0) - fp = cfopen(path, mode, 0); + if (compression->alg == COMPR_ALG_NONE) + fp = cfopen(path, mode, compression); else { -#ifdef HAVE_LIBZ char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); + fname = psprintf("%s%s", path, suffix); fp = cfopen(fname, mode, compression); free_keep_errno(fname); -#else - fatal("not built with zlib support"); - fp = NULL; /* keep compiler quiet */ -#endif } return fp; } @@ -515,20 +482,21 @@ cfopen_write(const char *path, const char *mode, int compression) * On failure, return NULL with an error code in errno. */ cfp * -cfopen(const char *path, const char *mode, int compression) +cfopen(const char *path, const char *mode, Compress *compression) { - cfp *fp = pg_malloc(sizeof(cfp)); + cfp *fp = pg_malloc0(sizeof(cfp)); - if (compression != 0) + switch (compression->alg) { #ifdef HAVE_LIBZ - if (compression != Z_DEFAULT_COMPRESSION) + case COMPR_ALG_LIBZ: + if (compression->level != Z_DEFAULT_COMPRESSION) { /* user has specified a compression level, so tell zlib to use it */ char mode_compression[32]; snprintf(mode_compression, sizeof(mode_compression), "%s%d", - mode, compression); + mode, compression->level); fp->compressedfp = gzopen(path, mode_compression); } else @@ -537,30 +505,27 @@ cfopen(const char *path, const char *mode, int compression) fp->compressedfp = gzopen(path, mode); } - fp->uncompressedfp = NULL; if (fp->compressedfp == NULL) { free_keep_errno(fp); fp = NULL; } -#else - fatal("not built with zlib support"); -#endif - } - else - { -#ifdef HAVE_LIBZ - fp->compressedfp = NULL; + return fp; #endif + + case COMPR_ALG_NONE: fp->uncompressedfp = fopen(path, mode); if (fp->uncompressedfp == NULL) { free_keep_errno(fp); fp = NULL; } - } + return fp; - return fp; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } } @@ -584,14 +549,13 @@ cfread(void *ptr, int size, cfp *fp) fatal("could not read from input file: %s", errnum == Z_ERRNO ? strerror(errno) : errmsg); } + return ret; } - else #endif - { - ret = fread(ptr, 1, size, fp->uncompressedfp); - if (ret != size && !feof(fp->uncompressedfp)) - READ_ERROR_EXIT(fp->uncompressedfp); - } + + ret = fread(ptr, 1, size, fp->uncompressedfp); + if (ret != size && !feof(fp->uncompressedfp)) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -601,9 +565,8 @@ cfwrite(const void *ptr, int size, cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzwrite(fp->compressedfp, ptr, size); - else #endif - return fwrite(ptr, 1, size, fp->uncompressedfp); + return fwrite(ptr, 1, size, fp->uncompressedfp); } int @@ -622,15 +585,12 @@ cfgetc(cfp *fp) else fatal("could not read from input file: end of file"); } + return ret; } - else #endif - { - ret = fgetc(fp->uncompressedfp); - if (ret == EOF) - READ_ERROR_EXIT(fp->uncompressedfp); - } - + ret = fgetc(fp->uncompressedfp); + if (ret == EOF) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -640,9 +600,8 @@ cfgets(cfp *fp, char *buf, int len) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzgets(fp->compressedfp, buf, len); - else #endif - return fgets(buf, len, fp->uncompressedfp); + return fgets(buf, len, fp->uncompressedfp); } int @@ -660,15 +619,13 @@ cfclose(cfp *fp) { result = gzclose(fp->compressedfp); fp->compressedfp = NULL; + return result; } - else #endif - { - result = fclose(fp->uncompressedfp); - fp->uncompressedfp = NULL; - } - free_keep_errno(fp); + result = fclose(fp->uncompressedfp); + fp->uncompressedfp = NULL; + free_keep_errno(fp); return result; } @@ -678,9 +635,9 @@ cfeof(cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzeof(fp->compressedfp); - else #endif - return feof(fp->uncompressedfp); + + return feof(fp->uncompressedfp); } const char * @@ -699,7 +656,6 @@ get_cfp_error(cfp *fp) return strerror(errno); } -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix) { @@ -714,4 +670,18 @@ hasSuffix(const char *filename, const char *suffix) suffixlen) == 0; } -#endif +/* + * Return a string for the given AH's compression. + * The string is statically allocated. + */ +const char * +compress_suffix(Compress *compression) +{ + switch (compression->alg) + { + case COMPR_ALG_LIBZ: + return ".gz"; + default: + return ""; + } +} diff --git a/src/bin/pg_dump/compress_io.h b/src/bin/pg_dump/compress_io.h index d2e6e1b854..2c073676eb 100644 --- a/src/bin/pg_dump/compress_io.h +++ b/src/bin/pg_dump/compress_io.h @@ -21,12 +21,6 @@ #define ZLIB_OUT_SIZE 4096 #define ZLIB_IN_SIZE 4096 -typedef enum -{ - COMPR_ALG_NONE, - COMPR_ALG_LIBZ -} CompressionAlgorithm; - /* Prototype for callback function to WriteDataToArchive() */ typedef void (*WriteFunc) (ArchiveHandle *AH, const char *buf, size_t len); @@ -46,8 +40,8 @@ typedef size_t (*ReadFunc) (ArchiveHandle *AH, char **buf, size_t *buflen); /* struct definition appears in compress_io.c */ typedef struct CompressorState CompressorState; -extern CompressorState *AllocateCompressor(int compression, WriteFunc writeF); -extern void ReadDataFromArchive(ArchiveHandle *AH, int compression, +extern CompressorState *AllocateCompressor(Compress *compression, WriteFunc writeF); +extern void ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF); extern void WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, const void *data, size_t dLen); @@ -56,9 +50,9 @@ extern void EndCompressor(ArchiveHandle *AH, CompressorState *cs); typedef struct cfp cfp; -extern cfp *cfopen(const char *path, const char *mode, int compression); -extern cfp *cfopen_read(const char *path, const char *mode); -extern cfp *cfopen_write(const char *path, const char *mode, int compression); +extern cfp *cfopen(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_read(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_write(const char *path, const char *mode, Compress *compression); extern int cfread(void *ptr, int size, cfp *fp); extern int cfwrite(const void *ptr, int size, cfp *fp); extern int cfgetc(cfp *fp); @@ -67,4 +61,7 @@ extern int cfclose(cfp *fp); extern int cfeof(cfp *fp); extern const char *get_cfp_error(cfp *fp); +/* also used by tar */ +extern const char * compress_suffix(Compress *compression); + #endif diff --git a/src/bin/pg_dump/pg_backup.h b/src/bin/pg_dump/pg_backup.h index 9d0056a569..f2390b7937 100644 --- a/src/bin/pg_dump/pg_backup.h +++ b/src/bin/pg_dump/pg_backup.h @@ -72,6 +72,25 @@ typedef struct _connParams char *override_dbname; } ConnParams; +typedef enum +{ + COMPR_ALG_DEFAULT = -1, + COMPR_ALG_NONE, + COMPR_ALG_LIBZ, +} CompressionAlgorithm; +/* Should be called "method" or "library" ? */ + +typedef struct Compress { + CompressionAlgorithm alg; + int level; + /* Is a nondefault level set ? This is useful since different compression + * methods have different "default" levels. For now we assume the levels + * are all integer, though. + */ + bool level_set; +} Compress; + + typedef struct _restoreOptions { int createDB; /* Issue commands to create the database */ @@ -125,7 +144,7 @@ typedef struct _restoreOptions int noDataForFailedTables; int exit_on_error; - int compression; + Compress compression; int suppressDumpWarnings; /* Suppress output of WARNING entries * to stderr */ bool single_txn; @@ -281,7 +300,7 @@ extern Archive *OpenArchive(const char *FileSpec, const ArchiveFormat fmt); /* Create a new archive */ extern Archive *CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker); /* The --list option */ diff --git a/src/bin/pg_dump/pg_backup_archiver.c b/src/bin/pg_dump/pg_backup_archiver.c index 1f82c6499b..3eb6c55600 100644 --- a/src/bin/pg_dump/pg_backup_archiver.c +++ b/src/bin/pg_dump/pg_backup_archiver.c @@ -70,7 +70,7 @@ typedef struct _parallelReadyList static ArchiveHandle *_allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr); static void _getObjectDescription(PQExpBuffer buf, TocEntry *te); static void _printTocEntry(ArchiveHandle *AH, TocEntry *te, bool isData); @@ -98,7 +98,7 @@ static int _discoverArchiveFormat(ArchiveHandle *AH); static int RestoringToDB(ArchiveHandle *AH); static void dump_lo_buf(ArchiveHandle *AH); static void dumpTimestamp(ArchiveHandle *AH, const char *msg, time_t tim); -static void SetOutput(ArchiveHandle *AH, const char *filename, int compression); +static void SetOutput(ArchiveHandle *AH, const char *filename, Compress *compress); static OutputContext SaveOutput(ArchiveHandle *AH); static void RestoreOutput(ArchiveHandle *AH, OutputContext savedContext); @@ -238,7 +238,7 @@ setupRestoreWorker(Archive *AHX) /* Public */ Archive * CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker) { @@ -253,7 +253,9 @@ CreateArchive(const char *FileSpec, const ArchiveFormat fmt, Archive * OpenArchive(const char *FileSpec, const ArchiveFormat fmt) { - ArchiveHandle *AH = _allocAH(FileSpec, fmt, 0, true, archModeRead, setupRestoreWorker); + Compress compress = {0}; + ArchiveHandle *AH = _allocAH(FileSpec, fmt, &compress, true, archModeRead, + setupRestoreWorker); return (Archive *) AH; } @@ -382,7 +384,7 @@ RestoreArchive(Archive *AHX) * Make sure we won't need (de)compression we haven't got */ #ifndef HAVE_LIBZ - if (AH->compression != 0 && AH->PrintTocDataPtr != NULL) + if (AH->compression.alg != COMPR_ALG_NONE && AH->PrintTocDataPtr != NULL) { for (te = AH->toc->next; te != AH->toc; te = te->next) { @@ -457,8 +459,8 @@ RestoreArchive(Archive *AHX) * Setup the output file if necessary. */ sav = SaveOutput(AH); - if (ropt->filename || ropt->compression) - SetOutput(AH, ropt->filename, ropt->compression); + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) + SetOutput(AH, ropt->filename, &ropt->compression); ahprintf(AH, "--\n-- PostgreSQL database dump\n--\n\n"); @@ -738,7 +740,7 @@ RestoreArchive(Archive *AHX) */ AH->stage = STAGE_FINALIZING; - if (ropt->filename || ropt->compression) + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) RestoreOutput(AH, sav); if (ropt->useDB) @@ -1123,8 +1125,9 @@ PrintTOCSummary(Archive *AHX) char stamp_str[64]; sav = SaveOutput(AH); + Assert(ropt->compression.alg == COMPR_ALG_NONE); if (ropt->filename) - SetOutput(AH, ropt->filename, 0 /* no compression */ ); + SetOutput(AH, ropt->filename, &ropt->compression); if (strftime(stamp_str, sizeof(stamp_str), PGDUMP_STRFTIME_FMT, localtime(&AH->createDate)) == 0) @@ -1133,7 +1136,7 @@ PrintTOCSummary(Archive *AHX) ahprintf(AH, ";\n; Archive created at %s\n", stamp_str); ahprintf(AH, "; dbname: %s\n; TOC Entries: %d\n; Compression: %d\n", sanitize_line(AH->archdbname, false), - AH->tocCount, AH->compression); + AH->tocCount, AH->compression.alg); switch (AH->format) { @@ -1487,7 +1490,7 @@ archprintf(Archive *AH, const char *fmt,...) *******************************/ static void -SetOutput(ArchiveHandle *AH, const char *filename, int compression) +SetOutput(ArchiveHandle *AH, const char *filename, Compress *compression) { int fn; @@ -1510,12 +1513,12 @@ SetOutput(ArchiveHandle *AH, const char *filename, int compression) /* If compression explicitly requested, use gzopen */ #ifdef HAVE_LIBZ - if (compression != 0) + if (compression->alg != COMPR_ALG_NONE) { char fmode[14]; /* Don't use PG_BINARY_x since this is zlib */ - sprintf(fmode, "wb%d", compression); + sprintf(fmode, "wb%d", compression->level); if (fn >= 0) AH->OF = gzdopen(dup(fn), fmode); else @@ -2259,7 +2262,7 @@ _discoverArchiveFormat(ArchiveHandle *AH) */ static ArchiveHandle * _allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr) { ArchiveHandle *AH; @@ -2310,7 +2313,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, AH->toc->prev = AH->toc; AH->mode = mode; - AH->compression = compression; + AH->compression = *compression; AH->dosync = dosync; memset(&(AH->sqlparse), 0, sizeof(AH->sqlparse)); @@ -2325,7 +2328,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, * Force stdin/stdout into binary mode if that is what we are using. */ #ifdef WIN32 - if ((fmt != archNull || compression != 0) && + if ((fmt != archNull || compression->alg != COMPR_ALG_NONE) && (AH->fSpec == NULL || strcmp(AH->fSpec, "") == 0)) { if (mode == archModeWrite) @@ -3741,7 +3744,7 @@ WriteHead(ArchiveHandle *AH) AH->WriteBytePtr(AH, AH->intSize); AH->WriteBytePtr(AH, AH->offSize); AH->WriteBytePtr(AH, AH->format); - WriteInt(AH, AH->compression); + WriteInt(AH, AH->compression.alg); crtm = *localtime(&AH->createDate); WriteInt(AH, crtm.tm_sec); WriteInt(AH, crtm.tm_min); @@ -3816,15 +3819,15 @@ ReadHead(ArchiveHandle *AH) if (AH->version >= K_VERS_1_2) { if (AH->version < K_VERS_1_4) - AH->compression = AH->ReadBytePtr(AH); + AH->compression.alg = AH->ReadBytePtr(AH); else - AH->compression = ReadInt(AH); + AH->compression.alg = ReadInt(AH); } else - AH->compression = Z_DEFAULT_COMPRESSION; + AH->compression.alg = Z_DEFAULT_COMPRESSION; #ifndef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) pg_log_warning("archive is compressed, but this installation does not support compression -- no data will be available"); #endif diff --git a/src/bin/pg_dump/pg_backup_archiver.h b/src/bin/pg_dump/pg_backup_archiver.h index a8ea5c7eae..6e033d040e 100644 --- a/src/bin/pg_dump/pg_backup_archiver.h +++ b/src/bin/pg_dump/pg_backup_archiver.h @@ -47,7 +47,8 @@ #define GZWRITE(p, s, n, fh) (fwrite(p, s, n, fh) * (s)) #define GZREAD(p, s, n, fh) fread(p, s, n, fh) #define GZEOF(fh) feof(fh) -/* this is just the redefinition of a libz constant */ +/* this is just the redefinition of a libz constant, in case zlib isn't + * available */ #define Z_DEFAULT_COMPRESSION (-1) typedef struct _z_stream @@ -329,14 +330,7 @@ struct _archiveHandle DumpId *tableDataId; /* TABLE DATA ids, indexed by table dumpId */ struct _tocEntry *currToc; /* Used when dumping data */ - int compression; /*--------- - * Compression requested on open(). - * Possible values for compression: - * -1 Z_DEFAULT_COMPRESSION - * 0 COMPRESSION_NONE - * 1-9 levels for gzip compression - *--------- - */ + Compress compression; /* Compression requested on open */ bool dosync; /* data requested to be synced on sight */ ArchiveMode mode; /* File mode - r or w */ void *formatData; /* Header data specific to file format */ diff --git a/src/bin/pg_dump/pg_backup_custom.c b/src/bin/pg_dump/pg_backup_custom.c index 77d402c323..55a887a236 100644 --- a/src/bin/pg_dump/pg_backup_custom.c +++ b/src/bin/pg_dump/pg_backup_custom.c @@ -298,7 +298,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) _WriteByte(AH, BLK_DATA); /* Block type */ WriteInt(AH, te->dumpId); /* For sanity check */ - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -377,7 +377,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) WriteInt(AH, oid); - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -566,7 +566,7 @@ _PrintTocData(ArchiveHandle *AH, TocEntry *te) static void _PrintData(ArchiveHandle *AH) { - ReadDataFromArchive(AH, AH->compression, _CustomReadFunc); + ReadDataFromArchive(AH, _CustomReadFunc); } static void diff --git a/src/bin/pg_dump/pg_backup_directory.c b/src/bin/pg_dump/pg_backup_directory.c index 650b542fce..8bf869c6ca 100644 --- a/src/bin/pg_dump/pg_backup_directory.c +++ b/src/bin/pg_dump/pg_backup_directory.c @@ -202,7 +202,7 @@ InitArchiveFmt_Directory(ArchiveHandle *AH) setFilePath(AH, fname, "toc.dat"); - tocFH = cfopen_read(fname, PG_BINARY_R); + tocFH = cfopen_read(fname, PG_BINARY_R, &AH->compression); if (tocFH == NULL) fatal("could not open input file \"%s\": %m", fname); @@ -327,7 +327,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) setFilePath(AH, fname, tctx->filename); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -388,7 +388,7 @@ _PrintFileData(ArchiveHandle *AH, char *filename) if (!filename) return; - cfp = cfopen_read(filename, PG_BINARY_R); + cfp = cfopen_read(filename, PG_BINARY_R, &AH->compression); if (!cfp) fatal("could not open input file \"%s\": %m", filename); @@ -435,12 +435,13 @@ _LoadBlobs(ArchiveHandle *AH) lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; char line[MAXPGPATH]; + Compress nocompression = {0}; StartRestoreBlobs(AH); setFilePath(AH, fname, "blobs.toc"); - ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R); + ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R, &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open large object TOC file \"%s\" for input: %m", @@ -573,6 +574,7 @@ _CloseArchive(ArchiveHandle *AH) { cfp *tocFH; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "toc.dat"); @@ -580,7 +582,7 @@ _CloseArchive(ArchiveHandle *AH) ctx->pstate = ParallelBackupStart(AH); /* The TOC is always created uncompressed */ - tocFH = cfopen_write(fname, PG_BINARY_W, 0); + tocFH = cfopen_write(fname, PG_BINARY_W, &nocompression); if (tocFH == NULL) fatal("could not open output file \"%s\": %m", fname); ctx->dataFH = tocFH; @@ -639,11 +641,12 @@ _StartBlobs(ArchiveHandle *AH, TocEntry *te) { lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "blobs.toc"); /* The blob TOC file is never compressed */ - ctx->blobsTocFH = cfopen_write(fname, "ab", 0); + ctx->blobsTocFH = cfopen_write(fname, "ab", &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -661,7 +664,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) snprintf(fname, MAXPGPATH, "%s/blob_%u.dat", ctx->directory, oid); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); diff --git a/src/bin/pg_dump/pg_backup_tar.c b/src/bin/pg_dump/pg_backup_tar.c index 61c9c87a9f..4ba79ab924 100644 --- a/src/bin/pg_dump/pg_backup_tar.c +++ b/src/bin/pg_dump/pg_backup_tar.c @@ -39,6 +39,7 @@ #include "pg_backup_archiver.h" #include "pg_backup_tar.h" #include "pg_backup_utils.h" +#include "compress_io.h" #include "pgtar.h" static void _ArchiveEntry(ArchiveHandle *AH, TocEntry *te); @@ -196,10 +197,10 @@ InitArchiveFmt_Tar(ArchiveHandle *AH) /* * We don't support compression because reading the files back is not - * possible since gzdopen uses buffered IO which totally screws file + * possible since gzdopen uses buffered IO which totally screws file XXX * positioning. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) fatal("compression is not supported by tar archive format"); } else @@ -254,14 +255,8 @@ _ArchiveEntry(ArchiveHandle *AH, TocEntry *te) ctx = (lclTocEntry *) pg_malloc0(sizeof(lclTocEntry)); if (te->dataDumper != NULL) { -#ifdef HAVE_LIBZ - if (AH->compression == 0) - sprintf(fn, "%d.dat", te->dumpId); - else - sprintf(fn, "%d.dat.gz", te->dumpId); -#else - sprintf(fn, "%d.dat", te->dumpId); -#endif + const char *suffix = compress_suffix(&AH->compression); + sprintf(fn, "%d.dat%s", te->dumpId, suffix); ctx->filename = pg_strdup(fn); } else @@ -352,7 +347,7 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression == 0) + if (AH->compression.alg == COMPR_ALG_NONE) tm->nFH = ctx->tarFH; else fatal("compression is not supported by tar archive format"); @@ -413,9 +408,9 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) { - sprintf(fmode, "wb%d", AH->compression); + sprintf(fmode, "wb%d", AH->compression.level); tm->zFH = gzdopen(dup(fileno(tm->tmpFH)), fmode); if (tm->zFH == NULL) fatal("could not open temporary file"); @@ -443,7 +438,7 @@ tarClose(ArchiveHandle *AH, TAR_MEMBER *th) /* * Close the GZ file since we dup'd. This will flush the buffers. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) if (GZCLOSE(th->zFH) != 0) fatal("could not close tar member"); @@ -868,7 +863,7 @@ _CloseArchive(ArchiveHandle *AH) memcpy(ropt, AH->public.ropt, sizeof(RestoreOptions)); ropt->filename = NULL; ropt->dropSchema = 1; - ropt->compression = 0; + ropt->compression.alg = COMPR_ALG_NONE; ropt->superuser = NULL; ropt->suppressDumpWarnings = true; @@ -952,16 +947,12 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) lclContext *ctx = (lclContext *) AH->formatData; lclTocEntry *tctx = (lclTocEntry *) te->formatData; char fname[255]; - char *sfx; + const char *sfx; if (oid == 0) fatal("invalid OID for large object (%u)", oid); - if (AH->compression != 0) - sfx = ".gz"; - else - sfx = ""; - + sfx = compress_suffix(&AH->compression); sprintf(fname, "blob_%u.dat%s", oid, sfx); tarPrintf(ctx->blobToc, "%u %s\n", oid, fname); diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c index 1ab98a2286..4cbc79aedc 100644 --- a/src/bin/pg_dump/pg_dump.c +++ b/src/bin/pg_dump/pg_dump.c @@ -59,6 +59,7 @@ #include "getopt_long.h" #include "libpq/libpq-fs.h" #include "parallel.h" +#include "compress_io.h" #include "pg_backup_db.h" #include "pg_backup_utils.h" #include "pg_dump.h" @@ -297,6 +298,82 @@ static void setupDumpWorker(Archive *AHX); static TableInfo *getRootTableInfo(TableInfo *tbinfo); +/* Parse the string into compression options */ +static void +parse_compression(const char *optarg, Compress *compress) +{ + if (optarg[0] == '0' && optarg[1] == '\0') + compress->alg = COMPR_ALG_NONE; + else if ((optarg[0] > '0' && optarg[0] <= '9') || + optarg[0] == '-') + { + compress->alg = COMPR_ALG_LIBZ; + compress->level_set = true; + compress->level = atoi(optarg); + if (optarg[1] != '\0') + { + pg_log_error("compression level must be in range 0..9"); + exit_nicely(1); + } + } + else + { + /* Parse a more flexible string like level=3 alg=zlib opts=long */ + for (;;) + { + char *eq = strchr(optarg, '='); + int len; + + if (eq == NULL) + { + pg_log_error("compression options must be key=value: %s", optarg); + exit_nicely(1); + } + + len = eq - optarg; + if (strncmp(optarg, "alg", len) == 0) + { + if (strchr(eq, ' ')) + len = strchr(eq, ' ') - eq - 1; + else + len = strlen(eq) - len; + if (strncmp(1+eq, "zlib", len) == 0 || + strncmp(1+eq, "libz", len) == 0) + compress->alg = COMPR_ALG_LIBZ; + else + { + pg_log_error("unknown compression algorithm: %s", 1+eq); + exit_nicely(1); + } + } + else if (strncmp(optarg, "level", len) == 0) + { + compress->level = atoi(1+eq); + compress->level_set = true; + } + else + { + pg_log_error("unknown compression setting: %s", optarg); + exit_nicely(1); + } + + optarg = strchr(eq, ' '); + if (!optarg++) + break; + } + + if (!compress->level_set) + { + const int default_compress_level[] = { + 0, /* COMPR_ALG_NONE */ + Z_DEFAULT_COMPRESSION, /* COMPR_ALG_ZLIB */ + }; + + compress->level = default_compress_level[compress->alg]; + } + } +} + int main(int argc, char **argv) { @@ -319,7 +396,7 @@ main(int argc, char **argv) char *use_role = NULL; long rowsPerInsert; int numWorkers = 1; - int compressLevel = -1; + Compress compress = { .alg = COMPR_ALG_DEFAULT }; int plainText = 0; ArchiveFormat archiveFormat = archUnknown; ArchiveMode archiveMode; @@ -532,12 +609,7 @@ main(int argc, char **argv) break; case 'Z': /* Compression Level */ - compressLevel = atoi(optarg); - if (compressLevel < 0 || compressLevel > 9) - { - pg_log_error("compression level must be in range 0..9"); - exit_nicely(1); - } + parse_compression(optarg, &compress); break; case 0: @@ -679,20 +751,28 @@ main(int argc, char **argv) plainText = 1; /* Custom and directory formats are compressed by default, others not */ - if (compressLevel == -1) + if (compress.alg == COMPR_ALG_DEFAULT) { -#ifdef HAVE_LIBZ if (archiveFormat == archCustom || archiveFormat == archDirectory) - compressLevel = Z_DEFAULT_COMPRESSION; - else + { +#ifdef HAVE_LIBZ + compress.alg = COMPR_ALG_LIBZ; + compress.level = Z_DEFAULT_COMPRESSION; #endif - compressLevel = 0; + } + else + { + compress.alg = COMPR_ALG_NONE; + compress.level = 0; + } } #ifndef HAVE_LIBZ - if (compressLevel != 0) + if (compress.alg == COMPR_ALG_LIBZ) + { pg_log_warning("requested compression not available in this installation -- archive will be uncompressed"); - compressLevel = 0; + compress.alg = 0; + } #endif /* @@ -723,7 +803,7 @@ main(int argc, char **argv) fatal("option --index-collation-versions-unknown only works in binary upgrade mode"); /* Open the output file */ - fout = CreateArchive(filename, archiveFormat, compressLevel, dosync, + fout = CreateArchive(filename, archiveFormat, &compress, dosync, archiveMode, setupDumpWorker); /* Make dump options accessible right away */ @@ -957,10 +1037,7 @@ main(int argc, char **argv) ropt->sequence_data = dopt.sequence_data; ropt->binary_upgrade = dopt.binary_upgrade; - if (compressLevel == -1) - ropt->compression = 0; - else - ropt->compression = compressLevel; + ropt->compression = compress; ropt->suppressDumpWarnings = true; /* We've already shown them */ -- 2.17.0 --GRPZ8SYKNexpdSJ7 Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="0004-struct-compressLibs.patch" ^ permalink raw reply [nested|flat] 23+ messages in thread
* [PATCH 03/20] Support multiple compression algs/levels/opts.. @ 2020-12-22 06:23 Justin Pryzby <[email protected]> 0 siblings, 0 replies; 23+ messages in thread From: Justin Pryzby @ 2020-12-22 06:23 UTC (permalink / raw) The existing implementation abtracts compressed and noncompressed I/O. This preliminary commit is intended to also allow for multiple compression algorithms. --- src/bin/pg_dump/compress_io.c | 220 +++++++++++--------------- src/bin/pg_dump/compress_io.h | 19 +-- src/bin/pg_dump/pg_backup.h | 23 ++- src/bin/pg_dump/pg_backup_archiver.c | 45 +++--- src/bin/pg_dump/pg_backup_archiver.h | 12 +- src/bin/pg_dump/pg_backup_custom.c | 6 +- src/bin/pg_dump/pg_backup_directory.c | 17 +- src/bin/pg_dump/pg_backup_tar.c | 33 ++-- src/bin/pg_dump/pg_dump.c | 115 +++++++++++--- 9 files changed, 272 insertions(+), 218 deletions(-) diff --git a/src/bin/pg_dump/compress_io.c b/src/bin/pg_dump/compress_io.c index 6a428978d4..db16fd33f2 100644 --- a/src/bin/pg_dump/compress_io.c +++ b/src/bin/pg_dump/compress_io.c @@ -74,12 +74,9 @@ struct CompressorState #endif }; -static void ParseCompressionOption(int compression, CompressionAlgorithm *alg, - int *level); - /* Routines that support zlib compressed data I/O */ #ifdef HAVE_LIBZ -static void InitCompressorZlib(CompressorState *cs, int level); +static void InitCompressorZlib(CompressorState *cs, Compress *compress); static void DeflateCompressorZlib(ArchiveHandle *AH, CompressorState *cs, bool flush); static void ReadDataFromArchiveZlib(ArchiveHandle *AH, ReadFunc readF); @@ -93,58 +90,36 @@ static void ReadDataFromArchiveNone(ArchiveHandle *AH, ReadFunc readF); static void WriteDataToArchiveNone(ArchiveHandle *AH, CompressorState *cs, const char *data, size_t dLen); -/* - * Interprets a numeric 'compression' value. The algorithm implied by the - * value (zlib or none at the moment), is returned in *alg, and the - * zlib compression level in *level. - */ -static void -ParseCompressionOption(int compression, CompressionAlgorithm *alg, int *level) -{ - if (compression == Z_DEFAULT_COMPRESSION || - (compression > 0 && compression <= 9)) - *alg = COMPR_ALG_LIBZ; - else if (compression == 0) - *alg = COMPR_ALG_NONE; - else - { - fatal("invalid compression code: %d", compression); - *alg = COMPR_ALG_NONE; /* keep compiler quiet */ - } - - /* The level is just the passed-in value. */ - if (level) - *level = compression; -} - /* Public interface routines */ /* Allocate a new compressor */ CompressorState * -AllocateCompressor(int compression, WriteFunc writeF) +AllocateCompressor(Compress *compression, WriteFunc writeF) { CompressorState *cs; - CompressionAlgorithm alg; - int level; - - ParseCompressionOption(compression, &alg, &level); - -#ifndef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - fatal("not built with zlib support"); -#endif cs = (CompressorState *) pg_malloc0(sizeof(CompressorState)); cs->writeF = writeF; - cs->comprAlg = alg; + cs->comprAlg = compression->alg; /* * Perform compression algorithm specific initialization. */ + Assert (compression->alg != COMPR_ALG_DEFAULT); + switch (compression->alg) + { #ifdef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - InitCompressorZlib(cs, level); + case COMPR_ALG_LIBZ: + InitCompressorZlib(cs, compression); + break; #endif + case COMPR_ALG_NONE: + /* Do nothing */ + break; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } return cs; } @@ -154,21 +129,21 @@ AllocateCompressor(int compression, WriteFunc writeF) * out with ahwrite(). */ void -ReadDataFromArchive(ArchiveHandle *AH, int compression, ReadFunc readF) +ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF) { - CompressionAlgorithm alg; - - ParseCompressionOption(compression, &alg, NULL); - - if (alg == COMPR_ALG_NONE) - ReadDataFromArchiveNone(AH, readF); - if (alg == COMPR_ALG_LIBZ) + switch (AH->compression.alg) { + case COMPR_ALG_NONE: + ReadDataFromArchiveNone(AH, readF); + break; #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: ReadDataFromArchiveZlib(AH, readF); -#else - fatal("not built with zlib support"); + break; #endif + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -181,16 +156,18 @@ WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, { switch (cs->comprAlg) { - case COMPR_ALG_LIBZ: #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: WriteDataToArchiveZlib(AH, cs, data, dLen); -#else - fatal("not built with zlib support"); -#endif break; +#endif case COMPR_ALG_NONE: WriteDataToArchiveNone(AH, cs, data, dLen); break; + + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -215,7 +192,7 @@ EndCompressor(ArchiveHandle *AH, CompressorState *cs) */ static void -InitCompressorZlib(CompressorState *cs, int level) +InitCompressorZlib(CompressorState *cs, Compress *compress) { z_streamp zp; @@ -232,7 +209,7 @@ InitCompressorZlib(CompressorState *cs, int level) cs->zlibOut = (char *) pg_malloc(ZLIB_OUT_SIZE + 1); cs->zlibOutSize = ZLIB_OUT_SIZE; - if (deflateInit(zp, level) != Z_OK) + if (deflateInit(zp, compress->level) != Z_OK) fatal("could not initialize compression library: %s", zp->msg); @@ -424,9 +401,7 @@ struct cfp #endif }; -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix); -#endif /* free() without changing errno; useful in several places below */ static void @@ -442,34 +417,31 @@ free_keep_errno(void *p) * Open a file for reading. 'path' is the file to open, and 'mode' should * be either "r" or "rb". * - * If the file at 'path' does not exist, we append the ".gz" suffix (if 'path' - * doesn't already have it) and try again. So if you pass "foo" as 'path', + * If the file at 'path' does not exist, we search with compressed suffix (if 'path' + * doesn't already have one) and try again. So if you pass "foo" as 'path', * this will open either "foo" or "foo.gz". * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_read(const char *path, const char *mode) +cfopen_read(const char *path, const char *mode, Compress *compression) { cfp *fp; -#ifdef HAVE_LIBZ if (hasSuffix(path, ".gz")) - fp = cfopen(path, mode, 1); + fp = cfopen(path, mode, compression); else -#endif { - fp = cfopen(path, mode, 0); -#ifdef HAVE_LIBZ + fp = cfopen(path, mode, compression); if (fp == NULL) { char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); - fp = cfopen(fname, mode, 1); + fname = psprintf("%s%s", path, suffix); + fp = cfopen(fname, mode, compression); free_keep_errno(fname); } -#endif } return fp; } @@ -479,31 +451,26 @@ cfopen_read(const char *path, const char *mode) * be a filemode as accepted by fopen() and gzopen() that indicates writing * ("w", "wb", "a", or "ab"). * - * If 'compression' is non-zero, a gzip compressed stream is opened, and - * 'compression' indicates the compression level used. The ".gz" suffix - * is automatically added to 'path' in that case. + * Use compression if specified. + * The appropriate suffix is automatically added to 'path' in that case. * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_write(const char *path, const char *mode, int compression) +cfopen_write(const char *path, const char *mode, Compress *compression) { cfp *fp; - if (compression == 0) - fp = cfopen(path, mode, 0); + if (compression->alg == COMPR_ALG_NONE) + fp = cfopen(path, mode, compression); else { -#ifdef HAVE_LIBZ char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); + fname = psprintf("%s%s", path, suffix); fp = cfopen(fname, mode, compression); free_keep_errno(fname); -#else - fatal("not built with zlib support"); - fp = NULL; /* keep compiler quiet */ -#endif } return fp; } @@ -515,20 +482,21 @@ cfopen_write(const char *path, const char *mode, int compression) * On failure, return NULL with an error code in errno. */ cfp * -cfopen(const char *path, const char *mode, int compression) +cfopen(const char *path, const char *mode, Compress *compression) { - cfp *fp = pg_malloc(sizeof(cfp)); + cfp *fp = pg_malloc0(sizeof(cfp)); - if (compression != 0) + switch (compression->alg) { #ifdef HAVE_LIBZ - if (compression != Z_DEFAULT_COMPRESSION) + case COMPR_ALG_LIBZ: + if (compression->level != Z_DEFAULT_COMPRESSION) { /* user has specified a compression level, so tell zlib to use it */ char mode_compression[32]; snprintf(mode_compression, sizeof(mode_compression), "%s%d", - mode, compression); + mode, compression->level); fp->compressedfp = gzopen(path, mode_compression); } else @@ -537,30 +505,27 @@ cfopen(const char *path, const char *mode, int compression) fp->compressedfp = gzopen(path, mode); } - fp->uncompressedfp = NULL; if (fp->compressedfp == NULL) { free_keep_errno(fp); fp = NULL; } -#else - fatal("not built with zlib support"); -#endif - } - else - { -#ifdef HAVE_LIBZ - fp->compressedfp = NULL; + return fp; #endif + + case COMPR_ALG_NONE: fp->uncompressedfp = fopen(path, mode); if (fp->uncompressedfp == NULL) { free_keep_errno(fp); fp = NULL; } - } + return fp; - return fp; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } } @@ -584,14 +549,13 @@ cfread(void *ptr, int size, cfp *fp) fatal("could not read from input file: %s", errnum == Z_ERRNO ? strerror(errno) : errmsg); } + return ret; } - else #endif - { - ret = fread(ptr, 1, size, fp->uncompressedfp); - if (ret != size && !feof(fp->uncompressedfp)) - READ_ERROR_EXIT(fp->uncompressedfp); - } + + ret = fread(ptr, 1, size, fp->uncompressedfp); + if (ret != size && !feof(fp->uncompressedfp)) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -601,9 +565,8 @@ cfwrite(const void *ptr, int size, cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzwrite(fp->compressedfp, ptr, size); - else #endif - return fwrite(ptr, 1, size, fp->uncompressedfp); + return fwrite(ptr, 1, size, fp->uncompressedfp); } int @@ -622,15 +585,12 @@ cfgetc(cfp *fp) else fatal("could not read from input file: end of file"); } + return ret; } - else #endif - { - ret = fgetc(fp->uncompressedfp); - if (ret == EOF) - READ_ERROR_EXIT(fp->uncompressedfp); - } - + ret = fgetc(fp->uncompressedfp); + if (ret == EOF) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -640,9 +600,8 @@ cfgets(cfp *fp, char *buf, int len) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzgets(fp->compressedfp, buf, len); - else #endif - return fgets(buf, len, fp->uncompressedfp); + return fgets(buf, len, fp->uncompressedfp); } int @@ -660,15 +619,13 @@ cfclose(cfp *fp) { result = gzclose(fp->compressedfp); fp->compressedfp = NULL; + return result; } - else #endif - { - result = fclose(fp->uncompressedfp); - fp->uncompressedfp = NULL; - } - free_keep_errno(fp); + result = fclose(fp->uncompressedfp); + fp->uncompressedfp = NULL; + free_keep_errno(fp); return result; } @@ -678,9 +635,9 @@ cfeof(cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzeof(fp->compressedfp); - else #endif - return feof(fp->uncompressedfp); + + return feof(fp->uncompressedfp); } const char * @@ -699,7 +656,6 @@ get_cfp_error(cfp *fp) return strerror(errno); } -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix) { @@ -714,4 +670,18 @@ hasSuffix(const char *filename, const char *suffix) suffixlen) == 0; } -#endif +/* + * Return a string for the given AH's compression. + * The string is statically allocated. + */ +const char * +compress_suffix(Compress *compression) +{ + switch (compression->alg) + { + case COMPR_ALG_LIBZ: + return ".gz"; + default: + return ""; + } +} diff --git a/src/bin/pg_dump/compress_io.h b/src/bin/pg_dump/compress_io.h index d2e6e1b854..2c073676eb 100644 --- a/src/bin/pg_dump/compress_io.h +++ b/src/bin/pg_dump/compress_io.h @@ -21,12 +21,6 @@ #define ZLIB_OUT_SIZE 4096 #define ZLIB_IN_SIZE 4096 -typedef enum -{ - COMPR_ALG_NONE, - COMPR_ALG_LIBZ -} CompressionAlgorithm; - /* Prototype for callback function to WriteDataToArchive() */ typedef void (*WriteFunc) (ArchiveHandle *AH, const char *buf, size_t len); @@ -46,8 +40,8 @@ typedef size_t (*ReadFunc) (ArchiveHandle *AH, char **buf, size_t *buflen); /* struct definition appears in compress_io.c */ typedef struct CompressorState CompressorState; -extern CompressorState *AllocateCompressor(int compression, WriteFunc writeF); -extern void ReadDataFromArchive(ArchiveHandle *AH, int compression, +extern CompressorState *AllocateCompressor(Compress *compression, WriteFunc writeF); +extern void ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF); extern void WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, const void *data, size_t dLen); @@ -56,9 +50,9 @@ extern void EndCompressor(ArchiveHandle *AH, CompressorState *cs); typedef struct cfp cfp; -extern cfp *cfopen(const char *path, const char *mode, int compression); -extern cfp *cfopen_read(const char *path, const char *mode); -extern cfp *cfopen_write(const char *path, const char *mode, int compression); +extern cfp *cfopen(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_read(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_write(const char *path, const char *mode, Compress *compression); extern int cfread(void *ptr, int size, cfp *fp); extern int cfwrite(const void *ptr, int size, cfp *fp); extern int cfgetc(cfp *fp); @@ -67,4 +61,7 @@ extern int cfclose(cfp *fp); extern int cfeof(cfp *fp); extern const char *get_cfp_error(cfp *fp); +/* also used by tar */ +extern const char * compress_suffix(Compress *compression); + #endif diff --git a/src/bin/pg_dump/pg_backup.h b/src/bin/pg_dump/pg_backup.h index 9d0056a569..f2390b7937 100644 --- a/src/bin/pg_dump/pg_backup.h +++ b/src/bin/pg_dump/pg_backup.h @@ -72,6 +72,25 @@ typedef struct _connParams char *override_dbname; } ConnParams; +typedef enum +{ + COMPR_ALG_DEFAULT = -1, + COMPR_ALG_NONE, + COMPR_ALG_LIBZ, +} CompressionAlgorithm; +/* Should be called "method" or "library" ? */ + +typedef struct Compress { + CompressionAlgorithm alg; + int level; + /* Is a nondefault level set ? This is useful since different compression + * methods have different "default" levels. For now we assume the levels + * are all integer, though. + */ + bool level_set; +} Compress; + + typedef struct _restoreOptions { int createDB; /* Issue commands to create the database */ @@ -125,7 +144,7 @@ typedef struct _restoreOptions int noDataForFailedTables; int exit_on_error; - int compression; + Compress compression; int suppressDumpWarnings; /* Suppress output of WARNING entries * to stderr */ bool single_txn; @@ -281,7 +300,7 @@ extern Archive *OpenArchive(const char *FileSpec, const ArchiveFormat fmt); /* Create a new archive */ extern Archive *CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker); /* The --list option */ diff --git a/src/bin/pg_dump/pg_backup_archiver.c b/src/bin/pg_dump/pg_backup_archiver.c index 1f82c6499b..3eb6c55600 100644 --- a/src/bin/pg_dump/pg_backup_archiver.c +++ b/src/bin/pg_dump/pg_backup_archiver.c @@ -70,7 +70,7 @@ typedef struct _parallelReadyList static ArchiveHandle *_allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr); static void _getObjectDescription(PQExpBuffer buf, TocEntry *te); static void _printTocEntry(ArchiveHandle *AH, TocEntry *te, bool isData); @@ -98,7 +98,7 @@ static int _discoverArchiveFormat(ArchiveHandle *AH); static int RestoringToDB(ArchiveHandle *AH); static void dump_lo_buf(ArchiveHandle *AH); static void dumpTimestamp(ArchiveHandle *AH, const char *msg, time_t tim); -static void SetOutput(ArchiveHandle *AH, const char *filename, int compression); +static void SetOutput(ArchiveHandle *AH, const char *filename, Compress *compress); static OutputContext SaveOutput(ArchiveHandle *AH); static void RestoreOutput(ArchiveHandle *AH, OutputContext savedContext); @@ -238,7 +238,7 @@ setupRestoreWorker(Archive *AHX) /* Public */ Archive * CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker) { @@ -253,7 +253,9 @@ CreateArchive(const char *FileSpec, const ArchiveFormat fmt, Archive * OpenArchive(const char *FileSpec, const ArchiveFormat fmt) { - ArchiveHandle *AH = _allocAH(FileSpec, fmt, 0, true, archModeRead, setupRestoreWorker); + Compress compress = {0}; + ArchiveHandle *AH = _allocAH(FileSpec, fmt, &compress, true, archModeRead, + setupRestoreWorker); return (Archive *) AH; } @@ -382,7 +384,7 @@ RestoreArchive(Archive *AHX) * Make sure we won't need (de)compression we haven't got */ #ifndef HAVE_LIBZ - if (AH->compression != 0 && AH->PrintTocDataPtr != NULL) + if (AH->compression.alg != COMPR_ALG_NONE && AH->PrintTocDataPtr != NULL) { for (te = AH->toc->next; te != AH->toc; te = te->next) { @@ -457,8 +459,8 @@ RestoreArchive(Archive *AHX) * Setup the output file if necessary. */ sav = SaveOutput(AH); - if (ropt->filename || ropt->compression) - SetOutput(AH, ropt->filename, ropt->compression); + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) + SetOutput(AH, ropt->filename, &ropt->compression); ahprintf(AH, "--\n-- PostgreSQL database dump\n--\n\n"); @@ -738,7 +740,7 @@ RestoreArchive(Archive *AHX) */ AH->stage = STAGE_FINALIZING; - if (ropt->filename || ropt->compression) + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) RestoreOutput(AH, sav); if (ropt->useDB) @@ -1123,8 +1125,9 @@ PrintTOCSummary(Archive *AHX) char stamp_str[64]; sav = SaveOutput(AH); + Assert(ropt->compression.alg == COMPR_ALG_NONE); if (ropt->filename) - SetOutput(AH, ropt->filename, 0 /* no compression */ ); + SetOutput(AH, ropt->filename, &ropt->compression); if (strftime(stamp_str, sizeof(stamp_str), PGDUMP_STRFTIME_FMT, localtime(&AH->createDate)) == 0) @@ -1133,7 +1136,7 @@ PrintTOCSummary(Archive *AHX) ahprintf(AH, ";\n; Archive created at %s\n", stamp_str); ahprintf(AH, "; dbname: %s\n; TOC Entries: %d\n; Compression: %d\n", sanitize_line(AH->archdbname, false), - AH->tocCount, AH->compression); + AH->tocCount, AH->compression.alg); switch (AH->format) { @@ -1487,7 +1490,7 @@ archprintf(Archive *AH, const char *fmt,...) *******************************/ static void -SetOutput(ArchiveHandle *AH, const char *filename, int compression) +SetOutput(ArchiveHandle *AH, const char *filename, Compress *compression) { int fn; @@ -1510,12 +1513,12 @@ SetOutput(ArchiveHandle *AH, const char *filename, int compression) /* If compression explicitly requested, use gzopen */ #ifdef HAVE_LIBZ - if (compression != 0) + if (compression->alg != COMPR_ALG_NONE) { char fmode[14]; /* Don't use PG_BINARY_x since this is zlib */ - sprintf(fmode, "wb%d", compression); + sprintf(fmode, "wb%d", compression->level); if (fn >= 0) AH->OF = gzdopen(dup(fn), fmode); else @@ -2259,7 +2262,7 @@ _discoverArchiveFormat(ArchiveHandle *AH) */ static ArchiveHandle * _allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr) { ArchiveHandle *AH; @@ -2310,7 +2313,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, AH->toc->prev = AH->toc; AH->mode = mode; - AH->compression = compression; + AH->compression = *compression; AH->dosync = dosync; memset(&(AH->sqlparse), 0, sizeof(AH->sqlparse)); @@ -2325,7 +2328,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, * Force stdin/stdout into binary mode if that is what we are using. */ #ifdef WIN32 - if ((fmt != archNull || compression != 0) && + if ((fmt != archNull || compression->alg != COMPR_ALG_NONE) && (AH->fSpec == NULL || strcmp(AH->fSpec, "") == 0)) { if (mode == archModeWrite) @@ -3741,7 +3744,7 @@ WriteHead(ArchiveHandle *AH) AH->WriteBytePtr(AH, AH->intSize); AH->WriteBytePtr(AH, AH->offSize); AH->WriteBytePtr(AH, AH->format); - WriteInt(AH, AH->compression); + WriteInt(AH, AH->compression.alg); crtm = *localtime(&AH->createDate); WriteInt(AH, crtm.tm_sec); WriteInt(AH, crtm.tm_min); @@ -3816,15 +3819,15 @@ ReadHead(ArchiveHandle *AH) if (AH->version >= K_VERS_1_2) { if (AH->version < K_VERS_1_4) - AH->compression = AH->ReadBytePtr(AH); + AH->compression.alg = AH->ReadBytePtr(AH); else - AH->compression = ReadInt(AH); + AH->compression.alg = ReadInt(AH); } else - AH->compression = Z_DEFAULT_COMPRESSION; + AH->compression.alg = Z_DEFAULT_COMPRESSION; #ifndef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) pg_log_warning("archive is compressed, but this installation does not support compression -- no data will be available"); #endif diff --git a/src/bin/pg_dump/pg_backup_archiver.h b/src/bin/pg_dump/pg_backup_archiver.h index a8ea5c7eae..6e033d040e 100644 --- a/src/bin/pg_dump/pg_backup_archiver.h +++ b/src/bin/pg_dump/pg_backup_archiver.h @@ -47,7 +47,8 @@ #define GZWRITE(p, s, n, fh) (fwrite(p, s, n, fh) * (s)) #define GZREAD(p, s, n, fh) fread(p, s, n, fh) #define GZEOF(fh) feof(fh) -/* this is just the redefinition of a libz constant */ +/* this is just the redefinition of a libz constant, in case zlib isn't + * available */ #define Z_DEFAULT_COMPRESSION (-1) typedef struct _z_stream @@ -329,14 +330,7 @@ struct _archiveHandle DumpId *tableDataId; /* TABLE DATA ids, indexed by table dumpId */ struct _tocEntry *currToc; /* Used when dumping data */ - int compression; /*--------- - * Compression requested on open(). - * Possible values for compression: - * -1 Z_DEFAULT_COMPRESSION - * 0 COMPRESSION_NONE - * 1-9 levels for gzip compression - *--------- - */ + Compress compression; /* Compression requested on open */ bool dosync; /* data requested to be synced on sight */ ArchiveMode mode; /* File mode - r or w */ void *formatData; /* Header data specific to file format */ diff --git a/src/bin/pg_dump/pg_backup_custom.c b/src/bin/pg_dump/pg_backup_custom.c index 77d402c323..55a887a236 100644 --- a/src/bin/pg_dump/pg_backup_custom.c +++ b/src/bin/pg_dump/pg_backup_custom.c @@ -298,7 +298,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) _WriteByte(AH, BLK_DATA); /* Block type */ WriteInt(AH, te->dumpId); /* For sanity check */ - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -377,7 +377,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) WriteInt(AH, oid); - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -566,7 +566,7 @@ _PrintTocData(ArchiveHandle *AH, TocEntry *te) static void _PrintData(ArchiveHandle *AH) { - ReadDataFromArchive(AH, AH->compression, _CustomReadFunc); + ReadDataFromArchive(AH, _CustomReadFunc); } static void diff --git a/src/bin/pg_dump/pg_backup_directory.c b/src/bin/pg_dump/pg_backup_directory.c index 650b542fce..8bf869c6ca 100644 --- a/src/bin/pg_dump/pg_backup_directory.c +++ b/src/bin/pg_dump/pg_backup_directory.c @@ -202,7 +202,7 @@ InitArchiveFmt_Directory(ArchiveHandle *AH) setFilePath(AH, fname, "toc.dat"); - tocFH = cfopen_read(fname, PG_BINARY_R); + tocFH = cfopen_read(fname, PG_BINARY_R, &AH->compression); if (tocFH == NULL) fatal("could not open input file \"%s\": %m", fname); @@ -327,7 +327,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) setFilePath(AH, fname, tctx->filename); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -388,7 +388,7 @@ _PrintFileData(ArchiveHandle *AH, char *filename) if (!filename) return; - cfp = cfopen_read(filename, PG_BINARY_R); + cfp = cfopen_read(filename, PG_BINARY_R, &AH->compression); if (!cfp) fatal("could not open input file \"%s\": %m", filename); @@ -435,12 +435,13 @@ _LoadBlobs(ArchiveHandle *AH) lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; char line[MAXPGPATH]; + Compress nocompression = {0}; StartRestoreBlobs(AH); setFilePath(AH, fname, "blobs.toc"); - ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R); + ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R, &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open large object TOC file \"%s\" for input: %m", @@ -573,6 +574,7 @@ _CloseArchive(ArchiveHandle *AH) { cfp *tocFH; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "toc.dat"); @@ -580,7 +582,7 @@ _CloseArchive(ArchiveHandle *AH) ctx->pstate = ParallelBackupStart(AH); /* The TOC is always created uncompressed */ - tocFH = cfopen_write(fname, PG_BINARY_W, 0); + tocFH = cfopen_write(fname, PG_BINARY_W, &nocompression); if (tocFH == NULL) fatal("could not open output file \"%s\": %m", fname); ctx->dataFH = tocFH; @@ -639,11 +641,12 @@ _StartBlobs(ArchiveHandle *AH, TocEntry *te) { lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "blobs.toc"); /* The blob TOC file is never compressed */ - ctx->blobsTocFH = cfopen_write(fname, "ab", 0); + ctx->blobsTocFH = cfopen_write(fname, "ab", &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -661,7 +664,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) snprintf(fname, MAXPGPATH, "%s/blob_%u.dat", ctx->directory, oid); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); diff --git a/src/bin/pg_dump/pg_backup_tar.c b/src/bin/pg_dump/pg_backup_tar.c index 61c9c87a9f..4ba79ab924 100644 --- a/src/bin/pg_dump/pg_backup_tar.c +++ b/src/bin/pg_dump/pg_backup_tar.c @@ -39,6 +39,7 @@ #include "pg_backup_archiver.h" #include "pg_backup_tar.h" #include "pg_backup_utils.h" +#include "compress_io.h" #include "pgtar.h" static void _ArchiveEntry(ArchiveHandle *AH, TocEntry *te); @@ -196,10 +197,10 @@ InitArchiveFmt_Tar(ArchiveHandle *AH) /* * We don't support compression because reading the files back is not - * possible since gzdopen uses buffered IO which totally screws file + * possible since gzdopen uses buffered IO which totally screws file XXX * positioning. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) fatal("compression is not supported by tar archive format"); } else @@ -254,14 +255,8 @@ _ArchiveEntry(ArchiveHandle *AH, TocEntry *te) ctx = (lclTocEntry *) pg_malloc0(sizeof(lclTocEntry)); if (te->dataDumper != NULL) { -#ifdef HAVE_LIBZ - if (AH->compression == 0) - sprintf(fn, "%d.dat", te->dumpId); - else - sprintf(fn, "%d.dat.gz", te->dumpId); -#else - sprintf(fn, "%d.dat", te->dumpId); -#endif + const char *suffix = compress_suffix(&AH->compression); + sprintf(fn, "%d.dat%s", te->dumpId, suffix); ctx->filename = pg_strdup(fn); } else @@ -352,7 +347,7 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression == 0) + if (AH->compression.alg == COMPR_ALG_NONE) tm->nFH = ctx->tarFH; else fatal("compression is not supported by tar archive format"); @@ -413,9 +408,9 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) { - sprintf(fmode, "wb%d", AH->compression); + sprintf(fmode, "wb%d", AH->compression.level); tm->zFH = gzdopen(dup(fileno(tm->tmpFH)), fmode); if (tm->zFH == NULL) fatal("could not open temporary file"); @@ -443,7 +438,7 @@ tarClose(ArchiveHandle *AH, TAR_MEMBER *th) /* * Close the GZ file since we dup'd. This will flush the buffers. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) if (GZCLOSE(th->zFH) != 0) fatal("could not close tar member"); @@ -868,7 +863,7 @@ _CloseArchive(ArchiveHandle *AH) memcpy(ropt, AH->public.ropt, sizeof(RestoreOptions)); ropt->filename = NULL; ropt->dropSchema = 1; - ropt->compression = 0; + ropt->compression.alg = COMPR_ALG_NONE; ropt->superuser = NULL; ropt->suppressDumpWarnings = true; @@ -952,16 +947,12 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) lclContext *ctx = (lclContext *) AH->formatData; lclTocEntry *tctx = (lclTocEntry *) te->formatData; char fname[255]; - char *sfx; + const char *sfx; if (oid == 0) fatal("invalid OID for large object (%u)", oid); - if (AH->compression != 0) - sfx = ".gz"; - else - sfx = ""; - + sfx = compress_suffix(&AH->compression); sprintf(fname, "blob_%u.dat%s", oid, sfx); tarPrintf(ctx->blobToc, "%u %s\n", oid, fname); diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c index 1ab98a2286..4cbc79aedc 100644 --- a/src/bin/pg_dump/pg_dump.c +++ b/src/bin/pg_dump/pg_dump.c @@ -59,6 +59,7 @@ #include "getopt_long.h" #include "libpq/libpq-fs.h" #include "parallel.h" +#include "compress_io.h" #include "pg_backup_db.h" #include "pg_backup_utils.h" #include "pg_dump.h" @@ -297,6 +298,82 @@ static void setupDumpWorker(Archive *AHX); static TableInfo *getRootTableInfo(TableInfo *tbinfo); +/* Parse the string into compression options */ +static void +parse_compression(const char *optarg, Compress *compress) +{ + if (optarg[0] == '0' && optarg[1] == '\0') + compress->alg = COMPR_ALG_NONE; + else if ((optarg[0] > '0' && optarg[0] <= '9') || + optarg[0] == '-') + { + compress->alg = COMPR_ALG_LIBZ; + compress->level_set = true; + compress->level = atoi(optarg); + if (optarg[1] != '\0') + { + pg_log_error("compression level must be in range 0..9"); + exit_nicely(1); + } + } + else + { + /* Parse a more flexible string like level=3 alg=zlib opts=long */ + for (;;) + { + char *eq = strchr(optarg, '='); + int len; + + if (eq == NULL) + { + pg_log_error("compression options must be key=value: %s", optarg); + exit_nicely(1); + } + + len = eq - optarg; + if (strncmp(optarg, "alg", len) == 0) + { + if (strchr(eq, ' ')) + len = strchr(eq, ' ') - eq - 1; + else + len = strlen(eq) - len; + if (strncmp(1+eq, "zlib", len) == 0 || + strncmp(1+eq, "libz", len) == 0) + compress->alg = COMPR_ALG_LIBZ; + else + { + pg_log_error("unknown compression algorithm: %s", 1+eq); + exit_nicely(1); + } + } + else if (strncmp(optarg, "level", len) == 0) + { + compress->level = atoi(1+eq); + compress->level_set = true; + } + else + { + pg_log_error("unknown compression setting: %s", optarg); + exit_nicely(1); + } + + optarg = strchr(eq, ' '); + if (!optarg++) + break; + } + + if (!compress->level_set) + { + const int default_compress_level[] = { + 0, /* COMPR_ALG_NONE */ + Z_DEFAULT_COMPRESSION, /* COMPR_ALG_ZLIB */ + }; + + compress->level = default_compress_level[compress->alg]; + } + } +} + int main(int argc, char **argv) { @@ -319,7 +396,7 @@ main(int argc, char **argv) char *use_role = NULL; long rowsPerInsert; int numWorkers = 1; - int compressLevel = -1; + Compress compress = { .alg = COMPR_ALG_DEFAULT }; int plainText = 0; ArchiveFormat archiveFormat = archUnknown; ArchiveMode archiveMode; @@ -532,12 +609,7 @@ main(int argc, char **argv) break; case 'Z': /* Compression Level */ - compressLevel = atoi(optarg); - if (compressLevel < 0 || compressLevel > 9) - { - pg_log_error("compression level must be in range 0..9"); - exit_nicely(1); - } + parse_compression(optarg, &compress); break; case 0: @@ -679,20 +751,28 @@ main(int argc, char **argv) plainText = 1; /* Custom and directory formats are compressed by default, others not */ - if (compressLevel == -1) + if (compress.alg == COMPR_ALG_DEFAULT) { -#ifdef HAVE_LIBZ if (archiveFormat == archCustom || archiveFormat == archDirectory) - compressLevel = Z_DEFAULT_COMPRESSION; - else + { +#ifdef HAVE_LIBZ + compress.alg = COMPR_ALG_LIBZ; + compress.level = Z_DEFAULT_COMPRESSION; #endif - compressLevel = 0; + } + else + { + compress.alg = COMPR_ALG_NONE; + compress.level = 0; + } } #ifndef HAVE_LIBZ - if (compressLevel != 0) + if (compress.alg == COMPR_ALG_LIBZ) + { pg_log_warning("requested compression not available in this installation -- archive will be uncompressed"); - compressLevel = 0; + compress.alg = 0; + } #endif /* @@ -723,7 +803,7 @@ main(int argc, char **argv) fatal("option --index-collation-versions-unknown only works in binary upgrade mode"); /* Open the output file */ - fout = CreateArchive(filename, archiveFormat, compressLevel, dosync, + fout = CreateArchive(filename, archiveFormat, &compress, dosync, archiveMode, setupDumpWorker); /* Make dump options accessible right away */ @@ -957,10 +1037,7 @@ main(int argc, char **argv) ropt->sequence_data = dopt.sequence_data; ropt->binary_upgrade = dopt.binary_upgrade; - if (compressLevel == -1) - ropt->compression = 0; - else - ropt->compression = compressLevel; + ropt->compression = compress; ropt->suppressDumpWarnings = true; /* We've already shown them */ -- 2.17.0 --GRPZ8SYKNexpdSJ7 Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="0004-struct-compressLibs.patch" ^ permalink raw reply [nested|flat] 23+ messages in thread
* [PATCH 03/20] Support multiple compression algs/levels/opts.. @ 2020-12-22 06:23 Justin Pryzby <[email protected]> 0 siblings, 0 replies; 23+ messages in thread From: Justin Pryzby @ 2020-12-22 06:23 UTC (permalink / raw) The existing implementation abtracts compressed and noncompressed I/O. This preliminary commit is intended to also allow for multiple compression algorithms. --- src/bin/pg_dump/compress_io.c | 220 +++++++++++--------------- src/bin/pg_dump/compress_io.h | 19 +-- src/bin/pg_dump/pg_backup.h | 23 ++- src/bin/pg_dump/pg_backup_archiver.c | 45 +++--- src/bin/pg_dump/pg_backup_archiver.h | 12 +- src/bin/pg_dump/pg_backup_custom.c | 6 +- src/bin/pg_dump/pg_backup_directory.c | 17 +- src/bin/pg_dump/pg_backup_tar.c | 33 ++-- src/bin/pg_dump/pg_dump.c | 115 +++++++++++--- 9 files changed, 272 insertions(+), 218 deletions(-) diff --git a/src/bin/pg_dump/compress_io.c b/src/bin/pg_dump/compress_io.c index 6a428978d4..db16fd33f2 100644 --- a/src/bin/pg_dump/compress_io.c +++ b/src/bin/pg_dump/compress_io.c @@ -74,12 +74,9 @@ struct CompressorState #endif }; -static void ParseCompressionOption(int compression, CompressionAlgorithm *alg, - int *level); - /* Routines that support zlib compressed data I/O */ #ifdef HAVE_LIBZ -static void InitCompressorZlib(CompressorState *cs, int level); +static void InitCompressorZlib(CompressorState *cs, Compress *compress); static void DeflateCompressorZlib(ArchiveHandle *AH, CompressorState *cs, bool flush); static void ReadDataFromArchiveZlib(ArchiveHandle *AH, ReadFunc readF); @@ -93,58 +90,36 @@ static void ReadDataFromArchiveNone(ArchiveHandle *AH, ReadFunc readF); static void WriteDataToArchiveNone(ArchiveHandle *AH, CompressorState *cs, const char *data, size_t dLen); -/* - * Interprets a numeric 'compression' value. The algorithm implied by the - * value (zlib or none at the moment), is returned in *alg, and the - * zlib compression level in *level. - */ -static void -ParseCompressionOption(int compression, CompressionAlgorithm *alg, int *level) -{ - if (compression == Z_DEFAULT_COMPRESSION || - (compression > 0 && compression <= 9)) - *alg = COMPR_ALG_LIBZ; - else if (compression == 0) - *alg = COMPR_ALG_NONE; - else - { - fatal("invalid compression code: %d", compression); - *alg = COMPR_ALG_NONE; /* keep compiler quiet */ - } - - /* The level is just the passed-in value. */ - if (level) - *level = compression; -} - /* Public interface routines */ /* Allocate a new compressor */ CompressorState * -AllocateCompressor(int compression, WriteFunc writeF) +AllocateCompressor(Compress *compression, WriteFunc writeF) { CompressorState *cs; - CompressionAlgorithm alg; - int level; - - ParseCompressionOption(compression, &alg, &level); - -#ifndef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - fatal("not built with zlib support"); -#endif cs = (CompressorState *) pg_malloc0(sizeof(CompressorState)); cs->writeF = writeF; - cs->comprAlg = alg; + cs->comprAlg = compression->alg; /* * Perform compression algorithm specific initialization. */ + Assert (compression->alg != COMPR_ALG_DEFAULT); + switch (compression->alg) + { #ifdef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - InitCompressorZlib(cs, level); + case COMPR_ALG_LIBZ: + InitCompressorZlib(cs, compression); + break; #endif + case COMPR_ALG_NONE: + /* Do nothing */ + break; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } return cs; } @@ -154,21 +129,21 @@ AllocateCompressor(int compression, WriteFunc writeF) * out with ahwrite(). */ void -ReadDataFromArchive(ArchiveHandle *AH, int compression, ReadFunc readF) +ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF) { - CompressionAlgorithm alg; - - ParseCompressionOption(compression, &alg, NULL); - - if (alg == COMPR_ALG_NONE) - ReadDataFromArchiveNone(AH, readF); - if (alg == COMPR_ALG_LIBZ) + switch (AH->compression.alg) { + case COMPR_ALG_NONE: + ReadDataFromArchiveNone(AH, readF); + break; #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: ReadDataFromArchiveZlib(AH, readF); -#else - fatal("not built with zlib support"); + break; #endif + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -181,16 +156,18 @@ WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, { switch (cs->comprAlg) { - case COMPR_ALG_LIBZ: #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: WriteDataToArchiveZlib(AH, cs, data, dLen); -#else - fatal("not built with zlib support"); -#endif break; +#endif case COMPR_ALG_NONE: WriteDataToArchiveNone(AH, cs, data, dLen); break; + + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -215,7 +192,7 @@ EndCompressor(ArchiveHandle *AH, CompressorState *cs) */ static void -InitCompressorZlib(CompressorState *cs, int level) +InitCompressorZlib(CompressorState *cs, Compress *compress) { z_streamp zp; @@ -232,7 +209,7 @@ InitCompressorZlib(CompressorState *cs, int level) cs->zlibOut = (char *) pg_malloc(ZLIB_OUT_SIZE + 1); cs->zlibOutSize = ZLIB_OUT_SIZE; - if (deflateInit(zp, level) != Z_OK) + if (deflateInit(zp, compress->level) != Z_OK) fatal("could not initialize compression library: %s", zp->msg); @@ -424,9 +401,7 @@ struct cfp #endif }; -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix); -#endif /* free() without changing errno; useful in several places below */ static void @@ -442,34 +417,31 @@ free_keep_errno(void *p) * Open a file for reading. 'path' is the file to open, and 'mode' should * be either "r" or "rb". * - * If the file at 'path' does not exist, we append the ".gz" suffix (if 'path' - * doesn't already have it) and try again. So if you pass "foo" as 'path', + * If the file at 'path' does not exist, we search with compressed suffix (if 'path' + * doesn't already have one) and try again. So if you pass "foo" as 'path', * this will open either "foo" or "foo.gz". * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_read(const char *path, const char *mode) +cfopen_read(const char *path, const char *mode, Compress *compression) { cfp *fp; -#ifdef HAVE_LIBZ if (hasSuffix(path, ".gz")) - fp = cfopen(path, mode, 1); + fp = cfopen(path, mode, compression); else -#endif { - fp = cfopen(path, mode, 0); -#ifdef HAVE_LIBZ + fp = cfopen(path, mode, compression); if (fp == NULL) { char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); - fp = cfopen(fname, mode, 1); + fname = psprintf("%s%s", path, suffix); + fp = cfopen(fname, mode, compression); free_keep_errno(fname); } -#endif } return fp; } @@ -479,31 +451,26 @@ cfopen_read(const char *path, const char *mode) * be a filemode as accepted by fopen() and gzopen() that indicates writing * ("w", "wb", "a", or "ab"). * - * If 'compression' is non-zero, a gzip compressed stream is opened, and - * 'compression' indicates the compression level used. The ".gz" suffix - * is automatically added to 'path' in that case. + * Use compression if specified. + * The appropriate suffix is automatically added to 'path' in that case. * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_write(const char *path, const char *mode, int compression) +cfopen_write(const char *path, const char *mode, Compress *compression) { cfp *fp; - if (compression == 0) - fp = cfopen(path, mode, 0); + if (compression->alg == COMPR_ALG_NONE) + fp = cfopen(path, mode, compression); else { -#ifdef HAVE_LIBZ char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); + fname = psprintf("%s%s", path, suffix); fp = cfopen(fname, mode, compression); free_keep_errno(fname); -#else - fatal("not built with zlib support"); - fp = NULL; /* keep compiler quiet */ -#endif } return fp; } @@ -515,20 +482,21 @@ cfopen_write(const char *path, const char *mode, int compression) * On failure, return NULL with an error code in errno. */ cfp * -cfopen(const char *path, const char *mode, int compression) +cfopen(const char *path, const char *mode, Compress *compression) { - cfp *fp = pg_malloc(sizeof(cfp)); + cfp *fp = pg_malloc0(sizeof(cfp)); - if (compression != 0) + switch (compression->alg) { #ifdef HAVE_LIBZ - if (compression != Z_DEFAULT_COMPRESSION) + case COMPR_ALG_LIBZ: + if (compression->level != Z_DEFAULT_COMPRESSION) { /* user has specified a compression level, so tell zlib to use it */ char mode_compression[32]; snprintf(mode_compression, sizeof(mode_compression), "%s%d", - mode, compression); + mode, compression->level); fp->compressedfp = gzopen(path, mode_compression); } else @@ -537,30 +505,27 @@ cfopen(const char *path, const char *mode, int compression) fp->compressedfp = gzopen(path, mode); } - fp->uncompressedfp = NULL; if (fp->compressedfp == NULL) { free_keep_errno(fp); fp = NULL; } -#else - fatal("not built with zlib support"); -#endif - } - else - { -#ifdef HAVE_LIBZ - fp->compressedfp = NULL; + return fp; #endif + + case COMPR_ALG_NONE: fp->uncompressedfp = fopen(path, mode); if (fp->uncompressedfp == NULL) { free_keep_errno(fp); fp = NULL; } - } + return fp; - return fp; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } } @@ -584,14 +549,13 @@ cfread(void *ptr, int size, cfp *fp) fatal("could not read from input file: %s", errnum == Z_ERRNO ? strerror(errno) : errmsg); } + return ret; } - else #endif - { - ret = fread(ptr, 1, size, fp->uncompressedfp); - if (ret != size && !feof(fp->uncompressedfp)) - READ_ERROR_EXIT(fp->uncompressedfp); - } + + ret = fread(ptr, 1, size, fp->uncompressedfp); + if (ret != size && !feof(fp->uncompressedfp)) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -601,9 +565,8 @@ cfwrite(const void *ptr, int size, cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzwrite(fp->compressedfp, ptr, size); - else #endif - return fwrite(ptr, 1, size, fp->uncompressedfp); + return fwrite(ptr, 1, size, fp->uncompressedfp); } int @@ -622,15 +585,12 @@ cfgetc(cfp *fp) else fatal("could not read from input file: end of file"); } + return ret; } - else #endif - { - ret = fgetc(fp->uncompressedfp); - if (ret == EOF) - READ_ERROR_EXIT(fp->uncompressedfp); - } - + ret = fgetc(fp->uncompressedfp); + if (ret == EOF) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -640,9 +600,8 @@ cfgets(cfp *fp, char *buf, int len) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzgets(fp->compressedfp, buf, len); - else #endif - return fgets(buf, len, fp->uncompressedfp); + return fgets(buf, len, fp->uncompressedfp); } int @@ -660,15 +619,13 @@ cfclose(cfp *fp) { result = gzclose(fp->compressedfp); fp->compressedfp = NULL; + return result; } - else #endif - { - result = fclose(fp->uncompressedfp); - fp->uncompressedfp = NULL; - } - free_keep_errno(fp); + result = fclose(fp->uncompressedfp); + fp->uncompressedfp = NULL; + free_keep_errno(fp); return result; } @@ -678,9 +635,9 @@ cfeof(cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzeof(fp->compressedfp); - else #endif - return feof(fp->uncompressedfp); + + return feof(fp->uncompressedfp); } const char * @@ -699,7 +656,6 @@ get_cfp_error(cfp *fp) return strerror(errno); } -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix) { @@ -714,4 +670,18 @@ hasSuffix(const char *filename, const char *suffix) suffixlen) == 0; } -#endif +/* + * Return a string for the given AH's compression. + * The string is statically allocated. + */ +const char * +compress_suffix(Compress *compression) +{ + switch (compression->alg) + { + case COMPR_ALG_LIBZ: + return ".gz"; + default: + return ""; + } +} diff --git a/src/bin/pg_dump/compress_io.h b/src/bin/pg_dump/compress_io.h index d2e6e1b854..2c073676eb 100644 --- a/src/bin/pg_dump/compress_io.h +++ b/src/bin/pg_dump/compress_io.h @@ -21,12 +21,6 @@ #define ZLIB_OUT_SIZE 4096 #define ZLIB_IN_SIZE 4096 -typedef enum -{ - COMPR_ALG_NONE, - COMPR_ALG_LIBZ -} CompressionAlgorithm; - /* Prototype for callback function to WriteDataToArchive() */ typedef void (*WriteFunc) (ArchiveHandle *AH, const char *buf, size_t len); @@ -46,8 +40,8 @@ typedef size_t (*ReadFunc) (ArchiveHandle *AH, char **buf, size_t *buflen); /* struct definition appears in compress_io.c */ typedef struct CompressorState CompressorState; -extern CompressorState *AllocateCompressor(int compression, WriteFunc writeF); -extern void ReadDataFromArchive(ArchiveHandle *AH, int compression, +extern CompressorState *AllocateCompressor(Compress *compression, WriteFunc writeF); +extern void ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF); extern void WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, const void *data, size_t dLen); @@ -56,9 +50,9 @@ extern void EndCompressor(ArchiveHandle *AH, CompressorState *cs); typedef struct cfp cfp; -extern cfp *cfopen(const char *path, const char *mode, int compression); -extern cfp *cfopen_read(const char *path, const char *mode); -extern cfp *cfopen_write(const char *path, const char *mode, int compression); +extern cfp *cfopen(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_read(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_write(const char *path, const char *mode, Compress *compression); extern int cfread(void *ptr, int size, cfp *fp); extern int cfwrite(const void *ptr, int size, cfp *fp); extern int cfgetc(cfp *fp); @@ -67,4 +61,7 @@ extern int cfclose(cfp *fp); extern int cfeof(cfp *fp); extern const char *get_cfp_error(cfp *fp); +/* also used by tar */ +extern const char * compress_suffix(Compress *compression); + #endif diff --git a/src/bin/pg_dump/pg_backup.h b/src/bin/pg_dump/pg_backup.h index 9d0056a569..f2390b7937 100644 --- a/src/bin/pg_dump/pg_backup.h +++ b/src/bin/pg_dump/pg_backup.h @@ -72,6 +72,25 @@ typedef struct _connParams char *override_dbname; } ConnParams; +typedef enum +{ + COMPR_ALG_DEFAULT = -1, + COMPR_ALG_NONE, + COMPR_ALG_LIBZ, +} CompressionAlgorithm; +/* Should be called "method" or "library" ? */ + +typedef struct Compress { + CompressionAlgorithm alg; + int level; + /* Is a nondefault level set ? This is useful since different compression + * methods have different "default" levels. For now we assume the levels + * are all integer, though. + */ + bool level_set; +} Compress; + + typedef struct _restoreOptions { int createDB; /* Issue commands to create the database */ @@ -125,7 +144,7 @@ typedef struct _restoreOptions int noDataForFailedTables; int exit_on_error; - int compression; + Compress compression; int suppressDumpWarnings; /* Suppress output of WARNING entries * to stderr */ bool single_txn; @@ -281,7 +300,7 @@ extern Archive *OpenArchive(const char *FileSpec, const ArchiveFormat fmt); /* Create a new archive */ extern Archive *CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker); /* The --list option */ diff --git a/src/bin/pg_dump/pg_backup_archiver.c b/src/bin/pg_dump/pg_backup_archiver.c index 1f82c6499b..3eb6c55600 100644 --- a/src/bin/pg_dump/pg_backup_archiver.c +++ b/src/bin/pg_dump/pg_backup_archiver.c @@ -70,7 +70,7 @@ typedef struct _parallelReadyList static ArchiveHandle *_allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr); static void _getObjectDescription(PQExpBuffer buf, TocEntry *te); static void _printTocEntry(ArchiveHandle *AH, TocEntry *te, bool isData); @@ -98,7 +98,7 @@ static int _discoverArchiveFormat(ArchiveHandle *AH); static int RestoringToDB(ArchiveHandle *AH); static void dump_lo_buf(ArchiveHandle *AH); static void dumpTimestamp(ArchiveHandle *AH, const char *msg, time_t tim); -static void SetOutput(ArchiveHandle *AH, const char *filename, int compression); +static void SetOutput(ArchiveHandle *AH, const char *filename, Compress *compress); static OutputContext SaveOutput(ArchiveHandle *AH); static void RestoreOutput(ArchiveHandle *AH, OutputContext savedContext); @@ -238,7 +238,7 @@ setupRestoreWorker(Archive *AHX) /* Public */ Archive * CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker) { @@ -253,7 +253,9 @@ CreateArchive(const char *FileSpec, const ArchiveFormat fmt, Archive * OpenArchive(const char *FileSpec, const ArchiveFormat fmt) { - ArchiveHandle *AH = _allocAH(FileSpec, fmt, 0, true, archModeRead, setupRestoreWorker); + Compress compress = {0}; + ArchiveHandle *AH = _allocAH(FileSpec, fmt, &compress, true, archModeRead, + setupRestoreWorker); return (Archive *) AH; } @@ -382,7 +384,7 @@ RestoreArchive(Archive *AHX) * Make sure we won't need (de)compression we haven't got */ #ifndef HAVE_LIBZ - if (AH->compression != 0 && AH->PrintTocDataPtr != NULL) + if (AH->compression.alg != COMPR_ALG_NONE && AH->PrintTocDataPtr != NULL) { for (te = AH->toc->next; te != AH->toc; te = te->next) { @@ -457,8 +459,8 @@ RestoreArchive(Archive *AHX) * Setup the output file if necessary. */ sav = SaveOutput(AH); - if (ropt->filename || ropt->compression) - SetOutput(AH, ropt->filename, ropt->compression); + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) + SetOutput(AH, ropt->filename, &ropt->compression); ahprintf(AH, "--\n-- PostgreSQL database dump\n--\n\n"); @@ -738,7 +740,7 @@ RestoreArchive(Archive *AHX) */ AH->stage = STAGE_FINALIZING; - if (ropt->filename || ropt->compression) + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) RestoreOutput(AH, sav); if (ropt->useDB) @@ -1123,8 +1125,9 @@ PrintTOCSummary(Archive *AHX) char stamp_str[64]; sav = SaveOutput(AH); + Assert(ropt->compression.alg == COMPR_ALG_NONE); if (ropt->filename) - SetOutput(AH, ropt->filename, 0 /* no compression */ ); + SetOutput(AH, ropt->filename, &ropt->compression); if (strftime(stamp_str, sizeof(stamp_str), PGDUMP_STRFTIME_FMT, localtime(&AH->createDate)) == 0) @@ -1133,7 +1136,7 @@ PrintTOCSummary(Archive *AHX) ahprintf(AH, ";\n; Archive created at %s\n", stamp_str); ahprintf(AH, "; dbname: %s\n; TOC Entries: %d\n; Compression: %d\n", sanitize_line(AH->archdbname, false), - AH->tocCount, AH->compression); + AH->tocCount, AH->compression.alg); switch (AH->format) { @@ -1487,7 +1490,7 @@ archprintf(Archive *AH, const char *fmt,...) *******************************/ static void -SetOutput(ArchiveHandle *AH, const char *filename, int compression) +SetOutput(ArchiveHandle *AH, const char *filename, Compress *compression) { int fn; @@ -1510,12 +1513,12 @@ SetOutput(ArchiveHandle *AH, const char *filename, int compression) /* If compression explicitly requested, use gzopen */ #ifdef HAVE_LIBZ - if (compression != 0) + if (compression->alg != COMPR_ALG_NONE) { char fmode[14]; /* Don't use PG_BINARY_x since this is zlib */ - sprintf(fmode, "wb%d", compression); + sprintf(fmode, "wb%d", compression->level); if (fn >= 0) AH->OF = gzdopen(dup(fn), fmode); else @@ -2259,7 +2262,7 @@ _discoverArchiveFormat(ArchiveHandle *AH) */ static ArchiveHandle * _allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr) { ArchiveHandle *AH; @@ -2310,7 +2313,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, AH->toc->prev = AH->toc; AH->mode = mode; - AH->compression = compression; + AH->compression = *compression; AH->dosync = dosync; memset(&(AH->sqlparse), 0, sizeof(AH->sqlparse)); @@ -2325,7 +2328,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, * Force stdin/stdout into binary mode if that is what we are using. */ #ifdef WIN32 - if ((fmt != archNull || compression != 0) && + if ((fmt != archNull || compression->alg != COMPR_ALG_NONE) && (AH->fSpec == NULL || strcmp(AH->fSpec, "") == 0)) { if (mode == archModeWrite) @@ -3741,7 +3744,7 @@ WriteHead(ArchiveHandle *AH) AH->WriteBytePtr(AH, AH->intSize); AH->WriteBytePtr(AH, AH->offSize); AH->WriteBytePtr(AH, AH->format); - WriteInt(AH, AH->compression); + WriteInt(AH, AH->compression.alg); crtm = *localtime(&AH->createDate); WriteInt(AH, crtm.tm_sec); WriteInt(AH, crtm.tm_min); @@ -3816,15 +3819,15 @@ ReadHead(ArchiveHandle *AH) if (AH->version >= K_VERS_1_2) { if (AH->version < K_VERS_1_4) - AH->compression = AH->ReadBytePtr(AH); + AH->compression.alg = AH->ReadBytePtr(AH); else - AH->compression = ReadInt(AH); + AH->compression.alg = ReadInt(AH); } else - AH->compression = Z_DEFAULT_COMPRESSION; + AH->compression.alg = Z_DEFAULT_COMPRESSION; #ifndef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) pg_log_warning("archive is compressed, but this installation does not support compression -- no data will be available"); #endif diff --git a/src/bin/pg_dump/pg_backup_archiver.h b/src/bin/pg_dump/pg_backup_archiver.h index a8ea5c7eae..6e033d040e 100644 --- a/src/bin/pg_dump/pg_backup_archiver.h +++ b/src/bin/pg_dump/pg_backup_archiver.h @@ -47,7 +47,8 @@ #define GZWRITE(p, s, n, fh) (fwrite(p, s, n, fh) * (s)) #define GZREAD(p, s, n, fh) fread(p, s, n, fh) #define GZEOF(fh) feof(fh) -/* this is just the redefinition of a libz constant */ +/* this is just the redefinition of a libz constant, in case zlib isn't + * available */ #define Z_DEFAULT_COMPRESSION (-1) typedef struct _z_stream @@ -329,14 +330,7 @@ struct _archiveHandle DumpId *tableDataId; /* TABLE DATA ids, indexed by table dumpId */ struct _tocEntry *currToc; /* Used when dumping data */ - int compression; /*--------- - * Compression requested on open(). - * Possible values for compression: - * -1 Z_DEFAULT_COMPRESSION - * 0 COMPRESSION_NONE - * 1-9 levels for gzip compression - *--------- - */ + Compress compression; /* Compression requested on open */ bool dosync; /* data requested to be synced on sight */ ArchiveMode mode; /* File mode - r or w */ void *formatData; /* Header data specific to file format */ diff --git a/src/bin/pg_dump/pg_backup_custom.c b/src/bin/pg_dump/pg_backup_custom.c index 77d402c323..55a887a236 100644 --- a/src/bin/pg_dump/pg_backup_custom.c +++ b/src/bin/pg_dump/pg_backup_custom.c @@ -298,7 +298,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) _WriteByte(AH, BLK_DATA); /* Block type */ WriteInt(AH, te->dumpId); /* For sanity check */ - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -377,7 +377,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) WriteInt(AH, oid); - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -566,7 +566,7 @@ _PrintTocData(ArchiveHandle *AH, TocEntry *te) static void _PrintData(ArchiveHandle *AH) { - ReadDataFromArchive(AH, AH->compression, _CustomReadFunc); + ReadDataFromArchive(AH, _CustomReadFunc); } static void diff --git a/src/bin/pg_dump/pg_backup_directory.c b/src/bin/pg_dump/pg_backup_directory.c index 650b542fce..8bf869c6ca 100644 --- a/src/bin/pg_dump/pg_backup_directory.c +++ b/src/bin/pg_dump/pg_backup_directory.c @@ -202,7 +202,7 @@ InitArchiveFmt_Directory(ArchiveHandle *AH) setFilePath(AH, fname, "toc.dat"); - tocFH = cfopen_read(fname, PG_BINARY_R); + tocFH = cfopen_read(fname, PG_BINARY_R, &AH->compression); if (tocFH == NULL) fatal("could not open input file \"%s\": %m", fname); @@ -327,7 +327,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) setFilePath(AH, fname, tctx->filename); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -388,7 +388,7 @@ _PrintFileData(ArchiveHandle *AH, char *filename) if (!filename) return; - cfp = cfopen_read(filename, PG_BINARY_R); + cfp = cfopen_read(filename, PG_BINARY_R, &AH->compression); if (!cfp) fatal("could not open input file \"%s\": %m", filename); @@ -435,12 +435,13 @@ _LoadBlobs(ArchiveHandle *AH) lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; char line[MAXPGPATH]; + Compress nocompression = {0}; StartRestoreBlobs(AH); setFilePath(AH, fname, "blobs.toc"); - ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R); + ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R, &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open large object TOC file \"%s\" for input: %m", @@ -573,6 +574,7 @@ _CloseArchive(ArchiveHandle *AH) { cfp *tocFH; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "toc.dat"); @@ -580,7 +582,7 @@ _CloseArchive(ArchiveHandle *AH) ctx->pstate = ParallelBackupStart(AH); /* The TOC is always created uncompressed */ - tocFH = cfopen_write(fname, PG_BINARY_W, 0); + tocFH = cfopen_write(fname, PG_BINARY_W, &nocompression); if (tocFH == NULL) fatal("could not open output file \"%s\": %m", fname); ctx->dataFH = tocFH; @@ -639,11 +641,12 @@ _StartBlobs(ArchiveHandle *AH, TocEntry *te) { lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "blobs.toc"); /* The blob TOC file is never compressed */ - ctx->blobsTocFH = cfopen_write(fname, "ab", 0); + ctx->blobsTocFH = cfopen_write(fname, "ab", &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -661,7 +664,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) snprintf(fname, MAXPGPATH, "%s/blob_%u.dat", ctx->directory, oid); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); diff --git a/src/bin/pg_dump/pg_backup_tar.c b/src/bin/pg_dump/pg_backup_tar.c index 61c9c87a9f..4ba79ab924 100644 --- a/src/bin/pg_dump/pg_backup_tar.c +++ b/src/bin/pg_dump/pg_backup_tar.c @@ -39,6 +39,7 @@ #include "pg_backup_archiver.h" #include "pg_backup_tar.h" #include "pg_backup_utils.h" +#include "compress_io.h" #include "pgtar.h" static void _ArchiveEntry(ArchiveHandle *AH, TocEntry *te); @@ -196,10 +197,10 @@ InitArchiveFmt_Tar(ArchiveHandle *AH) /* * We don't support compression because reading the files back is not - * possible since gzdopen uses buffered IO which totally screws file + * possible since gzdopen uses buffered IO which totally screws file XXX * positioning. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) fatal("compression is not supported by tar archive format"); } else @@ -254,14 +255,8 @@ _ArchiveEntry(ArchiveHandle *AH, TocEntry *te) ctx = (lclTocEntry *) pg_malloc0(sizeof(lclTocEntry)); if (te->dataDumper != NULL) { -#ifdef HAVE_LIBZ - if (AH->compression == 0) - sprintf(fn, "%d.dat", te->dumpId); - else - sprintf(fn, "%d.dat.gz", te->dumpId); -#else - sprintf(fn, "%d.dat", te->dumpId); -#endif + const char *suffix = compress_suffix(&AH->compression); + sprintf(fn, "%d.dat%s", te->dumpId, suffix); ctx->filename = pg_strdup(fn); } else @@ -352,7 +347,7 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression == 0) + if (AH->compression.alg == COMPR_ALG_NONE) tm->nFH = ctx->tarFH; else fatal("compression is not supported by tar archive format"); @@ -413,9 +408,9 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) { - sprintf(fmode, "wb%d", AH->compression); + sprintf(fmode, "wb%d", AH->compression.level); tm->zFH = gzdopen(dup(fileno(tm->tmpFH)), fmode); if (tm->zFH == NULL) fatal("could not open temporary file"); @@ -443,7 +438,7 @@ tarClose(ArchiveHandle *AH, TAR_MEMBER *th) /* * Close the GZ file since we dup'd. This will flush the buffers. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) if (GZCLOSE(th->zFH) != 0) fatal("could not close tar member"); @@ -868,7 +863,7 @@ _CloseArchive(ArchiveHandle *AH) memcpy(ropt, AH->public.ropt, sizeof(RestoreOptions)); ropt->filename = NULL; ropt->dropSchema = 1; - ropt->compression = 0; + ropt->compression.alg = COMPR_ALG_NONE; ropt->superuser = NULL; ropt->suppressDumpWarnings = true; @@ -952,16 +947,12 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) lclContext *ctx = (lclContext *) AH->formatData; lclTocEntry *tctx = (lclTocEntry *) te->formatData; char fname[255]; - char *sfx; + const char *sfx; if (oid == 0) fatal("invalid OID for large object (%u)", oid); - if (AH->compression != 0) - sfx = ".gz"; - else - sfx = ""; - + sfx = compress_suffix(&AH->compression); sprintf(fname, "blob_%u.dat%s", oid, sfx); tarPrintf(ctx->blobToc, "%u %s\n", oid, fname); diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c index 1ab98a2286..4cbc79aedc 100644 --- a/src/bin/pg_dump/pg_dump.c +++ b/src/bin/pg_dump/pg_dump.c @@ -59,6 +59,7 @@ #include "getopt_long.h" #include "libpq/libpq-fs.h" #include "parallel.h" +#include "compress_io.h" #include "pg_backup_db.h" #include "pg_backup_utils.h" #include "pg_dump.h" @@ -297,6 +298,82 @@ static void setupDumpWorker(Archive *AHX); static TableInfo *getRootTableInfo(TableInfo *tbinfo); +/* Parse the string into compression options */ +static void +parse_compression(const char *optarg, Compress *compress) +{ + if (optarg[0] == '0' && optarg[1] == '\0') + compress->alg = COMPR_ALG_NONE; + else if ((optarg[0] > '0' && optarg[0] <= '9') || + optarg[0] == '-') + { + compress->alg = COMPR_ALG_LIBZ; + compress->level_set = true; + compress->level = atoi(optarg); + if (optarg[1] != '\0') + { + pg_log_error("compression level must be in range 0..9"); + exit_nicely(1); + } + } + else + { + /* Parse a more flexible string like level=3 alg=zlib opts=long */ + for (;;) + { + char *eq = strchr(optarg, '='); + int len; + + if (eq == NULL) + { + pg_log_error("compression options must be key=value: %s", optarg); + exit_nicely(1); + } + + len = eq - optarg; + if (strncmp(optarg, "alg", len) == 0) + { + if (strchr(eq, ' ')) + len = strchr(eq, ' ') - eq - 1; + else + len = strlen(eq) - len; + if (strncmp(1+eq, "zlib", len) == 0 || + strncmp(1+eq, "libz", len) == 0) + compress->alg = COMPR_ALG_LIBZ; + else + { + pg_log_error("unknown compression algorithm: %s", 1+eq); + exit_nicely(1); + } + } + else if (strncmp(optarg, "level", len) == 0) + { + compress->level = atoi(1+eq); + compress->level_set = true; + } + else + { + pg_log_error("unknown compression setting: %s", optarg); + exit_nicely(1); + } + + optarg = strchr(eq, ' '); + if (!optarg++) + break; + } + + if (!compress->level_set) + { + const int default_compress_level[] = { + 0, /* COMPR_ALG_NONE */ + Z_DEFAULT_COMPRESSION, /* COMPR_ALG_ZLIB */ + }; + + compress->level = default_compress_level[compress->alg]; + } + } +} + int main(int argc, char **argv) { @@ -319,7 +396,7 @@ main(int argc, char **argv) char *use_role = NULL; long rowsPerInsert; int numWorkers = 1; - int compressLevel = -1; + Compress compress = { .alg = COMPR_ALG_DEFAULT }; int plainText = 0; ArchiveFormat archiveFormat = archUnknown; ArchiveMode archiveMode; @@ -532,12 +609,7 @@ main(int argc, char **argv) break; case 'Z': /* Compression Level */ - compressLevel = atoi(optarg); - if (compressLevel < 0 || compressLevel > 9) - { - pg_log_error("compression level must be in range 0..9"); - exit_nicely(1); - } + parse_compression(optarg, &compress); break; case 0: @@ -679,20 +751,28 @@ main(int argc, char **argv) plainText = 1; /* Custom and directory formats are compressed by default, others not */ - if (compressLevel == -1) + if (compress.alg == COMPR_ALG_DEFAULT) { -#ifdef HAVE_LIBZ if (archiveFormat == archCustom || archiveFormat == archDirectory) - compressLevel = Z_DEFAULT_COMPRESSION; - else + { +#ifdef HAVE_LIBZ + compress.alg = COMPR_ALG_LIBZ; + compress.level = Z_DEFAULT_COMPRESSION; #endif - compressLevel = 0; + } + else + { + compress.alg = COMPR_ALG_NONE; + compress.level = 0; + } } #ifndef HAVE_LIBZ - if (compressLevel != 0) + if (compress.alg == COMPR_ALG_LIBZ) + { pg_log_warning("requested compression not available in this installation -- archive will be uncompressed"); - compressLevel = 0; + compress.alg = 0; + } #endif /* @@ -723,7 +803,7 @@ main(int argc, char **argv) fatal("option --index-collation-versions-unknown only works in binary upgrade mode"); /* Open the output file */ - fout = CreateArchive(filename, archiveFormat, compressLevel, dosync, + fout = CreateArchive(filename, archiveFormat, &compress, dosync, archiveMode, setupDumpWorker); /* Make dump options accessible right away */ @@ -957,10 +1037,7 @@ main(int argc, char **argv) ropt->sequence_data = dopt.sequence_data; ropt->binary_upgrade = dopt.binary_upgrade; - if (compressLevel == -1) - ropt->compression = 0; - else - ropt->compression = compressLevel; + ropt->compression = compress; ropt->suppressDumpWarnings = true; /* We've already shown them */ -- 2.17.0 --GRPZ8SYKNexpdSJ7 Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="0004-struct-compressLibs.patch" ^ permalink raw reply [nested|flat] 23+ messages in thread
* [PATCH 03/20] Support multiple compression algs/levels/opts.. @ 2020-12-22 06:23 Justin Pryzby <[email protected]> 0 siblings, 0 replies; 23+ messages in thread From: Justin Pryzby @ 2020-12-22 06:23 UTC (permalink / raw) The existing implementation abtracts compressed and noncompressed I/O. This preliminary commit is intended to also allow for multiple compression algorithms. --- src/bin/pg_dump/compress_io.c | 220 +++++++++++--------------- src/bin/pg_dump/compress_io.h | 19 +-- src/bin/pg_dump/pg_backup.h | 23 ++- src/bin/pg_dump/pg_backup_archiver.c | 45 +++--- src/bin/pg_dump/pg_backup_archiver.h | 12 +- src/bin/pg_dump/pg_backup_custom.c | 6 +- src/bin/pg_dump/pg_backup_directory.c | 17 +- src/bin/pg_dump/pg_backup_tar.c | 33 ++-- src/bin/pg_dump/pg_dump.c | 115 +++++++++++--- 9 files changed, 272 insertions(+), 218 deletions(-) diff --git a/src/bin/pg_dump/compress_io.c b/src/bin/pg_dump/compress_io.c index 6a428978d4..db16fd33f2 100644 --- a/src/bin/pg_dump/compress_io.c +++ b/src/bin/pg_dump/compress_io.c @@ -74,12 +74,9 @@ struct CompressorState #endif }; -static void ParseCompressionOption(int compression, CompressionAlgorithm *alg, - int *level); - /* Routines that support zlib compressed data I/O */ #ifdef HAVE_LIBZ -static void InitCompressorZlib(CompressorState *cs, int level); +static void InitCompressorZlib(CompressorState *cs, Compress *compress); static void DeflateCompressorZlib(ArchiveHandle *AH, CompressorState *cs, bool flush); static void ReadDataFromArchiveZlib(ArchiveHandle *AH, ReadFunc readF); @@ -93,58 +90,36 @@ static void ReadDataFromArchiveNone(ArchiveHandle *AH, ReadFunc readF); static void WriteDataToArchiveNone(ArchiveHandle *AH, CompressorState *cs, const char *data, size_t dLen); -/* - * Interprets a numeric 'compression' value. The algorithm implied by the - * value (zlib or none at the moment), is returned in *alg, and the - * zlib compression level in *level. - */ -static void -ParseCompressionOption(int compression, CompressionAlgorithm *alg, int *level) -{ - if (compression == Z_DEFAULT_COMPRESSION || - (compression > 0 && compression <= 9)) - *alg = COMPR_ALG_LIBZ; - else if (compression == 0) - *alg = COMPR_ALG_NONE; - else - { - fatal("invalid compression code: %d", compression); - *alg = COMPR_ALG_NONE; /* keep compiler quiet */ - } - - /* The level is just the passed-in value. */ - if (level) - *level = compression; -} - /* Public interface routines */ /* Allocate a new compressor */ CompressorState * -AllocateCompressor(int compression, WriteFunc writeF) +AllocateCompressor(Compress *compression, WriteFunc writeF) { CompressorState *cs; - CompressionAlgorithm alg; - int level; - - ParseCompressionOption(compression, &alg, &level); - -#ifndef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - fatal("not built with zlib support"); -#endif cs = (CompressorState *) pg_malloc0(sizeof(CompressorState)); cs->writeF = writeF; - cs->comprAlg = alg; + cs->comprAlg = compression->alg; /* * Perform compression algorithm specific initialization. */ + Assert (compression->alg != COMPR_ALG_DEFAULT); + switch (compression->alg) + { #ifdef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - InitCompressorZlib(cs, level); + case COMPR_ALG_LIBZ: + InitCompressorZlib(cs, compression); + break; #endif + case COMPR_ALG_NONE: + /* Do nothing */ + break; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } return cs; } @@ -154,21 +129,21 @@ AllocateCompressor(int compression, WriteFunc writeF) * out with ahwrite(). */ void -ReadDataFromArchive(ArchiveHandle *AH, int compression, ReadFunc readF) +ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF) { - CompressionAlgorithm alg; - - ParseCompressionOption(compression, &alg, NULL); - - if (alg == COMPR_ALG_NONE) - ReadDataFromArchiveNone(AH, readF); - if (alg == COMPR_ALG_LIBZ) + switch (AH->compression.alg) { + case COMPR_ALG_NONE: + ReadDataFromArchiveNone(AH, readF); + break; #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: ReadDataFromArchiveZlib(AH, readF); -#else - fatal("not built with zlib support"); + break; #endif + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -181,16 +156,18 @@ WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, { switch (cs->comprAlg) { - case COMPR_ALG_LIBZ: #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: WriteDataToArchiveZlib(AH, cs, data, dLen); -#else - fatal("not built with zlib support"); -#endif break; +#endif case COMPR_ALG_NONE: WriteDataToArchiveNone(AH, cs, data, dLen); break; + + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -215,7 +192,7 @@ EndCompressor(ArchiveHandle *AH, CompressorState *cs) */ static void -InitCompressorZlib(CompressorState *cs, int level) +InitCompressorZlib(CompressorState *cs, Compress *compress) { z_streamp zp; @@ -232,7 +209,7 @@ InitCompressorZlib(CompressorState *cs, int level) cs->zlibOut = (char *) pg_malloc(ZLIB_OUT_SIZE + 1); cs->zlibOutSize = ZLIB_OUT_SIZE; - if (deflateInit(zp, level) != Z_OK) + if (deflateInit(zp, compress->level) != Z_OK) fatal("could not initialize compression library: %s", zp->msg); @@ -424,9 +401,7 @@ struct cfp #endif }; -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix); -#endif /* free() without changing errno; useful in several places below */ static void @@ -442,34 +417,31 @@ free_keep_errno(void *p) * Open a file for reading. 'path' is the file to open, and 'mode' should * be either "r" or "rb". * - * If the file at 'path' does not exist, we append the ".gz" suffix (if 'path' - * doesn't already have it) and try again. So if you pass "foo" as 'path', + * If the file at 'path' does not exist, we search with compressed suffix (if 'path' + * doesn't already have one) and try again. So if you pass "foo" as 'path', * this will open either "foo" or "foo.gz". * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_read(const char *path, const char *mode) +cfopen_read(const char *path, const char *mode, Compress *compression) { cfp *fp; -#ifdef HAVE_LIBZ if (hasSuffix(path, ".gz")) - fp = cfopen(path, mode, 1); + fp = cfopen(path, mode, compression); else -#endif { - fp = cfopen(path, mode, 0); -#ifdef HAVE_LIBZ + fp = cfopen(path, mode, compression); if (fp == NULL) { char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); - fp = cfopen(fname, mode, 1); + fname = psprintf("%s%s", path, suffix); + fp = cfopen(fname, mode, compression); free_keep_errno(fname); } -#endif } return fp; } @@ -479,31 +451,26 @@ cfopen_read(const char *path, const char *mode) * be a filemode as accepted by fopen() and gzopen() that indicates writing * ("w", "wb", "a", or "ab"). * - * If 'compression' is non-zero, a gzip compressed stream is opened, and - * 'compression' indicates the compression level used. The ".gz" suffix - * is automatically added to 'path' in that case. + * Use compression if specified. + * The appropriate suffix is automatically added to 'path' in that case. * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_write(const char *path, const char *mode, int compression) +cfopen_write(const char *path, const char *mode, Compress *compression) { cfp *fp; - if (compression == 0) - fp = cfopen(path, mode, 0); + if (compression->alg == COMPR_ALG_NONE) + fp = cfopen(path, mode, compression); else { -#ifdef HAVE_LIBZ char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); + fname = psprintf("%s%s", path, suffix); fp = cfopen(fname, mode, compression); free_keep_errno(fname); -#else - fatal("not built with zlib support"); - fp = NULL; /* keep compiler quiet */ -#endif } return fp; } @@ -515,20 +482,21 @@ cfopen_write(const char *path, const char *mode, int compression) * On failure, return NULL with an error code in errno. */ cfp * -cfopen(const char *path, const char *mode, int compression) +cfopen(const char *path, const char *mode, Compress *compression) { - cfp *fp = pg_malloc(sizeof(cfp)); + cfp *fp = pg_malloc0(sizeof(cfp)); - if (compression != 0) + switch (compression->alg) { #ifdef HAVE_LIBZ - if (compression != Z_DEFAULT_COMPRESSION) + case COMPR_ALG_LIBZ: + if (compression->level != Z_DEFAULT_COMPRESSION) { /* user has specified a compression level, so tell zlib to use it */ char mode_compression[32]; snprintf(mode_compression, sizeof(mode_compression), "%s%d", - mode, compression); + mode, compression->level); fp->compressedfp = gzopen(path, mode_compression); } else @@ -537,30 +505,27 @@ cfopen(const char *path, const char *mode, int compression) fp->compressedfp = gzopen(path, mode); } - fp->uncompressedfp = NULL; if (fp->compressedfp == NULL) { free_keep_errno(fp); fp = NULL; } -#else - fatal("not built with zlib support"); -#endif - } - else - { -#ifdef HAVE_LIBZ - fp->compressedfp = NULL; + return fp; #endif + + case COMPR_ALG_NONE: fp->uncompressedfp = fopen(path, mode); if (fp->uncompressedfp == NULL) { free_keep_errno(fp); fp = NULL; } - } + return fp; - return fp; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } } @@ -584,14 +549,13 @@ cfread(void *ptr, int size, cfp *fp) fatal("could not read from input file: %s", errnum == Z_ERRNO ? strerror(errno) : errmsg); } + return ret; } - else #endif - { - ret = fread(ptr, 1, size, fp->uncompressedfp); - if (ret != size && !feof(fp->uncompressedfp)) - READ_ERROR_EXIT(fp->uncompressedfp); - } + + ret = fread(ptr, 1, size, fp->uncompressedfp); + if (ret != size && !feof(fp->uncompressedfp)) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -601,9 +565,8 @@ cfwrite(const void *ptr, int size, cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzwrite(fp->compressedfp, ptr, size); - else #endif - return fwrite(ptr, 1, size, fp->uncompressedfp); + return fwrite(ptr, 1, size, fp->uncompressedfp); } int @@ -622,15 +585,12 @@ cfgetc(cfp *fp) else fatal("could not read from input file: end of file"); } + return ret; } - else #endif - { - ret = fgetc(fp->uncompressedfp); - if (ret == EOF) - READ_ERROR_EXIT(fp->uncompressedfp); - } - + ret = fgetc(fp->uncompressedfp); + if (ret == EOF) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -640,9 +600,8 @@ cfgets(cfp *fp, char *buf, int len) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzgets(fp->compressedfp, buf, len); - else #endif - return fgets(buf, len, fp->uncompressedfp); + return fgets(buf, len, fp->uncompressedfp); } int @@ -660,15 +619,13 @@ cfclose(cfp *fp) { result = gzclose(fp->compressedfp); fp->compressedfp = NULL; + return result; } - else #endif - { - result = fclose(fp->uncompressedfp); - fp->uncompressedfp = NULL; - } - free_keep_errno(fp); + result = fclose(fp->uncompressedfp); + fp->uncompressedfp = NULL; + free_keep_errno(fp); return result; } @@ -678,9 +635,9 @@ cfeof(cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzeof(fp->compressedfp); - else #endif - return feof(fp->uncompressedfp); + + return feof(fp->uncompressedfp); } const char * @@ -699,7 +656,6 @@ get_cfp_error(cfp *fp) return strerror(errno); } -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix) { @@ -714,4 +670,18 @@ hasSuffix(const char *filename, const char *suffix) suffixlen) == 0; } -#endif +/* + * Return a string for the given AH's compression. + * The string is statically allocated. + */ +const char * +compress_suffix(Compress *compression) +{ + switch (compression->alg) + { + case COMPR_ALG_LIBZ: + return ".gz"; + default: + return ""; + } +} diff --git a/src/bin/pg_dump/compress_io.h b/src/bin/pg_dump/compress_io.h index d2e6e1b854..2c073676eb 100644 --- a/src/bin/pg_dump/compress_io.h +++ b/src/bin/pg_dump/compress_io.h @@ -21,12 +21,6 @@ #define ZLIB_OUT_SIZE 4096 #define ZLIB_IN_SIZE 4096 -typedef enum -{ - COMPR_ALG_NONE, - COMPR_ALG_LIBZ -} CompressionAlgorithm; - /* Prototype for callback function to WriteDataToArchive() */ typedef void (*WriteFunc) (ArchiveHandle *AH, const char *buf, size_t len); @@ -46,8 +40,8 @@ typedef size_t (*ReadFunc) (ArchiveHandle *AH, char **buf, size_t *buflen); /* struct definition appears in compress_io.c */ typedef struct CompressorState CompressorState; -extern CompressorState *AllocateCompressor(int compression, WriteFunc writeF); -extern void ReadDataFromArchive(ArchiveHandle *AH, int compression, +extern CompressorState *AllocateCompressor(Compress *compression, WriteFunc writeF); +extern void ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF); extern void WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, const void *data, size_t dLen); @@ -56,9 +50,9 @@ extern void EndCompressor(ArchiveHandle *AH, CompressorState *cs); typedef struct cfp cfp; -extern cfp *cfopen(const char *path, const char *mode, int compression); -extern cfp *cfopen_read(const char *path, const char *mode); -extern cfp *cfopen_write(const char *path, const char *mode, int compression); +extern cfp *cfopen(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_read(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_write(const char *path, const char *mode, Compress *compression); extern int cfread(void *ptr, int size, cfp *fp); extern int cfwrite(const void *ptr, int size, cfp *fp); extern int cfgetc(cfp *fp); @@ -67,4 +61,7 @@ extern int cfclose(cfp *fp); extern int cfeof(cfp *fp); extern const char *get_cfp_error(cfp *fp); +/* also used by tar */ +extern const char * compress_suffix(Compress *compression); + #endif diff --git a/src/bin/pg_dump/pg_backup.h b/src/bin/pg_dump/pg_backup.h index 9d0056a569..f2390b7937 100644 --- a/src/bin/pg_dump/pg_backup.h +++ b/src/bin/pg_dump/pg_backup.h @@ -72,6 +72,25 @@ typedef struct _connParams char *override_dbname; } ConnParams; +typedef enum +{ + COMPR_ALG_DEFAULT = -1, + COMPR_ALG_NONE, + COMPR_ALG_LIBZ, +} CompressionAlgorithm; +/* Should be called "method" or "library" ? */ + +typedef struct Compress { + CompressionAlgorithm alg; + int level; + /* Is a nondefault level set ? This is useful since different compression + * methods have different "default" levels. For now we assume the levels + * are all integer, though. + */ + bool level_set; +} Compress; + + typedef struct _restoreOptions { int createDB; /* Issue commands to create the database */ @@ -125,7 +144,7 @@ typedef struct _restoreOptions int noDataForFailedTables; int exit_on_error; - int compression; + Compress compression; int suppressDumpWarnings; /* Suppress output of WARNING entries * to stderr */ bool single_txn; @@ -281,7 +300,7 @@ extern Archive *OpenArchive(const char *FileSpec, const ArchiveFormat fmt); /* Create a new archive */ extern Archive *CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker); /* The --list option */ diff --git a/src/bin/pg_dump/pg_backup_archiver.c b/src/bin/pg_dump/pg_backup_archiver.c index 1f82c6499b..3eb6c55600 100644 --- a/src/bin/pg_dump/pg_backup_archiver.c +++ b/src/bin/pg_dump/pg_backup_archiver.c @@ -70,7 +70,7 @@ typedef struct _parallelReadyList static ArchiveHandle *_allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr); static void _getObjectDescription(PQExpBuffer buf, TocEntry *te); static void _printTocEntry(ArchiveHandle *AH, TocEntry *te, bool isData); @@ -98,7 +98,7 @@ static int _discoverArchiveFormat(ArchiveHandle *AH); static int RestoringToDB(ArchiveHandle *AH); static void dump_lo_buf(ArchiveHandle *AH); static void dumpTimestamp(ArchiveHandle *AH, const char *msg, time_t tim); -static void SetOutput(ArchiveHandle *AH, const char *filename, int compression); +static void SetOutput(ArchiveHandle *AH, const char *filename, Compress *compress); static OutputContext SaveOutput(ArchiveHandle *AH); static void RestoreOutput(ArchiveHandle *AH, OutputContext savedContext); @@ -238,7 +238,7 @@ setupRestoreWorker(Archive *AHX) /* Public */ Archive * CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker) { @@ -253,7 +253,9 @@ CreateArchive(const char *FileSpec, const ArchiveFormat fmt, Archive * OpenArchive(const char *FileSpec, const ArchiveFormat fmt) { - ArchiveHandle *AH = _allocAH(FileSpec, fmt, 0, true, archModeRead, setupRestoreWorker); + Compress compress = {0}; + ArchiveHandle *AH = _allocAH(FileSpec, fmt, &compress, true, archModeRead, + setupRestoreWorker); return (Archive *) AH; } @@ -382,7 +384,7 @@ RestoreArchive(Archive *AHX) * Make sure we won't need (de)compression we haven't got */ #ifndef HAVE_LIBZ - if (AH->compression != 0 && AH->PrintTocDataPtr != NULL) + if (AH->compression.alg != COMPR_ALG_NONE && AH->PrintTocDataPtr != NULL) { for (te = AH->toc->next; te != AH->toc; te = te->next) { @@ -457,8 +459,8 @@ RestoreArchive(Archive *AHX) * Setup the output file if necessary. */ sav = SaveOutput(AH); - if (ropt->filename || ropt->compression) - SetOutput(AH, ropt->filename, ropt->compression); + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) + SetOutput(AH, ropt->filename, &ropt->compression); ahprintf(AH, "--\n-- PostgreSQL database dump\n--\n\n"); @@ -738,7 +740,7 @@ RestoreArchive(Archive *AHX) */ AH->stage = STAGE_FINALIZING; - if (ropt->filename || ropt->compression) + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) RestoreOutput(AH, sav); if (ropt->useDB) @@ -1123,8 +1125,9 @@ PrintTOCSummary(Archive *AHX) char stamp_str[64]; sav = SaveOutput(AH); + Assert(ropt->compression.alg == COMPR_ALG_NONE); if (ropt->filename) - SetOutput(AH, ropt->filename, 0 /* no compression */ ); + SetOutput(AH, ropt->filename, &ropt->compression); if (strftime(stamp_str, sizeof(stamp_str), PGDUMP_STRFTIME_FMT, localtime(&AH->createDate)) == 0) @@ -1133,7 +1136,7 @@ PrintTOCSummary(Archive *AHX) ahprintf(AH, ";\n; Archive created at %s\n", stamp_str); ahprintf(AH, "; dbname: %s\n; TOC Entries: %d\n; Compression: %d\n", sanitize_line(AH->archdbname, false), - AH->tocCount, AH->compression); + AH->tocCount, AH->compression.alg); switch (AH->format) { @@ -1487,7 +1490,7 @@ archprintf(Archive *AH, const char *fmt,...) *******************************/ static void -SetOutput(ArchiveHandle *AH, const char *filename, int compression) +SetOutput(ArchiveHandle *AH, const char *filename, Compress *compression) { int fn; @@ -1510,12 +1513,12 @@ SetOutput(ArchiveHandle *AH, const char *filename, int compression) /* If compression explicitly requested, use gzopen */ #ifdef HAVE_LIBZ - if (compression != 0) + if (compression->alg != COMPR_ALG_NONE) { char fmode[14]; /* Don't use PG_BINARY_x since this is zlib */ - sprintf(fmode, "wb%d", compression); + sprintf(fmode, "wb%d", compression->level); if (fn >= 0) AH->OF = gzdopen(dup(fn), fmode); else @@ -2259,7 +2262,7 @@ _discoverArchiveFormat(ArchiveHandle *AH) */ static ArchiveHandle * _allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr) { ArchiveHandle *AH; @@ -2310,7 +2313,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, AH->toc->prev = AH->toc; AH->mode = mode; - AH->compression = compression; + AH->compression = *compression; AH->dosync = dosync; memset(&(AH->sqlparse), 0, sizeof(AH->sqlparse)); @@ -2325,7 +2328,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, * Force stdin/stdout into binary mode if that is what we are using. */ #ifdef WIN32 - if ((fmt != archNull || compression != 0) && + if ((fmt != archNull || compression->alg != COMPR_ALG_NONE) && (AH->fSpec == NULL || strcmp(AH->fSpec, "") == 0)) { if (mode == archModeWrite) @@ -3741,7 +3744,7 @@ WriteHead(ArchiveHandle *AH) AH->WriteBytePtr(AH, AH->intSize); AH->WriteBytePtr(AH, AH->offSize); AH->WriteBytePtr(AH, AH->format); - WriteInt(AH, AH->compression); + WriteInt(AH, AH->compression.alg); crtm = *localtime(&AH->createDate); WriteInt(AH, crtm.tm_sec); WriteInt(AH, crtm.tm_min); @@ -3816,15 +3819,15 @@ ReadHead(ArchiveHandle *AH) if (AH->version >= K_VERS_1_2) { if (AH->version < K_VERS_1_4) - AH->compression = AH->ReadBytePtr(AH); + AH->compression.alg = AH->ReadBytePtr(AH); else - AH->compression = ReadInt(AH); + AH->compression.alg = ReadInt(AH); } else - AH->compression = Z_DEFAULT_COMPRESSION; + AH->compression.alg = Z_DEFAULT_COMPRESSION; #ifndef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) pg_log_warning("archive is compressed, but this installation does not support compression -- no data will be available"); #endif diff --git a/src/bin/pg_dump/pg_backup_archiver.h b/src/bin/pg_dump/pg_backup_archiver.h index a8ea5c7eae..6e033d040e 100644 --- a/src/bin/pg_dump/pg_backup_archiver.h +++ b/src/bin/pg_dump/pg_backup_archiver.h @@ -47,7 +47,8 @@ #define GZWRITE(p, s, n, fh) (fwrite(p, s, n, fh) * (s)) #define GZREAD(p, s, n, fh) fread(p, s, n, fh) #define GZEOF(fh) feof(fh) -/* this is just the redefinition of a libz constant */ +/* this is just the redefinition of a libz constant, in case zlib isn't + * available */ #define Z_DEFAULT_COMPRESSION (-1) typedef struct _z_stream @@ -329,14 +330,7 @@ struct _archiveHandle DumpId *tableDataId; /* TABLE DATA ids, indexed by table dumpId */ struct _tocEntry *currToc; /* Used when dumping data */ - int compression; /*--------- - * Compression requested on open(). - * Possible values for compression: - * -1 Z_DEFAULT_COMPRESSION - * 0 COMPRESSION_NONE - * 1-9 levels for gzip compression - *--------- - */ + Compress compression; /* Compression requested on open */ bool dosync; /* data requested to be synced on sight */ ArchiveMode mode; /* File mode - r or w */ void *formatData; /* Header data specific to file format */ diff --git a/src/bin/pg_dump/pg_backup_custom.c b/src/bin/pg_dump/pg_backup_custom.c index 77d402c323..55a887a236 100644 --- a/src/bin/pg_dump/pg_backup_custom.c +++ b/src/bin/pg_dump/pg_backup_custom.c @@ -298,7 +298,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) _WriteByte(AH, BLK_DATA); /* Block type */ WriteInt(AH, te->dumpId); /* For sanity check */ - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -377,7 +377,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) WriteInt(AH, oid); - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -566,7 +566,7 @@ _PrintTocData(ArchiveHandle *AH, TocEntry *te) static void _PrintData(ArchiveHandle *AH) { - ReadDataFromArchive(AH, AH->compression, _CustomReadFunc); + ReadDataFromArchive(AH, _CustomReadFunc); } static void diff --git a/src/bin/pg_dump/pg_backup_directory.c b/src/bin/pg_dump/pg_backup_directory.c index 650b542fce..8bf869c6ca 100644 --- a/src/bin/pg_dump/pg_backup_directory.c +++ b/src/bin/pg_dump/pg_backup_directory.c @@ -202,7 +202,7 @@ InitArchiveFmt_Directory(ArchiveHandle *AH) setFilePath(AH, fname, "toc.dat"); - tocFH = cfopen_read(fname, PG_BINARY_R); + tocFH = cfopen_read(fname, PG_BINARY_R, &AH->compression); if (tocFH == NULL) fatal("could not open input file \"%s\": %m", fname); @@ -327,7 +327,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) setFilePath(AH, fname, tctx->filename); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -388,7 +388,7 @@ _PrintFileData(ArchiveHandle *AH, char *filename) if (!filename) return; - cfp = cfopen_read(filename, PG_BINARY_R); + cfp = cfopen_read(filename, PG_BINARY_R, &AH->compression); if (!cfp) fatal("could not open input file \"%s\": %m", filename); @@ -435,12 +435,13 @@ _LoadBlobs(ArchiveHandle *AH) lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; char line[MAXPGPATH]; + Compress nocompression = {0}; StartRestoreBlobs(AH); setFilePath(AH, fname, "blobs.toc"); - ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R); + ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R, &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open large object TOC file \"%s\" for input: %m", @@ -573,6 +574,7 @@ _CloseArchive(ArchiveHandle *AH) { cfp *tocFH; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "toc.dat"); @@ -580,7 +582,7 @@ _CloseArchive(ArchiveHandle *AH) ctx->pstate = ParallelBackupStart(AH); /* The TOC is always created uncompressed */ - tocFH = cfopen_write(fname, PG_BINARY_W, 0); + tocFH = cfopen_write(fname, PG_BINARY_W, &nocompression); if (tocFH == NULL) fatal("could not open output file \"%s\": %m", fname); ctx->dataFH = tocFH; @@ -639,11 +641,12 @@ _StartBlobs(ArchiveHandle *AH, TocEntry *te) { lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "blobs.toc"); /* The blob TOC file is never compressed */ - ctx->blobsTocFH = cfopen_write(fname, "ab", 0); + ctx->blobsTocFH = cfopen_write(fname, "ab", &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -661,7 +664,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) snprintf(fname, MAXPGPATH, "%s/blob_%u.dat", ctx->directory, oid); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); diff --git a/src/bin/pg_dump/pg_backup_tar.c b/src/bin/pg_dump/pg_backup_tar.c index 61c9c87a9f..4ba79ab924 100644 --- a/src/bin/pg_dump/pg_backup_tar.c +++ b/src/bin/pg_dump/pg_backup_tar.c @@ -39,6 +39,7 @@ #include "pg_backup_archiver.h" #include "pg_backup_tar.h" #include "pg_backup_utils.h" +#include "compress_io.h" #include "pgtar.h" static void _ArchiveEntry(ArchiveHandle *AH, TocEntry *te); @@ -196,10 +197,10 @@ InitArchiveFmt_Tar(ArchiveHandle *AH) /* * We don't support compression because reading the files back is not - * possible since gzdopen uses buffered IO which totally screws file + * possible since gzdopen uses buffered IO which totally screws file XXX * positioning. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) fatal("compression is not supported by tar archive format"); } else @@ -254,14 +255,8 @@ _ArchiveEntry(ArchiveHandle *AH, TocEntry *te) ctx = (lclTocEntry *) pg_malloc0(sizeof(lclTocEntry)); if (te->dataDumper != NULL) { -#ifdef HAVE_LIBZ - if (AH->compression == 0) - sprintf(fn, "%d.dat", te->dumpId); - else - sprintf(fn, "%d.dat.gz", te->dumpId); -#else - sprintf(fn, "%d.dat", te->dumpId); -#endif + const char *suffix = compress_suffix(&AH->compression); + sprintf(fn, "%d.dat%s", te->dumpId, suffix); ctx->filename = pg_strdup(fn); } else @@ -352,7 +347,7 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression == 0) + if (AH->compression.alg == COMPR_ALG_NONE) tm->nFH = ctx->tarFH; else fatal("compression is not supported by tar archive format"); @@ -413,9 +408,9 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) { - sprintf(fmode, "wb%d", AH->compression); + sprintf(fmode, "wb%d", AH->compression.level); tm->zFH = gzdopen(dup(fileno(tm->tmpFH)), fmode); if (tm->zFH == NULL) fatal("could not open temporary file"); @@ -443,7 +438,7 @@ tarClose(ArchiveHandle *AH, TAR_MEMBER *th) /* * Close the GZ file since we dup'd. This will flush the buffers. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) if (GZCLOSE(th->zFH) != 0) fatal("could not close tar member"); @@ -868,7 +863,7 @@ _CloseArchive(ArchiveHandle *AH) memcpy(ropt, AH->public.ropt, sizeof(RestoreOptions)); ropt->filename = NULL; ropt->dropSchema = 1; - ropt->compression = 0; + ropt->compression.alg = COMPR_ALG_NONE; ropt->superuser = NULL; ropt->suppressDumpWarnings = true; @@ -952,16 +947,12 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) lclContext *ctx = (lclContext *) AH->formatData; lclTocEntry *tctx = (lclTocEntry *) te->formatData; char fname[255]; - char *sfx; + const char *sfx; if (oid == 0) fatal("invalid OID for large object (%u)", oid); - if (AH->compression != 0) - sfx = ".gz"; - else - sfx = ""; - + sfx = compress_suffix(&AH->compression); sprintf(fname, "blob_%u.dat%s", oid, sfx); tarPrintf(ctx->blobToc, "%u %s\n", oid, fname); diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c index 1ab98a2286..4cbc79aedc 100644 --- a/src/bin/pg_dump/pg_dump.c +++ b/src/bin/pg_dump/pg_dump.c @@ -59,6 +59,7 @@ #include "getopt_long.h" #include "libpq/libpq-fs.h" #include "parallel.h" +#include "compress_io.h" #include "pg_backup_db.h" #include "pg_backup_utils.h" #include "pg_dump.h" @@ -297,6 +298,82 @@ static void setupDumpWorker(Archive *AHX); static TableInfo *getRootTableInfo(TableInfo *tbinfo); +/* Parse the string into compression options */ +static void +parse_compression(const char *optarg, Compress *compress) +{ + if (optarg[0] == '0' && optarg[1] == '\0') + compress->alg = COMPR_ALG_NONE; + else if ((optarg[0] > '0' && optarg[0] <= '9') || + optarg[0] == '-') + { + compress->alg = COMPR_ALG_LIBZ; + compress->level_set = true; + compress->level = atoi(optarg); + if (optarg[1] != '\0') + { + pg_log_error("compression level must be in range 0..9"); + exit_nicely(1); + } + } + else + { + /* Parse a more flexible string like level=3 alg=zlib opts=long */ + for (;;) + { + char *eq = strchr(optarg, '='); + int len; + + if (eq == NULL) + { + pg_log_error("compression options must be key=value: %s", optarg); + exit_nicely(1); + } + + len = eq - optarg; + if (strncmp(optarg, "alg", len) == 0) + { + if (strchr(eq, ' ')) + len = strchr(eq, ' ') - eq - 1; + else + len = strlen(eq) - len; + if (strncmp(1+eq, "zlib", len) == 0 || + strncmp(1+eq, "libz", len) == 0) + compress->alg = COMPR_ALG_LIBZ; + else + { + pg_log_error("unknown compression algorithm: %s", 1+eq); + exit_nicely(1); + } + } + else if (strncmp(optarg, "level", len) == 0) + { + compress->level = atoi(1+eq); + compress->level_set = true; + } + else + { + pg_log_error("unknown compression setting: %s", optarg); + exit_nicely(1); + } + + optarg = strchr(eq, ' '); + if (!optarg++) + break; + } + + if (!compress->level_set) + { + const int default_compress_level[] = { + 0, /* COMPR_ALG_NONE */ + Z_DEFAULT_COMPRESSION, /* COMPR_ALG_ZLIB */ + }; + + compress->level = default_compress_level[compress->alg]; + } + } +} + int main(int argc, char **argv) { @@ -319,7 +396,7 @@ main(int argc, char **argv) char *use_role = NULL; long rowsPerInsert; int numWorkers = 1; - int compressLevel = -1; + Compress compress = { .alg = COMPR_ALG_DEFAULT }; int plainText = 0; ArchiveFormat archiveFormat = archUnknown; ArchiveMode archiveMode; @@ -532,12 +609,7 @@ main(int argc, char **argv) break; case 'Z': /* Compression Level */ - compressLevel = atoi(optarg); - if (compressLevel < 0 || compressLevel > 9) - { - pg_log_error("compression level must be in range 0..9"); - exit_nicely(1); - } + parse_compression(optarg, &compress); break; case 0: @@ -679,20 +751,28 @@ main(int argc, char **argv) plainText = 1; /* Custom and directory formats are compressed by default, others not */ - if (compressLevel == -1) + if (compress.alg == COMPR_ALG_DEFAULT) { -#ifdef HAVE_LIBZ if (archiveFormat == archCustom || archiveFormat == archDirectory) - compressLevel = Z_DEFAULT_COMPRESSION; - else + { +#ifdef HAVE_LIBZ + compress.alg = COMPR_ALG_LIBZ; + compress.level = Z_DEFAULT_COMPRESSION; #endif - compressLevel = 0; + } + else + { + compress.alg = COMPR_ALG_NONE; + compress.level = 0; + } } #ifndef HAVE_LIBZ - if (compressLevel != 0) + if (compress.alg == COMPR_ALG_LIBZ) + { pg_log_warning("requested compression not available in this installation -- archive will be uncompressed"); - compressLevel = 0; + compress.alg = 0; + } #endif /* @@ -723,7 +803,7 @@ main(int argc, char **argv) fatal("option --index-collation-versions-unknown only works in binary upgrade mode"); /* Open the output file */ - fout = CreateArchive(filename, archiveFormat, compressLevel, dosync, + fout = CreateArchive(filename, archiveFormat, &compress, dosync, archiveMode, setupDumpWorker); /* Make dump options accessible right away */ @@ -957,10 +1037,7 @@ main(int argc, char **argv) ropt->sequence_data = dopt.sequence_data; ropt->binary_upgrade = dopt.binary_upgrade; - if (compressLevel == -1) - ropt->compression = 0; - else - ropt->compression = compressLevel; + ropt->compression = compress; ropt->suppressDumpWarnings = true; /* We've already shown them */ -- 2.17.0 --GRPZ8SYKNexpdSJ7 Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="0004-struct-compressLibs.patch" ^ permalink raw reply [nested|flat] 23+ messages in thread
* [PATCH 03/20] Support multiple compression algs/levels/opts.. @ 2020-12-22 06:23 Justin Pryzby <[email protected]> 0 siblings, 0 replies; 23+ messages in thread From: Justin Pryzby @ 2020-12-22 06:23 UTC (permalink / raw) The existing implementation abtracts compressed and noncompressed I/O. This preliminary commit is intended to also allow for multiple compression algorithms. --- src/bin/pg_dump/compress_io.c | 220 +++++++++++--------------- src/bin/pg_dump/compress_io.h | 19 +-- src/bin/pg_dump/pg_backup.h | 23 ++- src/bin/pg_dump/pg_backup_archiver.c | 45 +++--- src/bin/pg_dump/pg_backup_archiver.h | 12 +- src/bin/pg_dump/pg_backup_custom.c | 6 +- src/bin/pg_dump/pg_backup_directory.c | 17 +- src/bin/pg_dump/pg_backup_tar.c | 33 ++-- src/bin/pg_dump/pg_dump.c | 115 +++++++++++--- 9 files changed, 272 insertions(+), 218 deletions(-) diff --git a/src/bin/pg_dump/compress_io.c b/src/bin/pg_dump/compress_io.c index 6a428978d4..db16fd33f2 100644 --- a/src/bin/pg_dump/compress_io.c +++ b/src/bin/pg_dump/compress_io.c @@ -74,12 +74,9 @@ struct CompressorState #endif }; -static void ParseCompressionOption(int compression, CompressionAlgorithm *alg, - int *level); - /* Routines that support zlib compressed data I/O */ #ifdef HAVE_LIBZ -static void InitCompressorZlib(CompressorState *cs, int level); +static void InitCompressorZlib(CompressorState *cs, Compress *compress); static void DeflateCompressorZlib(ArchiveHandle *AH, CompressorState *cs, bool flush); static void ReadDataFromArchiveZlib(ArchiveHandle *AH, ReadFunc readF); @@ -93,58 +90,36 @@ static void ReadDataFromArchiveNone(ArchiveHandle *AH, ReadFunc readF); static void WriteDataToArchiveNone(ArchiveHandle *AH, CompressorState *cs, const char *data, size_t dLen); -/* - * Interprets a numeric 'compression' value. The algorithm implied by the - * value (zlib or none at the moment), is returned in *alg, and the - * zlib compression level in *level. - */ -static void -ParseCompressionOption(int compression, CompressionAlgorithm *alg, int *level) -{ - if (compression == Z_DEFAULT_COMPRESSION || - (compression > 0 && compression <= 9)) - *alg = COMPR_ALG_LIBZ; - else if (compression == 0) - *alg = COMPR_ALG_NONE; - else - { - fatal("invalid compression code: %d", compression); - *alg = COMPR_ALG_NONE; /* keep compiler quiet */ - } - - /* The level is just the passed-in value. */ - if (level) - *level = compression; -} - /* Public interface routines */ /* Allocate a new compressor */ CompressorState * -AllocateCompressor(int compression, WriteFunc writeF) +AllocateCompressor(Compress *compression, WriteFunc writeF) { CompressorState *cs; - CompressionAlgorithm alg; - int level; - - ParseCompressionOption(compression, &alg, &level); - -#ifndef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - fatal("not built with zlib support"); -#endif cs = (CompressorState *) pg_malloc0(sizeof(CompressorState)); cs->writeF = writeF; - cs->comprAlg = alg; + cs->comprAlg = compression->alg; /* * Perform compression algorithm specific initialization. */ + Assert (compression->alg != COMPR_ALG_DEFAULT); + switch (compression->alg) + { #ifdef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - InitCompressorZlib(cs, level); + case COMPR_ALG_LIBZ: + InitCompressorZlib(cs, compression); + break; #endif + case COMPR_ALG_NONE: + /* Do nothing */ + break; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } return cs; } @@ -154,21 +129,21 @@ AllocateCompressor(int compression, WriteFunc writeF) * out with ahwrite(). */ void -ReadDataFromArchive(ArchiveHandle *AH, int compression, ReadFunc readF) +ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF) { - CompressionAlgorithm alg; - - ParseCompressionOption(compression, &alg, NULL); - - if (alg == COMPR_ALG_NONE) - ReadDataFromArchiveNone(AH, readF); - if (alg == COMPR_ALG_LIBZ) + switch (AH->compression.alg) { + case COMPR_ALG_NONE: + ReadDataFromArchiveNone(AH, readF); + break; #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: ReadDataFromArchiveZlib(AH, readF); -#else - fatal("not built with zlib support"); + break; #endif + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -181,16 +156,18 @@ WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, { switch (cs->comprAlg) { - case COMPR_ALG_LIBZ: #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: WriteDataToArchiveZlib(AH, cs, data, dLen); -#else - fatal("not built with zlib support"); -#endif break; +#endif case COMPR_ALG_NONE: WriteDataToArchiveNone(AH, cs, data, dLen); break; + + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -215,7 +192,7 @@ EndCompressor(ArchiveHandle *AH, CompressorState *cs) */ static void -InitCompressorZlib(CompressorState *cs, int level) +InitCompressorZlib(CompressorState *cs, Compress *compress) { z_streamp zp; @@ -232,7 +209,7 @@ InitCompressorZlib(CompressorState *cs, int level) cs->zlibOut = (char *) pg_malloc(ZLIB_OUT_SIZE + 1); cs->zlibOutSize = ZLIB_OUT_SIZE; - if (deflateInit(zp, level) != Z_OK) + if (deflateInit(zp, compress->level) != Z_OK) fatal("could not initialize compression library: %s", zp->msg); @@ -424,9 +401,7 @@ struct cfp #endif }; -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix); -#endif /* free() without changing errno; useful in several places below */ static void @@ -442,34 +417,31 @@ free_keep_errno(void *p) * Open a file for reading. 'path' is the file to open, and 'mode' should * be either "r" or "rb". * - * If the file at 'path' does not exist, we append the ".gz" suffix (if 'path' - * doesn't already have it) and try again. So if you pass "foo" as 'path', + * If the file at 'path' does not exist, we search with compressed suffix (if 'path' + * doesn't already have one) and try again. So if you pass "foo" as 'path', * this will open either "foo" or "foo.gz". * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_read(const char *path, const char *mode) +cfopen_read(const char *path, const char *mode, Compress *compression) { cfp *fp; -#ifdef HAVE_LIBZ if (hasSuffix(path, ".gz")) - fp = cfopen(path, mode, 1); + fp = cfopen(path, mode, compression); else -#endif { - fp = cfopen(path, mode, 0); -#ifdef HAVE_LIBZ + fp = cfopen(path, mode, compression); if (fp == NULL) { char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); - fp = cfopen(fname, mode, 1); + fname = psprintf("%s%s", path, suffix); + fp = cfopen(fname, mode, compression); free_keep_errno(fname); } -#endif } return fp; } @@ -479,31 +451,26 @@ cfopen_read(const char *path, const char *mode) * be a filemode as accepted by fopen() and gzopen() that indicates writing * ("w", "wb", "a", or "ab"). * - * If 'compression' is non-zero, a gzip compressed stream is opened, and - * 'compression' indicates the compression level used. The ".gz" suffix - * is automatically added to 'path' in that case. + * Use compression if specified. + * The appropriate suffix is automatically added to 'path' in that case. * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_write(const char *path, const char *mode, int compression) +cfopen_write(const char *path, const char *mode, Compress *compression) { cfp *fp; - if (compression == 0) - fp = cfopen(path, mode, 0); + if (compression->alg == COMPR_ALG_NONE) + fp = cfopen(path, mode, compression); else { -#ifdef HAVE_LIBZ char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); + fname = psprintf("%s%s", path, suffix); fp = cfopen(fname, mode, compression); free_keep_errno(fname); -#else - fatal("not built with zlib support"); - fp = NULL; /* keep compiler quiet */ -#endif } return fp; } @@ -515,20 +482,21 @@ cfopen_write(const char *path, const char *mode, int compression) * On failure, return NULL with an error code in errno. */ cfp * -cfopen(const char *path, const char *mode, int compression) +cfopen(const char *path, const char *mode, Compress *compression) { - cfp *fp = pg_malloc(sizeof(cfp)); + cfp *fp = pg_malloc0(sizeof(cfp)); - if (compression != 0) + switch (compression->alg) { #ifdef HAVE_LIBZ - if (compression != Z_DEFAULT_COMPRESSION) + case COMPR_ALG_LIBZ: + if (compression->level != Z_DEFAULT_COMPRESSION) { /* user has specified a compression level, so tell zlib to use it */ char mode_compression[32]; snprintf(mode_compression, sizeof(mode_compression), "%s%d", - mode, compression); + mode, compression->level); fp->compressedfp = gzopen(path, mode_compression); } else @@ -537,30 +505,27 @@ cfopen(const char *path, const char *mode, int compression) fp->compressedfp = gzopen(path, mode); } - fp->uncompressedfp = NULL; if (fp->compressedfp == NULL) { free_keep_errno(fp); fp = NULL; } -#else - fatal("not built with zlib support"); -#endif - } - else - { -#ifdef HAVE_LIBZ - fp->compressedfp = NULL; + return fp; #endif + + case COMPR_ALG_NONE: fp->uncompressedfp = fopen(path, mode); if (fp->uncompressedfp == NULL) { free_keep_errno(fp); fp = NULL; } - } + return fp; - return fp; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } } @@ -584,14 +549,13 @@ cfread(void *ptr, int size, cfp *fp) fatal("could not read from input file: %s", errnum == Z_ERRNO ? strerror(errno) : errmsg); } + return ret; } - else #endif - { - ret = fread(ptr, 1, size, fp->uncompressedfp); - if (ret != size && !feof(fp->uncompressedfp)) - READ_ERROR_EXIT(fp->uncompressedfp); - } + + ret = fread(ptr, 1, size, fp->uncompressedfp); + if (ret != size && !feof(fp->uncompressedfp)) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -601,9 +565,8 @@ cfwrite(const void *ptr, int size, cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzwrite(fp->compressedfp, ptr, size); - else #endif - return fwrite(ptr, 1, size, fp->uncompressedfp); + return fwrite(ptr, 1, size, fp->uncompressedfp); } int @@ -622,15 +585,12 @@ cfgetc(cfp *fp) else fatal("could not read from input file: end of file"); } + return ret; } - else #endif - { - ret = fgetc(fp->uncompressedfp); - if (ret == EOF) - READ_ERROR_EXIT(fp->uncompressedfp); - } - + ret = fgetc(fp->uncompressedfp); + if (ret == EOF) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -640,9 +600,8 @@ cfgets(cfp *fp, char *buf, int len) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzgets(fp->compressedfp, buf, len); - else #endif - return fgets(buf, len, fp->uncompressedfp); + return fgets(buf, len, fp->uncompressedfp); } int @@ -660,15 +619,13 @@ cfclose(cfp *fp) { result = gzclose(fp->compressedfp); fp->compressedfp = NULL; + return result; } - else #endif - { - result = fclose(fp->uncompressedfp); - fp->uncompressedfp = NULL; - } - free_keep_errno(fp); + result = fclose(fp->uncompressedfp); + fp->uncompressedfp = NULL; + free_keep_errno(fp); return result; } @@ -678,9 +635,9 @@ cfeof(cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzeof(fp->compressedfp); - else #endif - return feof(fp->uncompressedfp); + + return feof(fp->uncompressedfp); } const char * @@ -699,7 +656,6 @@ get_cfp_error(cfp *fp) return strerror(errno); } -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix) { @@ -714,4 +670,18 @@ hasSuffix(const char *filename, const char *suffix) suffixlen) == 0; } -#endif +/* + * Return a string for the given AH's compression. + * The string is statically allocated. + */ +const char * +compress_suffix(Compress *compression) +{ + switch (compression->alg) + { + case COMPR_ALG_LIBZ: + return ".gz"; + default: + return ""; + } +} diff --git a/src/bin/pg_dump/compress_io.h b/src/bin/pg_dump/compress_io.h index d2e6e1b854..2c073676eb 100644 --- a/src/bin/pg_dump/compress_io.h +++ b/src/bin/pg_dump/compress_io.h @@ -21,12 +21,6 @@ #define ZLIB_OUT_SIZE 4096 #define ZLIB_IN_SIZE 4096 -typedef enum -{ - COMPR_ALG_NONE, - COMPR_ALG_LIBZ -} CompressionAlgorithm; - /* Prototype for callback function to WriteDataToArchive() */ typedef void (*WriteFunc) (ArchiveHandle *AH, const char *buf, size_t len); @@ -46,8 +40,8 @@ typedef size_t (*ReadFunc) (ArchiveHandle *AH, char **buf, size_t *buflen); /* struct definition appears in compress_io.c */ typedef struct CompressorState CompressorState; -extern CompressorState *AllocateCompressor(int compression, WriteFunc writeF); -extern void ReadDataFromArchive(ArchiveHandle *AH, int compression, +extern CompressorState *AllocateCompressor(Compress *compression, WriteFunc writeF); +extern void ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF); extern void WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, const void *data, size_t dLen); @@ -56,9 +50,9 @@ extern void EndCompressor(ArchiveHandle *AH, CompressorState *cs); typedef struct cfp cfp; -extern cfp *cfopen(const char *path, const char *mode, int compression); -extern cfp *cfopen_read(const char *path, const char *mode); -extern cfp *cfopen_write(const char *path, const char *mode, int compression); +extern cfp *cfopen(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_read(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_write(const char *path, const char *mode, Compress *compression); extern int cfread(void *ptr, int size, cfp *fp); extern int cfwrite(const void *ptr, int size, cfp *fp); extern int cfgetc(cfp *fp); @@ -67,4 +61,7 @@ extern int cfclose(cfp *fp); extern int cfeof(cfp *fp); extern const char *get_cfp_error(cfp *fp); +/* also used by tar */ +extern const char * compress_suffix(Compress *compression); + #endif diff --git a/src/bin/pg_dump/pg_backup.h b/src/bin/pg_dump/pg_backup.h index 9d0056a569..f2390b7937 100644 --- a/src/bin/pg_dump/pg_backup.h +++ b/src/bin/pg_dump/pg_backup.h @@ -72,6 +72,25 @@ typedef struct _connParams char *override_dbname; } ConnParams; +typedef enum +{ + COMPR_ALG_DEFAULT = -1, + COMPR_ALG_NONE, + COMPR_ALG_LIBZ, +} CompressionAlgorithm; +/* Should be called "method" or "library" ? */ + +typedef struct Compress { + CompressionAlgorithm alg; + int level; + /* Is a nondefault level set ? This is useful since different compression + * methods have different "default" levels. For now we assume the levels + * are all integer, though. + */ + bool level_set; +} Compress; + + typedef struct _restoreOptions { int createDB; /* Issue commands to create the database */ @@ -125,7 +144,7 @@ typedef struct _restoreOptions int noDataForFailedTables; int exit_on_error; - int compression; + Compress compression; int suppressDumpWarnings; /* Suppress output of WARNING entries * to stderr */ bool single_txn; @@ -281,7 +300,7 @@ extern Archive *OpenArchive(const char *FileSpec, const ArchiveFormat fmt); /* Create a new archive */ extern Archive *CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker); /* The --list option */ diff --git a/src/bin/pg_dump/pg_backup_archiver.c b/src/bin/pg_dump/pg_backup_archiver.c index 1f82c6499b..3eb6c55600 100644 --- a/src/bin/pg_dump/pg_backup_archiver.c +++ b/src/bin/pg_dump/pg_backup_archiver.c @@ -70,7 +70,7 @@ typedef struct _parallelReadyList static ArchiveHandle *_allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr); static void _getObjectDescription(PQExpBuffer buf, TocEntry *te); static void _printTocEntry(ArchiveHandle *AH, TocEntry *te, bool isData); @@ -98,7 +98,7 @@ static int _discoverArchiveFormat(ArchiveHandle *AH); static int RestoringToDB(ArchiveHandle *AH); static void dump_lo_buf(ArchiveHandle *AH); static void dumpTimestamp(ArchiveHandle *AH, const char *msg, time_t tim); -static void SetOutput(ArchiveHandle *AH, const char *filename, int compression); +static void SetOutput(ArchiveHandle *AH, const char *filename, Compress *compress); static OutputContext SaveOutput(ArchiveHandle *AH); static void RestoreOutput(ArchiveHandle *AH, OutputContext savedContext); @@ -238,7 +238,7 @@ setupRestoreWorker(Archive *AHX) /* Public */ Archive * CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker) { @@ -253,7 +253,9 @@ CreateArchive(const char *FileSpec, const ArchiveFormat fmt, Archive * OpenArchive(const char *FileSpec, const ArchiveFormat fmt) { - ArchiveHandle *AH = _allocAH(FileSpec, fmt, 0, true, archModeRead, setupRestoreWorker); + Compress compress = {0}; + ArchiveHandle *AH = _allocAH(FileSpec, fmt, &compress, true, archModeRead, + setupRestoreWorker); return (Archive *) AH; } @@ -382,7 +384,7 @@ RestoreArchive(Archive *AHX) * Make sure we won't need (de)compression we haven't got */ #ifndef HAVE_LIBZ - if (AH->compression != 0 && AH->PrintTocDataPtr != NULL) + if (AH->compression.alg != COMPR_ALG_NONE && AH->PrintTocDataPtr != NULL) { for (te = AH->toc->next; te != AH->toc; te = te->next) { @@ -457,8 +459,8 @@ RestoreArchive(Archive *AHX) * Setup the output file if necessary. */ sav = SaveOutput(AH); - if (ropt->filename || ropt->compression) - SetOutput(AH, ropt->filename, ropt->compression); + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) + SetOutput(AH, ropt->filename, &ropt->compression); ahprintf(AH, "--\n-- PostgreSQL database dump\n--\n\n"); @@ -738,7 +740,7 @@ RestoreArchive(Archive *AHX) */ AH->stage = STAGE_FINALIZING; - if (ropt->filename || ropt->compression) + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) RestoreOutput(AH, sav); if (ropt->useDB) @@ -1123,8 +1125,9 @@ PrintTOCSummary(Archive *AHX) char stamp_str[64]; sav = SaveOutput(AH); + Assert(ropt->compression.alg == COMPR_ALG_NONE); if (ropt->filename) - SetOutput(AH, ropt->filename, 0 /* no compression */ ); + SetOutput(AH, ropt->filename, &ropt->compression); if (strftime(stamp_str, sizeof(stamp_str), PGDUMP_STRFTIME_FMT, localtime(&AH->createDate)) == 0) @@ -1133,7 +1136,7 @@ PrintTOCSummary(Archive *AHX) ahprintf(AH, ";\n; Archive created at %s\n", stamp_str); ahprintf(AH, "; dbname: %s\n; TOC Entries: %d\n; Compression: %d\n", sanitize_line(AH->archdbname, false), - AH->tocCount, AH->compression); + AH->tocCount, AH->compression.alg); switch (AH->format) { @@ -1487,7 +1490,7 @@ archprintf(Archive *AH, const char *fmt,...) *******************************/ static void -SetOutput(ArchiveHandle *AH, const char *filename, int compression) +SetOutput(ArchiveHandle *AH, const char *filename, Compress *compression) { int fn; @@ -1510,12 +1513,12 @@ SetOutput(ArchiveHandle *AH, const char *filename, int compression) /* If compression explicitly requested, use gzopen */ #ifdef HAVE_LIBZ - if (compression != 0) + if (compression->alg != COMPR_ALG_NONE) { char fmode[14]; /* Don't use PG_BINARY_x since this is zlib */ - sprintf(fmode, "wb%d", compression); + sprintf(fmode, "wb%d", compression->level); if (fn >= 0) AH->OF = gzdopen(dup(fn), fmode); else @@ -2259,7 +2262,7 @@ _discoverArchiveFormat(ArchiveHandle *AH) */ static ArchiveHandle * _allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr) { ArchiveHandle *AH; @@ -2310,7 +2313,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, AH->toc->prev = AH->toc; AH->mode = mode; - AH->compression = compression; + AH->compression = *compression; AH->dosync = dosync; memset(&(AH->sqlparse), 0, sizeof(AH->sqlparse)); @@ -2325,7 +2328,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, * Force stdin/stdout into binary mode if that is what we are using. */ #ifdef WIN32 - if ((fmt != archNull || compression != 0) && + if ((fmt != archNull || compression->alg != COMPR_ALG_NONE) && (AH->fSpec == NULL || strcmp(AH->fSpec, "") == 0)) { if (mode == archModeWrite) @@ -3741,7 +3744,7 @@ WriteHead(ArchiveHandle *AH) AH->WriteBytePtr(AH, AH->intSize); AH->WriteBytePtr(AH, AH->offSize); AH->WriteBytePtr(AH, AH->format); - WriteInt(AH, AH->compression); + WriteInt(AH, AH->compression.alg); crtm = *localtime(&AH->createDate); WriteInt(AH, crtm.tm_sec); WriteInt(AH, crtm.tm_min); @@ -3816,15 +3819,15 @@ ReadHead(ArchiveHandle *AH) if (AH->version >= K_VERS_1_2) { if (AH->version < K_VERS_1_4) - AH->compression = AH->ReadBytePtr(AH); + AH->compression.alg = AH->ReadBytePtr(AH); else - AH->compression = ReadInt(AH); + AH->compression.alg = ReadInt(AH); } else - AH->compression = Z_DEFAULT_COMPRESSION; + AH->compression.alg = Z_DEFAULT_COMPRESSION; #ifndef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) pg_log_warning("archive is compressed, but this installation does not support compression -- no data will be available"); #endif diff --git a/src/bin/pg_dump/pg_backup_archiver.h b/src/bin/pg_dump/pg_backup_archiver.h index a8ea5c7eae..6e033d040e 100644 --- a/src/bin/pg_dump/pg_backup_archiver.h +++ b/src/bin/pg_dump/pg_backup_archiver.h @@ -47,7 +47,8 @@ #define GZWRITE(p, s, n, fh) (fwrite(p, s, n, fh) * (s)) #define GZREAD(p, s, n, fh) fread(p, s, n, fh) #define GZEOF(fh) feof(fh) -/* this is just the redefinition of a libz constant */ +/* this is just the redefinition of a libz constant, in case zlib isn't + * available */ #define Z_DEFAULT_COMPRESSION (-1) typedef struct _z_stream @@ -329,14 +330,7 @@ struct _archiveHandle DumpId *tableDataId; /* TABLE DATA ids, indexed by table dumpId */ struct _tocEntry *currToc; /* Used when dumping data */ - int compression; /*--------- - * Compression requested on open(). - * Possible values for compression: - * -1 Z_DEFAULT_COMPRESSION - * 0 COMPRESSION_NONE - * 1-9 levels for gzip compression - *--------- - */ + Compress compression; /* Compression requested on open */ bool dosync; /* data requested to be synced on sight */ ArchiveMode mode; /* File mode - r or w */ void *formatData; /* Header data specific to file format */ diff --git a/src/bin/pg_dump/pg_backup_custom.c b/src/bin/pg_dump/pg_backup_custom.c index 77d402c323..55a887a236 100644 --- a/src/bin/pg_dump/pg_backup_custom.c +++ b/src/bin/pg_dump/pg_backup_custom.c @@ -298,7 +298,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) _WriteByte(AH, BLK_DATA); /* Block type */ WriteInt(AH, te->dumpId); /* For sanity check */ - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -377,7 +377,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) WriteInt(AH, oid); - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -566,7 +566,7 @@ _PrintTocData(ArchiveHandle *AH, TocEntry *te) static void _PrintData(ArchiveHandle *AH) { - ReadDataFromArchive(AH, AH->compression, _CustomReadFunc); + ReadDataFromArchive(AH, _CustomReadFunc); } static void diff --git a/src/bin/pg_dump/pg_backup_directory.c b/src/bin/pg_dump/pg_backup_directory.c index 650b542fce..8bf869c6ca 100644 --- a/src/bin/pg_dump/pg_backup_directory.c +++ b/src/bin/pg_dump/pg_backup_directory.c @@ -202,7 +202,7 @@ InitArchiveFmt_Directory(ArchiveHandle *AH) setFilePath(AH, fname, "toc.dat"); - tocFH = cfopen_read(fname, PG_BINARY_R); + tocFH = cfopen_read(fname, PG_BINARY_R, &AH->compression); if (tocFH == NULL) fatal("could not open input file \"%s\": %m", fname); @@ -327,7 +327,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) setFilePath(AH, fname, tctx->filename); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -388,7 +388,7 @@ _PrintFileData(ArchiveHandle *AH, char *filename) if (!filename) return; - cfp = cfopen_read(filename, PG_BINARY_R); + cfp = cfopen_read(filename, PG_BINARY_R, &AH->compression); if (!cfp) fatal("could not open input file \"%s\": %m", filename); @@ -435,12 +435,13 @@ _LoadBlobs(ArchiveHandle *AH) lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; char line[MAXPGPATH]; + Compress nocompression = {0}; StartRestoreBlobs(AH); setFilePath(AH, fname, "blobs.toc"); - ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R); + ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R, &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open large object TOC file \"%s\" for input: %m", @@ -573,6 +574,7 @@ _CloseArchive(ArchiveHandle *AH) { cfp *tocFH; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "toc.dat"); @@ -580,7 +582,7 @@ _CloseArchive(ArchiveHandle *AH) ctx->pstate = ParallelBackupStart(AH); /* The TOC is always created uncompressed */ - tocFH = cfopen_write(fname, PG_BINARY_W, 0); + tocFH = cfopen_write(fname, PG_BINARY_W, &nocompression); if (tocFH == NULL) fatal("could not open output file \"%s\": %m", fname); ctx->dataFH = tocFH; @@ -639,11 +641,12 @@ _StartBlobs(ArchiveHandle *AH, TocEntry *te) { lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "blobs.toc"); /* The blob TOC file is never compressed */ - ctx->blobsTocFH = cfopen_write(fname, "ab", 0); + ctx->blobsTocFH = cfopen_write(fname, "ab", &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -661,7 +664,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) snprintf(fname, MAXPGPATH, "%s/blob_%u.dat", ctx->directory, oid); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); diff --git a/src/bin/pg_dump/pg_backup_tar.c b/src/bin/pg_dump/pg_backup_tar.c index 61c9c87a9f..4ba79ab924 100644 --- a/src/bin/pg_dump/pg_backup_tar.c +++ b/src/bin/pg_dump/pg_backup_tar.c @@ -39,6 +39,7 @@ #include "pg_backup_archiver.h" #include "pg_backup_tar.h" #include "pg_backup_utils.h" +#include "compress_io.h" #include "pgtar.h" static void _ArchiveEntry(ArchiveHandle *AH, TocEntry *te); @@ -196,10 +197,10 @@ InitArchiveFmt_Tar(ArchiveHandle *AH) /* * We don't support compression because reading the files back is not - * possible since gzdopen uses buffered IO which totally screws file + * possible since gzdopen uses buffered IO which totally screws file XXX * positioning. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) fatal("compression is not supported by tar archive format"); } else @@ -254,14 +255,8 @@ _ArchiveEntry(ArchiveHandle *AH, TocEntry *te) ctx = (lclTocEntry *) pg_malloc0(sizeof(lclTocEntry)); if (te->dataDumper != NULL) { -#ifdef HAVE_LIBZ - if (AH->compression == 0) - sprintf(fn, "%d.dat", te->dumpId); - else - sprintf(fn, "%d.dat.gz", te->dumpId); -#else - sprintf(fn, "%d.dat", te->dumpId); -#endif + const char *suffix = compress_suffix(&AH->compression); + sprintf(fn, "%d.dat%s", te->dumpId, suffix); ctx->filename = pg_strdup(fn); } else @@ -352,7 +347,7 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression == 0) + if (AH->compression.alg == COMPR_ALG_NONE) tm->nFH = ctx->tarFH; else fatal("compression is not supported by tar archive format"); @@ -413,9 +408,9 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) { - sprintf(fmode, "wb%d", AH->compression); + sprintf(fmode, "wb%d", AH->compression.level); tm->zFH = gzdopen(dup(fileno(tm->tmpFH)), fmode); if (tm->zFH == NULL) fatal("could not open temporary file"); @@ -443,7 +438,7 @@ tarClose(ArchiveHandle *AH, TAR_MEMBER *th) /* * Close the GZ file since we dup'd. This will flush the buffers. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) if (GZCLOSE(th->zFH) != 0) fatal("could not close tar member"); @@ -868,7 +863,7 @@ _CloseArchive(ArchiveHandle *AH) memcpy(ropt, AH->public.ropt, sizeof(RestoreOptions)); ropt->filename = NULL; ropt->dropSchema = 1; - ropt->compression = 0; + ropt->compression.alg = COMPR_ALG_NONE; ropt->superuser = NULL; ropt->suppressDumpWarnings = true; @@ -952,16 +947,12 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) lclContext *ctx = (lclContext *) AH->formatData; lclTocEntry *tctx = (lclTocEntry *) te->formatData; char fname[255]; - char *sfx; + const char *sfx; if (oid == 0) fatal("invalid OID for large object (%u)", oid); - if (AH->compression != 0) - sfx = ".gz"; - else - sfx = ""; - + sfx = compress_suffix(&AH->compression); sprintf(fname, "blob_%u.dat%s", oid, sfx); tarPrintf(ctx->blobToc, "%u %s\n", oid, fname); diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c index 1ab98a2286..4cbc79aedc 100644 --- a/src/bin/pg_dump/pg_dump.c +++ b/src/bin/pg_dump/pg_dump.c @@ -59,6 +59,7 @@ #include "getopt_long.h" #include "libpq/libpq-fs.h" #include "parallel.h" +#include "compress_io.h" #include "pg_backup_db.h" #include "pg_backup_utils.h" #include "pg_dump.h" @@ -297,6 +298,82 @@ static void setupDumpWorker(Archive *AHX); static TableInfo *getRootTableInfo(TableInfo *tbinfo); +/* Parse the string into compression options */ +static void +parse_compression(const char *optarg, Compress *compress) +{ + if (optarg[0] == '0' && optarg[1] == '\0') + compress->alg = COMPR_ALG_NONE; + else if ((optarg[0] > '0' && optarg[0] <= '9') || + optarg[0] == '-') + { + compress->alg = COMPR_ALG_LIBZ; + compress->level_set = true; + compress->level = atoi(optarg); + if (optarg[1] != '\0') + { + pg_log_error("compression level must be in range 0..9"); + exit_nicely(1); + } + } + else + { + /* Parse a more flexible string like level=3 alg=zlib opts=long */ + for (;;) + { + char *eq = strchr(optarg, '='); + int len; + + if (eq == NULL) + { + pg_log_error("compression options must be key=value: %s", optarg); + exit_nicely(1); + } + + len = eq - optarg; + if (strncmp(optarg, "alg", len) == 0) + { + if (strchr(eq, ' ')) + len = strchr(eq, ' ') - eq - 1; + else + len = strlen(eq) - len; + if (strncmp(1+eq, "zlib", len) == 0 || + strncmp(1+eq, "libz", len) == 0) + compress->alg = COMPR_ALG_LIBZ; + else + { + pg_log_error("unknown compression algorithm: %s", 1+eq); + exit_nicely(1); + } + } + else if (strncmp(optarg, "level", len) == 0) + { + compress->level = atoi(1+eq); + compress->level_set = true; + } + else + { + pg_log_error("unknown compression setting: %s", optarg); + exit_nicely(1); + } + + optarg = strchr(eq, ' '); + if (!optarg++) + break; + } + + if (!compress->level_set) + { + const int default_compress_level[] = { + 0, /* COMPR_ALG_NONE */ + Z_DEFAULT_COMPRESSION, /* COMPR_ALG_ZLIB */ + }; + + compress->level = default_compress_level[compress->alg]; + } + } +} + int main(int argc, char **argv) { @@ -319,7 +396,7 @@ main(int argc, char **argv) char *use_role = NULL; long rowsPerInsert; int numWorkers = 1; - int compressLevel = -1; + Compress compress = { .alg = COMPR_ALG_DEFAULT }; int plainText = 0; ArchiveFormat archiveFormat = archUnknown; ArchiveMode archiveMode; @@ -532,12 +609,7 @@ main(int argc, char **argv) break; case 'Z': /* Compression Level */ - compressLevel = atoi(optarg); - if (compressLevel < 0 || compressLevel > 9) - { - pg_log_error("compression level must be in range 0..9"); - exit_nicely(1); - } + parse_compression(optarg, &compress); break; case 0: @@ -679,20 +751,28 @@ main(int argc, char **argv) plainText = 1; /* Custom and directory formats are compressed by default, others not */ - if (compressLevel == -1) + if (compress.alg == COMPR_ALG_DEFAULT) { -#ifdef HAVE_LIBZ if (archiveFormat == archCustom || archiveFormat == archDirectory) - compressLevel = Z_DEFAULT_COMPRESSION; - else + { +#ifdef HAVE_LIBZ + compress.alg = COMPR_ALG_LIBZ; + compress.level = Z_DEFAULT_COMPRESSION; #endif - compressLevel = 0; + } + else + { + compress.alg = COMPR_ALG_NONE; + compress.level = 0; + } } #ifndef HAVE_LIBZ - if (compressLevel != 0) + if (compress.alg == COMPR_ALG_LIBZ) + { pg_log_warning("requested compression not available in this installation -- archive will be uncompressed"); - compressLevel = 0; + compress.alg = 0; + } #endif /* @@ -723,7 +803,7 @@ main(int argc, char **argv) fatal("option --index-collation-versions-unknown only works in binary upgrade mode"); /* Open the output file */ - fout = CreateArchive(filename, archiveFormat, compressLevel, dosync, + fout = CreateArchive(filename, archiveFormat, &compress, dosync, archiveMode, setupDumpWorker); /* Make dump options accessible right away */ @@ -957,10 +1037,7 @@ main(int argc, char **argv) ropt->sequence_data = dopt.sequence_data; ropt->binary_upgrade = dopt.binary_upgrade; - if (compressLevel == -1) - ropt->compression = 0; - else - ropt->compression = compressLevel; + ropt->compression = compress; ropt->suppressDumpWarnings = true; /* We've already shown them */ -- 2.17.0 --GRPZ8SYKNexpdSJ7 Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="0004-struct-compressLibs.patch" ^ permalink raw reply [nested|flat] 23+ messages in thread
* [PATCH 03/20] Support multiple compression algs/levels/opts.. @ 2020-12-22 06:23 Justin Pryzby <[email protected]> 0 siblings, 0 replies; 23+ messages in thread From: Justin Pryzby @ 2020-12-22 06:23 UTC (permalink / raw) The existing implementation abtracts compressed and noncompressed I/O. This preliminary commit is intended to also allow for multiple compression algorithms. --- src/bin/pg_dump/compress_io.c | 220 +++++++++++--------------- src/bin/pg_dump/compress_io.h | 19 +-- src/bin/pg_dump/pg_backup.h | 23 ++- src/bin/pg_dump/pg_backup_archiver.c | 45 +++--- src/bin/pg_dump/pg_backup_archiver.h | 12 +- src/bin/pg_dump/pg_backup_custom.c | 6 +- src/bin/pg_dump/pg_backup_directory.c | 17 +- src/bin/pg_dump/pg_backup_tar.c | 33 ++-- src/bin/pg_dump/pg_dump.c | 115 +++++++++++--- 9 files changed, 272 insertions(+), 218 deletions(-) diff --git a/src/bin/pg_dump/compress_io.c b/src/bin/pg_dump/compress_io.c index 6a428978d4..db16fd33f2 100644 --- a/src/bin/pg_dump/compress_io.c +++ b/src/bin/pg_dump/compress_io.c @@ -74,12 +74,9 @@ struct CompressorState #endif }; -static void ParseCompressionOption(int compression, CompressionAlgorithm *alg, - int *level); - /* Routines that support zlib compressed data I/O */ #ifdef HAVE_LIBZ -static void InitCompressorZlib(CompressorState *cs, int level); +static void InitCompressorZlib(CompressorState *cs, Compress *compress); static void DeflateCompressorZlib(ArchiveHandle *AH, CompressorState *cs, bool flush); static void ReadDataFromArchiveZlib(ArchiveHandle *AH, ReadFunc readF); @@ -93,58 +90,36 @@ static void ReadDataFromArchiveNone(ArchiveHandle *AH, ReadFunc readF); static void WriteDataToArchiveNone(ArchiveHandle *AH, CompressorState *cs, const char *data, size_t dLen); -/* - * Interprets a numeric 'compression' value. The algorithm implied by the - * value (zlib or none at the moment), is returned in *alg, and the - * zlib compression level in *level. - */ -static void -ParseCompressionOption(int compression, CompressionAlgorithm *alg, int *level) -{ - if (compression == Z_DEFAULT_COMPRESSION || - (compression > 0 && compression <= 9)) - *alg = COMPR_ALG_LIBZ; - else if (compression == 0) - *alg = COMPR_ALG_NONE; - else - { - fatal("invalid compression code: %d", compression); - *alg = COMPR_ALG_NONE; /* keep compiler quiet */ - } - - /* The level is just the passed-in value. */ - if (level) - *level = compression; -} - /* Public interface routines */ /* Allocate a new compressor */ CompressorState * -AllocateCompressor(int compression, WriteFunc writeF) +AllocateCompressor(Compress *compression, WriteFunc writeF) { CompressorState *cs; - CompressionAlgorithm alg; - int level; - - ParseCompressionOption(compression, &alg, &level); - -#ifndef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - fatal("not built with zlib support"); -#endif cs = (CompressorState *) pg_malloc0(sizeof(CompressorState)); cs->writeF = writeF; - cs->comprAlg = alg; + cs->comprAlg = compression->alg; /* * Perform compression algorithm specific initialization. */ + Assert (compression->alg != COMPR_ALG_DEFAULT); + switch (compression->alg) + { #ifdef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - InitCompressorZlib(cs, level); + case COMPR_ALG_LIBZ: + InitCompressorZlib(cs, compression); + break; #endif + case COMPR_ALG_NONE: + /* Do nothing */ + break; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } return cs; } @@ -154,21 +129,21 @@ AllocateCompressor(int compression, WriteFunc writeF) * out with ahwrite(). */ void -ReadDataFromArchive(ArchiveHandle *AH, int compression, ReadFunc readF) +ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF) { - CompressionAlgorithm alg; - - ParseCompressionOption(compression, &alg, NULL); - - if (alg == COMPR_ALG_NONE) - ReadDataFromArchiveNone(AH, readF); - if (alg == COMPR_ALG_LIBZ) + switch (AH->compression.alg) { + case COMPR_ALG_NONE: + ReadDataFromArchiveNone(AH, readF); + break; #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: ReadDataFromArchiveZlib(AH, readF); -#else - fatal("not built with zlib support"); + break; #endif + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -181,16 +156,18 @@ WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, { switch (cs->comprAlg) { - case COMPR_ALG_LIBZ: #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: WriteDataToArchiveZlib(AH, cs, data, dLen); -#else - fatal("not built with zlib support"); -#endif break; +#endif case COMPR_ALG_NONE: WriteDataToArchiveNone(AH, cs, data, dLen); break; + + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -215,7 +192,7 @@ EndCompressor(ArchiveHandle *AH, CompressorState *cs) */ static void -InitCompressorZlib(CompressorState *cs, int level) +InitCompressorZlib(CompressorState *cs, Compress *compress) { z_streamp zp; @@ -232,7 +209,7 @@ InitCompressorZlib(CompressorState *cs, int level) cs->zlibOut = (char *) pg_malloc(ZLIB_OUT_SIZE + 1); cs->zlibOutSize = ZLIB_OUT_SIZE; - if (deflateInit(zp, level) != Z_OK) + if (deflateInit(zp, compress->level) != Z_OK) fatal("could not initialize compression library: %s", zp->msg); @@ -424,9 +401,7 @@ struct cfp #endif }; -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix); -#endif /* free() without changing errno; useful in several places below */ static void @@ -442,34 +417,31 @@ free_keep_errno(void *p) * Open a file for reading. 'path' is the file to open, and 'mode' should * be either "r" or "rb". * - * If the file at 'path' does not exist, we append the ".gz" suffix (if 'path' - * doesn't already have it) and try again. So if you pass "foo" as 'path', + * If the file at 'path' does not exist, we search with compressed suffix (if 'path' + * doesn't already have one) and try again. So if you pass "foo" as 'path', * this will open either "foo" or "foo.gz". * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_read(const char *path, const char *mode) +cfopen_read(const char *path, const char *mode, Compress *compression) { cfp *fp; -#ifdef HAVE_LIBZ if (hasSuffix(path, ".gz")) - fp = cfopen(path, mode, 1); + fp = cfopen(path, mode, compression); else -#endif { - fp = cfopen(path, mode, 0); -#ifdef HAVE_LIBZ + fp = cfopen(path, mode, compression); if (fp == NULL) { char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); - fp = cfopen(fname, mode, 1); + fname = psprintf("%s%s", path, suffix); + fp = cfopen(fname, mode, compression); free_keep_errno(fname); } -#endif } return fp; } @@ -479,31 +451,26 @@ cfopen_read(const char *path, const char *mode) * be a filemode as accepted by fopen() and gzopen() that indicates writing * ("w", "wb", "a", or "ab"). * - * If 'compression' is non-zero, a gzip compressed stream is opened, and - * 'compression' indicates the compression level used. The ".gz" suffix - * is automatically added to 'path' in that case. + * Use compression if specified. + * The appropriate suffix is automatically added to 'path' in that case. * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_write(const char *path, const char *mode, int compression) +cfopen_write(const char *path, const char *mode, Compress *compression) { cfp *fp; - if (compression == 0) - fp = cfopen(path, mode, 0); + if (compression->alg == COMPR_ALG_NONE) + fp = cfopen(path, mode, compression); else { -#ifdef HAVE_LIBZ char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); + fname = psprintf("%s%s", path, suffix); fp = cfopen(fname, mode, compression); free_keep_errno(fname); -#else - fatal("not built with zlib support"); - fp = NULL; /* keep compiler quiet */ -#endif } return fp; } @@ -515,20 +482,21 @@ cfopen_write(const char *path, const char *mode, int compression) * On failure, return NULL with an error code in errno. */ cfp * -cfopen(const char *path, const char *mode, int compression) +cfopen(const char *path, const char *mode, Compress *compression) { - cfp *fp = pg_malloc(sizeof(cfp)); + cfp *fp = pg_malloc0(sizeof(cfp)); - if (compression != 0) + switch (compression->alg) { #ifdef HAVE_LIBZ - if (compression != Z_DEFAULT_COMPRESSION) + case COMPR_ALG_LIBZ: + if (compression->level != Z_DEFAULT_COMPRESSION) { /* user has specified a compression level, so tell zlib to use it */ char mode_compression[32]; snprintf(mode_compression, sizeof(mode_compression), "%s%d", - mode, compression); + mode, compression->level); fp->compressedfp = gzopen(path, mode_compression); } else @@ -537,30 +505,27 @@ cfopen(const char *path, const char *mode, int compression) fp->compressedfp = gzopen(path, mode); } - fp->uncompressedfp = NULL; if (fp->compressedfp == NULL) { free_keep_errno(fp); fp = NULL; } -#else - fatal("not built with zlib support"); -#endif - } - else - { -#ifdef HAVE_LIBZ - fp->compressedfp = NULL; + return fp; #endif + + case COMPR_ALG_NONE: fp->uncompressedfp = fopen(path, mode); if (fp->uncompressedfp == NULL) { free_keep_errno(fp); fp = NULL; } - } + return fp; - return fp; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } } @@ -584,14 +549,13 @@ cfread(void *ptr, int size, cfp *fp) fatal("could not read from input file: %s", errnum == Z_ERRNO ? strerror(errno) : errmsg); } + return ret; } - else #endif - { - ret = fread(ptr, 1, size, fp->uncompressedfp); - if (ret != size && !feof(fp->uncompressedfp)) - READ_ERROR_EXIT(fp->uncompressedfp); - } + + ret = fread(ptr, 1, size, fp->uncompressedfp); + if (ret != size && !feof(fp->uncompressedfp)) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -601,9 +565,8 @@ cfwrite(const void *ptr, int size, cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzwrite(fp->compressedfp, ptr, size); - else #endif - return fwrite(ptr, 1, size, fp->uncompressedfp); + return fwrite(ptr, 1, size, fp->uncompressedfp); } int @@ -622,15 +585,12 @@ cfgetc(cfp *fp) else fatal("could not read from input file: end of file"); } + return ret; } - else #endif - { - ret = fgetc(fp->uncompressedfp); - if (ret == EOF) - READ_ERROR_EXIT(fp->uncompressedfp); - } - + ret = fgetc(fp->uncompressedfp); + if (ret == EOF) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -640,9 +600,8 @@ cfgets(cfp *fp, char *buf, int len) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzgets(fp->compressedfp, buf, len); - else #endif - return fgets(buf, len, fp->uncompressedfp); + return fgets(buf, len, fp->uncompressedfp); } int @@ -660,15 +619,13 @@ cfclose(cfp *fp) { result = gzclose(fp->compressedfp); fp->compressedfp = NULL; + return result; } - else #endif - { - result = fclose(fp->uncompressedfp); - fp->uncompressedfp = NULL; - } - free_keep_errno(fp); + result = fclose(fp->uncompressedfp); + fp->uncompressedfp = NULL; + free_keep_errno(fp); return result; } @@ -678,9 +635,9 @@ cfeof(cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzeof(fp->compressedfp); - else #endif - return feof(fp->uncompressedfp); + + return feof(fp->uncompressedfp); } const char * @@ -699,7 +656,6 @@ get_cfp_error(cfp *fp) return strerror(errno); } -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix) { @@ -714,4 +670,18 @@ hasSuffix(const char *filename, const char *suffix) suffixlen) == 0; } -#endif +/* + * Return a string for the given AH's compression. + * The string is statically allocated. + */ +const char * +compress_suffix(Compress *compression) +{ + switch (compression->alg) + { + case COMPR_ALG_LIBZ: + return ".gz"; + default: + return ""; + } +} diff --git a/src/bin/pg_dump/compress_io.h b/src/bin/pg_dump/compress_io.h index d2e6e1b854..2c073676eb 100644 --- a/src/bin/pg_dump/compress_io.h +++ b/src/bin/pg_dump/compress_io.h @@ -21,12 +21,6 @@ #define ZLIB_OUT_SIZE 4096 #define ZLIB_IN_SIZE 4096 -typedef enum -{ - COMPR_ALG_NONE, - COMPR_ALG_LIBZ -} CompressionAlgorithm; - /* Prototype for callback function to WriteDataToArchive() */ typedef void (*WriteFunc) (ArchiveHandle *AH, const char *buf, size_t len); @@ -46,8 +40,8 @@ typedef size_t (*ReadFunc) (ArchiveHandle *AH, char **buf, size_t *buflen); /* struct definition appears in compress_io.c */ typedef struct CompressorState CompressorState; -extern CompressorState *AllocateCompressor(int compression, WriteFunc writeF); -extern void ReadDataFromArchive(ArchiveHandle *AH, int compression, +extern CompressorState *AllocateCompressor(Compress *compression, WriteFunc writeF); +extern void ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF); extern void WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, const void *data, size_t dLen); @@ -56,9 +50,9 @@ extern void EndCompressor(ArchiveHandle *AH, CompressorState *cs); typedef struct cfp cfp; -extern cfp *cfopen(const char *path, const char *mode, int compression); -extern cfp *cfopen_read(const char *path, const char *mode); -extern cfp *cfopen_write(const char *path, const char *mode, int compression); +extern cfp *cfopen(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_read(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_write(const char *path, const char *mode, Compress *compression); extern int cfread(void *ptr, int size, cfp *fp); extern int cfwrite(const void *ptr, int size, cfp *fp); extern int cfgetc(cfp *fp); @@ -67,4 +61,7 @@ extern int cfclose(cfp *fp); extern int cfeof(cfp *fp); extern const char *get_cfp_error(cfp *fp); +/* also used by tar */ +extern const char * compress_suffix(Compress *compression); + #endif diff --git a/src/bin/pg_dump/pg_backup.h b/src/bin/pg_dump/pg_backup.h index 9d0056a569..f2390b7937 100644 --- a/src/bin/pg_dump/pg_backup.h +++ b/src/bin/pg_dump/pg_backup.h @@ -72,6 +72,25 @@ typedef struct _connParams char *override_dbname; } ConnParams; +typedef enum +{ + COMPR_ALG_DEFAULT = -1, + COMPR_ALG_NONE, + COMPR_ALG_LIBZ, +} CompressionAlgorithm; +/* Should be called "method" or "library" ? */ + +typedef struct Compress { + CompressionAlgorithm alg; + int level; + /* Is a nondefault level set ? This is useful since different compression + * methods have different "default" levels. For now we assume the levels + * are all integer, though. + */ + bool level_set; +} Compress; + + typedef struct _restoreOptions { int createDB; /* Issue commands to create the database */ @@ -125,7 +144,7 @@ typedef struct _restoreOptions int noDataForFailedTables; int exit_on_error; - int compression; + Compress compression; int suppressDumpWarnings; /* Suppress output of WARNING entries * to stderr */ bool single_txn; @@ -281,7 +300,7 @@ extern Archive *OpenArchive(const char *FileSpec, const ArchiveFormat fmt); /* Create a new archive */ extern Archive *CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker); /* The --list option */ diff --git a/src/bin/pg_dump/pg_backup_archiver.c b/src/bin/pg_dump/pg_backup_archiver.c index 1f82c6499b..3eb6c55600 100644 --- a/src/bin/pg_dump/pg_backup_archiver.c +++ b/src/bin/pg_dump/pg_backup_archiver.c @@ -70,7 +70,7 @@ typedef struct _parallelReadyList static ArchiveHandle *_allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr); static void _getObjectDescription(PQExpBuffer buf, TocEntry *te); static void _printTocEntry(ArchiveHandle *AH, TocEntry *te, bool isData); @@ -98,7 +98,7 @@ static int _discoverArchiveFormat(ArchiveHandle *AH); static int RestoringToDB(ArchiveHandle *AH); static void dump_lo_buf(ArchiveHandle *AH); static void dumpTimestamp(ArchiveHandle *AH, const char *msg, time_t tim); -static void SetOutput(ArchiveHandle *AH, const char *filename, int compression); +static void SetOutput(ArchiveHandle *AH, const char *filename, Compress *compress); static OutputContext SaveOutput(ArchiveHandle *AH); static void RestoreOutput(ArchiveHandle *AH, OutputContext savedContext); @@ -238,7 +238,7 @@ setupRestoreWorker(Archive *AHX) /* Public */ Archive * CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker) { @@ -253,7 +253,9 @@ CreateArchive(const char *FileSpec, const ArchiveFormat fmt, Archive * OpenArchive(const char *FileSpec, const ArchiveFormat fmt) { - ArchiveHandle *AH = _allocAH(FileSpec, fmt, 0, true, archModeRead, setupRestoreWorker); + Compress compress = {0}; + ArchiveHandle *AH = _allocAH(FileSpec, fmt, &compress, true, archModeRead, + setupRestoreWorker); return (Archive *) AH; } @@ -382,7 +384,7 @@ RestoreArchive(Archive *AHX) * Make sure we won't need (de)compression we haven't got */ #ifndef HAVE_LIBZ - if (AH->compression != 0 && AH->PrintTocDataPtr != NULL) + if (AH->compression.alg != COMPR_ALG_NONE && AH->PrintTocDataPtr != NULL) { for (te = AH->toc->next; te != AH->toc; te = te->next) { @@ -457,8 +459,8 @@ RestoreArchive(Archive *AHX) * Setup the output file if necessary. */ sav = SaveOutput(AH); - if (ropt->filename || ropt->compression) - SetOutput(AH, ropt->filename, ropt->compression); + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) + SetOutput(AH, ropt->filename, &ropt->compression); ahprintf(AH, "--\n-- PostgreSQL database dump\n--\n\n"); @@ -738,7 +740,7 @@ RestoreArchive(Archive *AHX) */ AH->stage = STAGE_FINALIZING; - if (ropt->filename || ropt->compression) + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) RestoreOutput(AH, sav); if (ropt->useDB) @@ -1123,8 +1125,9 @@ PrintTOCSummary(Archive *AHX) char stamp_str[64]; sav = SaveOutput(AH); + Assert(ropt->compression.alg == COMPR_ALG_NONE); if (ropt->filename) - SetOutput(AH, ropt->filename, 0 /* no compression */ ); + SetOutput(AH, ropt->filename, &ropt->compression); if (strftime(stamp_str, sizeof(stamp_str), PGDUMP_STRFTIME_FMT, localtime(&AH->createDate)) == 0) @@ -1133,7 +1136,7 @@ PrintTOCSummary(Archive *AHX) ahprintf(AH, ";\n; Archive created at %s\n", stamp_str); ahprintf(AH, "; dbname: %s\n; TOC Entries: %d\n; Compression: %d\n", sanitize_line(AH->archdbname, false), - AH->tocCount, AH->compression); + AH->tocCount, AH->compression.alg); switch (AH->format) { @@ -1487,7 +1490,7 @@ archprintf(Archive *AH, const char *fmt,...) *******************************/ static void -SetOutput(ArchiveHandle *AH, const char *filename, int compression) +SetOutput(ArchiveHandle *AH, const char *filename, Compress *compression) { int fn; @@ -1510,12 +1513,12 @@ SetOutput(ArchiveHandle *AH, const char *filename, int compression) /* If compression explicitly requested, use gzopen */ #ifdef HAVE_LIBZ - if (compression != 0) + if (compression->alg != COMPR_ALG_NONE) { char fmode[14]; /* Don't use PG_BINARY_x since this is zlib */ - sprintf(fmode, "wb%d", compression); + sprintf(fmode, "wb%d", compression->level); if (fn >= 0) AH->OF = gzdopen(dup(fn), fmode); else @@ -2259,7 +2262,7 @@ _discoverArchiveFormat(ArchiveHandle *AH) */ static ArchiveHandle * _allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr) { ArchiveHandle *AH; @@ -2310,7 +2313,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, AH->toc->prev = AH->toc; AH->mode = mode; - AH->compression = compression; + AH->compression = *compression; AH->dosync = dosync; memset(&(AH->sqlparse), 0, sizeof(AH->sqlparse)); @@ -2325,7 +2328,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, * Force stdin/stdout into binary mode if that is what we are using. */ #ifdef WIN32 - if ((fmt != archNull || compression != 0) && + if ((fmt != archNull || compression->alg != COMPR_ALG_NONE) && (AH->fSpec == NULL || strcmp(AH->fSpec, "") == 0)) { if (mode == archModeWrite) @@ -3741,7 +3744,7 @@ WriteHead(ArchiveHandle *AH) AH->WriteBytePtr(AH, AH->intSize); AH->WriteBytePtr(AH, AH->offSize); AH->WriteBytePtr(AH, AH->format); - WriteInt(AH, AH->compression); + WriteInt(AH, AH->compression.alg); crtm = *localtime(&AH->createDate); WriteInt(AH, crtm.tm_sec); WriteInt(AH, crtm.tm_min); @@ -3816,15 +3819,15 @@ ReadHead(ArchiveHandle *AH) if (AH->version >= K_VERS_1_2) { if (AH->version < K_VERS_1_4) - AH->compression = AH->ReadBytePtr(AH); + AH->compression.alg = AH->ReadBytePtr(AH); else - AH->compression = ReadInt(AH); + AH->compression.alg = ReadInt(AH); } else - AH->compression = Z_DEFAULT_COMPRESSION; + AH->compression.alg = Z_DEFAULT_COMPRESSION; #ifndef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) pg_log_warning("archive is compressed, but this installation does not support compression -- no data will be available"); #endif diff --git a/src/bin/pg_dump/pg_backup_archiver.h b/src/bin/pg_dump/pg_backup_archiver.h index a8ea5c7eae..6e033d040e 100644 --- a/src/bin/pg_dump/pg_backup_archiver.h +++ b/src/bin/pg_dump/pg_backup_archiver.h @@ -47,7 +47,8 @@ #define GZWRITE(p, s, n, fh) (fwrite(p, s, n, fh) * (s)) #define GZREAD(p, s, n, fh) fread(p, s, n, fh) #define GZEOF(fh) feof(fh) -/* this is just the redefinition of a libz constant */ +/* this is just the redefinition of a libz constant, in case zlib isn't + * available */ #define Z_DEFAULT_COMPRESSION (-1) typedef struct _z_stream @@ -329,14 +330,7 @@ struct _archiveHandle DumpId *tableDataId; /* TABLE DATA ids, indexed by table dumpId */ struct _tocEntry *currToc; /* Used when dumping data */ - int compression; /*--------- - * Compression requested on open(). - * Possible values for compression: - * -1 Z_DEFAULT_COMPRESSION - * 0 COMPRESSION_NONE - * 1-9 levels for gzip compression - *--------- - */ + Compress compression; /* Compression requested on open */ bool dosync; /* data requested to be synced on sight */ ArchiveMode mode; /* File mode - r or w */ void *formatData; /* Header data specific to file format */ diff --git a/src/bin/pg_dump/pg_backup_custom.c b/src/bin/pg_dump/pg_backup_custom.c index 77d402c323..55a887a236 100644 --- a/src/bin/pg_dump/pg_backup_custom.c +++ b/src/bin/pg_dump/pg_backup_custom.c @@ -298,7 +298,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) _WriteByte(AH, BLK_DATA); /* Block type */ WriteInt(AH, te->dumpId); /* For sanity check */ - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -377,7 +377,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) WriteInt(AH, oid); - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -566,7 +566,7 @@ _PrintTocData(ArchiveHandle *AH, TocEntry *te) static void _PrintData(ArchiveHandle *AH) { - ReadDataFromArchive(AH, AH->compression, _CustomReadFunc); + ReadDataFromArchive(AH, _CustomReadFunc); } static void diff --git a/src/bin/pg_dump/pg_backup_directory.c b/src/bin/pg_dump/pg_backup_directory.c index 650b542fce..8bf869c6ca 100644 --- a/src/bin/pg_dump/pg_backup_directory.c +++ b/src/bin/pg_dump/pg_backup_directory.c @@ -202,7 +202,7 @@ InitArchiveFmt_Directory(ArchiveHandle *AH) setFilePath(AH, fname, "toc.dat"); - tocFH = cfopen_read(fname, PG_BINARY_R); + tocFH = cfopen_read(fname, PG_BINARY_R, &AH->compression); if (tocFH == NULL) fatal("could not open input file \"%s\": %m", fname); @@ -327,7 +327,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) setFilePath(AH, fname, tctx->filename); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -388,7 +388,7 @@ _PrintFileData(ArchiveHandle *AH, char *filename) if (!filename) return; - cfp = cfopen_read(filename, PG_BINARY_R); + cfp = cfopen_read(filename, PG_BINARY_R, &AH->compression); if (!cfp) fatal("could not open input file \"%s\": %m", filename); @@ -435,12 +435,13 @@ _LoadBlobs(ArchiveHandle *AH) lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; char line[MAXPGPATH]; + Compress nocompression = {0}; StartRestoreBlobs(AH); setFilePath(AH, fname, "blobs.toc"); - ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R); + ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R, &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open large object TOC file \"%s\" for input: %m", @@ -573,6 +574,7 @@ _CloseArchive(ArchiveHandle *AH) { cfp *tocFH; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "toc.dat"); @@ -580,7 +582,7 @@ _CloseArchive(ArchiveHandle *AH) ctx->pstate = ParallelBackupStart(AH); /* The TOC is always created uncompressed */ - tocFH = cfopen_write(fname, PG_BINARY_W, 0); + tocFH = cfopen_write(fname, PG_BINARY_W, &nocompression); if (tocFH == NULL) fatal("could not open output file \"%s\": %m", fname); ctx->dataFH = tocFH; @@ -639,11 +641,12 @@ _StartBlobs(ArchiveHandle *AH, TocEntry *te) { lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "blobs.toc"); /* The blob TOC file is never compressed */ - ctx->blobsTocFH = cfopen_write(fname, "ab", 0); + ctx->blobsTocFH = cfopen_write(fname, "ab", &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -661,7 +664,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) snprintf(fname, MAXPGPATH, "%s/blob_%u.dat", ctx->directory, oid); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); diff --git a/src/bin/pg_dump/pg_backup_tar.c b/src/bin/pg_dump/pg_backup_tar.c index 61c9c87a9f..4ba79ab924 100644 --- a/src/bin/pg_dump/pg_backup_tar.c +++ b/src/bin/pg_dump/pg_backup_tar.c @@ -39,6 +39,7 @@ #include "pg_backup_archiver.h" #include "pg_backup_tar.h" #include "pg_backup_utils.h" +#include "compress_io.h" #include "pgtar.h" static void _ArchiveEntry(ArchiveHandle *AH, TocEntry *te); @@ -196,10 +197,10 @@ InitArchiveFmt_Tar(ArchiveHandle *AH) /* * We don't support compression because reading the files back is not - * possible since gzdopen uses buffered IO which totally screws file + * possible since gzdopen uses buffered IO which totally screws file XXX * positioning. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) fatal("compression is not supported by tar archive format"); } else @@ -254,14 +255,8 @@ _ArchiveEntry(ArchiveHandle *AH, TocEntry *te) ctx = (lclTocEntry *) pg_malloc0(sizeof(lclTocEntry)); if (te->dataDumper != NULL) { -#ifdef HAVE_LIBZ - if (AH->compression == 0) - sprintf(fn, "%d.dat", te->dumpId); - else - sprintf(fn, "%d.dat.gz", te->dumpId); -#else - sprintf(fn, "%d.dat", te->dumpId); -#endif + const char *suffix = compress_suffix(&AH->compression); + sprintf(fn, "%d.dat%s", te->dumpId, suffix); ctx->filename = pg_strdup(fn); } else @@ -352,7 +347,7 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression == 0) + if (AH->compression.alg == COMPR_ALG_NONE) tm->nFH = ctx->tarFH; else fatal("compression is not supported by tar archive format"); @@ -413,9 +408,9 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) { - sprintf(fmode, "wb%d", AH->compression); + sprintf(fmode, "wb%d", AH->compression.level); tm->zFH = gzdopen(dup(fileno(tm->tmpFH)), fmode); if (tm->zFH == NULL) fatal("could not open temporary file"); @@ -443,7 +438,7 @@ tarClose(ArchiveHandle *AH, TAR_MEMBER *th) /* * Close the GZ file since we dup'd. This will flush the buffers. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) if (GZCLOSE(th->zFH) != 0) fatal("could not close tar member"); @@ -868,7 +863,7 @@ _CloseArchive(ArchiveHandle *AH) memcpy(ropt, AH->public.ropt, sizeof(RestoreOptions)); ropt->filename = NULL; ropt->dropSchema = 1; - ropt->compression = 0; + ropt->compression.alg = COMPR_ALG_NONE; ropt->superuser = NULL; ropt->suppressDumpWarnings = true; @@ -952,16 +947,12 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) lclContext *ctx = (lclContext *) AH->formatData; lclTocEntry *tctx = (lclTocEntry *) te->formatData; char fname[255]; - char *sfx; + const char *sfx; if (oid == 0) fatal("invalid OID for large object (%u)", oid); - if (AH->compression != 0) - sfx = ".gz"; - else - sfx = ""; - + sfx = compress_suffix(&AH->compression); sprintf(fname, "blob_%u.dat%s", oid, sfx); tarPrintf(ctx->blobToc, "%u %s\n", oid, fname); diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c index 1ab98a2286..4cbc79aedc 100644 --- a/src/bin/pg_dump/pg_dump.c +++ b/src/bin/pg_dump/pg_dump.c @@ -59,6 +59,7 @@ #include "getopt_long.h" #include "libpq/libpq-fs.h" #include "parallel.h" +#include "compress_io.h" #include "pg_backup_db.h" #include "pg_backup_utils.h" #include "pg_dump.h" @@ -297,6 +298,82 @@ static void setupDumpWorker(Archive *AHX); static TableInfo *getRootTableInfo(TableInfo *tbinfo); +/* Parse the string into compression options */ +static void +parse_compression(const char *optarg, Compress *compress) +{ + if (optarg[0] == '0' && optarg[1] == '\0') + compress->alg = COMPR_ALG_NONE; + else if ((optarg[0] > '0' && optarg[0] <= '9') || + optarg[0] == '-') + { + compress->alg = COMPR_ALG_LIBZ; + compress->level_set = true; + compress->level = atoi(optarg); + if (optarg[1] != '\0') + { + pg_log_error("compression level must be in range 0..9"); + exit_nicely(1); + } + } + else + { + /* Parse a more flexible string like level=3 alg=zlib opts=long */ + for (;;) + { + char *eq = strchr(optarg, '='); + int len; + + if (eq == NULL) + { + pg_log_error("compression options must be key=value: %s", optarg); + exit_nicely(1); + } + + len = eq - optarg; + if (strncmp(optarg, "alg", len) == 0) + { + if (strchr(eq, ' ')) + len = strchr(eq, ' ') - eq - 1; + else + len = strlen(eq) - len; + if (strncmp(1+eq, "zlib", len) == 0 || + strncmp(1+eq, "libz", len) == 0) + compress->alg = COMPR_ALG_LIBZ; + else + { + pg_log_error("unknown compression algorithm: %s", 1+eq); + exit_nicely(1); + } + } + else if (strncmp(optarg, "level", len) == 0) + { + compress->level = atoi(1+eq); + compress->level_set = true; + } + else + { + pg_log_error("unknown compression setting: %s", optarg); + exit_nicely(1); + } + + optarg = strchr(eq, ' '); + if (!optarg++) + break; + } + + if (!compress->level_set) + { + const int default_compress_level[] = { + 0, /* COMPR_ALG_NONE */ + Z_DEFAULT_COMPRESSION, /* COMPR_ALG_ZLIB */ + }; + + compress->level = default_compress_level[compress->alg]; + } + } +} + int main(int argc, char **argv) { @@ -319,7 +396,7 @@ main(int argc, char **argv) char *use_role = NULL; long rowsPerInsert; int numWorkers = 1; - int compressLevel = -1; + Compress compress = { .alg = COMPR_ALG_DEFAULT }; int plainText = 0; ArchiveFormat archiveFormat = archUnknown; ArchiveMode archiveMode; @@ -532,12 +609,7 @@ main(int argc, char **argv) break; case 'Z': /* Compression Level */ - compressLevel = atoi(optarg); - if (compressLevel < 0 || compressLevel > 9) - { - pg_log_error("compression level must be in range 0..9"); - exit_nicely(1); - } + parse_compression(optarg, &compress); break; case 0: @@ -679,20 +751,28 @@ main(int argc, char **argv) plainText = 1; /* Custom and directory formats are compressed by default, others not */ - if (compressLevel == -1) + if (compress.alg == COMPR_ALG_DEFAULT) { -#ifdef HAVE_LIBZ if (archiveFormat == archCustom || archiveFormat == archDirectory) - compressLevel = Z_DEFAULT_COMPRESSION; - else + { +#ifdef HAVE_LIBZ + compress.alg = COMPR_ALG_LIBZ; + compress.level = Z_DEFAULT_COMPRESSION; #endif - compressLevel = 0; + } + else + { + compress.alg = COMPR_ALG_NONE; + compress.level = 0; + } } #ifndef HAVE_LIBZ - if (compressLevel != 0) + if (compress.alg == COMPR_ALG_LIBZ) + { pg_log_warning("requested compression not available in this installation -- archive will be uncompressed"); - compressLevel = 0; + compress.alg = 0; + } #endif /* @@ -723,7 +803,7 @@ main(int argc, char **argv) fatal("option --index-collation-versions-unknown only works in binary upgrade mode"); /* Open the output file */ - fout = CreateArchive(filename, archiveFormat, compressLevel, dosync, + fout = CreateArchive(filename, archiveFormat, &compress, dosync, archiveMode, setupDumpWorker); /* Make dump options accessible right away */ @@ -957,10 +1037,7 @@ main(int argc, char **argv) ropt->sequence_data = dopt.sequence_data; ropt->binary_upgrade = dopt.binary_upgrade; - if (compressLevel == -1) - ropt->compression = 0; - else - ropt->compression = compressLevel; + ropt->compression = compress; ropt->suppressDumpWarnings = true; /* We've already shown them */ -- 2.17.0 --GRPZ8SYKNexpdSJ7 Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="0004-struct-compressLibs.patch" ^ permalink raw reply [nested|flat] 23+ messages in thread
* [PATCH 03/20] Support multiple compression algs/levels/opts.. @ 2020-12-22 06:23 Justin Pryzby <[email protected]> 0 siblings, 0 replies; 23+ messages in thread From: Justin Pryzby @ 2020-12-22 06:23 UTC (permalink / raw) The existing implementation abtracts compressed and noncompressed I/O. This preliminary commit is intended to also allow for multiple compression algorithms. --- src/bin/pg_dump/compress_io.c | 220 +++++++++++--------------- src/bin/pg_dump/compress_io.h | 19 +-- src/bin/pg_dump/pg_backup.h | 23 ++- src/bin/pg_dump/pg_backup_archiver.c | 45 +++--- src/bin/pg_dump/pg_backup_archiver.h | 12 +- src/bin/pg_dump/pg_backup_custom.c | 6 +- src/bin/pg_dump/pg_backup_directory.c | 17 +- src/bin/pg_dump/pg_backup_tar.c | 33 ++-- src/bin/pg_dump/pg_dump.c | 115 +++++++++++--- 9 files changed, 272 insertions(+), 218 deletions(-) diff --git a/src/bin/pg_dump/compress_io.c b/src/bin/pg_dump/compress_io.c index 6a428978d4..db16fd33f2 100644 --- a/src/bin/pg_dump/compress_io.c +++ b/src/bin/pg_dump/compress_io.c @@ -74,12 +74,9 @@ struct CompressorState #endif }; -static void ParseCompressionOption(int compression, CompressionAlgorithm *alg, - int *level); - /* Routines that support zlib compressed data I/O */ #ifdef HAVE_LIBZ -static void InitCompressorZlib(CompressorState *cs, int level); +static void InitCompressorZlib(CompressorState *cs, Compress *compress); static void DeflateCompressorZlib(ArchiveHandle *AH, CompressorState *cs, bool flush); static void ReadDataFromArchiveZlib(ArchiveHandle *AH, ReadFunc readF); @@ -93,58 +90,36 @@ static void ReadDataFromArchiveNone(ArchiveHandle *AH, ReadFunc readF); static void WriteDataToArchiveNone(ArchiveHandle *AH, CompressorState *cs, const char *data, size_t dLen); -/* - * Interprets a numeric 'compression' value. The algorithm implied by the - * value (zlib or none at the moment), is returned in *alg, and the - * zlib compression level in *level. - */ -static void -ParseCompressionOption(int compression, CompressionAlgorithm *alg, int *level) -{ - if (compression == Z_DEFAULT_COMPRESSION || - (compression > 0 && compression <= 9)) - *alg = COMPR_ALG_LIBZ; - else if (compression == 0) - *alg = COMPR_ALG_NONE; - else - { - fatal("invalid compression code: %d", compression); - *alg = COMPR_ALG_NONE; /* keep compiler quiet */ - } - - /* The level is just the passed-in value. */ - if (level) - *level = compression; -} - /* Public interface routines */ /* Allocate a new compressor */ CompressorState * -AllocateCompressor(int compression, WriteFunc writeF) +AllocateCompressor(Compress *compression, WriteFunc writeF) { CompressorState *cs; - CompressionAlgorithm alg; - int level; - - ParseCompressionOption(compression, &alg, &level); - -#ifndef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - fatal("not built with zlib support"); -#endif cs = (CompressorState *) pg_malloc0(sizeof(CompressorState)); cs->writeF = writeF; - cs->comprAlg = alg; + cs->comprAlg = compression->alg; /* * Perform compression algorithm specific initialization. */ + Assert (compression->alg != COMPR_ALG_DEFAULT); + switch (compression->alg) + { #ifdef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - InitCompressorZlib(cs, level); + case COMPR_ALG_LIBZ: + InitCompressorZlib(cs, compression); + break; #endif + case COMPR_ALG_NONE: + /* Do nothing */ + break; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } return cs; } @@ -154,21 +129,21 @@ AllocateCompressor(int compression, WriteFunc writeF) * out with ahwrite(). */ void -ReadDataFromArchive(ArchiveHandle *AH, int compression, ReadFunc readF) +ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF) { - CompressionAlgorithm alg; - - ParseCompressionOption(compression, &alg, NULL); - - if (alg == COMPR_ALG_NONE) - ReadDataFromArchiveNone(AH, readF); - if (alg == COMPR_ALG_LIBZ) + switch (AH->compression.alg) { + case COMPR_ALG_NONE: + ReadDataFromArchiveNone(AH, readF); + break; #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: ReadDataFromArchiveZlib(AH, readF); -#else - fatal("not built with zlib support"); + break; #endif + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -181,16 +156,18 @@ WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, { switch (cs->comprAlg) { - case COMPR_ALG_LIBZ: #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: WriteDataToArchiveZlib(AH, cs, data, dLen); -#else - fatal("not built with zlib support"); -#endif break; +#endif case COMPR_ALG_NONE: WriteDataToArchiveNone(AH, cs, data, dLen); break; + + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -215,7 +192,7 @@ EndCompressor(ArchiveHandle *AH, CompressorState *cs) */ static void -InitCompressorZlib(CompressorState *cs, int level) +InitCompressorZlib(CompressorState *cs, Compress *compress) { z_streamp zp; @@ -232,7 +209,7 @@ InitCompressorZlib(CompressorState *cs, int level) cs->zlibOut = (char *) pg_malloc(ZLIB_OUT_SIZE + 1); cs->zlibOutSize = ZLIB_OUT_SIZE; - if (deflateInit(zp, level) != Z_OK) + if (deflateInit(zp, compress->level) != Z_OK) fatal("could not initialize compression library: %s", zp->msg); @@ -424,9 +401,7 @@ struct cfp #endif }; -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix); -#endif /* free() without changing errno; useful in several places below */ static void @@ -442,34 +417,31 @@ free_keep_errno(void *p) * Open a file for reading. 'path' is the file to open, and 'mode' should * be either "r" or "rb". * - * If the file at 'path' does not exist, we append the ".gz" suffix (if 'path' - * doesn't already have it) and try again. So if you pass "foo" as 'path', + * If the file at 'path' does not exist, we search with compressed suffix (if 'path' + * doesn't already have one) and try again. So if you pass "foo" as 'path', * this will open either "foo" or "foo.gz". * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_read(const char *path, const char *mode) +cfopen_read(const char *path, const char *mode, Compress *compression) { cfp *fp; -#ifdef HAVE_LIBZ if (hasSuffix(path, ".gz")) - fp = cfopen(path, mode, 1); + fp = cfopen(path, mode, compression); else -#endif { - fp = cfopen(path, mode, 0); -#ifdef HAVE_LIBZ + fp = cfopen(path, mode, compression); if (fp == NULL) { char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); - fp = cfopen(fname, mode, 1); + fname = psprintf("%s%s", path, suffix); + fp = cfopen(fname, mode, compression); free_keep_errno(fname); } -#endif } return fp; } @@ -479,31 +451,26 @@ cfopen_read(const char *path, const char *mode) * be a filemode as accepted by fopen() and gzopen() that indicates writing * ("w", "wb", "a", or "ab"). * - * If 'compression' is non-zero, a gzip compressed stream is opened, and - * 'compression' indicates the compression level used. The ".gz" suffix - * is automatically added to 'path' in that case. + * Use compression if specified. + * The appropriate suffix is automatically added to 'path' in that case. * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_write(const char *path, const char *mode, int compression) +cfopen_write(const char *path, const char *mode, Compress *compression) { cfp *fp; - if (compression == 0) - fp = cfopen(path, mode, 0); + if (compression->alg == COMPR_ALG_NONE) + fp = cfopen(path, mode, compression); else { -#ifdef HAVE_LIBZ char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); + fname = psprintf("%s%s", path, suffix); fp = cfopen(fname, mode, compression); free_keep_errno(fname); -#else - fatal("not built with zlib support"); - fp = NULL; /* keep compiler quiet */ -#endif } return fp; } @@ -515,20 +482,21 @@ cfopen_write(const char *path, const char *mode, int compression) * On failure, return NULL with an error code in errno. */ cfp * -cfopen(const char *path, const char *mode, int compression) +cfopen(const char *path, const char *mode, Compress *compression) { - cfp *fp = pg_malloc(sizeof(cfp)); + cfp *fp = pg_malloc0(sizeof(cfp)); - if (compression != 0) + switch (compression->alg) { #ifdef HAVE_LIBZ - if (compression != Z_DEFAULT_COMPRESSION) + case COMPR_ALG_LIBZ: + if (compression->level != Z_DEFAULT_COMPRESSION) { /* user has specified a compression level, so tell zlib to use it */ char mode_compression[32]; snprintf(mode_compression, sizeof(mode_compression), "%s%d", - mode, compression); + mode, compression->level); fp->compressedfp = gzopen(path, mode_compression); } else @@ -537,30 +505,27 @@ cfopen(const char *path, const char *mode, int compression) fp->compressedfp = gzopen(path, mode); } - fp->uncompressedfp = NULL; if (fp->compressedfp == NULL) { free_keep_errno(fp); fp = NULL; } -#else - fatal("not built with zlib support"); -#endif - } - else - { -#ifdef HAVE_LIBZ - fp->compressedfp = NULL; + return fp; #endif + + case COMPR_ALG_NONE: fp->uncompressedfp = fopen(path, mode); if (fp->uncompressedfp == NULL) { free_keep_errno(fp); fp = NULL; } - } + return fp; - return fp; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } } @@ -584,14 +549,13 @@ cfread(void *ptr, int size, cfp *fp) fatal("could not read from input file: %s", errnum == Z_ERRNO ? strerror(errno) : errmsg); } + return ret; } - else #endif - { - ret = fread(ptr, 1, size, fp->uncompressedfp); - if (ret != size && !feof(fp->uncompressedfp)) - READ_ERROR_EXIT(fp->uncompressedfp); - } + + ret = fread(ptr, 1, size, fp->uncompressedfp); + if (ret != size && !feof(fp->uncompressedfp)) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -601,9 +565,8 @@ cfwrite(const void *ptr, int size, cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzwrite(fp->compressedfp, ptr, size); - else #endif - return fwrite(ptr, 1, size, fp->uncompressedfp); + return fwrite(ptr, 1, size, fp->uncompressedfp); } int @@ -622,15 +585,12 @@ cfgetc(cfp *fp) else fatal("could not read from input file: end of file"); } + return ret; } - else #endif - { - ret = fgetc(fp->uncompressedfp); - if (ret == EOF) - READ_ERROR_EXIT(fp->uncompressedfp); - } - + ret = fgetc(fp->uncompressedfp); + if (ret == EOF) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -640,9 +600,8 @@ cfgets(cfp *fp, char *buf, int len) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzgets(fp->compressedfp, buf, len); - else #endif - return fgets(buf, len, fp->uncompressedfp); + return fgets(buf, len, fp->uncompressedfp); } int @@ -660,15 +619,13 @@ cfclose(cfp *fp) { result = gzclose(fp->compressedfp); fp->compressedfp = NULL; + return result; } - else #endif - { - result = fclose(fp->uncompressedfp); - fp->uncompressedfp = NULL; - } - free_keep_errno(fp); + result = fclose(fp->uncompressedfp); + fp->uncompressedfp = NULL; + free_keep_errno(fp); return result; } @@ -678,9 +635,9 @@ cfeof(cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzeof(fp->compressedfp); - else #endif - return feof(fp->uncompressedfp); + + return feof(fp->uncompressedfp); } const char * @@ -699,7 +656,6 @@ get_cfp_error(cfp *fp) return strerror(errno); } -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix) { @@ -714,4 +670,18 @@ hasSuffix(const char *filename, const char *suffix) suffixlen) == 0; } -#endif +/* + * Return a string for the given AH's compression. + * The string is statically allocated. + */ +const char * +compress_suffix(Compress *compression) +{ + switch (compression->alg) + { + case COMPR_ALG_LIBZ: + return ".gz"; + default: + return ""; + } +} diff --git a/src/bin/pg_dump/compress_io.h b/src/bin/pg_dump/compress_io.h index d2e6e1b854..2c073676eb 100644 --- a/src/bin/pg_dump/compress_io.h +++ b/src/bin/pg_dump/compress_io.h @@ -21,12 +21,6 @@ #define ZLIB_OUT_SIZE 4096 #define ZLIB_IN_SIZE 4096 -typedef enum -{ - COMPR_ALG_NONE, - COMPR_ALG_LIBZ -} CompressionAlgorithm; - /* Prototype for callback function to WriteDataToArchive() */ typedef void (*WriteFunc) (ArchiveHandle *AH, const char *buf, size_t len); @@ -46,8 +40,8 @@ typedef size_t (*ReadFunc) (ArchiveHandle *AH, char **buf, size_t *buflen); /* struct definition appears in compress_io.c */ typedef struct CompressorState CompressorState; -extern CompressorState *AllocateCompressor(int compression, WriteFunc writeF); -extern void ReadDataFromArchive(ArchiveHandle *AH, int compression, +extern CompressorState *AllocateCompressor(Compress *compression, WriteFunc writeF); +extern void ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF); extern void WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, const void *data, size_t dLen); @@ -56,9 +50,9 @@ extern void EndCompressor(ArchiveHandle *AH, CompressorState *cs); typedef struct cfp cfp; -extern cfp *cfopen(const char *path, const char *mode, int compression); -extern cfp *cfopen_read(const char *path, const char *mode); -extern cfp *cfopen_write(const char *path, const char *mode, int compression); +extern cfp *cfopen(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_read(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_write(const char *path, const char *mode, Compress *compression); extern int cfread(void *ptr, int size, cfp *fp); extern int cfwrite(const void *ptr, int size, cfp *fp); extern int cfgetc(cfp *fp); @@ -67,4 +61,7 @@ extern int cfclose(cfp *fp); extern int cfeof(cfp *fp); extern const char *get_cfp_error(cfp *fp); +/* also used by tar */ +extern const char * compress_suffix(Compress *compression); + #endif diff --git a/src/bin/pg_dump/pg_backup.h b/src/bin/pg_dump/pg_backup.h index 9d0056a569..f2390b7937 100644 --- a/src/bin/pg_dump/pg_backup.h +++ b/src/bin/pg_dump/pg_backup.h @@ -72,6 +72,25 @@ typedef struct _connParams char *override_dbname; } ConnParams; +typedef enum +{ + COMPR_ALG_DEFAULT = -1, + COMPR_ALG_NONE, + COMPR_ALG_LIBZ, +} CompressionAlgorithm; +/* Should be called "method" or "library" ? */ + +typedef struct Compress { + CompressionAlgorithm alg; + int level; + /* Is a nondefault level set ? This is useful since different compression + * methods have different "default" levels. For now we assume the levels + * are all integer, though. + */ + bool level_set; +} Compress; + + typedef struct _restoreOptions { int createDB; /* Issue commands to create the database */ @@ -125,7 +144,7 @@ typedef struct _restoreOptions int noDataForFailedTables; int exit_on_error; - int compression; + Compress compression; int suppressDumpWarnings; /* Suppress output of WARNING entries * to stderr */ bool single_txn; @@ -281,7 +300,7 @@ extern Archive *OpenArchive(const char *FileSpec, const ArchiveFormat fmt); /* Create a new archive */ extern Archive *CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker); /* The --list option */ diff --git a/src/bin/pg_dump/pg_backup_archiver.c b/src/bin/pg_dump/pg_backup_archiver.c index 1f82c6499b..3eb6c55600 100644 --- a/src/bin/pg_dump/pg_backup_archiver.c +++ b/src/bin/pg_dump/pg_backup_archiver.c @@ -70,7 +70,7 @@ typedef struct _parallelReadyList static ArchiveHandle *_allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr); static void _getObjectDescription(PQExpBuffer buf, TocEntry *te); static void _printTocEntry(ArchiveHandle *AH, TocEntry *te, bool isData); @@ -98,7 +98,7 @@ static int _discoverArchiveFormat(ArchiveHandle *AH); static int RestoringToDB(ArchiveHandle *AH); static void dump_lo_buf(ArchiveHandle *AH); static void dumpTimestamp(ArchiveHandle *AH, const char *msg, time_t tim); -static void SetOutput(ArchiveHandle *AH, const char *filename, int compression); +static void SetOutput(ArchiveHandle *AH, const char *filename, Compress *compress); static OutputContext SaveOutput(ArchiveHandle *AH); static void RestoreOutput(ArchiveHandle *AH, OutputContext savedContext); @@ -238,7 +238,7 @@ setupRestoreWorker(Archive *AHX) /* Public */ Archive * CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker) { @@ -253,7 +253,9 @@ CreateArchive(const char *FileSpec, const ArchiveFormat fmt, Archive * OpenArchive(const char *FileSpec, const ArchiveFormat fmt) { - ArchiveHandle *AH = _allocAH(FileSpec, fmt, 0, true, archModeRead, setupRestoreWorker); + Compress compress = {0}; + ArchiveHandle *AH = _allocAH(FileSpec, fmt, &compress, true, archModeRead, + setupRestoreWorker); return (Archive *) AH; } @@ -382,7 +384,7 @@ RestoreArchive(Archive *AHX) * Make sure we won't need (de)compression we haven't got */ #ifndef HAVE_LIBZ - if (AH->compression != 0 && AH->PrintTocDataPtr != NULL) + if (AH->compression.alg != COMPR_ALG_NONE && AH->PrintTocDataPtr != NULL) { for (te = AH->toc->next; te != AH->toc; te = te->next) { @@ -457,8 +459,8 @@ RestoreArchive(Archive *AHX) * Setup the output file if necessary. */ sav = SaveOutput(AH); - if (ropt->filename || ropt->compression) - SetOutput(AH, ropt->filename, ropt->compression); + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) + SetOutput(AH, ropt->filename, &ropt->compression); ahprintf(AH, "--\n-- PostgreSQL database dump\n--\n\n"); @@ -738,7 +740,7 @@ RestoreArchive(Archive *AHX) */ AH->stage = STAGE_FINALIZING; - if (ropt->filename || ropt->compression) + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) RestoreOutput(AH, sav); if (ropt->useDB) @@ -1123,8 +1125,9 @@ PrintTOCSummary(Archive *AHX) char stamp_str[64]; sav = SaveOutput(AH); + Assert(ropt->compression.alg == COMPR_ALG_NONE); if (ropt->filename) - SetOutput(AH, ropt->filename, 0 /* no compression */ ); + SetOutput(AH, ropt->filename, &ropt->compression); if (strftime(stamp_str, sizeof(stamp_str), PGDUMP_STRFTIME_FMT, localtime(&AH->createDate)) == 0) @@ -1133,7 +1136,7 @@ PrintTOCSummary(Archive *AHX) ahprintf(AH, ";\n; Archive created at %s\n", stamp_str); ahprintf(AH, "; dbname: %s\n; TOC Entries: %d\n; Compression: %d\n", sanitize_line(AH->archdbname, false), - AH->tocCount, AH->compression); + AH->tocCount, AH->compression.alg); switch (AH->format) { @@ -1487,7 +1490,7 @@ archprintf(Archive *AH, const char *fmt,...) *******************************/ static void -SetOutput(ArchiveHandle *AH, const char *filename, int compression) +SetOutput(ArchiveHandle *AH, const char *filename, Compress *compression) { int fn; @@ -1510,12 +1513,12 @@ SetOutput(ArchiveHandle *AH, const char *filename, int compression) /* If compression explicitly requested, use gzopen */ #ifdef HAVE_LIBZ - if (compression != 0) + if (compression->alg != COMPR_ALG_NONE) { char fmode[14]; /* Don't use PG_BINARY_x since this is zlib */ - sprintf(fmode, "wb%d", compression); + sprintf(fmode, "wb%d", compression->level); if (fn >= 0) AH->OF = gzdopen(dup(fn), fmode); else @@ -2259,7 +2262,7 @@ _discoverArchiveFormat(ArchiveHandle *AH) */ static ArchiveHandle * _allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr) { ArchiveHandle *AH; @@ -2310,7 +2313,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, AH->toc->prev = AH->toc; AH->mode = mode; - AH->compression = compression; + AH->compression = *compression; AH->dosync = dosync; memset(&(AH->sqlparse), 0, sizeof(AH->sqlparse)); @@ -2325,7 +2328,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, * Force stdin/stdout into binary mode if that is what we are using. */ #ifdef WIN32 - if ((fmt != archNull || compression != 0) && + if ((fmt != archNull || compression->alg != COMPR_ALG_NONE) && (AH->fSpec == NULL || strcmp(AH->fSpec, "") == 0)) { if (mode == archModeWrite) @@ -3741,7 +3744,7 @@ WriteHead(ArchiveHandle *AH) AH->WriteBytePtr(AH, AH->intSize); AH->WriteBytePtr(AH, AH->offSize); AH->WriteBytePtr(AH, AH->format); - WriteInt(AH, AH->compression); + WriteInt(AH, AH->compression.alg); crtm = *localtime(&AH->createDate); WriteInt(AH, crtm.tm_sec); WriteInt(AH, crtm.tm_min); @@ -3816,15 +3819,15 @@ ReadHead(ArchiveHandle *AH) if (AH->version >= K_VERS_1_2) { if (AH->version < K_VERS_1_4) - AH->compression = AH->ReadBytePtr(AH); + AH->compression.alg = AH->ReadBytePtr(AH); else - AH->compression = ReadInt(AH); + AH->compression.alg = ReadInt(AH); } else - AH->compression = Z_DEFAULT_COMPRESSION; + AH->compression.alg = Z_DEFAULT_COMPRESSION; #ifndef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) pg_log_warning("archive is compressed, but this installation does not support compression -- no data will be available"); #endif diff --git a/src/bin/pg_dump/pg_backup_archiver.h b/src/bin/pg_dump/pg_backup_archiver.h index a8ea5c7eae..6e033d040e 100644 --- a/src/bin/pg_dump/pg_backup_archiver.h +++ b/src/bin/pg_dump/pg_backup_archiver.h @@ -47,7 +47,8 @@ #define GZWRITE(p, s, n, fh) (fwrite(p, s, n, fh) * (s)) #define GZREAD(p, s, n, fh) fread(p, s, n, fh) #define GZEOF(fh) feof(fh) -/* this is just the redefinition of a libz constant */ +/* this is just the redefinition of a libz constant, in case zlib isn't + * available */ #define Z_DEFAULT_COMPRESSION (-1) typedef struct _z_stream @@ -329,14 +330,7 @@ struct _archiveHandle DumpId *tableDataId; /* TABLE DATA ids, indexed by table dumpId */ struct _tocEntry *currToc; /* Used when dumping data */ - int compression; /*--------- - * Compression requested on open(). - * Possible values for compression: - * -1 Z_DEFAULT_COMPRESSION - * 0 COMPRESSION_NONE - * 1-9 levels for gzip compression - *--------- - */ + Compress compression; /* Compression requested on open */ bool dosync; /* data requested to be synced on sight */ ArchiveMode mode; /* File mode - r or w */ void *formatData; /* Header data specific to file format */ diff --git a/src/bin/pg_dump/pg_backup_custom.c b/src/bin/pg_dump/pg_backup_custom.c index 77d402c323..55a887a236 100644 --- a/src/bin/pg_dump/pg_backup_custom.c +++ b/src/bin/pg_dump/pg_backup_custom.c @@ -298,7 +298,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) _WriteByte(AH, BLK_DATA); /* Block type */ WriteInt(AH, te->dumpId); /* For sanity check */ - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -377,7 +377,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) WriteInt(AH, oid); - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -566,7 +566,7 @@ _PrintTocData(ArchiveHandle *AH, TocEntry *te) static void _PrintData(ArchiveHandle *AH) { - ReadDataFromArchive(AH, AH->compression, _CustomReadFunc); + ReadDataFromArchive(AH, _CustomReadFunc); } static void diff --git a/src/bin/pg_dump/pg_backup_directory.c b/src/bin/pg_dump/pg_backup_directory.c index 650b542fce..8bf869c6ca 100644 --- a/src/bin/pg_dump/pg_backup_directory.c +++ b/src/bin/pg_dump/pg_backup_directory.c @@ -202,7 +202,7 @@ InitArchiveFmt_Directory(ArchiveHandle *AH) setFilePath(AH, fname, "toc.dat"); - tocFH = cfopen_read(fname, PG_BINARY_R); + tocFH = cfopen_read(fname, PG_BINARY_R, &AH->compression); if (tocFH == NULL) fatal("could not open input file \"%s\": %m", fname); @@ -327,7 +327,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) setFilePath(AH, fname, tctx->filename); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -388,7 +388,7 @@ _PrintFileData(ArchiveHandle *AH, char *filename) if (!filename) return; - cfp = cfopen_read(filename, PG_BINARY_R); + cfp = cfopen_read(filename, PG_BINARY_R, &AH->compression); if (!cfp) fatal("could not open input file \"%s\": %m", filename); @@ -435,12 +435,13 @@ _LoadBlobs(ArchiveHandle *AH) lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; char line[MAXPGPATH]; + Compress nocompression = {0}; StartRestoreBlobs(AH); setFilePath(AH, fname, "blobs.toc"); - ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R); + ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R, &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open large object TOC file \"%s\" for input: %m", @@ -573,6 +574,7 @@ _CloseArchive(ArchiveHandle *AH) { cfp *tocFH; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "toc.dat"); @@ -580,7 +582,7 @@ _CloseArchive(ArchiveHandle *AH) ctx->pstate = ParallelBackupStart(AH); /* The TOC is always created uncompressed */ - tocFH = cfopen_write(fname, PG_BINARY_W, 0); + tocFH = cfopen_write(fname, PG_BINARY_W, &nocompression); if (tocFH == NULL) fatal("could not open output file \"%s\": %m", fname); ctx->dataFH = tocFH; @@ -639,11 +641,12 @@ _StartBlobs(ArchiveHandle *AH, TocEntry *te) { lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "blobs.toc"); /* The blob TOC file is never compressed */ - ctx->blobsTocFH = cfopen_write(fname, "ab", 0); + ctx->blobsTocFH = cfopen_write(fname, "ab", &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -661,7 +664,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) snprintf(fname, MAXPGPATH, "%s/blob_%u.dat", ctx->directory, oid); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); diff --git a/src/bin/pg_dump/pg_backup_tar.c b/src/bin/pg_dump/pg_backup_tar.c index 61c9c87a9f..4ba79ab924 100644 --- a/src/bin/pg_dump/pg_backup_tar.c +++ b/src/bin/pg_dump/pg_backup_tar.c @@ -39,6 +39,7 @@ #include "pg_backup_archiver.h" #include "pg_backup_tar.h" #include "pg_backup_utils.h" +#include "compress_io.h" #include "pgtar.h" static void _ArchiveEntry(ArchiveHandle *AH, TocEntry *te); @@ -196,10 +197,10 @@ InitArchiveFmt_Tar(ArchiveHandle *AH) /* * We don't support compression because reading the files back is not - * possible since gzdopen uses buffered IO which totally screws file + * possible since gzdopen uses buffered IO which totally screws file XXX * positioning. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) fatal("compression is not supported by tar archive format"); } else @@ -254,14 +255,8 @@ _ArchiveEntry(ArchiveHandle *AH, TocEntry *te) ctx = (lclTocEntry *) pg_malloc0(sizeof(lclTocEntry)); if (te->dataDumper != NULL) { -#ifdef HAVE_LIBZ - if (AH->compression == 0) - sprintf(fn, "%d.dat", te->dumpId); - else - sprintf(fn, "%d.dat.gz", te->dumpId); -#else - sprintf(fn, "%d.dat", te->dumpId); -#endif + const char *suffix = compress_suffix(&AH->compression); + sprintf(fn, "%d.dat%s", te->dumpId, suffix); ctx->filename = pg_strdup(fn); } else @@ -352,7 +347,7 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression == 0) + if (AH->compression.alg == COMPR_ALG_NONE) tm->nFH = ctx->tarFH; else fatal("compression is not supported by tar archive format"); @@ -413,9 +408,9 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) { - sprintf(fmode, "wb%d", AH->compression); + sprintf(fmode, "wb%d", AH->compression.level); tm->zFH = gzdopen(dup(fileno(tm->tmpFH)), fmode); if (tm->zFH == NULL) fatal("could not open temporary file"); @@ -443,7 +438,7 @@ tarClose(ArchiveHandle *AH, TAR_MEMBER *th) /* * Close the GZ file since we dup'd. This will flush the buffers. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) if (GZCLOSE(th->zFH) != 0) fatal("could not close tar member"); @@ -868,7 +863,7 @@ _CloseArchive(ArchiveHandle *AH) memcpy(ropt, AH->public.ropt, sizeof(RestoreOptions)); ropt->filename = NULL; ropt->dropSchema = 1; - ropt->compression = 0; + ropt->compression.alg = COMPR_ALG_NONE; ropt->superuser = NULL; ropt->suppressDumpWarnings = true; @@ -952,16 +947,12 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) lclContext *ctx = (lclContext *) AH->formatData; lclTocEntry *tctx = (lclTocEntry *) te->formatData; char fname[255]; - char *sfx; + const char *sfx; if (oid == 0) fatal("invalid OID for large object (%u)", oid); - if (AH->compression != 0) - sfx = ".gz"; - else - sfx = ""; - + sfx = compress_suffix(&AH->compression); sprintf(fname, "blob_%u.dat%s", oid, sfx); tarPrintf(ctx->blobToc, "%u %s\n", oid, fname); diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c index 1ab98a2286..4cbc79aedc 100644 --- a/src/bin/pg_dump/pg_dump.c +++ b/src/bin/pg_dump/pg_dump.c @@ -59,6 +59,7 @@ #include "getopt_long.h" #include "libpq/libpq-fs.h" #include "parallel.h" +#include "compress_io.h" #include "pg_backup_db.h" #include "pg_backup_utils.h" #include "pg_dump.h" @@ -297,6 +298,82 @@ static void setupDumpWorker(Archive *AHX); static TableInfo *getRootTableInfo(TableInfo *tbinfo); +/* Parse the string into compression options */ +static void +parse_compression(const char *optarg, Compress *compress) +{ + if (optarg[0] == '0' && optarg[1] == '\0') + compress->alg = COMPR_ALG_NONE; + else if ((optarg[0] > '0' && optarg[0] <= '9') || + optarg[0] == '-') + { + compress->alg = COMPR_ALG_LIBZ; + compress->level_set = true; + compress->level = atoi(optarg); + if (optarg[1] != '\0') + { + pg_log_error("compression level must be in range 0..9"); + exit_nicely(1); + } + } + else + { + /* Parse a more flexible string like level=3 alg=zlib opts=long */ + for (;;) + { + char *eq = strchr(optarg, '='); + int len; + + if (eq == NULL) + { + pg_log_error("compression options must be key=value: %s", optarg); + exit_nicely(1); + } + + len = eq - optarg; + if (strncmp(optarg, "alg", len) == 0) + { + if (strchr(eq, ' ')) + len = strchr(eq, ' ') - eq - 1; + else + len = strlen(eq) - len; + if (strncmp(1+eq, "zlib", len) == 0 || + strncmp(1+eq, "libz", len) == 0) + compress->alg = COMPR_ALG_LIBZ; + else + { + pg_log_error("unknown compression algorithm: %s", 1+eq); + exit_nicely(1); + } + } + else if (strncmp(optarg, "level", len) == 0) + { + compress->level = atoi(1+eq); + compress->level_set = true; + } + else + { + pg_log_error("unknown compression setting: %s", optarg); + exit_nicely(1); + } + + optarg = strchr(eq, ' '); + if (!optarg++) + break; + } + + if (!compress->level_set) + { + const int default_compress_level[] = { + 0, /* COMPR_ALG_NONE */ + Z_DEFAULT_COMPRESSION, /* COMPR_ALG_ZLIB */ + }; + + compress->level = default_compress_level[compress->alg]; + } + } +} + int main(int argc, char **argv) { @@ -319,7 +396,7 @@ main(int argc, char **argv) char *use_role = NULL; long rowsPerInsert; int numWorkers = 1; - int compressLevel = -1; + Compress compress = { .alg = COMPR_ALG_DEFAULT }; int plainText = 0; ArchiveFormat archiveFormat = archUnknown; ArchiveMode archiveMode; @@ -532,12 +609,7 @@ main(int argc, char **argv) break; case 'Z': /* Compression Level */ - compressLevel = atoi(optarg); - if (compressLevel < 0 || compressLevel > 9) - { - pg_log_error("compression level must be in range 0..9"); - exit_nicely(1); - } + parse_compression(optarg, &compress); break; case 0: @@ -679,20 +751,28 @@ main(int argc, char **argv) plainText = 1; /* Custom and directory formats are compressed by default, others not */ - if (compressLevel == -1) + if (compress.alg == COMPR_ALG_DEFAULT) { -#ifdef HAVE_LIBZ if (archiveFormat == archCustom || archiveFormat == archDirectory) - compressLevel = Z_DEFAULT_COMPRESSION; - else + { +#ifdef HAVE_LIBZ + compress.alg = COMPR_ALG_LIBZ; + compress.level = Z_DEFAULT_COMPRESSION; #endif - compressLevel = 0; + } + else + { + compress.alg = COMPR_ALG_NONE; + compress.level = 0; + } } #ifndef HAVE_LIBZ - if (compressLevel != 0) + if (compress.alg == COMPR_ALG_LIBZ) + { pg_log_warning("requested compression not available in this installation -- archive will be uncompressed"); - compressLevel = 0; + compress.alg = 0; + } #endif /* @@ -723,7 +803,7 @@ main(int argc, char **argv) fatal("option --index-collation-versions-unknown only works in binary upgrade mode"); /* Open the output file */ - fout = CreateArchive(filename, archiveFormat, compressLevel, dosync, + fout = CreateArchive(filename, archiveFormat, &compress, dosync, archiveMode, setupDumpWorker); /* Make dump options accessible right away */ @@ -957,10 +1037,7 @@ main(int argc, char **argv) ropt->sequence_data = dopt.sequence_data; ropt->binary_upgrade = dopt.binary_upgrade; - if (compressLevel == -1) - ropt->compression = 0; - else - ropt->compression = compressLevel; + ropt->compression = compress; ropt->suppressDumpWarnings = true; /* We've already shown them */ -- 2.17.0 --GRPZ8SYKNexpdSJ7 Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="0004-struct-compressLibs.patch" ^ permalink raw reply [nested|flat] 23+ messages in thread
* [PATCH 03/20] Support multiple compression algs/levels/opts.. @ 2020-12-22 06:23 Justin Pryzby <[email protected]> 0 siblings, 0 replies; 23+ messages in thread From: Justin Pryzby @ 2020-12-22 06:23 UTC (permalink / raw) The existing implementation abtracts compressed and noncompressed I/O. This preliminary commit is intended to also allow for multiple compression algorithms. --- src/bin/pg_dump/compress_io.c | 220 +++++++++++--------------- src/bin/pg_dump/compress_io.h | 19 +-- src/bin/pg_dump/pg_backup.h | 23 ++- src/bin/pg_dump/pg_backup_archiver.c | 45 +++--- src/bin/pg_dump/pg_backup_archiver.h | 12 +- src/bin/pg_dump/pg_backup_custom.c | 6 +- src/bin/pg_dump/pg_backup_directory.c | 17 +- src/bin/pg_dump/pg_backup_tar.c | 33 ++-- src/bin/pg_dump/pg_dump.c | 115 +++++++++++--- 9 files changed, 272 insertions(+), 218 deletions(-) diff --git a/src/bin/pg_dump/compress_io.c b/src/bin/pg_dump/compress_io.c index 6a428978d4..db16fd33f2 100644 --- a/src/bin/pg_dump/compress_io.c +++ b/src/bin/pg_dump/compress_io.c @@ -74,12 +74,9 @@ struct CompressorState #endif }; -static void ParseCompressionOption(int compression, CompressionAlgorithm *alg, - int *level); - /* Routines that support zlib compressed data I/O */ #ifdef HAVE_LIBZ -static void InitCompressorZlib(CompressorState *cs, int level); +static void InitCompressorZlib(CompressorState *cs, Compress *compress); static void DeflateCompressorZlib(ArchiveHandle *AH, CompressorState *cs, bool flush); static void ReadDataFromArchiveZlib(ArchiveHandle *AH, ReadFunc readF); @@ -93,58 +90,36 @@ static void ReadDataFromArchiveNone(ArchiveHandle *AH, ReadFunc readF); static void WriteDataToArchiveNone(ArchiveHandle *AH, CompressorState *cs, const char *data, size_t dLen); -/* - * Interprets a numeric 'compression' value. The algorithm implied by the - * value (zlib or none at the moment), is returned in *alg, and the - * zlib compression level in *level. - */ -static void -ParseCompressionOption(int compression, CompressionAlgorithm *alg, int *level) -{ - if (compression == Z_DEFAULT_COMPRESSION || - (compression > 0 && compression <= 9)) - *alg = COMPR_ALG_LIBZ; - else if (compression == 0) - *alg = COMPR_ALG_NONE; - else - { - fatal("invalid compression code: %d", compression); - *alg = COMPR_ALG_NONE; /* keep compiler quiet */ - } - - /* The level is just the passed-in value. */ - if (level) - *level = compression; -} - /* Public interface routines */ /* Allocate a new compressor */ CompressorState * -AllocateCompressor(int compression, WriteFunc writeF) +AllocateCompressor(Compress *compression, WriteFunc writeF) { CompressorState *cs; - CompressionAlgorithm alg; - int level; - - ParseCompressionOption(compression, &alg, &level); - -#ifndef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - fatal("not built with zlib support"); -#endif cs = (CompressorState *) pg_malloc0(sizeof(CompressorState)); cs->writeF = writeF; - cs->comprAlg = alg; + cs->comprAlg = compression->alg; /* * Perform compression algorithm specific initialization. */ + Assert (compression->alg != COMPR_ALG_DEFAULT); + switch (compression->alg) + { #ifdef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - InitCompressorZlib(cs, level); + case COMPR_ALG_LIBZ: + InitCompressorZlib(cs, compression); + break; #endif + case COMPR_ALG_NONE: + /* Do nothing */ + break; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } return cs; } @@ -154,21 +129,21 @@ AllocateCompressor(int compression, WriteFunc writeF) * out with ahwrite(). */ void -ReadDataFromArchive(ArchiveHandle *AH, int compression, ReadFunc readF) +ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF) { - CompressionAlgorithm alg; - - ParseCompressionOption(compression, &alg, NULL); - - if (alg == COMPR_ALG_NONE) - ReadDataFromArchiveNone(AH, readF); - if (alg == COMPR_ALG_LIBZ) + switch (AH->compression.alg) { + case COMPR_ALG_NONE: + ReadDataFromArchiveNone(AH, readF); + break; #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: ReadDataFromArchiveZlib(AH, readF); -#else - fatal("not built with zlib support"); + break; #endif + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -181,16 +156,18 @@ WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, { switch (cs->comprAlg) { - case COMPR_ALG_LIBZ: #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: WriteDataToArchiveZlib(AH, cs, data, dLen); -#else - fatal("not built with zlib support"); -#endif break; +#endif case COMPR_ALG_NONE: WriteDataToArchiveNone(AH, cs, data, dLen); break; + + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -215,7 +192,7 @@ EndCompressor(ArchiveHandle *AH, CompressorState *cs) */ static void -InitCompressorZlib(CompressorState *cs, int level) +InitCompressorZlib(CompressorState *cs, Compress *compress) { z_streamp zp; @@ -232,7 +209,7 @@ InitCompressorZlib(CompressorState *cs, int level) cs->zlibOut = (char *) pg_malloc(ZLIB_OUT_SIZE + 1); cs->zlibOutSize = ZLIB_OUT_SIZE; - if (deflateInit(zp, level) != Z_OK) + if (deflateInit(zp, compress->level) != Z_OK) fatal("could not initialize compression library: %s", zp->msg); @@ -424,9 +401,7 @@ struct cfp #endif }; -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix); -#endif /* free() without changing errno; useful in several places below */ static void @@ -442,34 +417,31 @@ free_keep_errno(void *p) * Open a file for reading. 'path' is the file to open, and 'mode' should * be either "r" or "rb". * - * If the file at 'path' does not exist, we append the ".gz" suffix (if 'path' - * doesn't already have it) and try again. So if you pass "foo" as 'path', + * If the file at 'path' does not exist, we search with compressed suffix (if 'path' + * doesn't already have one) and try again. So if you pass "foo" as 'path', * this will open either "foo" or "foo.gz". * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_read(const char *path, const char *mode) +cfopen_read(const char *path, const char *mode, Compress *compression) { cfp *fp; -#ifdef HAVE_LIBZ if (hasSuffix(path, ".gz")) - fp = cfopen(path, mode, 1); + fp = cfopen(path, mode, compression); else -#endif { - fp = cfopen(path, mode, 0); -#ifdef HAVE_LIBZ + fp = cfopen(path, mode, compression); if (fp == NULL) { char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); - fp = cfopen(fname, mode, 1); + fname = psprintf("%s%s", path, suffix); + fp = cfopen(fname, mode, compression); free_keep_errno(fname); } -#endif } return fp; } @@ -479,31 +451,26 @@ cfopen_read(const char *path, const char *mode) * be a filemode as accepted by fopen() and gzopen() that indicates writing * ("w", "wb", "a", or "ab"). * - * If 'compression' is non-zero, a gzip compressed stream is opened, and - * 'compression' indicates the compression level used. The ".gz" suffix - * is automatically added to 'path' in that case. + * Use compression if specified. + * The appropriate suffix is automatically added to 'path' in that case. * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_write(const char *path, const char *mode, int compression) +cfopen_write(const char *path, const char *mode, Compress *compression) { cfp *fp; - if (compression == 0) - fp = cfopen(path, mode, 0); + if (compression->alg == COMPR_ALG_NONE) + fp = cfopen(path, mode, compression); else { -#ifdef HAVE_LIBZ char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); + fname = psprintf("%s%s", path, suffix); fp = cfopen(fname, mode, compression); free_keep_errno(fname); -#else - fatal("not built with zlib support"); - fp = NULL; /* keep compiler quiet */ -#endif } return fp; } @@ -515,20 +482,21 @@ cfopen_write(const char *path, const char *mode, int compression) * On failure, return NULL with an error code in errno. */ cfp * -cfopen(const char *path, const char *mode, int compression) +cfopen(const char *path, const char *mode, Compress *compression) { - cfp *fp = pg_malloc(sizeof(cfp)); + cfp *fp = pg_malloc0(sizeof(cfp)); - if (compression != 0) + switch (compression->alg) { #ifdef HAVE_LIBZ - if (compression != Z_DEFAULT_COMPRESSION) + case COMPR_ALG_LIBZ: + if (compression->level != Z_DEFAULT_COMPRESSION) { /* user has specified a compression level, so tell zlib to use it */ char mode_compression[32]; snprintf(mode_compression, sizeof(mode_compression), "%s%d", - mode, compression); + mode, compression->level); fp->compressedfp = gzopen(path, mode_compression); } else @@ -537,30 +505,27 @@ cfopen(const char *path, const char *mode, int compression) fp->compressedfp = gzopen(path, mode); } - fp->uncompressedfp = NULL; if (fp->compressedfp == NULL) { free_keep_errno(fp); fp = NULL; } -#else - fatal("not built with zlib support"); -#endif - } - else - { -#ifdef HAVE_LIBZ - fp->compressedfp = NULL; + return fp; #endif + + case COMPR_ALG_NONE: fp->uncompressedfp = fopen(path, mode); if (fp->uncompressedfp == NULL) { free_keep_errno(fp); fp = NULL; } - } + return fp; - return fp; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } } @@ -584,14 +549,13 @@ cfread(void *ptr, int size, cfp *fp) fatal("could not read from input file: %s", errnum == Z_ERRNO ? strerror(errno) : errmsg); } + return ret; } - else #endif - { - ret = fread(ptr, 1, size, fp->uncompressedfp); - if (ret != size && !feof(fp->uncompressedfp)) - READ_ERROR_EXIT(fp->uncompressedfp); - } + + ret = fread(ptr, 1, size, fp->uncompressedfp); + if (ret != size && !feof(fp->uncompressedfp)) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -601,9 +565,8 @@ cfwrite(const void *ptr, int size, cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzwrite(fp->compressedfp, ptr, size); - else #endif - return fwrite(ptr, 1, size, fp->uncompressedfp); + return fwrite(ptr, 1, size, fp->uncompressedfp); } int @@ -622,15 +585,12 @@ cfgetc(cfp *fp) else fatal("could not read from input file: end of file"); } + return ret; } - else #endif - { - ret = fgetc(fp->uncompressedfp); - if (ret == EOF) - READ_ERROR_EXIT(fp->uncompressedfp); - } - + ret = fgetc(fp->uncompressedfp); + if (ret == EOF) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -640,9 +600,8 @@ cfgets(cfp *fp, char *buf, int len) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzgets(fp->compressedfp, buf, len); - else #endif - return fgets(buf, len, fp->uncompressedfp); + return fgets(buf, len, fp->uncompressedfp); } int @@ -660,15 +619,13 @@ cfclose(cfp *fp) { result = gzclose(fp->compressedfp); fp->compressedfp = NULL; + return result; } - else #endif - { - result = fclose(fp->uncompressedfp); - fp->uncompressedfp = NULL; - } - free_keep_errno(fp); + result = fclose(fp->uncompressedfp); + fp->uncompressedfp = NULL; + free_keep_errno(fp); return result; } @@ -678,9 +635,9 @@ cfeof(cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzeof(fp->compressedfp); - else #endif - return feof(fp->uncompressedfp); + + return feof(fp->uncompressedfp); } const char * @@ -699,7 +656,6 @@ get_cfp_error(cfp *fp) return strerror(errno); } -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix) { @@ -714,4 +670,18 @@ hasSuffix(const char *filename, const char *suffix) suffixlen) == 0; } -#endif +/* + * Return a string for the given AH's compression. + * The string is statically allocated. + */ +const char * +compress_suffix(Compress *compression) +{ + switch (compression->alg) + { + case COMPR_ALG_LIBZ: + return ".gz"; + default: + return ""; + } +} diff --git a/src/bin/pg_dump/compress_io.h b/src/bin/pg_dump/compress_io.h index d2e6e1b854..2c073676eb 100644 --- a/src/bin/pg_dump/compress_io.h +++ b/src/bin/pg_dump/compress_io.h @@ -21,12 +21,6 @@ #define ZLIB_OUT_SIZE 4096 #define ZLIB_IN_SIZE 4096 -typedef enum -{ - COMPR_ALG_NONE, - COMPR_ALG_LIBZ -} CompressionAlgorithm; - /* Prototype for callback function to WriteDataToArchive() */ typedef void (*WriteFunc) (ArchiveHandle *AH, const char *buf, size_t len); @@ -46,8 +40,8 @@ typedef size_t (*ReadFunc) (ArchiveHandle *AH, char **buf, size_t *buflen); /* struct definition appears in compress_io.c */ typedef struct CompressorState CompressorState; -extern CompressorState *AllocateCompressor(int compression, WriteFunc writeF); -extern void ReadDataFromArchive(ArchiveHandle *AH, int compression, +extern CompressorState *AllocateCompressor(Compress *compression, WriteFunc writeF); +extern void ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF); extern void WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, const void *data, size_t dLen); @@ -56,9 +50,9 @@ extern void EndCompressor(ArchiveHandle *AH, CompressorState *cs); typedef struct cfp cfp; -extern cfp *cfopen(const char *path, const char *mode, int compression); -extern cfp *cfopen_read(const char *path, const char *mode); -extern cfp *cfopen_write(const char *path, const char *mode, int compression); +extern cfp *cfopen(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_read(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_write(const char *path, const char *mode, Compress *compression); extern int cfread(void *ptr, int size, cfp *fp); extern int cfwrite(const void *ptr, int size, cfp *fp); extern int cfgetc(cfp *fp); @@ -67,4 +61,7 @@ extern int cfclose(cfp *fp); extern int cfeof(cfp *fp); extern const char *get_cfp_error(cfp *fp); +/* also used by tar */ +extern const char * compress_suffix(Compress *compression); + #endif diff --git a/src/bin/pg_dump/pg_backup.h b/src/bin/pg_dump/pg_backup.h index 9d0056a569..f2390b7937 100644 --- a/src/bin/pg_dump/pg_backup.h +++ b/src/bin/pg_dump/pg_backup.h @@ -72,6 +72,25 @@ typedef struct _connParams char *override_dbname; } ConnParams; +typedef enum +{ + COMPR_ALG_DEFAULT = -1, + COMPR_ALG_NONE, + COMPR_ALG_LIBZ, +} CompressionAlgorithm; +/* Should be called "method" or "library" ? */ + +typedef struct Compress { + CompressionAlgorithm alg; + int level; + /* Is a nondefault level set ? This is useful since different compression + * methods have different "default" levels. For now we assume the levels + * are all integer, though. + */ + bool level_set; +} Compress; + + typedef struct _restoreOptions { int createDB; /* Issue commands to create the database */ @@ -125,7 +144,7 @@ typedef struct _restoreOptions int noDataForFailedTables; int exit_on_error; - int compression; + Compress compression; int suppressDumpWarnings; /* Suppress output of WARNING entries * to stderr */ bool single_txn; @@ -281,7 +300,7 @@ extern Archive *OpenArchive(const char *FileSpec, const ArchiveFormat fmt); /* Create a new archive */ extern Archive *CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker); /* The --list option */ diff --git a/src/bin/pg_dump/pg_backup_archiver.c b/src/bin/pg_dump/pg_backup_archiver.c index 1f82c6499b..3eb6c55600 100644 --- a/src/bin/pg_dump/pg_backup_archiver.c +++ b/src/bin/pg_dump/pg_backup_archiver.c @@ -70,7 +70,7 @@ typedef struct _parallelReadyList static ArchiveHandle *_allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr); static void _getObjectDescription(PQExpBuffer buf, TocEntry *te); static void _printTocEntry(ArchiveHandle *AH, TocEntry *te, bool isData); @@ -98,7 +98,7 @@ static int _discoverArchiveFormat(ArchiveHandle *AH); static int RestoringToDB(ArchiveHandle *AH); static void dump_lo_buf(ArchiveHandle *AH); static void dumpTimestamp(ArchiveHandle *AH, const char *msg, time_t tim); -static void SetOutput(ArchiveHandle *AH, const char *filename, int compression); +static void SetOutput(ArchiveHandle *AH, const char *filename, Compress *compress); static OutputContext SaveOutput(ArchiveHandle *AH); static void RestoreOutput(ArchiveHandle *AH, OutputContext savedContext); @@ -238,7 +238,7 @@ setupRestoreWorker(Archive *AHX) /* Public */ Archive * CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker) { @@ -253,7 +253,9 @@ CreateArchive(const char *FileSpec, const ArchiveFormat fmt, Archive * OpenArchive(const char *FileSpec, const ArchiveFormat fmt) { - ArchiveHandle *AH = _allocAH(FileSpec, fmt, 0, true, archModeRead, setupRestoreWorker); + Compress compress = {0}; + ArchiveHandle *AH = _allocAH(FileSpec, fmt, &compress, true, archModeRead, + setupRestoreWorker); return (Archive *) AH; } @@ -382,7 +384,7 @@ RestoreArchive(Archive *AHX) * Make sure we won't need (de)compression we haven't got */ #ifndef HAVE_LIBZ - if (AH->compression != 0 && AH->PrintTocDataPtr != NULL) + if (AH->compression.alg != COMPR_ALG_NONE && AH->PrintTocDataPtr != NULL) { for (te = AH->toc->next; te != AH->toc; te = te->next) { @@ -457,8 +459,8 @@ RestoreArchive(Archive *AHX) * Setup the output file if necessary. */ sav = SaveOutput(AH); - if (ropt->filename || ropt->compression) - SetOutput(AH, ropt->filename, ropt->compression); + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) + SetOutput(AH, ropt->filename, &ropt->compression); ahprintf(AH, "--\n-- PostgreSQL database dump\n--\n\n"); @@ -738,7 +740,7 @@ RestoreArchive(Archive *AHX) */ AH->stage = STAGE_FINALIZING; - if (ropt->filename || ropt->compression) + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) RestoreOutput(AH, sav); if (ropt->useDB) @@ -1123,8 +1125,9 @@ PrintTOCSummary(Archive *AHX) char stamp_str[64]; sav = SaveOutput(AH); + Assert(ropt->compression.alg == COMPR_ALG_NONE); if (ropt->filename) - SetOutput(AH, ropt->filename, 0 /* no compression */ ); + SetOutput(AH, ropt->filename, &ropt->compression); if (strftime(stamp_str, sizeof(stamp_str), PGDUMP_STRFTIME_FMT, localtime(&AH->createDate)) == 0) @@ -1133,7 +1136,7 @@ PrintTOCSummary(Archive *AHX) ahprintf(AH, ";\n; Archive created at %s\n", stamp_str); ahprintf(AH, "; dbname: %s\n; TOC Entries: %d\n; Compression: %d\n", sanitize_line(AH->archdbname, false), - AH->tocCount, AH->compression); + AH->tocCount, AH->compression.alg); switch (AH->format) { @@ -1487,7 +1490,7 @@ archprintf(Archive *AH, const char *fmt,...) *******************************/ static void -SetOutput(ArchiveHandle *AH, const char *filename, int compression) +SetOutput(ArchiveHandle *AH, const char *filename, Compress *compression) { int fn; @@ -1510,12 +1513,12 @@ SetOutput(ArchiveHandle *AH, const char *filename, int compression) /* If compression explicitly requested, use gzopen */ #ifdef HAVE_LIBZ - if (compression != 0) + if (compression->alg != COMPR_ALG_NONE) { char fmode[14]; /* Don't use PG_BINARY_x since this is zlib */ - sprintf(fmode, "wb%d", compression); + sprintf(fmode, "wb%d", compression->level); if (fn >= 0) AH->OF = gzdopen(dup(fn), fmode); else @@ -2259,7 +2262,7 @@ _discoverArchiveFormat(ArchiveHandle *AH) */ static ArchiveHandle * _allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr) { ArchiveHandle *AH; @@ -2310,7 +2313,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, AH->toc->prev = AH->toc; AH->mode = mode; - AH->compression = compression; + AH->compression = *compression; AH->dosync = dosync; memset(&(AH->sqlparse), 0, sizeof(AH->sqlparse)); @@ -2325,7 +2328,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, * Force stdin/stdout into binary mode if that is what we are using. */ #ifdef WIN32 - if ((fmt != archNull || compression != 0) && + if ((fmt != archNull || compression->alg != COMPR_ALG_NONE) && (AH->fSpec == NULL || strcmp(AH->fSpec, "") == 0)) { if (mode == archModeWrite) @@ -3741,7 +3744,7 @@ WriteHead(ArchiveHandle *AH) AH->WriteBytePtr(AH, AH->intSize); AH->WriteBytePtr(AH, AH->offSize); AH->WriteBytePtr(AH, AH->format); - WriteInt(AH, AH->compression); + WriteInt(AH, AH->compression.alg); crtm = *localtime(&AH->createDate); WriteInt(AH, crtm.tm_sec); WriteInt(AH, crtm.tm_min); @@ -3816,15 +3819,15 @@ ReadHead(ArchiveHandle *AH) if (AH->version >= K_VERS_1_2) { if (AH->version < K_VERS_1_4) - AH->compression = AH->ReadBytePtr(AH); + AH->compression.alg = AH->ReadBytePtr(AH); else - AH->compression = ReadInt(AH); + AH->compression.alg = ReadInt(AH); } else - AH->compression = Z_DEFAULT_COMPRESSION; + AH->compression.alg = Z_DEFAULT_COMPRESSION; #ifndef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) pg_log_warning("archive is compressed, but this installation does not support compression -- no data will be available"); #endif diff --git a/src/bin/pg_dump/pg_backup_archiver.h b/src/bin/pg_dump/pg_backup_archiver.h index a8ea5c7eae..6e033d040e 100644 --- a/src/bin/pg_dump/pg_backup_archiver.h +++ b/src/bin/pg_dump/pg_backup_archiver.h @@ -47,7 +47,8 @@ #define GZWRITE(p, s, n, fh) (fwrite(p, s, n, fh) * (s)) #define GZREAD(p, s, n, fh) fread(p, s, n, fh) #define GZEOF(fh) feof(fh) -/* this is just the redefinition of a libz constant */ +/* this is just the redefinition of a libz constant, in case zlib isn't + * available */ #define Z_DEFAULT_COMPRESSION (-1) typedef struct _z_stream @@ -329,14 +330,7 @@ struct _archiveHandle DumpId *tableDataId; /* TABLE DATA ids, indexed by table dumpId */ struct _tocEntry *currToc; /* Used when dumping data */ - int compression; /*--------- - * Compression requested on open(). - * Possible values for compression: - * -1 Z_DEFAULT_COMPRESSION - * 0 COMPRESSION_NONE - * 1-9 levels for gzip compression - *--------- - */ + Compress compression; /* Compression requested on open */ bool dosync; /* data requested to be synced on sight */ ArchiveMode mode; /* File mode - r or w */ void *formatData; /* Header data specific to file format */ diff --git a/src/bin/pg_dump/pg_backup_custom.c b/src/bin/pg_dump/pg_backup_custom.c index 77d402c323..55a887a236 100644 --- a/src/bin/pg_dump/pg_backup_custom.c +++ b/src/bin/pg_dump/pg_backup_custom.c @@ -298,7 +298,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) _WriteByte(AH, BLK_DATA); /* Block type */ WriteInt(AH, te->dumpId); /* For sanity check */ - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -377,7 +377,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) WriteInt(AH, oid); - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -566,7 +566,7 @@ _PrintTocData(ArchiveHandle *AH, TocEntry *te) static void _PrintData(ArchiveHandle *AH) { - ReadDataFromArchive(AH, AH->compression, _CustomReadFunc); + ReadDataFromArchive(AH, _CustomReadFunc); } static void diff --git a/src/bin/pg_dump/pg_backup_directory.c b/src/bin/pg_dump/pg_backup_directory.c index 650b542fce..8bf869c6ca 100644 --- a/src/bin/pg_dump/pg_backup_directory.c +++ b/src/bin/pg_dump/pg_backup_directory.c @@ -202,7 +202,7 @@ InitArchiveFmt_Directory(ArchiveHandle *AH) setFilePath(AH, fname, "toc.dat"); - tocFH = cfopen_read(fname, PG_BINARY_R); + tocFH = cfopen_read(fname, PG_BINARY_R, &AH->compression); if (tocFH == NULL) fatal("could not open input file \"%s\": %m", fname); @@ -327,7 +327,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) setFilePath(AH, fname, tctx->filename); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -388,7 +388,7 @@ _PrintFileData(ArchiveHandle *AH, char *filename) if (!filename) return; - cfp = cfopen_read(filename, PG_BINARY_R); + cfp = cfopen_read(filename, PG_BINARY_R, &AH->compression); if (!cfp) fatal("could not open input file \"%s\": %m", filename); @@ -435,12 +435,13 @@ _LoadBlobs(ArchiveHandle *AH) lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; char line[MAXPGPATH]; + Compress nocompression = {0}; StartRestoreBlobs(AH); setFilePath(AH, fname, "blobs.toc"); - ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R); + ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R, &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open large object TOC file \"%s\" for input: %m", @@ -573,6 +574,7 @@ _CloseArchive(ArchiveHandle *AH) { cfp *tocFH; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "toc.dat"); @@ -580,7 +582,7 @@ _CloseArchive(ArchiveHandle *AH) ctx->pstate = ParallelBackupStart(AH); /* The TOC is always created uncompressed */ - tocFH = cfopen_write(fname, PG_BINARY_W, 0); + tocFH = cfopen_write(fname, PG_BINARY_W, &nocompression); if (tocFH == NULL) fatal("could not open output file \"%s\": %m", fname); ctx->dataFH = tocFH; @@ -639,11 +641,12 @@ _StartBlobs(ArchiveHandle *AH, TocEntry *te) { lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "blobs.toc"); /* The blob TOC file is never compressed */ - ctx->blobsTocFH = cfopen_write(fname, "ab", 0); + ctx->blobsTocFH = cfopen_write(fname, "ab", &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -661,7 +664,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) snprintf(fname, MAXPGPATH, "%s/blob_%u.dat", ctx->directory, oid); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); diff --git a/src/bin/pg_dump/pg_backup_tar.c b/src/bin/pg_dump/pg_backup_tar.c index 61c9c87a9f..4ba79ab924 100644 --- a/src/bin/pg_dump/pg_backup_tar.c +++ b/src/bin/pg_dump/pg_backup_tar.c @@ -39,6 +39,7 @@ #include "pg_backup_archiver.h" #include "pg_backup_tar.h" #include "pg_backup_utils.h" +#include "compress_io.h" #include "pgtar.h" static void _ArchiveEntry(ArchiveHandle *AH, TocEntry *te); @@ -196,10 +197,10 @@ InitArchiveFmt_Tar(ArchiveHandle *AH) /* * We don't support compression because reading the files back is not - * possible since gzdopen uses buffered IO which totally screws file + * possible since gzdopen uses buffered IO which totally screws file XXX * positioning. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) fatal("compression is not supported by tar archive format"); } else @@ -254,14 +255,8 @@ _ArchiveEntry(ArchiveHandle *AH, TocEntry *te) ctx = (lclTocEntry *) pg_malloc0(sizeof(lclTocEntry)); if (te->dataDumper != NULL) { -#ifdef HAVE_LIBZ - if (AH->compression == 0) - sprintf(fn, "%d.dat", te->dumpId); - else - sprintf(fn, "%d.dat.gz", te->dumpId); -#else - sprintf(fn, "%d.dat", te->dumpId); -#endif + const char *suffix = compress_suffix(&AH->compression); + sprintf(fn, "%d.dat%s", te->dumpId, suffix); ctx->filename = pg_strdup(fn); } else @@ -352,7 +347,7 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression == 0) + if (AH->compression.alg == COMPR_ALG_NONE) tm->nFH = ctx->tarFH; else fatal("compression is not supported by tar archive format"); @@ -413,9 +408,9 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) { - sprintf(fmode, "wb%d", AH->compression); + sprintf(fmode, "wb%d", AH->compression.level); tm->zFH = gzdopen(dup(fileno(tm->tmpFH)), fmode); if (tm->zFH == NULL) fatal("could not open temporary file"); @@ -443,7 +438,7 @@ tarClose(ArchiveHandle *AH, TAR_MEMBER *th) /* * Close the GZ file since we dup'd. This will flush the buffers. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) if (GZCLOSE(th->zFH) != 0) fatal("could not close tar member"); @@ -868,7 +863,7 @@ _CloseArchive(ArchiveHandle *AH) memcpy(ropt, AH->public.ropt, sizeof(RestoreOptions)); ropt->filename = NULL; ropt->dropSchema = 1; - ropt->compression = 0; + ropt->compression.alg = COMPR_ALG_NONE; ropt->superuser = NULL; ropt->suppressDumpWarnings = true; @@ -952,16 +947,12 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) lclContext *ctx = (lclContext *) AH->formatData; lclTocEntry *tctx = (lclTocEntry *) te->formatData; char fname[255]; - char *sfx; + const char *sfx; if (oid == 0) fatal("invalid OID for large object (%u)", oid); - if (AH->compression != 0) - sfx = ".gz"; - else - sfx = ""; - + sfx = compress_suffix(&AH->compression); sprintf(fname, "blob_%u.dat%s", oid, sfx); tarPrintf(ctx->blobToc, "%u %s\n", oid, fname); diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c index 1ab98a2286..4cbc79aedc 100644 --- a/src/bin/pg_dump/pg_dump.c +++ b/src/bin/pg_dump/pg_dump.c @@ -59,6 +59,7 @@ #include "getopt_long.h" #include "libpq/libpq-fs.h" #include "parallel.h" +#include "compress_io.h" #include "pg_backup_db.h" #include "pg_backup_utils.h" #include "pg_dump.h" @@ -297,6 +298,82 @@ static void setupDumpWorker(Archive *AHX); static TableInfo *getRootTableInfo(TableInfo *tbinfo); +/* Parse the string into compression options */ +static void +parse_compression(const char *optarg, Compress *compress) +{ + if (optarg[0] == '0' && optarg[1] == '\0') + compress->alg = COMPR_ALG_NONE; + else if ((optarg[0] > '0' && optarg[0] <= '9') || + optarg[0] == '-') + { + compress->alg = COMPR_ALG_LIBZ; + compress->level_set = true; + compress->level = atoi(optarg); + if (optarg[1] != '\0') + { + pg_log_error("compression level must be in range 0..9"); + exit_nicely(1); + } + } + else + { + /* Parse a more flexible string like level=3 alg=zlib opts=long */ + for (;;) + { + char *eq = strchr(optarg, '='); + int len; + + if (eq == NULL) + { + pg_log_error("compression options must be key=value: %s", optarg); + exit_nicely(1); + } + + len = eq - optarg; + if (strncmp(optarg, "alg", len) == 0) + { + if (strchr(eq, ' ')) + len = strchr(eq, ' ') - eq - 1; + else + len = strlen(eq) - len; + if (strncmp(1+eq, "zlib", len) == 0 || + strncmp(1+eq, "libz", len) == 0) + compress->alg = COMPR_ALG_LIBZ; + else + { + pg_log_error("unknown compression algorithm: %s", 1+eq); + exit_nicely(1); + } + } + else if (strncmp(optarg, "level", len) == 0) + { + compress->level = atoi(1+eq); + compress->level_set = true; + } + else + { + pg_log_error("unknown compression setting: %s", optarg); + exit_nicely(1); + } + + optarg = strchr(eq, ' '); + if (!optarg++) + break; + } + + if (!compress->level_set) + { + const int default_compress_level[] = { + 0, /* COMPR_ALG_NONE */ + Z_DEFAULT_COMPRESSION, /* COMPR_ALG_ZLIB */ + }; + + compress->level = default_compress_level[compress->alg]; + } + } +} + int main(int argc, char **argv) { @@ -319,7 +396,7 @@ main(int argc, char **argv) char *use_role = NULL; long rowsPerInsert; int numWorkers = 1; - int compressLevel = -1; + Compress compress = { .alg = COMPR_ALG_DEFAULT }; int plainText = 0; ArchiveFormat archiveFormat = archUnknown; ArchiveMode archiveMode; @@ -532,12 +609,7 @@ main(int argc, char **argv) break; case 'Z': /* Compression Level */ - compressLevel = atoi(optarg); - if (compressLevel < 0 || compressLevel > 9) - { - pg_log_error("compression level must be in range 0..9"); - exit_nicely(1); - } + parse_compression(optarg, &compress); break; case 0: @@ -679,20 +751,28 @@ main(int argc, char **argv) plainText = 1; /* Custom and directory formats are compressed by default, others not */ - if (compressLevel == -1) + if (compress.alg == COMPR_ALG_DEFAULT) { -#ifdef HAVE_LIBZ if (archiveFormat == archCustom || archiveFormat == archDirectory) - compressLevel = Z_DEFAULT_COMPRESSION; - else + { +#ifdef HAVE_LIBZ + compress.alg = COMPR_ALG_LIBZ; + compress.level = Z_DEFAULT_COMPRESSION; #endif - compressLevel = 0; + } + else + { + compress.alg = COMPR_ALG_NONE; + compress.level = 0; + } } #ifndef HAVE_LIBZ - if (compressLevel != 0) + if (compress.alg == COMPR_ALG_LIBZ) + { pg_log_warning("requested compression not available in this installation -- archive will be uncompressed"); - compressLevel = 0; + compress.alg = 0; + } #endif /* @@ -723,7 +803,7 @@ main(int argc, char **argv) fatal("option --index-collation-versions-unknown only works in binary upgrade mode"); /* Open the output file */ - fout = CreateArchive(filename, archiveFormat, compressLevel, dosync, + fout = CreateArchive(filename, archiveFormat, &compress, dosync, archiveMode, setupDumpWorker); /* Make dump options accessible right away */ @@ -957,10 +1037,7 @@ main(int argc, char **argv) ropt->sequence_data = dopt.sequence_data; ropt->binary_upgrade = dopt.binary_upgrade; - if (compressLevel == -1) - ropt->compression = 0; - else - ropt->compression = compressLevel; + ropt->compression = compress; ropt->suppressDumpWarnings = true; /* We've already shown them */ -- 2.17.0 --GRPZ8SYKNexpdSJ7 Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="0004-struct-compressLibs.patch" ^ permalink raw reply [nested|flat] 23+ messages in thread
* [PATCH 03/20] Support multiple compression algs/levels/opts.. @ 2020-12-22 06:23 Justin Pryzby <[email protected]> 0 siblings, 0 replies; 23+ messages in thread From: Justin Pryzby @ 2020-12-22 06:23 UTC (permalink / raw) The existing implementation abtracts compressed and noncompressed I/O. This preliminary commit is intended to also allow for multiple compression algorithms. --- src/bin/pg_dump/compress_io.c | 220 +++++++++++--------------- src/bin/pg_dump/compress_io.h | 19 +-- src/bin/pg_dump/pg_backup.h | 23 ++- src/bin/pg_dump/pg_backup_archiver.c | 45 +++--- src/bin/pg_dump/pg_backup_archiver.h | 12 +- src/bin/pg_dump/pg_backup_custom.c | 6 +- src/bin/pg_dump/pg_backup_directory.c | 17 +- src/bin/pg_dump/pg_backup_tar.c | 33 ++-- src/bin/pg_dump/pg_dump.c | 115 +++++++++++--- 9 files changed, 272 insertions(+), 218 deletions(-) diff --git a/src/bin/pg_dump/compress_io.c b/src/bin/pg_dump/compress_io.c index 6a428978d4..db16fd33f2 100644 --- a/src/bin/pg_dump/compress_io.c +++ b/src/bin/pg_dump/compress_io.c @@ -74,12 +74,9 @@ struct CompressorState #endif }; -static void ParseCompressionOption(int compression, CompressionAlgorithm *alg, - int *level); - /* Routines that support zlib compressed data I/O */ #ifdef HAVE_LIBZ -static void InitCompressorZlib(CompressorState *cs, int level); +static void InitCompressorZlib(CompressorState *cs, Compress *compress); static void DeflateCompressorZlib(ArchiveHandle *AH, CompressorState *cs, bool flush); static void ReadDataFromArchiveZlib(ArchiveHandle *AH, ReadFunc readF); @@ -93,58 +90,36 @@ static void ReadDataFromArchiveNone(ArchiveHandle *AH, ReadFunc readF); static void WriteDataToArchiveNone(ArchiveHandle *AH, CompressorState *cs, const char *data, size_t dLen); -/* - * Interprets a numeric 'compression' value. The algorithm implied by the - * value (zlib or none at the moment), is returned in *alg, and the - * zlib compression level in *level. - */ -static void -ParseCompressionOption(int compression, CompressionAlgorithm *alg, int *level) -{ - if (compression == Z_DEFAULT_COMPRESSION || - (compression > 0 && compression <= 9)) - *alg = COMPR_ALG_LIBZ; - else if (compression == 0) - *alg = COMPR_ALG_NONE; - else - { - fatal("invalid compression code: %d", compression); - *alg = COMPR_ALG_NONE; /* keep compiler quiet */ - } - - /* The level is just the passed-in value. */ - if (level) - *level = compression; -} - /* Public interface routines */ /* Allocate a new compressor */ CompressorState * -AllocateCompressor(int compression, WriteFunc writeF) +AllocateCompressor(Compress *compression, WriteFunc writeF) { CompressorState *cs; - CompressionAlgorithm alg; - int level; - - ParseCompressionOption(compression, &alg, &level); - -#ifndef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - fatal("not built with zlib support"); -#endif cs = (CompressorState *) pg_malloc0(sizeof(CompressorState)); cs->writeF = writeF; - cs->comprAlg = alg; + cs->comprAlg = compression->alg; /* * Perform compression algorithm specific initialization. */ + Assert (compression->alg != COMPR_ALG_DEFAULT); + switch (compression->alg) + { #ifdef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - InitCompressorZlib(cs, level); + case COMPR_ALG_LIBZ: + InitCompressorZlib(cs, compression); + break; #endif + case COMPR_ALG_NONE: + /* Do nothing */ + break; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } return cs; } @@ -154,21 +129,21 @@ AllocateCompressor(int compression, WriteFunc writeF) * out with ahwrite(). */ void -ReadDataFromArchive(ArchiveHandle *AH, int compression, ReadFunc readF) +ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF) { - CompressionAlgorithm alg; - - ParseCompressionOption(compression, &alg, NULL); - - if (alg == COMPR_ALG_NONE) - ReadDataFromArchiveNone(AH, readF); - if (alg == COMPR_ALG_LIBZ) + switch (AH->compression.alg) { + case COMPR_ALG_NONE: + ReadDataFromArchiveNone(AH, readF); + break; #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: ReadDataFromArchiveZlib(AH, readF); -#else - fatal("not built with zlib support"); + break; #endif + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -181,16 +156,18 @@ WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, { switch (cs->comprAlg) { - case COMPR_ALG_LIBZ: #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: WriteDataToArchiveZlib(AH, cs, data, dLen); -#else - fatal("not built with zlib support"); -#endif break; +#endif case COMPR_ALG_NONE: WriteDataToArchiveNone(AH, cs, data, dLen); break; + + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -215,7 +192,7 @@ EndCompressor(ArchiveHandle *AH, CompressorState *cs) */ static void -InitCompressorZlib(CompressorState *cs, int level) +InitCompressorZlib(CompressorState *cs, Compress *compress) { z_streamp zp; @@ -232,7 +209,7 @@ InitCompressorZlib(CompressorState *cs, int level) cs->zlibOut = (char *) pg_malloc(ZLIB_OUT_SIZE + 1); cs->zlibOutSize = ZLIB_OUT_SIZE; - if (deflateInit(zp, level) != Z_OK) + if (deflateInit(zp, compress->level) != Z_OK) fatal("could not initialize compression library: %s", zp->msg); @@ -424,9 +401,7 @@ struct cfp #endif }; -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix); -#endif /* free() without changing errno; useful in several places below */ static void @@ -442,34 +417,31 @@ free_keep_errno(void *p) * Open a file for reading. 'path' is the file to open, and 'mode' should * be either "r" or "rb". * - * If the file at 'path' does not exist, we append the ".gz" suffix (if 'path' - * doesn't already have it) and try again. So if you pass "foo" as 'path', + * If the file at 'path' does not exist, we search with compressed suffix (if 'path' + * doesn't already have one) and try again. So if you pass "foo" as 'path', * this will open either "foo" or "foo.gz". * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_read(const char *path, const char *mode) +cfopen_read(const char *path, const char *mode, Compress *compression) { cfp *fp; -#ifdef HAVE_LIBZ if (hasSuffix(path, ".gz")) - fp = cfopen(path, mode, 1); + fp = cfopen(path, mode, compression); else -#endif { - fp = cfopen(path, mode, 0); -#ifdef HAVE_LIBZ + fp = cfopen(path, mode, compression); if (fp == NULL) { char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); - fp = cfopen(fname, mode, 1); + fname = psprintf("%s%s", path, suffix); + fp = cfopen(fname, mode, compression); free_keep_errno(fname); } -#endif } return fp; } @@ -479,31 +451,26 @@ cfopen_read(const char *path, const char *mode) * be a filemode as accepted by fopen() and gzopen() that indicates writing * ("w", "wb", "a", or "ab"). * - * If 'compression' is non-zero, a gzip compressed stream is opened, and - * 'compression' indicates the compression level used. The ".gz" suffix - * is automatically added to 'path' in that case. + * Use compression if specified. + * The appropriate suffix is automatically added to 'path' in that case. * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_write(const char *path, const char *mode, int compression) +cfopen_write(const char *path, const char *mode, Compress *compression) { cfp *fp; - if (compression == 0) - fp = cfopen(path, mode, 0); + if (compression->alg == COMPR_ALG_NONE) + fp = cfopen(path, mode, compression); else { -#ifdef HAVE_LIBZ char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); + fname = psprintf("%s%s", path, suffix); fp = cfopen(fname, mode, compression); free_keep_errno(fname); -#else - fatal("not built with zlib support"); - fp = NULL; /* keep compiler quiet */ -#endif } return fp; } @@ -515,20 +482,21 @@ cfopen_write(const char *path, const char *mode, int compression) * On failure, return NULL with an error code in errno. */ cfp * -cfopen(const char *path, const char *mode, int compression) +cfopen(const char *path, const char *mode, Compress *compression) { - cfp *fp = pg_malloc(sizeof(cfp)); + cfp *fp = pg_malloc0(sizeof(cfp)); - if (compression != 0) + switch (compression->alg) { #ifdef HAVE_LIBZ - if (compression != Z_DEFAULT_COMPRESSION) + case COMPR_ALG_LIBZ: + if (compression->level != Z_DEFAULT_COMPRESSION) { /* user has specified a compression level, so tell zlib to use it */ char mode_compression[32]; snprintf(mode_compression, sizeof(mode_compression), "%s%d", - mode, compression); + mode, compression->level); fp->compressedfp = gzopen(path, mode_compression); } else @@ -537,30 +505,27 @@ cfopen(const char *path, const char *mode, int compression) fp->compressedfp = gzopen(path, mode); } - fp->uncompressedfp = NULL; if (fp->compressedfp == NULL) { free_keep_errno(fp); fp = NULL; } -#else - fatal("not built with zlib support"); -#endif - } - else - { -#ifdef HAVE_LIBZ - fp->compressedfp = NULL; + return fp; #endif + + case COMPR_ALG_NONE: fp->uncompressedfp = fopen(path, mode); if (fp->uncompressedfp == NULL) { free_keep_errno(fp); fp = NULL; } - } + return fp; - return fp; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } } @@ -584,14 +549,13 @@ cfread(void *ptr, int size, cfp *fp) fatal("could not read from input file: %s", errnum == Z_ERRNO ? strerror(errno) : errmsg); } + return ret; } - else #endif - { - ret = fread(ptr, 1, size, fp->uncompressedfp); - if (ret != size && !feof(fp->uncompressedfp)) - READ_ERROR_EXIT(fp->uncompressedfp); - } + + ret = fread(ptr, 1, size, fp->uncompressedfp); + if (ret != size && !feof(fp->uncompressedfp)) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -601,9 +565,8 @@ cfwrite(const void *ptr, int size, cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzwrite(fp->compressedfp, ptr, size); - else #endif - return fwrite(ptr, 1, size, fp->uncompressedfp); + return fwrite(ptr, 1, size, fp->uncompressedfp); } int @@ -622,15 +585,12 @@ cfgetc(cfp *fp) else fatal("could not read from input file: end of file"); } + return ret; } - else #endif - { - ret = fgetc(fp->uncompressedfp); - if (ret == EOF) - READ_ERROR_EXIT(fp->uncompressedfp); - } - + ret = fgetc(fp->uncompressedfp); + if (ret == EOF) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -640,9 +600,8 @@ cfgets(cfp *fp, char *buf, int len) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzgets(fp->compressedfp, buf, len); - else #endif - return fgets(buf, len, fp->uncompressedfp); + return fgets(buf, len, fp->uncompressedfp); } int @@ -660,15 +619,13 @@ cfclose(cfp *fp) { result = gzclose(fp->compressedfp); fp->compressedfp = NULL; + return result; } - else #endif - { - result = fclose(fp->uncompressedfp); - fp->uncompressedfp = NULL; - } - free_keep_errno(fp); + result = fclose(fp->uncompressedfp); + fp->uncompressedfp = NULL; + free_keep_errno(fp); return result; } @@ -678,9 +635,9 @@ cfeof(cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzeof(fp->compressedfp); - else #endif - return feof(fp->uncompressedfp); + + return feof(fp->uncompressedfp); } const char * @@ -699,7 +656,6 @@ get_cfp_error(cfp *fp) return strerror(errno); } -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix) { @@ -714,4 +670,18 @@ hasSuffix(const char *filename, const char *suffix) suffixlen) == 0; } -#endif +/* + * Return a string for the given AH's compression. + * The string is statically allocated. + */ +const char * +compress_suffix(Compress *compression) +{ + switch (compression->alg) + { + case COMPR_ALG_LIBZ: + return ".gz"; + default: + return ""; + } +} diff --git a/src/bin/pg_dump/compress_io.h b/src/bin/pg_dump/compress_io.h index d2e6e1b854..2c073676eb 100644 --- a/src/bin/pg_dump/compress_io.h +++ b/src/bin/pg_dump/compress_io.h @@ -21,12 +21,6 @@ #define ZLIB_OUT_SIZE 4096 #define ZLIB_IN_SIZE 4096 -typedef enum -{ - COMPR_ALG_NONE, - COMPR_ALG_LIBZ -} CompressionAlgorithm; - /* Prototype for callback function to WriteDataToArchive() */ typedef void (*WriteFunc) (ArchiveHandle *AH, const char *buf, size_t len); @@ -46,8 +40,8 @@ typedef size_t (*ReadFunc) (ArchiveHandle *AH, char **buf, size_t *buflen); /* struct definition appears in compress_io.c */ typedef struct CompressorState CompressorState; -extern CompressorState *AllocateCompressor(int compression, WriteFunc writeF); -extern void ReadDataFromArchive(ArchiveHandle *AH, int compression, +extern CompressorState *AllocateCompressor(Compress *compression, WriteFunc writeF); +extern void ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF); extern void WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, const void *data, size_t dLen); @@ -56,9 +50,9 @@ extern void EndCompressor(ArchiveHandle *AH, CompressorState *cs); typedef struct cfp cfp; -extern cfp *cfopen(const char *path, const char *mode, int compression); -extern cfp *cfopen_read(const char *path, const char *mode); -extern cfp *cfopen_write(const char *path, const char *mode, int compression); +extern cfp *cfopen(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_read(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_write(const char *path, const char *mode, Compress *compression); extern int cfread(void *ptr, int size, cfp *fp); extern int cfwrite(const void *ptr, int size, cfp *fp); extern int cfgetc(cfp *fp); @@ -67,4 +61,7 @@ extern int cfclose(cfp *fp); extern int cfeof(cfp *fp); extern const char *get_cfp_error(cfp *fp); +/* also used by tar */ +extern const char * compress_suffix(Compress *compression); + #endif diff --git a/src/bin/pg_dump/pg_backup.h b/src/bin/pg_dump/pg_backup.h index 9d0056a569..f2390b7937 100644 --- a/src/bin/pg_dump/pg_backup.h +++ b/src/bin/pg_dump/pg_backup.h @@ -72,6 +72,25 @@ typedef struct _connParams char *override_dbname; } ConnParams; +typedef enum +{ + COMPR_ALG_DEFAULT = -1, + COMPR_ALG_NONE, + COMPR_ALG_LIBZ, +} CompressionAlgorithm; +/* Should be called "method" or "library" ? */ + +typedef struct Compress { + CompressionAlgorithm alg; + int level; + /* Is a nondefault level set ? This is useful since different compression + * methods have different "default" levels. For now we assume the levels + * are all integer, though. + */ + bool level_set; +} Compress; + + typedef struct _restoreOptions { int createDB; /* Issue commands to create the database */ @@ -125,7 +144,7 @@ typedef struct _restoreOptions int noDataForFailedTables; int exit_on_error; - int compression; + Compress compression; int suppressDumpWarnings; /* Suppress output of WARNING entries * to stderr */ bool single_txn; @@ -281,7 +300,7 @@ extern Archive *OpenArchive(const char *FileSpec, const ArchiveFormat fmt); /* Create a new archive */ extern Archive *CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker); /* The --list option */ diff --git a/src/bin/pg_dump/pg_backup_archiver.c b/src/bin/pg_dump/pg_backup_archiver.c index 1f82c6499b..3eb6c55600 100644 --- a/src/bin/pg_dump/pg_backup_archiver.c +++ b/src/bin/pg_dump/pg_backup_archiver.c @@ -70,7 +70,7 @@ typedef struct _parallelReadyList static ArchiveHandle *_allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr); static void _getObjectDescription(PQExpBuffer buf, TocEntry *te); static void _printTocEntry(ArchiveHandle *AH, TocEntry *te, bool isData); @@ -98,7 +98,7 @@ static int _discoverArchiveFormat(ArchiveHandle *AH); static int RestoringToDB(ArchiveHandle *AH); static void dump_lo_buf(ArchiveHandle *AH); static void dumpTimestamp(ArchiveHandle *AH, const char *msg, time_t tim); -static void SetOutput(ArchiveHandle *AH, const char *filename, int compression); +static void SetOutput(ArchiveHandle *AH, const char *filename, Compress *compress); static OutputContext SaveOutput(ArchiveHandle *AH); static void RestoreOutput(ArchiveHandle *AH, OutputContext savedContext); @@ -238,7 +238,7 @@ setupRestoreWorker(Archive *AHX) /* Public */ Archive * CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker) { @@ -253,7 +253,9 @@ CreateArchive(const char *FileSpec, const ArchiveFormat fmt, Archive * OpenArchive(const char *FileSpec, const ArchiveFormat fmt) { - ArchiveHandle *AH = _allocAH(FileSpec, fmt, 0, true, archModeRead, setupRestoreWorker); + Compress compress = {0}; + ArchiveHandle *AH = _allocAH(FileSpec, fmt, &compress, true, archModeRead, + setupRestoreWorker); return (Archive *) AH; } @@ -382,7 +384,7 @@ RestoreArchive(Archive *AHX) * Make sure we won't need (de)compression we haven't got */ #ifndef HAVE_LIBZ - if (AH->compression != 0 && AH->PrintTocDataPtr != NULL) + if (AH->compression.alg != COMPR_ALG_NONE && AH->PrintTocDataPtr != NULL) { for (te = AH->toc->next; te != AH->toc; te = te->next) { @@ -457,8 +459,8 @@ RestoreArchive(Archive *AHX) * Setup the output file if necessary. */ sav = SaveOutput(AH); - if (ropt->filename || ropt->compression) - SetOutput(AH, ropt->filename, ropt->compression); + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) + SetOutput(AH, ropt->filename, &ropt->compression); ahprintf(AH, "--\n-- PostgreSQL database dump\n--\n\n"); @@ -738,7 +740,7 @@ RestoreArchive(Archive *AHX) */ AH->stage = STAGE_FINALIZING; - if (ropt->filename || ropt->compression) + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) RestoreOutput(AH, sav); if (ropt->useDB) @@ -1123,8 +1125,9 @@ PrintTOCSummary(Archive *AHX) char stamp_str[64]; sav = SaveOutput(AH); + Assert(ropt->compression.alg == COMPR_ALG_NONE); if (ropt->filename) - SetOutput(AH, ropt->filename, 0 /* no compression */ ); + SetOutput(AH, ropt->filename, &ropt->compression); if (strftime(stamp_str, sizeof(stamp_str), PGDUMP_STRFTIME_FMT, localtime(&AH->createDate)) == 0) @@ -1133,7 +1136,7 @@ PrintTOCSummary(Archive *AHX) ahprintf(AH, ";\n; Archive created at %s\n", stamp_str); ahprintf(AH, "; dbname: %s\n; TOC Entries: %d\n; Compression: %d\n", sanitize_line(AH->archdbname, false), - AH->tocCount, AH->compression); + AH->tocCount, AH->compression.alg); switch (AH->format) { @@ -1487,7 +1490,7 @@ archprintf(Archive *AH, const char *fmt,...) *******************************/ static void -SetOutput(ArchiveHandle *AH, const char *filename, int compression) +SetOutput(ArchiveHandle *AH, const char *filename, Compress *compression) { int fn; @@ -1510,12 +1513,12 @@ SetOutput(ArchiveHandle *AH, const char *filename, int compression) /* If compression explicitly requested, use gzopen */ #ifdef HAVE_LIBZ - if (compression != 0) + if (compression->alg != COMPR_ALG_NONE) { char fmode[14]; /* Don't use PG_BINARY_x since this is zlib */ - sprintf(fmode, "wb%d", compression); + sprintf(fmode, "wb%d", compression->level); if (fn >= 0) AH->OF = gzdopen(dup(fn), fmode); else @@ -2259,7 +2262,7 @@ _discoverArchiveFormat(ArchiveHandle *AH) */ static ArchiveHandle * _allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr) { ArchiveHandle *AH; @@ -2310,7 +2313,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, AH->toc->prev = AH->toc; AH->mode = mode; - AH->compression = compression; + AH->compression = *compression; AH->dosync = dosync; memset(&(AH->sqlparse), 0, sizeof(AH->sqlparse)); @@ -2325,7 +2328,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, * Force stdin/stdout into binary mode if that is what we are using. */ #ifdef WIN32 - if ((fmt != archNull || compression != 0) && + if ((fmt != archNull || compression->alg != COMPR_ALG_NONE) && (AH->fSpec == NULL || strcmp(AH->fSpec, "") == 0)) { if (mode == archModeWrite) @@ -3741,7 +3744,7 @@ WriteHead(ArchiveHandle *AH) AH->WriteBytePtr(AH, AH->intSize); AH->WriteBytePtr(AH, AH->offSize); AH->WriteBytePtr(AH, AH->format); - WriteInt(AH, AH->compression); + WriteInt(AH, AH->compression.alg); crtm = *localtime(&AH->createDate); WriteInt(AH, crtm.tm_sec); WriteInt(AH, crtm.tm_min); @@ -3816,15 +3819,15 @@ ReadHead(ArchiveHandle *AH) if (AH->version >= K_VERS_1_2) { if (AH->version < K_VERS_1_4) - AH->compression = AH->ReadBytePtr(AH); + AH->compression.alg = AH->ReadBytePtr(AH); else - AH->compression = ReadInt(AH); + AH->compression.alg = ReadInt(AH); } else - AH->compression = Z_DEFAULT_COMPRESSION; + AH->compression.alg = Z_DEFAULT_COMPRESSION; #ifndef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) pg_log_warning("archive is compressed, but this installation does not support compression -- no data will be available"); #endif diff --git a/src/bin/pg_dump/pg_backup_archiver.h b/src/bin/pg_dump/pg_backup_archiver.h index a8ea5c7eae..6e033d040e 100644 --- a/src/bin/pg_dump/pg_backup_archiver.h +++ b/src/bin/pg_dump/pg_backup_archiver.h @@ -47,7 +47,8 @@ #define GZWRITE(p, s, n, fh) (fwrite(p, s, n, fh) * (s)) #define GZREAD(p, s, n, fh) fread(p, s, n, fh) #define GZEOF(fh) feof(fh) -/* this is just the redefinition of a libz constant */ +/* this is just the redefinition of a libz constant, in case zlib isn't + * available */ #define Z_DEFAULT_COMPRESSION (-1) typedef struct _z_stream @@ -329,14 +330,7 @@ struct _archiveHandle DumpId *tableDataId; /* TABLE DATA ids, indexed by table dumpId */ struct _tocEntry *currToc; /* Used when dumping data */ - int compression; /*--------- - * Compression requested on open(). - * Possible values for compression: - * -1 Z_DEFAULT_COMPRESSION - * 0 COMPRESSION_NONE - * 1-9 levels for gzip compression - *--------- - */ + Compress compression; /* Compression requested on open */ bool dosync; /* data requested to be synced on sight */ ArchiveMode mode; /* File mode - r or w */ void *formatData; /* Header data specific to file format */ diff --git a/src/bin/pg_dump/pg_backup_custom.c b/src/bin/pg_dump/pg_backup_custom.c index 77d402c323..55a887a236 100644 --- a/src/bin/pg_dump/pg_backup_custom.c +++ b/src/bin/pg_dump/pg_backup_custom.c @@ -298,7 +298,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) _WriteByte(AH, BLK_DATA); /* Block type */ WriteInt(AH, te->dumpId); /* For sanity check */ - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -377,7 +377,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) WriteInt(AH, oid); - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -566,7 +566,7 @@ _PrintTocData(ArchiveHandle *AH, TocEntry *te) static void _PrintData(ArchiveHandle *AH) { - ReadDataFromArchive(AH, AH->compression, _CustomReadFunc); + ReadDataFromArchive(AH, _CustomReadFunc); } static void diff --git a/src/bin/pg_dump/pg_backup_directory.c b/src/bin/pg_dump/pg_backup_directory.c index 650b542fce..8bf869c6ca 100644 --- a/src/bin/pg_dump/pg_backup_directory.c +++ b/src/bin/pg_dump/pg_backup_directory.c @@ -202,7 +202,7 @@ InitArchiveFmt_Directory(ArchiveHandle *AH) setFilePath(AH, fname, "toc.dat"); - tocFH = cfopen_read(fname, PG_BINARY_R); + tocFH = cfopen_read(fname, PG_BINARY_R, &AH->compression); if (tocFH == NULL) fatal("could not open input file \"%s\": %m", fname); @@ -327,7 +327,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) setFilePath(AH, fname, tctx->filename); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -388,7 +388,7 @@ _PrintFileData(ArchiveHandle *AH, char *filename) if (!filename) return; - cfp = cfopen_read(filename, PG_BINARY_R); + cfp = cfopen_read(filename, PG_BINARY_R, &AH->compression); if (!cfp) fatal("could not open input file \"%s\": %m", filename); @@ -435,12 +435,13 @@ _LoadBlobs(ArchiveHandle *AH) lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; char line[MAXPGPATH]; + Compress nocompression = {0}; StartRestoreBlobs(AH); setFilePath(AH, fname, "blobs.toc"); - ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R); + ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R, &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open large object TOC file \"%s\" for input: %m", @@ -573,6 +574,7 @@ _CloseArchive(ArchiveHandle *AH) { cfp *tocFH; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "toc.dat"); @@ -580,7 +582,7 @@ _CloseArchive(ArchiveHandle *AH) ctx->pstate = ParallelBackupStart(AH); /* The TOC is always created uncompressed */ - tocFH = cfopen_write(fname, PG_BINARY_W, 0); + tocFH = cfopen_write(fname, PG_BINARY_W, &nocompression); if (tocFH == NULL) fatal("could not open output file \"%s\": %m", fname); ctx->dataFH = tocFH; @@ -639,11 +641,12 @@ _StartBlobs(ArchiveHandle *AH, TocEntry *te) { lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "blobs.toc"); /* The blob TOC file is never compressed */ - ctx->blobsTocFH = cfopen_write(fname, "ab", 0); + ctx->blobsTocFH = cfopen_write(fname, "ab", &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -661,7 +664,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) snprintf(fname, MAXPGPATH, "%s/blob_%u.dat", ctx->directory, oid); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); diff --git a/src/bin/pg_dump/pg_backup_tar.c b/src/bin/pg_dump/pg_backup_tar.c index 61c9c87a9f..4ba79ab924 100644 --- a/src/bin/pg_dump/pg_backup_tar.c +++ b/src/bin/pg_dump/pg_backup_tar.c @@ -39,6 +39,7 @@ #include "pg_backup_archiver.h" #include "pg_backup_tar.h" #include "pg_backup_utils.h" +#include "compress_io.h" #include "pgtar.h" static void _ArchiveEntry(ArchiveHandle *AH, TocEntry *te); @@ -196,10 +197,10 @@ InitArchiveFmt_Tar(ArchiveHandle *AH) /* * We don't support compression because reading the files back is not - * possible since gzdopen uses buffered IO which totally screws file + * possible since gzdopen uses buffered IO which totally screws file XXX * positioning. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) fatal("compression is not supported by tar archive format"); } else @@ -254,14 +255,8 @@ _ArchiveEntry(ArchiveHandle *AH, TocEntry *te) ctx = (lclTocEntry *) pg_malloc0(sizeof(lclTocEntry)); if (te->dataDumper != NULL) { -#ifdef HAVE_LIBZ - if (AH->compression == 0) - sprintf(fn, "%d.dat", te->dumpId); - else - sprintf(fn, "%d.dat.gz", te->dumpId); -#else - sprintf(fn, "%d.dat", te->dumpId); -#endif + const char *suffix = compress_suffix(&AH->compression); + sprintf(fn, "%d.dat%s", te->dumpId, suffix); ctx->filename = pg_strdup(fn); } else @@ -352,7 +347,7 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression == 0) + if (AH->compression.alg == COMPR_ALG_NONE) tm->nFH = ctx->tarFH; else fatal("compression is not supported by tar archive format"); @@ -413,9 +408,9 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) { - sprintf(fmode, "wb%d", AH->compression); + sprintf(fmode, "wb%d", AH->compression.level); tm->zFH = gzdopen(dup(fileno(tm->tmpFH)), fmode); if (tm->zFH == NULL) fatal("could not open temporary file"); @@ -443,7 +438,7 @@ tarClose(ArchiveHandle *AH, TAR_MEMBER *th) /* * Close the GZ file since we dup'd. This will flush the buffers. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) if (GZCLOSE(th->zFH) != 0) fatal("could not close tar member"); @@ -868,7 +863,7 @@ _CloseArchive(ArchiveHandle *AH) memcpy(ropt, AH->public.ropt, sizeof(RestoreOptions)); ropt->filename = NULL; ropt->dropSchema = 1; - ropt->compression = 0; + ropt->compression.alg = COMPR_ALG_NONE; ropt->superuser = NULL; ropt->suppressDumpWarnings = true; @@ -952,16 +947,12 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) lclContext *ctx = (lclContext *) AH->formatData; lclTocEntry *tctx = (lclTocEntry *) te->formatData; char fname[255]; - char *sfx; + const char *sfx; if (oid == 0) fatal("invalid OID for large object (%u)", oid); - if (AH->compression != 0) - sfx = ".gz"; - else - sfx = ""; - + sfx = compress_suffix(&AH->compression); sprintf(fname, "blob_%u.dat%s", oid, sfx); tarPrintf(ctx->blobToc, "%u %s\n", oid, fname); diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c index 1ab98a2286..4cbc79aedc 100644 --- a/src/bin/pg_dump/pg_dump.c +++ b/src/bin/pg_dump/pg_dump.c @@ -59,6 +59,7 @@ #include "getopt_long.h" #include "libpq/libpq-fs.h" #include "parallel.h" +#include "compress_io.h" #include "pg_backup_db.h" #include "pg_backup_utils.h" #include "pg_dump.h" @@ -297,6 +298,82 @@ static void setupDumpWorker(Archive *AHX); static TableInfo *getRootTableInfo(TableInfo *tbinfo); +/* Parse the string into compression options */ +static void +parse_compression(const char *optarg, Compress *compress) +{ + if (optarg[0] == '0' && optarg[1] == '\0') + compress->alg = COMPR_ALG_NONE; + else if ((optarg[0] > '0' && optarg[0] <= '9') || + optarg[0] == '-') + { + compress->alg = COMPR_ALG_LIBZ; + compress->level_set = true; + compress->level = atoi(optarg); + if (optarg[1] != '\0') + { + pg_log_error("compression level must be in range 0..9"); + exit_nicely(1); + } + } + else + { + /* Parse a more flexible string like level=3 alg=zlib opts=long */ + for (;;) + { + char *eq = strchr(optarg, '='); + int len; + + if (eq == NULL) + { + pg_log_error("compression options must be key=value: %s", optarg); + exit_nicely(1); + } + + len = eq - optarg; + if (strncmp(optarg, "alg", len) == 0) + { + if (strchr(eq, ' ')) + len = strchr(eq, ' ') - eq - 1; + else + len = strlen(eq) - len; + if (strncmp(1+eq, "zlib", len) == 0 || + strncmp(1+eq, "libz", len) == 0) + compress->alg = COMPR_ALG_LIBZ; + else + { + pg_log_error("unknown compression algorithm: %s", 1+eq); + exit_nicely(1); + } + } + else if (strncmp(optarg, "level", len) == 0) + { + compress->level = atoi(1+eq); + compress->level_set = true; + } + else + { + pg_log_error("unknown compression setting: %s", optarg); + exit_nicely(1); + } + + optarg = strchr(eq, ' '); + if (!optarg++) + break; + } + + if (!compress->level_set) + { + const int default_compress_level[] = { + 0, /* COMPR_ALG_NONE */ + Z_DEFAULT_COMPRESSION, /* COMPR_ALG_ZLIB */ + }; + + compress->level = default_compress_level[compress->alg]; + } + } +} + int main(int argc, char **argv) { @@ -319,7 +396,7 @@ main(int argc, char **argv) char *use_role = NULL; long rowsPerInsert; int numWorkers = 1; - int compressLevel = -1; + Compress compress = { .alg = COMPR_ALG_DEFAULT }; int plainText = 0; ArchiveFormat archiveFormat = archUnknown; ArchiveMode archiveMode; @@ -532,12 +609,7 @@ main(int argc, char **argv) break; case 'Z': /* Compression Level */ - compressLevel = atoi(optarg); - if (compressLevel < 0 || compressLevel > 9) - { - pg_log_error("compression level must be in range 0..9"); - exit_nicely(1); - } + parse_compression(optarg, &compress); break; case 0: @@ -679,20 +751,28 @@ main(int argc, char **argv) plainText = 1; /* Custom and directory formats are compressed by default, others not */ - if (compressLevel == -1) + if (compress.alg == COMPR_ALG_DEFAULT) { -#ifdef HAVE_LIBZ if (archiveFormat == archCustom || archiveFormat == archDirectory) - compressLevel = Z_DEFAULT_COMPRESSION; - else + { +#ifdef HAVE_LIBZ + compress.alg = COMPR_ALG_LIBZ; + compress.level = Z_DEFAULT_COMPRESSION; #endif - compressLevel = 0; + } + else + { + compress.alg = COMPR_ALG_NONE; + compress.level = 0; + } } #ifndef HAVE_LIBZ - if (compressLevel != 0) + if (compress.alg == COMPR_ALG_LIBZ) + { pg_log_warning("requested compression not available in this installation -- archive will be uncompressed"); - compressLevel = 0; + compress.alg = 0; + } #endif /* @@ -723,7 +803,7 @@ main(int argc, char **argv) fatal("option --index-collation-versions-unknown only works in binary upgrade mode"); /* Open the output file */ - fout = CreateArchive(filename, archiveFormat, compressLevel, dosync, + fout = CreateArchive(filename, archiveFormat, &compress, dosync, archiveMode, setupDumpWorker); /* Make dump options accessible right away */ @@ -957,10 +1037,7 @@ main(int argc, char **argv) ropt->sequence_data = dopt.sequence_data; ropt->binary_upgrade = dopt.binary_upgrade; - if (compressLevel == -1) - ropt->compression = 0; - else - ropt->compression = compressLevel; + ropt->compression = compress; ropt->suppressDumpWarnings = true; /* We've already shown them */ -- 2.17.0 --GRPZ8SYKNexpdSJ7 Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="0004-struct-compressLibs.patch" ^ permalink raw reply [nested|flat] 23+ messages in thread
* [PATCH 03/20] Support multiple compression algs/levels/opts.. @ 2020-12-22 06:23 Justin Pryzby <[email protected]> 0 siblings, 0 replies; 23+ messages in thread From: Justin Pryzby @ 2020-12-22 06:23 UTC (permalink / raw) The existing implementation abtracts compressed and noncompressed I/O. This preliminary commit is intended to also allow for multiple compression algorithms. --- src/bin/pg_dump/compress_io.c | 220 +++++++++++--------------- src/bin/pg_dump/compress_io.h | 19 +-- src/bin/pg_dump/pg_backup.h | 23 ++- src/bin/pg_dump/pg_backup_archiver.c | 45 +++--- src/bin/pg_dump/pg_backup_archiver.h | 12 +- src/bin/pg_dump/pg_backup_custom.c | 6 +- src/bin/pg_dump/pg_backup_directory.c | 17 +- src/bin/pg_dump/pg_backup_tar.c | 33 ++-- src/bin/pg_dump/pg_dump.c | 115 +++++++++++--- 9 files changed, 272 insertions(+), 218 deletions(-) diff --git a/src/bin/pg_dump/compress_io.c b/src/bin/pg_dump/compress_io.c index 6a428978d4..db16fd33f2 100644 --- a/src/bin/pg_dump/compress_io.c +++ b/src/bin/pg_dump/compress_io.c @@ -74,12 +74,9 @@ struct CompressorState #endif }; -static void ParseCompressionOption(int compression, CompressionAlgorithm *alg, - int *level); - /* Routines that support zlib compressed data I/O */ #ifdef HAVE_LIBZ -static void InitCompressorZlib(CompressorState *cs, int level); +static void InitCompressorZlib(CompressorState *cs, Compress *compress); static void DeflateCompressorZlib(ArchiveHandle *AH, CompressorState *cs, bool flush); static void ReadDataFromArchiveZlib(ArchiveHandle *AH, ReadFunc readF); @@ -93,58 +90,36 @@ static void ReadDataFromArchiveNone(ArchiveHandle *AH, ReadFunc readF); static void WriteDataToArchiveNone(ArchiveHandle *AH, CompressorState *cs, const char *data, size_t dLen); -/* - * Interprets a numeric 'compression' value. The algorithm implied by the - * value (zlib or none at the moment), is returned in *alg, and the - * zlib compression level in *level. - */ -static void -ParseCompressionOption(int compression, CompressionAlgorithm *alg, int *level) -{ - if (compression == Z_DEFAULT_COMPRESSION || - (compression > 0 && compression <= 9)) - *alg = COMPR_ALG_LIBZ; - else if (compression == 0) - *alg = COMPR_ALG_NONE; - else - { - fatal("invalid compression code: %d", compression); - *alg = COMPR_ALG_NONE; /* keep compiler quiet */ - } - - /* The level is just the passed-in value. */ - if (level) - *level = compression; -} - /* Public interface routines */ /* Allocate a new compressor */ CompressorState * -AllocateCompressor(int compression, WriteFunc writeF) +AllocateCompressor(Compress *compression, WriteFunc writeF) { CompressorState *cs; - CompressionAlgorithm alg; - int level; - - ParseCompressionOption(compression, &alg, &level); - -#ifndef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - fatal("not built with zlib support"); -#endif cs = (CompressorState *) pg_malloc0(sizeof(CompressorState)); cs->writeF = writeF; - cs->comprAlg = alg; + cs->comprAlg = compression->alg; /* * Perform compression algorithm specific initialization. */ + Assert (compression->alg != COMPR_ALG_DEFAULT); + switch (compression->alg) + { #ifdef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - InitCompressorZlib(cs, level); + case COMPR_ALG_LIBZ: + InitCompressorZlib(cs, compression); + break; #endif + case COMPR_ALG_NONE: + /* Do nothing */ + break; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } return cs; } @@ -154,21 +129,21 @@ AllocateCompressor(int compression, WriteFunc writeF) * out with ahwrite(). */ void -ReadDataFromArchive(ArchiveHandle *AH, int compression, ReadFunc readF) +ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF) { - CompressionAlgorithm alg; - - ParseCompressionOption(compression, &alg, NULL); - - if (alg == COMPR_ALG_NONE) - ReadDataFromArchiveNone(AH, readF); - if (alg == COMPR_ALG_LIBZ) + switch (AH->compression.alg) { + case COMPR_ALG_NONE: + ReadDataFromArchiveNone(AH, readF); + break; #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: ReadDataFromArchiveZlib(AH, readF); -#else - fatal("not built with zlib support"); + break; #endif + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -181,16 +156,18 @@ WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, { switch (cs->comprAlg) { - case COMPR_ALG_LIBZ: #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: WriteDataToArchiveZlib(AH, cs, data, dLen); -#else - fatal("not built with zlib support"); -#endif break; +#endif case COMPR_ALG_NONE: WriteDataToArchiveNone(AH, cs, data, dLen); break; + + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -215,7 +192,7 @@ EndCompressor(ArchiveHandle *AH, CompressorState *cs) */ static void -InitCompressorZlib(CompressorState *cs, int level) +InitCompressorZlib(CompressorState *cs, Compress *compress) { z_streamp zp; @@ -232,7 +209,7 @@ InitCompressorZlib(CompressorState *cs, int level) cs->zlibOut = (char *) pg_malloc(ZLIB_OUT_SIZE + 1); cs->zlibOutSize = ZLIB_OUT_SIZE; - if (deflateInit(zp, level) != Z_OK) + if (deflateInit(zp, compress->level) != Z_OK) fatal("could not initialize compression library: %s", zp->msg); @@ -424,9 +401,7 @@ struct cfp #endif }; -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix); -#endif /* free() without changing errno; useful in several places below */ static void @@ -442,34 +417,31 @@ free_keep_errno(void *p) * Open a file for reading. 'path' is the file to open, and 'mode' should * be either "r" or "rb". * - * If the file at 'path' does not exist, we append the ".gz" suffix (if 'path' - * doesn't already have it) and try again. So if you pass "foo" as 'path', + * If the file at 'path' does not exist, we search with compressed suffix (if 'path' + * doesn't already have one) and try again. So if you pass "foo" as 'path', * this will open either "foo" or "foo.gz". * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_read(const char *path, const char *mode) +cfopen_read(const char *path, const char *mode, Compress *compression) { cfp *fp; -#ifdef HAVE_LIBZ if (hasSuffix(path, ".gz")) - fp = cfopen(path, mode, 1); + fp = cfopen(path, mode, compression); else -#endif { - fp = cfopen(path, mode, 0); -#ifdef HAVE_LIBZ + fp = cfopen(path, mode, compression); if (fp == NULL) { char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); - fp = cfopen(fname, mode, 1); + fname = psprintf("%s%s", path, suffix); + fp = cfopen(fname, mode, compression); free_keep_errno(fname); } -#endif } return fp; } @@ -479,31 +451,26 @@ cfopen_read(const char *path, const char *mode) * be a filemode as accepted by fopen() and gzopen() that indicates writing * ("w", "wb", "a", or "ab"). * - * If 'compression' is non-zero, a gzip compressed stream is opened, and - * 'compression' indicates the compression level used. The ".gz" suffix - * is automatically added to 'path' in that case. + * Use compression if specified. + * The appropriate suffix is automatically added to 'path' in that case. * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_write(const char *path, const char *mode, int compression) +cfopen_write(const char *path, const char *mode, Compress *compression) { cfp *fp; - if (compression == 0) - fp = cfopen(path, mode, 0); + if (compression->alg == COMPR_ALG_NONE) + fp = cfopen(path, mode, compression); else { -#ifdef HAVE_LIBZ char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); + fname = psprintf("%s%s", path, suffix); fp = cfopen(fname, mode, compression); free_keep_errno(fname); -#else - fatal("not built with zlib support"); - fp = NULL; /* keep compiler quiet */ -#endif } return fp; } @@ -515,20 +482,21 @@ cfopen_write(const char *path, const char *mode, int compression) * On failure, return NULL with an error code in errno. */ cfp * -cfopen(const char *path, const char *mode, int compression) +cfopen(const char *path, const char *mode, Compress *compression) { - cfp *fp = pg_malloc(sizeof(cfp)); + cfp *fp = pg_malloc0(sizeof(cfp)); - if (compression != 0) + switch (compression->alg) { #ifdef HAVE_LIBZ - if (compression != Z_DEFAULT_COMPRESSION) + case COMPR_ALG_LIBZ: + if (compression->level != Z_DEFAULT_COMPRESSION) { /* user has specified a compression level, so tell zlib to use it */ char mode_compression[32]; snprintf(mode_compression, sizeof(mode_compression), "%s%d", - mode, compression); + mode, compression->level); fp->compressedfp = gzopen(path, mode_compression); } else @@ -537,30 +505,27 @@ cfopen(const char *path, const char *mode, int compression) fp->compressedfp = gzopen(path, mode); } - fp->uncompressedfp = NULL; if (fp->compressedfp == NULL) { free_keep_errno(fp); fp = NULL; } -#else - fatal("not built with zlib support"); -#endif - } - else - { -#ifdef HAVE_LIBZ - fp->compressedfp = NULL; + return fp; #endif + + case COMPR_ALG_NONE: fp->uncompressedfp = fopen(path, mode); if (fp->uncompressedfp == NULL) { free_keep_errno(fp); fp = NULL; } - } + return fp; - return fp; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } } @@ -584,14 +549,13 @@ cfread(void *ptr, int size, cfp *fp) fatal("could not read from input file: %s", errnum == Z_ERRNO ? strerror(errno) : errmsg); } + return ret; } - else #endif - { - ret = fread(ptr, 1, size, fp->uncompressedfp); - if (ret != size && !feof(fp->uncompressedfp)) - READ_ERROR_EXIT(fp->uncompressedfp); - } + + ret = fread(ptr, 1, size, fp->uncompressedfp); + if (ret != size && !feof(fp->uncompressedfp)) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -601,9 +565,8 @@ cfwrite(const void *ptr, int size, cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzwrite(fp->compressedfp, ptr, size); - else #endif - return fwrite(ptr, 1, size, fp->uncompressedfp); + return fwrite(ptr, 1, size, fp->uncompressedfp); } int @@ -622,15 +585,12 @@ cfgetc(cfp *fp) else fatal("could not read from input file: end of file"); } + return ret; } - else #endif - { - ret = fgetc(fp->uncompressedfp); - if (ret == EOF) - READ_ERROR_EXIT(fp->uncompressedfp); - } - + ret = fgetc(fp->uncompressedfp); + if (ret == EOF) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -640,9 +600,8 @@ cfgets(cfp *fp, char *buf, int len) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzgets(fp->compressedfp, buf, len); - else #endif - return fgets(buf, len, fp->uncompressedfp); + return fgets(buf, len, fp->uncompressedfp); } int @@ -660,15 +619,13 @@ cfclose(cfp *fp) { result = gzclose(fp->compressedfp); fp->compressedfp = NULL; + return result; } - else #endif - { - result = fclose(fp->uncompressedfp); - fp->uncompressedfp = NULL; - } - free_keep_errno(fp); + result = fclose(fp->uncompressedfp); + fp->uncompressedfp = NULL; + free_keep_errno(fp); return result; } @@ -678,9 +635,9 @@ cfeof(cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzeof(fp->compressedfp); - else #endif - return feof(fp->uncompressedfp); + + return feof(fp->uncompressedfp); } const char * @@ -699,7 +656,6 @@ get_cfp_error(cfp *fp) return strerror(errno); } -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix) { @@ -714,4 +670,18 @@ hasSuffix(const char *filename, const char *suffix) suffixlen) == 0; } -#endif +/* + * Return a string for the given AH's compression. + * The string is statically allocated. + */ +const char * +compress_suffix(Compress *compression) +{ + switch (compression->alg) + { + case COMPR_ALG_LIBZ: + return ".gz"; + default: + return ""; + } +} diff --git a/src/bin/pg_dump/compress_io.h b/src/bin/pg_dump/compress_io.h index d2e6e1b854..2c073676eb 100644 --- a/src/bin/pg_dump/compress_io.h +++ b/src/bin/pg_dump/compress_io.h @@ -21,12 +21,6 @@ #define ZLIB_OUT_SIZE 4096 #define ZLIB_IN_SIZE 4096 -typedef enum -{ - COMPR_ALG_NONE, - COMPR_ALG_LIBZ -} CompressionAlgorithm; - /* Prototype for callback function to WriteDataToArchive() */ typedef void (*WriteFunc) (ArchiveHandle *AH, const char *buf, size_t len); @@ -46,8 +40,8 @@ typedef size_t (*ReadFunc) (ArchiveHandle *AH, char **buf, size_t *buflen); /* struct definition appears in compress_io.c */ typedef struct CompressorState CompressorState; -extern CompressorState *AllocateCompressor(int compression, WriteFunc writeF); -extern void ReadDataFromArchive(ArchiveHandle *AH, int compression, +extern CompressorState *AllocateCompressor(Compress *compression, WriteFunc writeF); +extern void ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF); extern void WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, const void *data, size_t dLen); @@ -56,9 +50,9 @@ extern void EndCompressor(ArchiveHandle *AH, CompressorState *cs); typedef struct cfp cfp; -extern cfp *cfopen(const char *path, const char *mode, int compression); -extern cfp *cfopen_read(const char *path, const char *mode); -extern cfp *cfopen_write(const char *path, const char *mode, int compression); +extern cfp *cfopen(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_read(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_write(const char *path, const char *mode, Compress *compression); extern int cfread(void *ptr, int size, cfp *fp); extern int cfwrite(const void *ptr, int size, cfp *fp); extern int cfgetc(cfp *fp); @@ -67,4 +61,7 @@ extern int cfclose(cfp *fp); extern int cfeof(cfp *fp); extern const char *get_cfp_error(cfp *fp); +/* also used by tar */ +extern const char * compress_suffix(Compress *compression); + #endif diff --git a/src/bin/pg_dump/pg_backup.h b/src/bin/pg_dump/pg_backup.h index 9d0056a569..f2390b7937 100644 --- a/src/bin/pg_dump/pg_backup.h +++ b/src/bin/pg_dump/pg_backup.h @@ -72,6 +72,25 @@ typedef struct _connParams char *override_dbname; } ConnParams; +typedef enum +{ + COMPR_ALG_DEFAULT = -1, + COMPR_ALG_NONE, + COMPR_ALG_LIBZ, +} CompressionAlgorithm; +/* Should be called "method" or "library" ? */ + +typedef struct Compress { + CompressionAlgorithm alg; + int level; + /* Is a nondefault level set ? This is useful since different compression + * methods have different "default" levels. For now we assume the levels + * are all integer, though. + */ + bool level_set; +} Compress; + + typedef struct _restoreOptions { int createDB; /* Issue commands to create the database */ @@ -125,7 +144,7 @@ typedef struct _restoreOptions int noDataForFailedTables; int exit_on_error; - int compression; + Compress compression; int suppressDumpWarnings; /* Suppress output of WARNING entries * to stderr */ bool single_txn; @@ -281,7 +300,7 @@ extern Archive *OpenArchive(const char *FileSpec, const ArchiveFormat fmt); /* Create a new archive */ extern Archive *CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker); /* The --list option */ diff --git a/src/bin/pg_dump/pg_backup_archiver.c b/src/bin/pg_dump/pg_backup_archiver.c index 1f82c6499b..3eb6c55600 100644 --- a/src/bin/pg_dump/pg_backup_archiver.c +++ b/src/bin/pg_dump/pg_backup_archiver.c @@ -70,7 +70,7 @@ typedef struct _parallelReadyList static ArchiveHandle *_allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr); static void _getObjectDescription(PQExpBuffer buf, TocEntry *te); static void _printTocEntry(ArchiveHandle *AH, TocEntry *te, bool isData); @@ -98,7 +98,7 @@ static int _discoverArchiveFormat(ArchiveHandle *AH); static int RestoringToDB(ArchiveHandle *AH); static void dump_lo_buf(ArchiveHandle *AH); static void dumpTimestamp(ArchiveHandle *AH, const char *msg, time_t tim); -static void SetOutput(ArchiveHandle *AH, const char *filename, int compression); +static void SetOutput(ArchiveHandle *AH, const char *filename, Compress *compress); static OutputContext SaveOutput(ArchiveHandle *AH); static void RestoreOutput(ArchiveHandle *AH, OutputContext savedContext); @@ -238,7 +238,7 @@ setupRestoreWorker(Archive *AHX) /* Public */ Archive * CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker) { @@ -253,7 +253,9 @@ CreateArchive(const char *FileSpec, const ArchiveFormat fmt, Archive * OpenArchive(const char *FileSpec, const ArchiveFormat fmt) { - ArchiveHandle *AH = _allocAH(FileSpec, fmt, 0, true, archModeRead, setupRestoreWorker); + Compress compress = {0}; + ArchiveHandle *AH = _allocAH(FileSpec, fmt, &compress, true, archModeRead, + setupRestoreWorker); return (Archive *) AH; } @@ -382,7 +384,7 @@ RestoreArchive(Archive *AHX) * Make sure we won't need (de)compression we haven't got */ #ifndef HAVE_LIBZ - if (AH->compression != 0 && AH->PrintTocDataPtr != NULL) + if (AH->compression.alg != COMPR_ALG_NONE && AH->PrintTocDataPtr != NULL) { for (te = AH->toc->next; te != AH->toc; te = te->next) { @@ -457,8 +459,8 @@ RestoreArchive(Archive *AHX) * Setup the output file if necessary. */ sav = SaveOutput(AH); - if (ropt->filename || ropt->compression) - SetOutput(AH, ropt->filename, ropt->compression); + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) + SetOutput(AH, ropt->filename, &ropt->compression); ahprintf(AH, "--\n-- PostgreSQL database dump\n--\n\n"); @@ -738,7 +740,7 @@ RestoreArchive(Archive *AHX) */ AH->stage = STAGE_FINALIZING; - if (ropt->filename || ropt->compression) + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) RestoreOutput(AH, sav); if (ropt->useDB) @@ -1123,8 +1125,9 @@ PrintTOCSummary(Archive *AHX) char stamp_str[64]; sav = SaveOutput(AH); + Assert(ropt->compression.alg == COMPR_ALG_NONE); if (ropt->filename) - SetOutput(AH, ropt->filename, 0 /* no compression */ ); + SetOutput(AH, ropt->filename, &ropt->compression); if (strftime(stamp_str, sizeof(stamp_str), PGDUMP_STRFTIME_FMT, localtime(&AH->createDate)) == 0) @@ -1133,7 +1136,7 @@ PrintTOCSummary(Archive *AHX) ahprintf(AH, ";\n; Archive created at %s\n", stamp_str); ahprintf(AH, "; dbname: %s\n; TOC Entries: %d\n; Compression: %d\n", sanitize_line(AH->archdbname, false), - AH->tocCount, AH->compression); + AH->tocCount, AH->compression.alg); switch (AH->format) { @@ -1487,7 +1490,7 @@ archprintf(Archive *AH, const char *fmt,...) *******************************/ static void -SetOutput(ArchiveHandle *AH, const char *filename, int compression) +SetOutput(ArchiveHandle *AH, const char *filename, Compress *compression) { int fn; @@ -1510,12 +1513,12 @@ SetOutput(ArchiveHandle *AH, const char *filename, int compression) /* If compression explicitly requested, use gzopen */ #ifdef HAVE_LIBZ - if (compression != 0) + if (compression->alg != COMPR_ALG_NONE) { char fmode[14]; /* Don't use PG_BINARY_x since this is zlib */ - sprintf(fmode, "wb%d", compression); + sprintf(fmode, "wb%d", compression->level); if (fn >= 0) AH->OF = gzdopen(dup(fn), fmode); else @@ -2259,7 +2262,7 @@ _discoverArchiveFormat(ArchiveHandle *AH) */ static ArchiveHandle * _allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr) { ArchiveHandle *AH; @@ -2310,7 +2313,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, AH->toc->prev = AH->toc; AH->mode = mode; - AH->compression = compression; + AH->compression = *compression; AH->dosync = dosync; memset(&(AH->sqlparse), 0, sizeof(AH->sqlparse)); @@ -2325,7 +2328,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, * Force stdin/stdout into binary mode if that is what we are using. */ #ifdef WIN32 - if ((fmt != archNull || compression != 0) && + if ((fmt != archNull || compression->alg != COMPR_ALG_NONE) && (AH->fSpec == NULL || strcmp(AH->fSpec, "") == 0)) { if (mode == archModeWrite) @@ -3741,7 +3744,7 @@ WriteHead(ArchiveHandle *AH) AH->WriteBytePtr(AH, AH->intSize); AH->WriteBytePtr(AH, AH->offSize); AH->WriteBytePtr(AH, AH->format); - WriteInt(AH, AH->compression); + WriteInt(AH, AH->compression.alg); crtm = *localtime(&AH->createDate); WriteInt(AH, crtm.tm_sec); WriteInt(AH, crtm.tm_min); @@ -3816,15 +3819,15 @@ ReadHead(ArchiveHandle *AH) if (AH->version >= K_VERS_1_2) { if (AH->version < K_VERS_1_4) - AH->compression = AH->ReadBytePtr(AH); + AH->compression.alg = AH->ReadBytePtr(AH); else - AH->compression = ReadInt(AH); + AH->compression.alg = ReadInt(AH); } else - AH->compression = Z_DEFAULT_COMPRESSION; + AH->compression.alg = Z_DEFAULT_COMPRESSION; #ifndef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) pg_log_warning("archive is compressed, but this installation does not support compression -- no data will be available"); #endif diff --git a/src/bin/pg_dump/pg_backup_archiver.h b/src/bin/pg_dump/pg_backup_archiver.h index a8ea5c7eae..6e033d040e 100644 --- a/src/bin/pg_dump/pg_backup_archiver.h +++ b/src/bin/pg_dump/pg_backup_archiver.h @@ -47,7 +47,8 @@ #define GZWRITE(p, s, n, fh) (fwrite(p, s, n, fh) * (s)) #define GZREAD(p, s, n, fh) fread(p, s, n, fh) #define GZEOF(fh) feof(fh) -/* this is just the redefinition of a libz constant */ +/* this is just the redefinition of a libz constant, in case zlib isn't + * available */ #define Z_DEFAULT_COMPRESSION (-1) typedef struct _z_stream @@ -329,14 +330,7 @@ struct _archiveHandle DumpId *tableDataId; /* TABLE DATA ids, indexed by table dumpId */ struct _tocEntry *currToc; /* Used when dumping data */ - int compression; /*--------- - * Compression requested on open(). - * Possible values for compression: - * -1 Z_DEFAULT_COMPRESSION - * 0 COMPRESSION_NONE - * 1-9 levels for gzip compression - *--------- - */ + Compress compression; /* Compression requested on open */ bool dosync; /* data requested to be synced on sight */ ArchiveMode mode; /* File mode - r or w */ void *formatData; /* Header data specific to file format */ diff --git a/src/bin/pg_dump/pg_backup_custom.c b/src/bin/pg_dump/pg_backup_custom.c index 77d402c323..55a887a236 100644 --- a/src/bin/pg_dump/pg_backup_custom.c +++ b/src/bin/pg_dump/pg_backup_custom.c @@ -298,7 +298,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) _WriteByte(AH, BLK_DATA); /* Block type */ WriteInt(AH, te->dumpId); /* For sanity check */ - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -377,7 +377,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) WriteInt(AH, oid); - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -566,7 +566,7 @@ _PrintTocData(ArchiveHandle *AH, TocEntry *te) static void _PrintData(ArchiveHandle *AH) { - ReadDataFromArchive(AH, AH->compression, _CustomReadFunc); + ReadDataFromArchive(AH, _CustomReadFunc); } static void diff --git a/src/bin/pg_dump/pg_backup_directory.c b/src/bin/pg_dump/pg_backup_directory.c index 650b542fce..8bf869c6ca 100644 --- a/src/bin/pg_dump/pg_backup_directory.c +++ b/src/bin/pg_dump/pg_backup_directory.c @@ -202,7 +202,7 @@ InitArchiveFmt_Directory(ArchiveHandle *AH) setFilePath(AH, fname, "toc.dat"); - tocFH = cfopen_read(fname, PG_BINARY_R); + tocFH = cfopen_read(fname, PG_BINARY_R, &AH->compression); if (tocFH == NULL) fatal("could not open input file \"%s\": %m", fname); @@ -327,7 +327,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) setFilePath(AH, fname, tctx->filename); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -388,7 +388,7 @@ _PrintFileData(ArchiveHandle *AH, char *filename) if (!filename) return; - cfp = cfopen_read(filename, PG_BINARY_R); + cfp = cfopen_read(filename, PG_BINARY_R, &AH->compression); if (!cfp) fatal("could not open input file \"%s\": %m", filename); @@ -435,12 +435,13 @@ _LoadBlobs(ArchiveHandle *AH) lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; char line[MAXPGPATH]; + Compress nocompression = {0}; StartRestoreBlobs(AH); setFilePath(AH, fname, "blobs.toc"); - ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R); + ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R, &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open large object TOC file \"%s\" for input: %m", @@ -573,6 +574,7 @@ _CloseArchive(ArchiveHandle *AH) { cfp *tocFH; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "toc.dat"); @@ -580,7 +582,7 @@ _CloseArchive(ArchiveHandle *AH) ctx->pstate = ParallelBackupStart(AH); /* The TOC is always created uncompressed */ - tocFH = cfopen_write(fname, PG_BINARY_W, 0); + tocFH = cfopen_write(fname, PG_BINARY_W, &nocompression); if (tocFH == NULL) fatal("could not open output file \"%s\": %m", fname); ctx->dataFH = tocFH; @@ -639,11 +641,12 @@ _StartBlobs(ArchiveHandle *AH, TocEntry *te) { lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "blobs.toc"); /* The blob TOC file is never compressed */ - ctx->blobsTocFH = cfopen_write(fname, "ab", 0); + ctx->blobsTocFH = cfopen_write(fname, "ab", &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -661,7 +664,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) snprintf(fname, MAXPGPATH, "%s/blob_%u.dat", ctx->directory, oid); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); diff --git a/src/bin/pg_dump/pg_backup_tar.c b/src/bin/pg_dump/pg_backup_tar.c index 61c9c87a9f..4ba79ab924 100644 --- a/src/bin/pg_dump/pg_backup_tar.c +++ b/src/bin/pg_dump/pg_backup_tar.c @@ -39,6 +39,7 @@ #include "pg_backup_archiver.h" #include "pg_backup_tar.h" #include "pg_backup_utils.h" +#include "compress_io.h" #include "pgtar.h" static void _ArchiveEntry(ArchiveHandle *AH, TocEntry *te); @@ -196,10 +197,10 @@ InitArchiveFmt_Tar(ArchiveHandle *AH) /* * We don't support compression because reading the files back is not - * possible since gzdopen uses buffered IO which totally screws file + * possible since gzdopen uses buffered IO which totally screws file XXX * positioning. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) fatal("compression is not supported by tar archive format"); } else @@ -254,14 +255,8 @@ _ArchiveEntry(ArchiveHandle *AH, TocEntry *te) ctx = (lclTocEntry *) pg_malloc0(sizeof(lclTocEntry)); if (te->dataDumper != NULL) { -#ifdef HAVE_LIBZ - if (AH->compression == 0) - sprintf(fn, "%d.dat", te->dumpId); - else - sprintf(fn, "%d.dat.gz", te->dumpId); -#else - sprintf(fn, "%d.dat", te->dumpId); -#endif + const char *suffix = compress_suffix(&AH->compression); + sprintf(fn, "%d.dat%s", te->dumpId, suffix); ctx->filename = pg_strdup(fn); } else @@ -352,7 +347,7 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression == 0) + if (AH->compression.alg == COMPR_ALG_NONE) tm->nFH = ctx->tarFH; else fatal("compression is not supported by tar archive format"); @@ -413,9 +408,9 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) { - sprintf(fmode, "wb%d", AH->compression); + sprintf(fmode, "wb%d", AH->compression.level); tm->zFH = gzdopen(dup(fileno(tm->tmpFH)), fmode); if (tm->zFH == NULL) fatal("could not open temporary file"); @@ -443,7 +438,7 @@ tarClose(ArchiveHandle *AH, TAR_MEMBER *th) /* * Close the GZ file since we dup'd. This will flush the buffers. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) if (GZCLOSE(th->zFH) != 0) fatal("could not close tar member"); @@ -868,7 +863,7 @@ _CloseArchive(ArchiveHandle *AH) memcpy(ropt, AH->public.ropt, sizeof(RestoreOptions)); ropt->filename = NULL; ropt->dropSchema = 1; - ropt->compression = 0; + ropt->compression.alg = COMPR_ALG_NONE; ropt->superuser = NULL; ropt->suppressDumpWarnings = true; @@ -952,16 +947,12 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) lclContext *ctx = (lclContext *) AH->formatData; lclTocEntry *tctx = (lclTocEntry *) te->formatData; char fname[255]; - char *sfx; + const char *sfx; if (oid == 0) fatal("invalid OID for large object (%u)", oid); - if (AH->compression != 0) - sfx = ".gz"; - else - sfx = ""; - + sfx = compress_suffix(&AH->compression); sprintf(fname, "blob_%u.dat%s", oid, sfx); tarPrintf(ctx->blobToc, "%u %s\n", oid, fname); diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c index 1ab98a2286..4cbc79aedc 100644 --- a/src/bin/pg_dump/pg_dump.c +++ b/src/bin/pg_dump/pg_dump.c @@ -59,6 +59,7 @@ #include "getopt_long.h" #include "libpq/libpq-fs.h" #include "parallel.h" +#include "compress_io.h" #include "pg_backup_db.h" #include "pg_backup_utils.h" #include "pg_dump.h" @@ -297,6 +298,82 @@ static void setupDumpWorker(Archive *AHX); static TableInfo *getRootTableInfo(TableInfo *tbinfo); +/* Parse the string into compression options */ +static void +parse_compression(const char *optarg, Compress *compress) +{ + if (optarg[0] == '0' && optarg[1] == '\0') + compress->alg = COMPR_ALG_NONE; + else if ((optarg[0] > '0' && optarg[0] <= '9') || + optarg[0] == '-') + { + compress->alg = COMPR_ALG_LIBZ; + compress->level_set = true; + compress->level = atoi(optarg); + if (optarg[1] != '\0') + { + pg_log_error("compression level must be in range 0..9"); + exit_nicely(1); + } + } + else + { + /* Parse a more flexible string like level=3 alg=zlib opts=long */ + for (;;) + { + char *eq = strchr(optarg, '='); + int len; + + if (eq == NULL) + { + pg_log_error("compression options must be key=value: %s", optarg); + exit_nicely(1); + } + + len = eq - optarg; + if (strncmp(optarg, "alg", len) == 0) + { + if (strchr(eq, ' ')) + len = strchr(eq, ' ') - eq - 1; + else + len = strlen(eq) - len; + if (strncmp(1+eq, "zlib", len) == 0 || + strncmp(1+eq, "libz", len) == 0) + compress->alg = COMPR_ALG_LIBZ; + else + { + pg_log_error("unknown compression algorithm: %s", 1+eq); + exit_nicely(1); + } + } + else if (strncmp(optarg, "level", len) == 0) + { + compress->level = atoi(1+eq); + compress->level_set = true; + } + else + { + pg_log_error("unknown compression setting: %s", optarg); + exit_nicely(1); + } + + optarg = strchr(eq, ' '); + if (!optarg++) + break; + } + + if (!compress->level_set) + { + const int default_compress_level[] = { + 0, /* COMPR_ALG_NONE */ + Z_DEFAULT_COMPRESSION, /* COMPR_ALG_ZLIB */ + }; + + compress->level = default_compress_level[compress->alg]; + } + } +} + int main(int argc, char **argv) { @@ -319,7 +396,7 @@ main(int argc, char **argv) char *use_role = NULL; long rowsPerInsert; int numWorkers = 1; - int compressLevel = -1; + Compress compress = { .alg = COMPR_ALG_DEFAULT }; int plainText = 0; ArchiveFormat archiveFormat = archUnknown; ArchiveMode archiveMode; @@ -532,12 +609,7 @@ main(int argc, char **argv) break; case 'Z': /* Compression Level */ - compressLevel = atoi(optarg); - if (compressLevel < 0 || compressLevel > 9) - { - pg_log_error("compression level must be in range 0..9"); - exit_nicely(1); - } + parse_compression(optarg, &compress); break; case 0: @@ -679,20 +751,28 @@ main(int argc, char **argv) plainText = 1; /* Custom and directory formats are compressed by default, others not */ - if (compressLevel == -1) + if (compress.alg == COMPR_ALG_DEFAULT) { -#ifdef HAVE_LIBZ if (archiveFormat == archCustom || archiveFormat == archDirectory) - compressLevel = Z_DEFAULT_COMPRESSION; - else + { +#ifdef HAVE_LIBZ + compress.alg = COMPR_ALG_LIBZ; + compress.level = Z_DEFAULT_COMPRESSION; #endif - compressLevel = 0; + } + else + { + compress.alg = COMPR_ALG_NONE; + compress.level = 0; + } } #ifndef HAVE_LIBZ - if (compressLevel != 0) + if (compress.alg == COMPR_ALG_LIBZ) + { pg_log_warning("requested compression not available in this installation -- archive will be uncompressed"); - compressLevel = 0; + compress.alg = 0; + } #endif /* @@ -723,7 +803,7 @@ main(int argc, char **argv) fatal("option --index-collation-versions-unknown only works in binary upgrade mode"); /* Open the output file */ - fout = CreateArchive(filename, archiveFormat, compressLevel, dosync, + fout = CreateArchive(filename, archiveFormat, &compress, dosync, archiveMode, setupDumpWorker); /* Make dump options accessible right away */ @@ -957,10 +1037,7 @@ main(int argc, char **argv) ropt->sequence_data = dopt.sequence_data; ropt->binary_upgrade = dopt.binary_upgrade; - if (compressLevel == -1) - ropt->compression = 0; - else - ropt->compression = compressLevel; + ropt->compression = compress; ropt->suppressDumpWarnings = true; /* We've already shown them */ -- 2.17.0 --GRPZ8SYKNexpdSJ7 Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="0004-struct-compressLibs.patch" ^ permalink raw reply [nested|flat] 23+ messages in thread
* [PATCH 03/20] Support multiple compression algs/levels/opts.. @ 2020-12-22 06:23 Justin Pryzby <[email protected]> 0 siblings, 0 replies; 23+ messages in thread From: Justin Pryzby @ 2020-12-22 06:23 UTC (permalink / raw) The existing implementation abtracts compressed and noncompressed I/O. This preliminary commit is intended to also allow for multiple compression algorithms. --- src/bin/pg_dump/compress_io.c | 220 +++++++++++--------------- src/bin/pg_dump/compress_io.h | 19 +-- src/bin/pg_dump/pg_backup.h | 23 ++- src/bin/pg_dump/pg_backup_archiver.c | 45 +++--- src/bin/pg_dump/pg_backup_archiver.h | 12 +- src/bin/pg_dump/pg_backup_custom.c | 6 +- src/bin/pg_dump/pg_backup_directory.c | 17 +- src/bin/pg_dump/pg_backup_tar.c | 33 ++-- src/bin/pg_dump/pg_dump.c | 115 +++++++++++--- 9 files changed, 272 insertions(+), 218 deletions(-) diff --git a/src/bin/pg_dump/compress_io.c b/src/bin/pg_dump/compress_io.c index 6a428978d4..db16fd33f2 100644 --- a/src/bin/pg_dump/compress_io.c +++ b/src/bin/pg_dump/compress_io.c @@ -74,12 +74,9 @@ struct CompressorState #endif }; -static void ParseCompressionOption(int compression, CompressionAlgorithm *alg, - int *level); - /* Routines that support zlib compressed data I/O */ #ifdef HAVE_LIBZ -static void InitCompressorZlib(CompressorState *cs, int level); +static void InitCompressorZlib(CompressorState *cs, Compress *compress); static void DeflateCompressorZlib(ArchiveHandle *AH, CompressorState *cs, bool flush); static void ReadDataFromArchiveZlib(ArchiveHandle *AH, ReadFunc readF); @@ -93,58 +90,36 @@ static void ReadDataFromArchiveNone(ArchiveHandle *AH, ReadFunc readF); static void WriteDataToArchiveNone(ArchiveHandle *AH, CompressorState *cs, const char *data, size_t dLen); -/* - * Interprets a numeric 'compression' value. The algorithm implied by the - * value (zlib or none at the moment), is returned in *alg, and the - * zlib compression level in *level. - */ -static void -ParseCompressionOption(int compression, CompressionAlgorithm *alg, int *level) -{ - if (compression == Z_DEFAULT_COMPRESSION || - (compression > 0 && compression <= 9)) - *alg = COMPR_ALG_LIBZ; - else if (compression == 0) - *alg = COMPR_ALG_NONE; - else - { - fatal("invalid compression code: %d", compression); - *alg = COMPR_ALG_NONE; /* keep compiler quiet */ - } - - /* The level is just the passed-in value. */ - if (level) - *level = compression; -} - /* Public interface routines */ /* Allocate a new compressor */ CompressorState * -AllocateCompressor(int compression, WriteFunc writeF) +AllocateCompressor(Compress *compression, WriteFunc writeF) { CompressorState *cs; - CompressionAlgorithm alg; - int level; - - ParseCompressionOption(compression, &alg, &level); - -#ifndef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - fatal("not built with zlib support"); -#endif cs = (CompressorState *) pg_malloc0(sizeof(CompressorState)); cs->writeF = writeF; - cs->comprAlg = alg; + cs->comprAlg = compression->alg; /* * Perform compression algorithm specific initialization. */ + Assert (compression->alg != COMPR_ALG_DEFAULT); + switch (compression->alg) + { #ifdef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - InitCompressorZlib(cs, level); + case COMPR_ALG_LIBZ: + InitCompressorZlib(cs, compression); + break; #endif + case COMPR_ALG_NONE: + /* Do nothing */ + break; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } return cs; } @@ -154,21 +129,21 @@ AllocateCompressor(int compression, WriteFunc writeF) * out with ahwrite(). */ void -ReadDataFromArchive(ArchiveHandle *AH, int compression, ReadFunc readF) +ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF) { - CompressionAlgorithm alg; - - ParseCompressionOption(compression, &alg, NULL); - - if (alg == COMPR_ALG_NONE) - ReadDataFromArchiveNone(AH, readF); - if (alg == COMPR_ALG_LIBZ) + switch (AH->compression.alg) { + case COMPR_ALG_NONE: + ReadDataFromArchiveNone(AH, readF); + break; #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: ReadDataFromArchiveZlib(AH, readF); -#else - fatal("not built with zlib support"); + break; #endif + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -181,16 +156,18 @@ WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, { switch (cs->comprAlg) { - case COMPR_ALG_LIBZ: #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: WriteDataToArchiveZlib(AH, cs, data, dLen); -#else - fatal("not built with zlib support"); -#endif break; +#endif case COMPR_ALG_NONE: WriteDataToArchiveNone(AH, cs, data, dLen); break; + + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -215,7 +192,7 @@ EndCompressor(ArchiveHandle *AH, CompressorState *cs) */ static void -InitCompressorZlib(CompressorState *cs, int level) +InitCompressorZlib(CompressorState *cs, Compress *compress) { z_streamp zp; @@ -232,7 +209,7 @@ InitCompressorZlib(CompressorState *cs, int level) cs->zlibOut = (char *) pg_malloc(ZLIB_OUT_SIZE + 1); cs->zlibOutSize = ZLIB_OUT_SIZE; - if (deflateInit(zp, level) != Z_OK) + if (deflateInit(zp, compress->level) != Z_OK) fatal("could not initialize compression library: %s", zp->msg); @@ -424,9 +401,7 @@ struct cfp #endif }; -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix); -#endif /* free() without changing errno; useful in several places below */ static void @@ -442,34 +417,31 @@ free_keep_errno(void *p) * Open a file for reading. 'path' is the file to open, and 'mode' should * be either "r" or "rb". * - * If the file at 'path' does not exist, we append the ".gz" suffix (if 'path' - * doesn't already have it) and try again. So if you pass "foo" as 'path', + * If the file at 'path' does not exist, we search with compressed suffix (if 'path' + * doesn't already have one) and try again. So if you pass "foo" as 'path', * this will open either "foo" or "foo.gz". * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_read(const char *path, const char *mode) +cfopen_read(const char *path, const char *mode, Compress *compression) { cfp *fp; -#ifdef HAVE_LIBZ if (hasSuffix(path, ".gz")) - fp = cfopen(path, mode, 1); + fp = cfopen(path, mode, compression); else -#endif { - fp = cfopen(path, mode, 0); -#ifdef HAVE_LIBZ + fp = cfopen(path, mode, compression); if (fp == NULL) { char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); - fp = cfopen(fname, mode, 1); + fname = psprintf("%s%s", path, suffix); + fp = cfopen(fname, mode, compression); free_keep_errno(fname); } -#endif } return fp; } @@ -479,31 +451,26 @@ cfopen_read(const char *path, const char *mode) * be a filemode as accepted by fopen() and gzopen() that indicates writing * ("w", "wb", "a", or "ab"). * - * If 'compression' is non-zero, a gzip compressed stream is opened, and - * 'compression' indicates the compression level used. The ".gz" suffix - * is automatically added to 'path' in that case. + * Use compression if specified. + * The appropriate suffix is automatically added to 'path' in that case. * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_write(const char *path, const char *mode, int compression) +cfopen_write(const char *path, const char *mode, Compress *compression) { cfp *fp; - if (compression == 0) - fp = cfopen(path, mode, 0); + if (compression->alg == COMPR_ALG_NONE) + fp = cfopen(path, mode, compression); else { -#ifdef HAVE_LIBZ char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); + fname = psprintf("%s%s", path, suffix); fp = cfopen(fname, mode, compression); free_keep_errno(fname); -#else - fatal("not built with zlib support"); - fp = NULL; /* keep compiler quiet */ -#endif } return fp; } @@ -515,20 +482,21 @@ cfopen_write(const char *path, const char *mode, int compression) * On failure, return NULL with an error code in errno. */ cfp * -cfopen(const char *path, const char *mode, int compression) +cfopen(const char *path, const char *mode, Compress *compression) { - cfp *fp = pg_malloc(sizeof(cfp)); + cfp *fp = pg_malloc0(sizeof(cfp)); - if (compression != 0) + switch (compression->alg) { #ifdef HAVE_LIBZ - if (compression != Z_DEFAULT_COMPRESSION) + case COMPR_ALG_LIBZ: + if (compression->level != Z_DEFAULT_COMPRESSION) { /* user has specified a compression level, so tell zlib to use it */ char mode_compression[32]; snprintf(mode_compression, sizeof(mode_compression), "%s%d", - mode, compression); + mode, compression->level); fp->compressedfp = gzopen(path, mode_compression); } else @@ -537,30 +505,27 @@ cfopen(const char *path, const char *mode, int compression) fp->compressedfp = gzopen(path, mode); } - fp->uncompressedfp = NULL; if (fp->compressedfp == NULL) { free_keep_errno(fp); fp = NULL; } -#else - fatal("not built with zlib support"); -#endif - } - else - { -#ifdef HAVE_LIBZ - fp->compressedfp = NULL; + return fp; #endif + + case COMPR_ALG_NONE: fp->uncompressedfp = fopen(path, mode); if (fp->uncompressedfp == NULL) { free_keep_errno(fp); fp = NULL; } - } + return fp; - return fp; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } } @@ -584,14 +549,13 @@ cfread(void *ptr, int size, cfp *fp) fatal("could not read from input file: %s", errnum == Z_ERRNO ? strerror(errno) : errmsg); } + return ret; } - else #endif - { - ret = fread(ptr, 1, size, fp->uncompressedfp); - if (ret != size && !feof(fp->uncompressedfp)) - READ_ERROR_EXIT(fp->uncompressedfp); - } + + ret = fread(ptr, 1, size, fp->uncompressedfp); + if (ret != size && !feof(fp->uncompressedfp)) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -601,9 +565,8 @@ cfwrite(const void *ptr, int size, cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzwrite(fp->compressedfp, ptr, size); - else #endif - return fwrite(ptr, 1, size, fp->uncompressedfp); + return fwrite(ptr, 1, size, fp->uncompressedfp); } int @@ -622,15 +585,12 @@ cfgetc(cfp *fp) else fatal("could not read from input file: end of file"); } + return ret; } - else #endif - { - ret = fgetc(fp->uncompressedfp); - if (ret == EOF) - READ_ERROR_EXIT(fp->uncompressedfp); - } - + ret = fgetc(fp->uncompressedfp); + if (ret == EOF) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -640,9 +600,8 @@ cfgets(cfp *fp, char *buf, int len) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzgets(fp->compressedfp, buf, len); - else #endif - return fgets(buf, len, fp->uncompressedfp); + return fgets(buf, len, fp->uncompressedfp); } int @@ -660,15 +619,13 @@ cfclose(cfp *fp) { result = gzclose(fp->compressedfp); fp->compressedfp = NULL; + return result; } - else #endif - { - result = fclose(fp->uncompressedfp); - fp->uncompressedfp = NULL; - } - free_keep_errno(fp); + result = fclose(fp->uncompressedfp); + fp->uncompressedfp = NULL; + free_keep_errno(fp); return result; } @@ -678,9 +635,9 @@ cfeof(cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzeof(fp->compressedfp); - else #endif - return feof(fp->uncompressedfp); + + return feof(fp->uncompressedfp); } const char * @@ -699,7 +656,6 @@ get_cfp_error(cfp *fp) return strerror(errno); } -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix) { @@ -714,4 +670,18 @@ hasSuffix(const char *filename, const char *suffix) suffixlen) == 0; } -#endif +/* + * Return a string for the given AH's compression. + * The string is statically allocated. + */ +const char * +compress_suffix(Compress *compression) +{ + switch (compression->alg) + { + case COMPR_ALG_LIBZ: + return ".gz"; + default: + return ""; + } +} diff --git a/src/bin/pg_dump/compress_io.h b/src/bin/pg_dump/compress_io.h index d2e6e1b854..2c073676eb 100644 --- a/src/bin/pg_dump/compress_io.h +++ b/src/bin/pg_dump/compress_io.h @@ -21,12 +21,6 @@ #define ZLIB_OUT_SIZE 4096 #define ZLIB_IN_SIZE 4096 -typedef enum -{ - COMPR_ALG_NONE, - COMPR_ALG_LIBZ -} CompressionAlgorithm; - /* Prototype for callback function to WriteDataToArchive() */ typedef void (*WriteFunc) (ArchiveHandle *AH, const char *buf, size_t len); @@ -46,8 +40,8 @@ typedef size_t (*ReadFunc) (ArchiveHandle *AH, char **buf, size_t *buflen); /* struct definition appears in compress_io.c */ typedef struct CompressorState CompressorState; -extern CompressorState *AllocateCompressor(int compression, WriteFunc writeF); -extern void ReadDataFromArchive(ArchiveHandle *AH, int compression, +extern CompressorState *AllocateCompressor(Compress *compression, WriteFunc writeF); +extern void ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF); extern void WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, const void *data, size_t dLen); @@ -56,9 +50,9 @@ extern void EndCompressor(ArchiveHandle *AH, CompressorState *cs); typedef struct cfp cfp; -extern cfp *cfopen(const char *path, const char *mode, int compression); -extern cfp *cfopen_read(const char *path, const char *mode); -extern cfp *cfopen_write(const char *path, const char *mode, int compression); +extern cfp *cfopen(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_read(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_write(const char *path, const char *mode, Compress *compression); extern int cfread(void *ptr, int size, cfp *fp); extern int cfwrite(const void *ptr, int size, cfp *fp); extern int cfgetc(cfp *fp); @@ -67,4 +61,7 @@ extern int cfclose(cfp *fp); extern int cfeof(cfp *fp); extern const char *get_cfp_error(cfp *fp); +/* also used by tar */ +extern const char * compress_suffix(Compress *compression); + #endif diff --git a/src/bin/pg_dump/pg_backup.h b/src/bin/pg_dump/pg_backup.h index 9d0056a569..f2390b7937 100644 --- a/src/bin/pg_dump/pg_backup.h +++ b/src/bin/pg_dump/pg_backup.h @@ -72,6 +72,25 @@ typedef struct _connParams char *override_dbname; } ConnParams; +typedef enum +{ + COMPR_ALG_DEFAULT = -1, + COMPR_ALG_NONE, + COMPR_ALG_LIBZ, +} CompressionAlgorithm; +/* Should be called "method" or "library" ? */ + +typedef struct Compress { + CompressionAlgorithm alg; + int level; + /* Is a nondefault level set ? This is useful since different compression + * methods have different "default" levels. For now we assume the levels + * are all integer, though. + */ + bool level_set; +} Compress; + + typedef struct _restoreOptions { int createDB; /* Issue commands to create the database */ @@ -125,7 +144,7 @@ typedef struct _restoreOptions int noDataForFailedTables; int exit_on_error; - int compression; + Compress compression; int suppressDumpWarnings; /* Suppress output of WARNING entries * to stderr */ bool single_txn; @@ -281,7 +300,7 @@ extern Archive *OpenArchive(const char *FileSpec, const ArchiveFormat fmt); /* Create a new archive */ extern Archive *CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker); /* The --list option */ diff --git a/src/bin/pg_dump/pg_backup_archiver.c b/src/bin/pg_dump/pg_backup_archiver.c index 1f82c6499b..3eb6c55600 100644 --- a/src/bin/pg_dump/pg_backup_archiver.c +++ b/src/bin/pg_dump/pg_backup_archiver.c @@ -70,7 +70,7 @@ typedef struct _parallelReadyList static ArchiveHandle *_allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr); static void _getObjectDescription(PQExpBuffer buf, TocEntry *te); static void _printTocEntry(ArchiveHandle *AH, TocEntry *te, bool isData); @@ -98,7 +98,7 @@ static int _discoverArchiveFormat(ArchiveHandle *AH); static int RestoringToDB(ArchiveHandle *AH); static void dump_lo_buf(ArchiveHandle *AH); static void dumpTimestamp(ArchiveHandle *AH, const char *msg, time_t tim); -static void SetOutput(ArchiveHandle *AH, const char *filename, int compression); +static void SetOutput(ArchiveHandle *AH, const char *filename, Compress *compress); static OutputContext SaveOutput(ArchiveHandle *AH); static void RestoreOutput(ArchiveHandle *AH, OutputContext savedContext); @@ -238,7 +238,7 @@ setupRestoreWorker(Archive *AHX) /* Public */ Archive * CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker) { @@ -253,7 +253,9 @@ CreateArchive(const char *FileSpec, const ArchiveFormat fmt, Archive * OpenArchive(const char *FileSpec, const ArchiveFormat fmt) { - ArchiveHandle *AH = _allocAH(FileSpec, fmt, 0, true, archModeRead, setupRestoreWorker); + Compress compress = {0}; + ArchiveHandle *AH = _allocAH(FileSpec, fmt, &compress, true, archModeRead, + setupRestoreWorker); return (Archive *) AH; } @@ -382,7 +384,7 @@ RestoreArchive(Archive *AHX) * Make sure we won't need (de)compression we haven't got */ #ifndef HAVE_LIBZ - if (AH->compression != 0 && AH->PrintTocDataPtr != NULL) + if (AH->compression.alg != COMPR_ALG_NONE && AH->PrintTocDataPtr != NULL) { for (te = AH->toc->next; te != AH->toc; te = te->next) { @@ -457,8 +459,8 @@ RestoreArchive(Archive *AHX) * Setup the output file if necessary. */ sav = SaveOutput(AH); - if (ropt->filename || ropt->compression) - SetOutput(AH, ropt->filename, ropt->compression); + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) + SetOutput(AH, ropt->filename, &ropt->compression); ahprintf(AH, "--\n-- PostgreSQL database dump\n--\n\n"); @@ -738,7 +740,7 @@ RestoreArchive(Archive *AHX) */ AH->stage = STAGE_FINALIZING; - if (ropt->filename || ropt->compression) + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) RestoreOutput(AH, sav); if (ropt->useDB) @@ -1123,8 +1125,9 @@ PrintTOCSummary(Archive *AHX) char stamp_str[64]; sav = SaveOutput(AH); + Assert(ropt->compression.alg == COMPR_ALG_NONE); if (ropt->filename) - SetOutput(AH, ropt->filename, 0 /* no compression */ ); + SetOutput(AH, ropt->filename, &ropt->compression); if (strftime(stamp_str, sizeof(stamp_str), PGDUMP_STRFTIME_FMT, localtime(&AH->createDate)) == 0) @@ -1133,7 +1136,7 @@ PrintTOCSummary(Archive *AHX) ahprintf(AH, ";\n; Archive created at %s\n", stamp_str); ahprintf(AH, "; dbname: %s\n; TOC Entries: %d\n; Compression: %d\n", sanitize_line(AH->archdbname, false), - AH->tocCount, AH->compression); + AH->tocCount, AH->compression.alg); switch (AH->format) { @@ -1487,7 +1490,7 @@ archprintf(Archive *AH, const char *fmt,...) *******************************/ static void -SetOutput(ArchiveHandle *AH, const char *filename, int compression) +SetOutput(ArchiveHandle *AH, const char *filename, Compress *compression) { int fn; @@ -1510,12 +1513,12 @@ SetOutput(ArchiveHandle *AH, const char *filename, int compression) /* If compression explicitly requested, use gzopen */ #ifdef HAVE_LIBZ - if (compression != 0) + if (compression->alg != COMPR_ALG_NONE) { char fmode[14]; /* Don't use PG_BINARY_x since this is zlib */ - sprintf(fmode, "wb%d", compression); + sprintf(fmode, "wb%d", compression->level); if (fn >= 0) AH->OF = gzdopen(dup(fn), fmode); else @@ -2259,7 +2262,7 @@ _discoverArchiveFormat(ArchiveHandle *AH) */ static ArchiveHandle * _allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr) { ArchiveHandle *AH; @@ -2310,7 +2313,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, AH->toc->prev = AH->toc; AH->mode = mode; - AH->compression = compression; + AH->compression = *compression; AH->dosync = dosync; memset(&(AH->sqlparse), 0, sizeof(AH->sqlparse)); @@ -2325,7 +2328,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, * Force stdin/stdout into binary mode if that is what we are using. */ #ifdef WIN32 - if ((fmt != archNull || compression != 0) && + if ((fmt != archNull || compression->alg != COMPR_ALG_NONE) && (AH->fSpec == NULL || strcmp(AH->fSpec, "") == 0)) { if (mode == archModeWrite) @@ -3741,7 +3744,7 @@ WriteHead(ArchiveHandle *AH) AH->WriteBytePtr(AH, AH->intSize); AH->WriteBytePtr(AH, AH->offSize); AH->WriteBytePtr(AH, AH->format); - WriteInt(AH, AH->compression); + WriteInt(AH, AH->compression.alg); crtm = *localtime(&AH->createDate); WriteInt(AH, crtm.tm_sec); WriteInt(AH, crtm.tm_min); @@ -3816,15 +3819,15 @@ ReadHead(ArchiveHandle *AH) if (AH->version >= K_VERS_1_2) { if (AH->version < K_VERS_1_4) - AH->compression = AH->ReadBytePtr(AH); + AH->compression.alg = AH->ReadBytePtr(AH); else - AH->compression = ReadInt(AH); + AH->compression.alg = ReadInt(AH); } else - AH->compression = Z_DEFAULT_COMPRESSION; + AH->compression.alg = Z_DEFAULT_COMPRESSION; #ifndef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) pg_log_warning("archive is compressed, but this installation does not support compression -- no data will be available"); #endif diff --git a/src/bin/pg_dump/pg_backup_archiver.h b/src/bin/pg_dump/pg_backup_archiver.h index a8ea5c7eae..6e033d040e 100644 --- a/src/bin/pg_dump/pg_backup_archiver.h +++ b/src/bin/pg_dump/pg_backup_archiver.h @@ -47,7 +47,8 @@ #define GZWRITE(p, s, n, fh) (fwrite(p, s, n, fh) * (s)) #define GZREAD(p, s, n, fh) fread(p, s, n, fh) #define GZEOF(fh) feof(fh) -/* this is just the redefinition of a libz constant */ +/* this is just the redefinition of a libz constant, in case zlib isn't + * available */ #define Z_DEFAULT_COMPRESSION (-1) typedef struct _z_stream @@ -329,14 +330,7 @@ struct _archiveHandle DumpId *tableDataId; /* TABLE DATA ids, indexed by table dumpId */ struct _tocEntry *currToc; /* Used when dumping data */ - int compression; /*--------- - * Compression requested on open(). - * Possible values for compression: - * -1 Z_DEFAULT_COMPRESSION - * 0 COMPRESSION_NONE - * 1-9 levels for gzip compression - *--------- - */ + Compress compression; /* Compression requested on open */ bool dosync; /* data requested to be synced on sight */ ArchiveMode mode; /* File mode - r or w */ void *formatData; /* Header data specific to file format */ diff --git a/src/bin/pg_dump/pg_backup_custom.c b/src/bin/pg_dump/pg_backup_custom.c index 77d402c323..55a887a236 100644 --- a/src/bin/pg_dump/pg_backup_custom.c +++ b/src/bin/pg_dump/pg_backup_custom.c @@ -298,7 +298,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) _WriteByte(AH, BLK_DATA); /* Block type */ WriteInt(AH, te->dumpId); /* For sanity check */ - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -377,7 +377,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) WriteInt(AH, oid); - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -566,7 +566,7 @@ _PrintTocData(ArchiveHandle *AH, TocEntry *te) static void _PrintData(ArchiveHandle *AH) { - ReadDataFromArchive(AH, AH->compression, _CustomReadFunc); + ReadDataFromArchive(AH, _CustomReadFunc); } static void diff --git a/src/bin/pg_dump/pg_backup_directory.c b/src/bin/pg_dump/pg_backup_directory.c index 650b542fce..8bf869c6ca 100644 --- a/src/bin/pg_dump/pg_backup_directory.c +++ b/src/bin/pg_dump/pg_backup_directory.c @@ -202,7 +202,7 @@ InitArchiveFmt_Directory(ArchiveHandle *AH) setFilePath(AH, fname, "toc.dat"); - tocFH = cfopen_read(fname, PG_BINARY_R); + tocFH = cfopen_read(fname, PG_BINARY_R, &AH->compression); if (tocFH == NULL) fatal("could not open input file \"%s\": %m", fname); @@ -327,7 +327,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) setFilePath(AH, fname, tctx->filename); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -388,7 +388,7 @@ _PrintFileData(ArchiveHandle *AH, char *filename) if (!filename) return; - cfp = cfopen_read(filename, PG_BINARY_R); + cfp = cfopen_read(filename, PG_BINARY_R, &AH->compression); if (!cfp) fatal("could not open input file \"%s\": %m", filename); @@ -435,12 +435,13 @@ _LoadBlobs(ArchiveHandle *AH) lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; char line[MAXPGPATH]; + Compress nocompression = {0}; StartRestoreBlobs(AH); setFilePath(AH, fname, "blobs.toc"); - ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R); + ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R, &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open large object TOC file \"%s\" for input: %m", @@ -573,6 +574,7 @@ _CloseArchive(ArchiveHandle *AH) { cfp *tocFH; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "toc.dat"); @@ -580,7 +582,7 @@ _CloseArchive(ArchiveHandle *AH) ctx->pstate = ParallelBackupStart(AH); /* The TOC is always created uncompressed */ - tocFH = cfopen_write(fname, PG_BINARY_W, 0); + tocFH = cfopen_write(fname, PG_BINARY_W, &nocompression); if (tocFH == NULL) fatal("could not open output file \"%s\": %m", fname); ctx->dataFH = tocFH; @@ -639,11 +641,12 @@ _StartBlobs(ArchiveHandle *AH, TocEntry *te) { lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "blobs.toc"); /* The blob TOC file is never compressed */ - ctx->blobsTocFH = cfopen_write(fname, "ab", 0); + ctx->blobsTocFH = cfopen_write(fname, "ab", &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -661,7 +664,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) snprintf(fname, MAXPGPATH, "%s/blob_%u.dat", ctx->directory, oid); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); diff --git a/src/bin/pg_dump/pg_backup_tar.c b/src/bin/pg_dump/pg_backup_tar.c index 61c9c87a9f..4ba79ab924 100644 --- a/src/bin/pg_dump/pg_backup_tar.c +++ b/src/bin/pg_dump/pg_backup_tar.c @@ -39,6 +39,7 @@ #include "pg_backup_archiver.h" #include "pg_backup_tar.h" #include "pg_backup_utils.h" +#include "compress_io.h" #include "pgtar.h" static void _ArchiveEntry(ArchiveHandle *AH, TocEntry *te); @@ -196,10 +197,10 @@ InitArchiveFmt_Tar(ArchiveHandle *AH) /* * We don't support compression because reading the files back is not - * possible since gzdopen uses buffered IO which totally screws file + * possible since gzdopen uses buffered IO which totally screws file XXX * positioning. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) fatal("compression is not supported by tar archive format"); } else @@ -254,14 +255,8 @@ _ArchiveEntry(ArchiveHandle *AH, TocEntry *te) ctx = (lclTocEntry *) pg_malloc0(sizeof(lclTocEntry)); if (te->dataDumper != NULL) { -#ifdef HAVE_LIBZ - if (AH->compression == 0) - sprintf(fn, "%d.dat", te->dumpId); - else - sprintf(fn, "%d.dat.gz", te->dumpId); -#else - sprintf(fn, "%d.dat", te->dumpId); -#endif + const char *suffix = compress_suffix(&AH->compression); + sprintf(fn, "%d.dat%s", te->dumpId, suffix); ctx->filename = pg_strdup(fn); } else @@ -352,7 +347,7 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression == 0) + if (AH->compression.alg == COMPR_ALG_NONE) tm->nFH = ctx->tarFH; else fatal("compression is not supported by tar archive format"); @@ -413,9 +408,9 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) { - sprintf(fmode, "wb%d", AH->compression); + sprintf(fmode, "wb%d", AH->compression.level); tm->zFH = gzdopen(dup(fileno(tm->tmpFH)), fmode); if (tm->zFH == NULL) fatal("could not open temporary file"); @@ -443,7 +438,7 @@ tarClose(ArchiveHandle *AH, TAR_MEMBER *th) /* * Close the GZ file since we dup'd. This will flush the buffers. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) if (GZCLOSE(th->zFH) != 0) fatal("could not close tar member"); @@ -868,7 +863,7 @@ _CloseArchive(ArchiveHandle *AH) memcpy(ropt, AH->public.ropt, sizeof(RestoreOptions)); ropt->filename = NULL; ropt->dropSchema = 1; - ropt->compression = 0; + ropt->compression.alg = COMPR_ALG_NONE; ropt->superuser = NULL; ropt->suppressDumpWarnings = true; @@ -952,16 +947,12 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) lclContext *ctx = (lclContext *) AH->formatData; lclTocEntry *tctx = (lclTocEntry *) te->formatData; char fname[255]; - char *sfx; + const char *sfx; if (oid == 0) fatal("invalid OID for large object (%u)", oid); - if (AH->compression != 0) - sfx = ".gz"; - else - sfx = ""; - + sfx = compress_suffix(&AH->compression); sprintf(fname, "blob_%u.dat%s", oid, sfx); tarPrintf(ctx->blobToc, "%u %s\n", oid, fname); diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c index 1ab98a2286..4cbc79aedc 100644 --- a/src/bin/pg_dump/pg_dump.c +++ b/src/bin/pg_dump/pg_dump.c @@ -59,6 +59,7 @@ #include "getopt_long.h" #include "libpq/libpq-fs.h" #include "parallel.h" +#include "compress_io.h" #include "pg_backup_db.h" #include "pg_backup_utils.h" #include "pg_dump.h" @@ -297,6 +298,82 @@ static void setupDumpWorker(Archive *AHX); static TableInfo *getRootTableInfo(TableInfo *tbinfo); +/* Parse the string into compression options */ +static void +parse_compression(const char *optarg, Compress *compress) +{ + if (optarg[0] == '0' && optarg[1] == '\0') + compress->alg = COMPR_ALG_NONE; + else if ((optarg[0] > '0' && optarg[0] <= '9') || + optarg[0] == '-') + { + compress->alg = COMPR_ALG_LIBZ; + compress->level_set = true; + compress->level = atoi(optarg); + if (optarg[1] != '\0') + { + pg_log_error("compression level must be in range 0..9"); + exit_nicely(1); + } + } + else + { + /* Parse a more flexible string like level=3 alg=zlib opts=long */ + for (;;) + { + char *eq = strchr(optarg, '='); + int len; + + if (eq == NULL) + { + pg_log_error("compression options must be key=value: %s", optarg); + exit_nicely(1); + } + + len = eq - optarg; + if (strncmp(optarg, "alg", len) == 0) + { + if (strchr(eq, ' ')) + len = strchr(eq, ' ') - eq - 1; + else + len = strlen(eq) - len; + if (strncmp(1+eq, "zlib", len) == 0 || + strncmp(1+eq, "libz", len) == 0) + compress->alg = COMPR_ALG_LIBZ; + else + { + pg_log_error("unknown compression algorithm: %s", 1+eq); + exit_nicely(1); + } + } + else if (strncmp(optarg, "level", len) == 0) + { + compress->level = atoi(1+eq); + compress->level_set = true; + } + else + { + pg_log_error("unknown compression setting: %s", optarg); + exit_nicely(1); + } + + optarg = strchr(eq, ' '); + if (!optarg++) + break; + } + + if (!compress->level_set) + { + const int default_compress_level[] = { + 0, /* COMPR_ALG_NONE */ + Z_DEFAULT_COMPRESSION, /* COMPR_ALG_ZLIB */ + }; + + compress->level = default_compress_level[compress->alg]; + } + } +} + int main(int argc, char **argv) { @@ -319,7 +396,7 @@ main(int argc, char **argv) char *use_role = NULL; long rowsPerInsert; int numWorkers = 1; - int compressLevel = -1; + Compress compress = { .alg = COMPR_ALG_DEFAULT }; int plainText = 0; ArchiveFormat archiveFormat = archUnknown; ArchiveMode archiveMode; @@ -532,12 +609,7 @@ main(int argc, char **argv) break; case 'Z': /* Compression Level */ - compressLevel = atoi(optarg); - if (compressLevel < 0 || compressLevel > 9) - { - pg_log_error("compression level must be in range 0..9"); - exit_nicely(1); - } + parse_compression(optarg, &compress); break; case 0: @@ -679,20 +751,28 @@ main(int argc, char **argv) plainText = 1; /* Custom and directory formats are compressed by default, others not */ - if (compressLevel == -1) + if (compress.alg == COMPR_ALG_DEFAULT) { -#ifdef HAVE_LIBZ if (archiveFormat == archCustom || archiveFormat == archDirectory) - compressLevel = Z_DEFAULT_COMPRESSION; - else + { +#ifdef HAVE_LIBZ + compress.alg = COMPR_ALG_LIBZ; + compress.level = Z_DEFAULT_COMPRESSION; #endif - compressLevel = 0; + } + else + { + compress.alg = COMPR_ALG_NONE; + compress.level = 0; + } } #ifndef HAVE_LIBZ - if (compressLevel != 0) + if (compress.alg == COMPR_ALG_LIBZ) + { pg_log_warning("requested compression not available in this installation -- archive will be uncompressed"); - compressLevel = 0; + compress.alg = 0; + } #endif /* @@ -723,7 +803,7 @@ main(int argc, char **argv) fatal("option --index-collation-versions-unknown only works in binary upgrade mode"); /* Open the output file */ - fout = CreateArchive(filename, archiveFormat, compressLevel, dosync, + fout = CreateArchive(filename, archiveFormat, &compress, dosync, archiveMode, setupDumpWorker); /* Make dump options accessible right away */ @@ -957,10 +1037,7 @@ main(int argc, char **argv) ropt->sequence_data = dopt.sequence_data; ropt->binary_upgrade = dopt.binary_upgrade; - if (compressLevel == -1) - ropt->compression = 0; - else - ropt->compression = compressLevel; + ropt->compression = compress; ropt->suppressDumpWarnings = true; /* We've already shown them */ -- 2.17.0 --GRPZ8SYKNexpdSJ7 Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="0004-struct-compressLibs.patch" ^ permalink raw reply [nested|flat] 23+ messages in thread
* [PATCH 03/20] Support multiple compression algs/levels/opts.. @ 2020-12-22 06:23 Justin Pryzby <[email protected]> 0 siblings, 0 replies; 23+ messages in thread From: Justin Pryzby @ 2020-12-22 06:23 UTC (permalink / raw) The existing implementation abtracts compressed and noncompressed I/O. This preliminary commit is intended to also allow for multiple compression algorithms. --- src/bin/pg_dump/compress_io.c | 220 +++++++++++--------------- src/bin/pg_dump/compress_io.h | 19 +-- src/bin/pg_dump/pg_backup.h | 23 ++- src/bin/pg_dump/pg_backup_archiver.c | 45 +++--- src/bin/pg_dump/pg_backup_archiver.h | 12 +- src/bin/pg_dump/pg_backup_custom.c | 6 +- src/bin/pg_dump/pg_backup_directory.c | 17 +- src/bin/pg_dump/pg_backup_tar.c | 33 ++-- src/bin/pg_dump/pg_dump.c | 115 +++++++++++--- 9 files changed, 272 insertions(+), 218 deletions(-) diff --git a/src/bin/pg_dump/compress_io.c b/src/bin/pg_dump/compress_io.c index 6a428978d4..db16fd33f2 100644 --- a/src/bin/pg_dump/compress_io.c +++ b/src/bin/pg_dump/compress_io.c @@ -74,12 +74,9 @@ struct CompressorState #endif }; -static void ParseCompressionOption(int compression, CompressionAlgorithm *alg, - int *level); - /* Routines that support zlib compressed data I/O */ #ifdef HAVE_LIBZ -static void InitCompressorZlib(CompressorState *cs, int level); +static void InitCompressorZlib(CompressorState *cs, Compress *compress); static void DeflateCompressorZlib(ArchiveHandle *AH, CompressorState *cs, bool flush); static void ReadDataFromArchiveZlib(ArchiveHandle *AH, ReadFunc readF); @@ -93,58 +90,36 @@ static void ReadDataFromArchiveNone(ArchiveHandle *AH, ReadFunc readF); static void WriteDataToArchiveNone(ArchiveHandle *AH, CompressorState *cs, const char *data, size_t dLen); -/* - * Interprets a numeric 'compression' value. The algorithm implied by the - * value (zlib or none at the moment), is returned in *alg, and the - * zlib compression level in *level. - */ -static void -ParseCompressionOption(int compression, CompressionAlgorithm *alg, int *level) -{ - if (compression == Z_DEFAULT_COMPRESSION || - (compression > 0 && compression <= 9)) - *alg = COMPR_ALG_LIBZ; - else if (compression == 0) - *alg = COMPR_ALG_NONE; - else - { - fatal("invalid compression code: %d", compression); - *alg = COMPR_ALG_NONE; /* keep compiler quiet */ - } - - /* The level is just the passed-in value. */ - if (level) - *level = compression; -} - /* Public interface routines */ /* Allocate a new compressor */ CompressorState * -AllocateCompressor(int compression, WriteFunc writeF) +AllocateCompressor(Compress *compression, WriteFunc writeF) { CompressorState *cs; - CompressionAlgorithm alg; - int level; - - ParseCompressionOption(compression, &alg, &level); - -#ifndef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - fatal("not built with zlib support"); -#endif cs = (CompressorState *) pg_malloc0(sizeof(CompressorState)); cs->writeF = writeF; - cs->comprAlg = alg; + cs->comprAlg = compression->alg; /* * Perform compression algorithm specific initialization. */ + Assert (compression->alg != COMPR_ALG_DEFAULT); + switch (compression->alg) + { #ifdef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - InitCompressorZlib(cs, level); + case COMPR_ALG_LIBZ: + InitCompressorZlib(cs, compression); + break; #endif + case COMPR_ALG_NONE: + /* Do nothing */ + break; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } return cs; } @@ -154,21 +129,21 @@ AllocateCompressor(int compression, WriteFunc writeF) * out with ahwrite(). */ void -ReadDataFromArchive(ArchiveHandle *AH, int compression, ReadFunc readF) +ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF) { - CompressionAlgorithm alg; - - ParseCompressionOption(compression, &alg, NULL); - - if (alg == COMPR_ALG_NONE) - ReadDataFromArchiveNone(AH, readF); - if (alg == COMPR_ALG_LIBZ) + switch (AH->compression.alg) { + case COMPR_ALG_NONE: + ReadDataFromArchiveNone(AH, readF); + break; #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: ReadDataFromArchiveZlib(AH, readF); -#else - fatal("not built with zlib support"); + break; #endif + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -181,16 +156,18 @@ WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, { switch (cs->comprAlg) { - case COMPR_ALG_LIBZ: #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: WriteDataToArchiveZlib(AH, cs, data, dLen); -#else - fatal("not built with zlib support"); -#endif break; +#endif case COMPR_ALG_NONE: WriteDataToArchiveNone(AH, cs, data, dLen); break; + + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -215,7 +192,7 @@ EndCompressor(ArchiveHandle *AH, CompressorState *cs) */ static void -InitCompressorZlib(CompressorState *cs, int level) +InitCompressorZlib(CompressorState *cs, Compress *compress) { z_streamp zp; @@ -232,7 +209,7 @@ InitCompressorZlib(CompressorState *cs, int level) cs->zlibOut = (char *) pg_malloc(ZLIB_OUT_SIZE + 1); cs->zlibOutSize = ZLIB_OUT_SIZE; - if (deflateInit(zp, level) != Z_OK) + if (deflateInit(zp, compress->level) != Z_OK) fatal("could not initialize compression library: %s", zp->msg); @@ -424,9 +401,7 @@ struct cfp #endif }; -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix); -#endif /* free() without changing errno; useful in several places below */ static void @@ -442,34 +417,31 @@ free_keep_errno(void *p) * Open a file for reading. 'path' is the file to open, and 'mode' should * be either "r" or "rb". * - * If the file at 'path' does not exist, we append the ".gz" suffix (if 'path' - * doesn't already have it) and try again. So if you pass "foo" as 'path', + * If the file at 'path' does not exist, we search with compressed suffix (if 'path' + * doesn't already have one) and try again. So if you pass "foo" as 'path', * this will open either "foo" or "foo.gz". * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_read(const char *path, const char *mode) +cfopen_read(const char *path, const char *mode, Compress *compression) { cfp *fp; -#ifdef HAVE_LIBZ if (hasSuffix(path, ".gz")) - fp = cfopen(path, mode, 1); + fp = cfopen(path, mode, compression); else -#endif { - fp = cfopen(path, mode, 0); -#ifdef HAVE_LIBZ + fp = cfopen(path, mode, compression); if (fp == NULL) { char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); - fp = cfopen(fname, mode, 1); + fname = psprintf("%s%s", path, suffix); + fp = cfopen(fname, mode, compression); free_keep_errno(fname); } -#endif } return fp; } @@ -479,31 +451,26 @@ cfopen_read(const char *path, const char *mode) * be a filemode as accepted by fopen() and gzopen() that indicates writing * ("w", "wb", "a", or "ab"). * - * If 'compression' is non-zero, a gzip compressed stream is opened, and - * 'compression' indicates the compression level used. The ".gz" suffix - * is automatically added to 'path' in that case. + * Use compression if specified. + * The appropriate suffix is automatically added to 'path' in that case. * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_write(const char *path, const char *mode, int compression) +cfopen_write(const char *path, const char *mode, Compress *compression) { cfp *fp; - if (compression == 0) - fp = cfopen(path, mode, 0); + if (compression->alg == COMPR_ALG_NONE) + fp = cfopen(path, mode, compression); else { -#ifdef HAVE_LIBZ char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); + fname = psprintf("%s%s", path, suffix); fp = cfopen(fname, mode, compression); free_keep_errno(fname); -#else - fatal("not built with zlib support"); - fp = NULL; /* keep compiler quiet */ -#endif } return fp; } @@ -515,20 +482,21 @@ cfopen_write(const char *path, const char *mode, int compression) * On failure, return NULL with an error code in errno. */ cfp * -cfopen(const char *path, const char *mode, int compression) +cfopen(const char *path, const char *mode, Compress *compression) { - cfp *fp = pg_malloc(sizeof(cfp)); + cfp *fp = pg_malloc0(sizeof(cfp)); - if (compression != 0) + switch (compression->alg) { #ifdef HAVE_LIBZ - if (compression != Z_DEFAULT_COMPRESSION) + case COMPR_ALG_LIBZ: + if (compression->level != Z_DEFAULT_COMPRESSION) { /* user has specified a compression level, so tell zlib to use it */ char mode_compression[32]; snprintf(mode_compression, sizeof(mode_compression), "%s%d", - mode, compression); + mode, compression->level); fp->compressedfp = gzopen(path, mode_compression); } else @@ -537,30 +505,27 @@ cfopen(const char *path, const char *mode, int compression) fp->compressedfp = gzopen(path, mode); } - fp->uncompressedfp = NULL; if (fp->compressedfp == NULL) { free_keep_errno(fp); fp = NULL; } -#else - fatal("not built with zlib support"); -#endif - } - else - { -#ifdef HAVE_LIBZ - fp->compressedfp = NULL; + return fp; #endif + + case COMPR_ALG_NONE: fp->uncompressedfp = fopen(path, mode); if (fp->uncompressedfp == NULL) { free_keep_errno(fp); fp = NULL; } - } + return fp; - return fp; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } } @@ -584,14 +549,13 @@ cfread(void *ptr, int size, cfp *fp) fatal("could not read from input file: %s", errnum == Z_ERRNO ? strerror(errno) : errmsg); } + return ret; } - else #endif - { - ret = fread(ptr, 1, size, fp->uncompressedfp); - if (ret != size && !feof(fp->uncompressedfp)) - READ_ERROR_EXIT(fp->uncompressedfp); - } + + ret = fread(ptr, 1, size, fp->uncompressedfp); + if (ret != size && !feof(fp->uncompressedfp)) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -601,9 +565,8 @@ cfwrite(const void *ptr, int size, cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzwrite(fp->compressedfp, ptr, size); - else #endif - return fwrite(ptr, 1, size, fp->uncompressedfp); + return fwrite(ptr, 1, size, fp->uncompressedfp); } int @@ -622,15 +585,12 @@ cfgetc(cfp *fp) else fatal("could not read from input file: end of file"); } + return ret; } - else #endif - { - ret = fgetc(fp->uncompressedfp); - if (ret == EOF) - READ_ERROR_EXIT(fp->uncompressedfp); - } - + ret = fgetc(fp->uncompressedfp); + if (ret == EOF) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -640,9 +600,8 @@ cfgets(cfp *fp, char *buf, int len) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzgets(fp->compressedfp, buf, len); - else #endif - return fgets(buf, len, fp->uncompressedfp); + return fgets(buf, len, fp->uncompressedfp); } int @@ -660,15 +619,13 @@ cfclose(cfp *fp) { result = gzclose(fp->compressedfp); fp->compressedfp = NULL; + return result; } - else #endif - { - result = fclose(fp->uncompressedfp); - fp->uncompressedfp = NULL; - } - free_keep_errno(fp); + result = fclose(fp->uncompressedfp); + fp->uncompressedfp = NULL; + free_keep_errno(fp); return result; } @@ -678,9 +635,9 @@ cfeof(cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzeof(fp->compressedfp); - else #endif - return feof(fp->uncompressedfp); + + return feof(fp->uncompressedfp); } const char * @@ -699,7 +656,6 @@ get_cfp_error(cfp *fp) return strerror(errno); } -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix) { @@ -714,4 +670,18 @@ hasSuffix(const char *filename, const char *suffix) suffixlen) == 0; } -#endif +/* + * Return a string for the given AH's compression. + * The string is statically allocated. + */ +const char * +compress_suffix(Compress *compression) +{ + switch (compression->alg) + { + case COMPR_ALG_LIBZ: + return ".gz"; + default: + return ""; + } +} diff --git a/src/bin/pg_dump/compress_io.h b/src/bin/pg_dump/compress_io.h index d2e6e1b854..2c073676eb 100644 --- a/src/bin/pg_dump/compress_io.h +++ b/src/bin/pg_dump/compress_io.h @@ -21,12 +21,6 @@ #define ZLIB_OUT_SIZE 4096 #define ZLIB_IN_SIZE 4096 -typedef enum -{ - COMPR_ALG_NONE, - COMPR_ALG_LIBZ -} CompressionAlgorithm; - /* Prototype for callback function to WriteDataToArchive() */ typedef void (*WriteFunc) (ArchiveHandle *AH, const char *buf, size_t len); @@ -46,8 +40,8 @@ typedef size_t (*ReadFunc) (ArchiveHandle *AH, char **buf, size_t *buflen); /* struct definition appears in compress_io.c */ typedef struct CompressorState CompressorState; -extern CompressorState *AllocateCompressor(int compression, WriteFunc writeF); -extern void ReadDataFromArchive(ArchiveHandle *AH, int compression, +extern CompressorState *AllocateCompressor(Compress *compression, WriteFunc writeF); +extern void ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF); extern void WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, const void *data, size_t dLen); @@ -56,9 +50,9 @@ extern void EndCompressor(ArchiveHandle *AH, CompressorState *cs); typedef struct cfp cfp; -extern cfp *cfopen(const char *path, const char *mode, int compression); -extern cfp *cfopen_read(const char *path, const char *mode); -extern cfp *cfopen_write(const char *path, const char *mode, int compression); +extern cfp *cfopen(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_read(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_write(const char *path, const char *mode, Compress *compression); extern int cfread(void *ptr, int size, cfp *fp); extern int cfwrite(const void *ptr, int size, cfp *fp); extern int cfgetc(cfp *fp); @@ -67,4 +61,7 @@ extern int cfclose(cfp *fp); extern int cfeof(cfp *fp); extern const char *get_cfp_error(cfp *fp); +/* also used by tar */ +extern const char * compress_suffix(Compress *compression); + #endif diff --git a/src/bin/pg_dump/pg_backup.h b/src/bin/pg_dump/pg_backup.h index 9d0056a569..f2390b7937 100644 --- a/src/bin/pg_dump/pg_backup.h +++ b/src/bin/pg_dump/pg_backup.h @@ -72,6 +72,25 @@ typedef struct _connParams char *override_dbname; } ConnParams; +typedef enum +{ + COMPR_ALG_DEFAULT = -1, + COMPR_ALG_NONE, + COMPR_ALG_LIBZ, +} CompressionAlgorithm; +/* Should be called "method" or "library" ? */ + +typedef struct Compress { + CompressionAlgorithm alg; + int level; + /* Is a nondefault level set ? This is useful since different compression + * methods have different "default" levels. For now we assume the levels + * are all integer, though. + */ + bool level_set; +} Compress; + + typedef struct _restoreOptions { int createDB; /* Issue commands to create the database */ @@ -125,7 +144,7 @@ typedef struct _restoreOptions int noDataForFailedTables; int exit_on_error; - int compression; + Compress compression; int suppressDumpWarnings; /* Suppress output of WARNING entries * to stderr */ bool single_txn; @@ -281,7 +300,7 @@ extern Archive *OpenArchive(const char *FileSpec, const ArchiveFormat fmt); /* Create a new archive */ extern Archive *CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker); /* The --list option */ diff --git a/src/bin/pg_dump/pg_backup_archiver.c b/src/bin/pg_dump/pg_backup_archiver.c index 1f82c6499b..3eb6c55600 100644 --- a/src/bin/pg_dump/pg_backup_archiver.c +++ b/src/bin/pg_dump/pg_backup_archiver.c @@ -70,7 +70,7 @@ typedef struct _parallelReadyList static ArchiveHandle *_allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr); static void _getObjectDescription(PQExpBuffer buf, TocEntry *te); static void _printTocEntry(ArchiveHandle *AH, TocEntry *te, bool isData); @@ -98,7 +98,7 @@ static int _discoverArchiveFormat(ArchiveHandle *AH); static int RestoringToDB(ArchiveHandle *AH); static void dump_lo_buf(ArchiveHandle *AH); static void dumpTimestamp(ArchiveHandle *AH, const char *msg, time_t tim); -static void SetOutput(ArchiveHandle *AH, const char *filename, int compression); +static void SetOutput(ArchiveHandle *AH, const char *filename, Compress *compress); static OutputContext SaveOutput(ArchiveHandle *AH); static void RestoreOutput(ArchiveHandle *AH, OutputContext savedContext); @@ -238,7 +238,7 @@ setupRestoreWorker(Archive *AHX) /* Public */ Archive * CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker) { @@ -253,7 +253,9 @@ CreateArchive(const char *FileSpec, const ArchiveFormat fmt, Archive * OpenArchive(const char *FileSpec, const ArchiveFormat fmt) { - ArchiveHandle *AH = _allocAH(FileSpec, fmt, 0, true, archModeRead, setupRestoreWorker); + Compress compress = {0}; + ArchiveHandle *AH = _allocAH(FileSpec, fmt, &compress, true, archModeRead, + setupRestoreWorker); return (Archive *) AH; } @@ -382,7 +384,7 @@ RestoreArchive(Archive *AHX) * Make sure we won't need (de)compression we haven't got */ #ifndef HAVE_LIBZ - if (AH->compression != 0 && AH->PrintTocDataPtr != NULL) + if (AH->compression.alg != COMPR_ALG_NONE && AH->PrintTocDataPtr != NULL) { for (te = AH->toc->next; te != AH->toc; te = te->next) { @@ -457,8 +459,8 @@ RestoreArchive(Archive *AHX) * Setup the output file if necessary. */ sav = SaveOutput(AH); - if (ropt->filename || ropt->compression) - SetOutput(AH, ropt->filename, ropt->compression); + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) + SetOutput(AH, ropt->filename, &ropt->compression); ahprintf(AH, "--\n-- PostgreSQL database dump\n--\n\n"); @@ -738,7 +740,7 @@ RestoreArchive(Archive *AHX) */ AH->stage = STAGE_FINALIZING; - if (ropt->filename || ropt->compression) + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) RestoreOutput(AH, sav); if (ropt->useDB) @@ -1123,8 +1125,9 @@ PrintTOCSummary(Archive *AHX) char stamp_str[64]; sav = SaveOutput(AH); + Assert(ropt->compression.alg == COMPR_ALG_NONE); if (ropt->filename) - SetOutput(AH, ropt->filename, 0 /* no compression */ ); + SetOutput(AH, ropt->filename, &ropt->compression); if (strftime(stamp_str, sizeof(stamp_str), PGDUMP_STRFTIME_FMT, localtime(&AH->createDate)) == 0) @@ -1133,7 +1136,7 @@ PrintTOCSummary(Archive *AHX) ahprintf(AH, ";\n; Archive created at %s\n", stamp_str); ahprintf(AH, "; dbname: %s\n; TOC Entries: %d\n; Compression: %d\n", sanitize_line(AH->archdbname, false), - AH->tocCount, AH->compression); + AH->tocCount, AH->compression.alg); switch (AH->format) { @@ -1487,7 +1490,7 @@ archprintf(Archive *AH, const char *fmt,...) *******************************/ static void -SetOutput(ArchiveHandle *AH, const char *filename, int compression) +SetOutput(ArchiveHandle *AH, const char *filename, Compress *compression) { int fn; @@ -1510,12 +1513,12 @@ SetOutput(ArchiveHandle *AH, const char *filename, int compression) /* If compression explicitly requested, use gzopen */ #ifdef HAVE_LIBZ - if (compression != 0) + if (compression->alg != COMPR_ALG_NONE) { char fmode[14]; /* Don't use PG_BINARY_x since this is zlib */ - sprintf(fmode, "wb%d", compression); + sprintf(fmode, "wb%d", compression->level); if (fn >= 0) AH->OF = gzdopen(dup(fn), fmode); else @@ -2259,7 +2262,7 @@ _discoverArchiveFormat(ArchiveHandle *AH) */ static ArchiveHandle * _allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr) { ArchiveHandle *AH; @@ -2310,7 +2313,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, AH->toc->prev = AH->toc; AH->mode = mode; - AH->compression = compression; + AH->compression = *compression; AH->dosync = dosync; memset(&(AH->sqlparse), 0, sizeof(AH->sqlparse)); @@ -2325,7 +2328,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, * Force stdin/stdout into binary mode if that is what we are using. */ #ifdef WIN32 - if ((fmt != archNull || compression != 0) && + if ((fmt != archNull || compression->alg != COMPR_ALG_NONE) && (AH->fSpec == NULL || strcmp(AH->fSpec, "") == 0)) { if (mode == archModeWrite) @@ -3741,7 +3744,7 @@ WriteHead(ArchiveHandle *AH) AH->WriteBytePtr(AH, AH->intSize); AH->WriteBytePtr(AH, AH->offSize); AH->WriteBytePtr(AH, AH->format); - WriteInt(AH, AH->compression); + WriteInt(AH, AH->compression.alg); crtm = *localtime(&AH->createDate); WriteInt(AH, crtm.tm_sec); WriteInt(AH, crtm.tm_min); @@ -3816,15 +3819,15 @@ ReadHead(ArchiveHandle *AH) if (AH->version >= K_VERS_1_2) { if (AH->version < K_VERS_1_4) - AH->compression = AH->ReadBytePtr(AH); + AH->compression.alg = AH->ReadBytePtr(AH); else - AH->compression = ReadInt(AH); + AH->compression.alg = ReadInt(AH); } else - AH->compression = Z_DEFAULT_COMPRESSION; + AH->compression.alg = Z_DEFAULT_COMPRESSION; #ifndef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) pg_log_warning("archive is compressed, but this installation does not support compression -- no data will be available"); #endif diff --git a/src/bin/pg_dump/pg_backup_archiver.h b/src/bin/pg_dump/pg_backup_archiver.h index a8ea5c7eae..6e033d040e 100644 --- a/src/bin/pg_dump/pg_backup_archiver.h +++ b/src/bin/pg_dump/pg_backup_archiver.h @@ -47,7 +47,8 @@ #define GZWRITE(p, s, n, fh) (fwrite(p, s, n, fh) * (s)) #define GZREAD(p, s, n, fh) fread(p, s, n, fh) #define GZEOF(fh) feof(fh) -/* this is just the redefinition of a libz constant */ +/* this is just the redefinition of a libz constant, in case zlib isn't + * available */ #define Z_DEFAULT_COMPRESSION (-1) typedef struct _z_stream @@ -329,14 +330,7 @@ struct _archiveHandle DumpId *tableDataId; /* TABLE DATA ids, indexed by table dumpId */ struct _tocEntry *currToc; /* Used when dumping data */ - int compression; /*--------- - * Compression requested on open(). - * Possible values for compression: - * -1 Z_DEFAULT_COMPRESSION - * 0 COMPRESSION_NONE - * 1-9 levels for gzip compression - *--------- - */ + Compress compression; /* Compression requested on open */ bool dosync; /* data requested to be synced on sight */ ArchiveMode mode; /* File mode - r or w */ void *formatData; /* Header data specific to file format */ diff --git a/src/bin/pg_dump/pg_backup_custom.c b/src/bin/pg_dump/pg_backup_custom.c index 77d402c323..55a887a236 100644 --- a/src/bin/pg_dump/pg_backup_custom.c +++ b/src/bin/pg_dump/pg_backup_custom.c @@ -298,7 +298,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) _WriteByte(AH, BLK_DATA); /* Block type */ WriteInt(AH, te->dumpId); /* For sanity check */ - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -377,7 +377,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) WriteInt(AH, oid); - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -566,7 +566,7 @@ _PrintTocData(ArchiveHandle *AH, TocEntry *te) static void _PrintData(ArchiveHandle *AH) { - ReadDataFromArchive(AH, AH->compression, _CustomReadFunc); + ReadDataFromArchive(AH, _CustomReadFunc); } static void diff --git a/src/bin/pg_dump/pg_backup_directory.c b/src/bin/pg_dump/pg_backup_directory.c index 650b542fce..8bf869c6ca 100644 --- a/src/bin/pg_dump/pg_backup_directory.c +++ b/src/bin/pg_dump/pg_backup_directory.c @@ -202,7 +202,7 @@ InitArchiveFmt_Directory(ArchiveHandle *AH) setFilePath(AH, fname, "toc.dat"); - tocFH = cfopen_read(fname, PG_BINARY_R); + tocFH = cfopen_read(fname, PG_BINARY_R, &AH->compression); if (tocFH == NULL) fatal("could not open input file \"%s\": %m", fname); @@ -327,7 +327,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) setFilePath(AH, fname, tctx->filename); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -388,7 +388,7 @@ _PrintFileData(ArchiveHandle *AH, char *filename) if (!filename) return; - cfp = cfopen_read(filename, PG_BINARY_R); + cfp = cfopen_read(filename, PG_BINARY_R, &AH->compression); if (!cfp) fatal("could not open input file \"%s\": %m", filename); @@ -435,12 +435,13 @@ _LoadBlobs(ArchiveHandle *AH) lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; char line[MAXPGPATH]; + Compress nocompression = {0}; StartRestoreBlobs(AH); setFilePath(AH, fname, "blobs.toc"); - ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R); + ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R, &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open large object TOC file \"%s\" for input: %m", @@ -573,6 +574,7 @@ _CloseArchive(ArchiveHandle *AH) { cfp *tocFH; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "toc.dat"); @@ -580,7 +582,7 @@ _CloseArchive(ArchiveHandle *AH) ctx->pstate = ParallelBackupStart(AH); /* The TOC is always created uncompressed */ - tocFH = cfopen_write(fname, PG_BINARY_W, 0); + tocFH = cfopen_write(fname, PG_BINARY_W, &nocompression); if (tocFH == NULL) fatal("could not open output file \"%s\": %m", fname); ctx->dataFH = tocFH; @@ -639,11 +641,12 @@ _StartBlobs(ArchiveHandle *AH, TocEntry *te) { lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "blobs.toc"); /* The blob TOC file is never compressed */ - ctx->blobsTocFH = cfopen_write(fname, "ab", 0); + ctx->blobsTocFH = cfopen_write(fname, "ab", &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -661,7 +664,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) snprintf(fname, MAXPGPATH, "%s/blob_%u.dat", ctx->directory, oid); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); diff --git a/src/bin/pg_dump/pg_backup_tar.c b/src/bin/pg_dump/pg_backup_tar.c index 61c9c87a9f..4ba79ab924 100644 --- a/src/bin/pg_dump/pg_backup_tar.c +++ b/src/bin/pg_dump/pg_backup_tar.c @@ -39,6 +39,7 @@ #include "pg_backup_archiver.h" #include "pg_backup_tar.h" #include "pg_backup_utils.h" +#include "compress_io.h" #include "pgtar.h" static void _ArchiveEntry(ArchiveHandle *AH, TocEntry *te); @@ -196,10 +197,10 @@ InitArchiveFmt_Tar(ArchiveHandle *AH) /* * We don't support compression because reading the files back is not - * possible since gzdopen uses buffered IO which totally screws file + * possible since gzdopen uses buffered IO which totally screws file XXX * positioning. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) fatal("compression is not supported by tar archive format"); } else @@ -254,14 +255,8 @@ _ArchiveEntry(ArchiveHandle *AH, TocEntry *te) ctx = (lclTocEntry *) pg_malloc0(sizeof(lclTocEntry)); if (te->dataDumper != NULL) { -#ifdef HAVE_LIBZ - if (AH->compression == 0) - sprintf(fn, "%d.dat", te->dumpId); - else - sprintf(fn, "%d.dat.gz", te->dumpId); -#else - sprintf(fn, "%d.dat", te->dumpId); -#endif + const char *suffix = compress_suffix(&AH->compression); + sprintf(fn, "%d.dat%s", te->dumpId, suffix); ctx->filename = pg_strdup(fn); } else @@ -352,7 +347,7 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression == 0) + if (AH->compression.alg == COMPR_ALG_NONE) tm->nFH = ctx->tarFH; else fatal("compression is not supported by tar archive format"); @@ -413,9 +408,9 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) { - sprintf(fmode, "wb%d", AH->compression); + sprintf(fmode, "wb%d", AH->compression.level); tm->zFH = gzdopen(dup(fileno(tm->tmpFH)), fmode); if (tm->zFH == NULL) fatal("could not open temporary file"); @@ -443,7 +438,7 @@ tarClose(ArchiveHandle *AH, TAR_MEMBER *th) /* * Close the GZ file since we dup'd. This will flush the buffers. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) if (GZCLOSE(th->zFH) != 0) fatal("could not close tar member"); @@ -868,7 +863,7 @@ _CloseArchive(ArchiveHandle *AH) memcpy(ropt, AH->public.ropt, sizeof(RestoreOptions)); ropt->filename = NULL; ropt->dropSchema = 1; - ropt->compression = 0; + ropt->compression.alg = COMPR_ALG_NONE; ropt->superuser = NULL; ropt->suppressDumpWarnings = true; @@ -952,16 +947,12 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) lclContext *ctx = (lclContext *) AH->formatData; lclTocEntry *tctx = (lclTocEntry *) te->formatData; char fname[255]; - char *sfx; + const char *sfx; if (oid == 0) fatal("invalid OID for large object (%u)", oid); - if (AH->compression != 0) - sfx = ".gz"; - else - sfx = ""; - + sfx = compress_suffix(&AH->compression); sprintf(fname, "blob_%u.dat%s", oid, sfx); tarPrintf(ctx->blobToc, "%u %s\n", oid, fname); diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c index 1ab98a2286..4cbc79aedc 100644 --- a/src/bin/pg_dump/pg_dump.c +++ b/src/bin/pg_dump/pg_dump.c @@ -59,6 +59,7 @@ #include "getopt_long.h" #include "libpq/libpq-fs.h" #include "parallel.h" +#include "compress_io.h" #include "pg_backup_db.h" #include "pg_backup_utils.h" #include "pg_dump.h" @@ -297,6 +298,82 @@ static void setupDumpWorker(Archive *AHX); static TableInfo *getRootTableInfo(TableInfo *tbinfo); +/* Parse the string into compression options */ +static void +parse_compression(const char *optarg, Compress *compress) +{ + if (optarg[0] == '0' && optarg[1] == '\0') + compress->alg = COMPR_ALG_NONE; + else if ((optarg[0] > '0' && optarg[0] <= '9') || + optarg[0] == '-') + { + compress->alg = COMPR_ALG_LIBZ; + compress->level_set = true; + compress->level = atoi(optarg); + if (optarg[1] != '\0') + { + pg_log_error("compression level must be in range 0..9"); + exit_nicely(1); + } + } + else + { + /* Parse a more flexible string like level=3 alg=zlib opts=long */ + for (;;) + { + char *eq = strchr(optarg, '='); + int len; + + if (eq == NULL) + { + pg_log_error("compression options must be key=value: %s", optarg); + exit_nicely(1); + } + + len = eq - optarg; + if (strncmp(optarg, "alg", len) == 0) + { + if (strchr(eq, ' ')) + len = strchr(eq, ' ') - eq - 1; + else + len = strlen(eq) - len; + if (strncmp(1+eq, "zlib", len) == 0 || + strncmp(1+eq, "libz", len) == 0) + compress->alg = COMPR_ALG_LIBZ; + else + { + pg_log_error("unknown compression algorithm: %s", 1+eq); + exit_nicely(1); + } + } + else if (strncmp(optarg, "level", len) == 0) + { + compress->level = atoi(1+eq); + compress->level_set = true; + } + else + { + pg_log_error("unknown compression setting: %s", optarg); + exit_nicely(1); + } + + optarg = strchr(eq, ' '); + if (!optarg++) + break; + } + + if (!compress->level_set) + { + const int default_compress_level[] = { + 0, /* COMPR_ALG_NONE */ + Z_DEFAULT_COMPRESSION, /* COMPR_ALG_ZLIB */ + }; + + compress->level = default_compress_level[compress->alg]; + } + } +} + int main(int argc, char **argv) { @@ -319,7 +396,7 @@ main(int argc, char **argv) char *use_role = NULL; long rowsPerInsert; int numWorkers = 1; - int compressLevel = -1; + Compress compress = { .alg = COMPR_ALG_DEFAULT }; int plainText = 0; ArchiveFormat archiveFormat = archUnknown; ArchiveMode archiveMode; @@ -532,12 +609,7 @@ main(int argc, char **argv) break; case 'Z': /* Compression Level */ - compressLevel = atoi(optarg); - if (compressLevel < 0 || compressLevel > 9) - { - pg_log_error("compression level must be in range 0..9"); - exit_nicely(1); - } + parse_compression(optarg, &compress); break; case 0: @@ -679,20 +751,28 @@ main(int argc, char **argv) plainText = 1; /* Custom and directory formats are compressed by default, others not */ - if (compressLevel == -1) + if (compress.alg == COMPR_ALG_DEFAULT) { -#ifdef HAVE_LIBZ if (archiveFormat == archCustom || archiveFormat == archDirectory) - compressLevel = Z_DEFAULT_COMPRESSION; - else + { +#ifdef HAVE_LIBZ + compress.alg = COMPR_ALG_LIBZ; + compress.level = Z_DEFAULT_COMPRESSION; #endif - compressLevel = 0; + } + else + { + compress.alg = COMPR_ALG_NONE; + compress.level = 0; + } } #ifndef HAVE_LIBZ - if (compressLevel != 0) + if (compress.alg == COMPR_ALG_LIBZ) + { pg_log_warning("requested compression not available in this installation -- archive will be uncompressed"); - compressLevel = 0; + compress.alg = 0; + } #endif /* @@ -723,7 +803,7 @@ main(int argc, char **argv) fatal("option --index-collation-versions-unknown only works in binary upgrade mode"); /* Open the output file */ - fout = CreateArchive(filename, archiveFormat, compressLevel, dosync, + fout = CreateArchive(filename, archiveFormat, &compress, dosync, archiveMode, setupDumpWorker); /* Make dump options accessible right away */ @@ -957,10 +1037,7 @@ main(int argc, char **argv) ropt->sequence_data = dopt.sequence_data; ropt->binary_upgrade = dopt.binary_upgrade; - if (compressLevel == -1) - ropt->compression = 0; - else - ropt->compression = compressLevel; + ropt->compression = compress; ropt->suppressDumpWarnings = true; /* We've already shown them */ -- 2.17.0 --GRPZ8SYKNexpdSJ7 Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="0004-struct-compressLibs.patch" ^ permalink raw reply [nested|flat] 23+ messages in thread
* [PATCH 03/20] Support multiple compression algs/levels/opts.. @ 2020-12-22 06:23 Justin Pryzby <[email protected]> 0 siblings, 0 replies; 23+ messages in thread From: Justin Pryzby @ 2020-12-22 06:23 UTC (permalink / raw) The existing implementation abtracts compressed and noncompressed I/O. This preliminary commit is intended to also allow for multiple compression algorithms. --- src/bin/pg_dump/compress_io.c | 220 +++++++++++--------------- src/bin/pg_dump/compress_io.h | 19 +-- src/bin/pg_dump/pg_backup.h | 23 ++- src/bin/pg_dump/pg_backup_archiver.c | 45 +++--- src/bin/pg_dump/pg_backup_archiver.h | 12 +- src/bin/pg_dump/pg_backup_custom.c | 6 +- src/bin/pg_dump/pg_backup_directory.c | 17 +- src/bin/pg_dump/pg_backup_tar.c | 33 ++-- src/bin/pg_dump/pg_dump.c | 115 +++++++++++--- 9 files changed, 272 insertions(+), 218 deletions(-) diff --git a/src/bin/pg_dump/compress_io.c b/src/bin/pg_dump/compress_io.c index 6a428978d4..db16fd33f2 100644 --- a/src/bin/pg_dump/compress_io.c +++ b/src/bin/pg_dump/compress_io.c @@ -74,12 +74,9 @@ struct CompressorState #endif }; -static void ParseCompressionOption(int compression, CompressionAlgorithm *alg, - int *level); - /* Routines that support zlib compressed data I/O */ #ifdef HAVE_LIBZ -static void InitCompressorZlib(CompressorState *cs, int level); +static void InitCompressorZlib(CompressorState *cs, Compress *compress); static void DeflateCompressorZlib(ArchiveHandle *AH, CompressorState *cs, bool flush); static void ReadDataFromArchiveZlib(ArchiveHandle *AH, ReadFunc readF); @@ -93,58 +90,36 @@ static void ReadDataFromArchiveNone(ArchiveHandle *AH, ReadFunc readF); static void WriteDataToArchiveNone(ArchiveHandle *AH, CompressorState *cs, const char *data, size_t dLen); -/* - * Interprets a numeric 'compression' value. The algorithm implied by the - * value (zlib or none at the moment), is returned in *alg, and the - * zlib compression level in *level. - */ -static void -ParseCompressionOption(int compression, CompressionAlgorithm *alg, int *level) -{ - if (compression == Z_DEFAULT_COMPRESSION || - (compression > 0 && compression <= 9)) - *alg = COMPR_ALG_LIBZ; - else if (compression == 0) - *alg = COMPR_ALG_NONE; - else - { - fatal("invalid compression code: %d", compression); - *alg = COMPR_ALG_NONE; /* keep compiler quiet */ - } - - /* The level is just the passed-in value. */ - if (level) - *level = compression; -} - /* Public interface routines */ /* Allocate a new compressor */ CompressorState * -AllocateCompressor(int compression, WriteFunc writeF) +AllocateCompressor(Compress *compression, WriteFunc writeF) { CompressorState *cs; - CompressionAlgorithm alg; - int level; - - ParseCompressionOption(compression, &alg, &level); - -#ifndef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - fatal("not built with zlib support"); -#endif cs = (CompressorState *) pg_malloc0(sizeof(CompressorState)); cs->writeF = writeF; - cs->comprAlg = alg; + cs->comprAlg = compression->alg; /* * Perform compression algorithm specific initialization. */ + Assert (compression->alg != COMPR_ALG_DEFAULT); + switch (compression->alg) + { #ifdef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - InitCompressorZlib(cs, level); + case COMPR_ALG_LIBZ: + InitCompressorZlib(cs, compression); + break; #endif + case COMPR_ALG_NONE: + /* Do nothing */ + break; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } return cs; } @@ -154,21 +129,21 @@ AllocateCompressor(int compression, WriteFunc writeF) * out with ahwrite(). */ void -ReadDataFromArchive(ArchiveHandle *AH, int compression, ReadFunc readF) +ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF) { - CompressionAlgorithm alg; - - ParseCompressionOption(compression, &alg, NULL); - - if (alg == COMPR_ALG_NONE) - ReadDataFromArchiveNone(AH, readF); - if (alg == COMPR_ALG_LIBZ) + switch (AH->compression.alg) { + case COMPR_ALG_NONE: + ReadDataFromArchiveNone(AH, readF); + break; #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: ReadDataFromArchiveZlib(AH, readF); -#else - fatal("not built with zlib support"); + break; #endif + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -181,16 +156,18 @@ WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, { switch (cs->comprAlg) { - case COMPR_ALG_LIBZ: #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: WriteDataToArchiveZlib(AH, cs, data, dLen); -#else - fatal("not built with zlib support"); -#endif break; +#endif case COMPR_ALG_NONE: WriteDataToArchiveNone(AH, cs, data, dLen); break; + + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -215,7 +192,7 @@ EndCompressor(ArchiveHandle *AH, CompressorState *cs) */ static void -InitCompressorZlib(CompressorState *cs, int level) +InitCompressorZlib(CompressorState *cs, Compress *compress) { z_streamp zp; @@ -232,7 +209,7 @@ InitCompressorZlib(CompressorState *cs, int level) cs->zlibOut = (char *) pg_malloc(ZLIB_OUT_SIZE + 1); cs->zlibOutSize = ZLIB_OUT_SIZE; - if (deflateInit(zp, level) != Z_OK) + if (deflateInit(zp, compress->level) != Z_OK) fatal("could not initialize compression library: %s", zp->msg); @@ -424,9 +401,7 @@ struct cfp #endif }; -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix); -#endif /* free() without changing errno; useful in several places below */ static void @@ -442,34 +417,31 @@ free_keep_errno(void *p) * Open a file for reading. 'path' is the file to open, and 'mode' should * be either "r" or "rb". * - * If the file at 'path' does not exist, we append the ".gz" suffix (if 'path' - * doesn't already have it) and try again. So if you pass "foo" as 'path', + * If the file at 'path' does not exist, we search with compressed suffix (if 'path' + * doesn't already have one) and try again. So if you pass "foo" as 'path', * this will open either "foo" or "foo.gz". * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_read(const char *path, const char *mode) +cfopen_read(const char *path, const char *mode, Compress *compression) { cfp *fp; -#ifdef HAVE_LIBZ if (hasSuffix(path, ".gz")) - fp = cfopen(path, mode, 1); + fp = cfopen(path, mode, compression); else -#endif { - fp = cfopen(path, mode, 0); -#ifdef HAVE_LIBZ + fp = cfopen(path, mode, compression); if (fp == NULL) { char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); - fp = cfopen(fname, mode, 1); + fname = psprintf("%s%s", path, suffix); + fp = cfopen(fname, mode, compression); free_keep_errno(fname); } -#endif } return fp; } @@ -479,31 +451,26 @@ cfopen_read(const char *path, const char *mode) * be a filemode as accepted by fopen() and gzopen() that indicates writing * ("w", "wb", "a", or "ab"). * - * If 'compression' is non-zero, a gzip compressed stream is opened, and - * 'compression' indicates the compression level used. The ".gz" suffix - * is automatically added to 'path' in that case. + * Use compression if specified. + * The appropriate suffix is automatically added to 'path' in that case. * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_write(const char *path, const char *mode, int compression) +cfopen_write(const char *path, const char *mode, Compress *compression) { cfp *fp; - if (compression == 0) - fp = cfopen(path, mode, 0); + if (compression->alg == COMPR_ALG_NONE) + fp = cfopen(path, mode, compression); else { -#ifdef HAVE_LIBZ char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); + fname = psprintf("%s%s", path, suffix); fp = cfopen(fname, mode, compression); free_keep_errno(fname); -#else - fatal("not built with zlib support"); - fp = NULL; /* keep compiler quiet */ -#endif } return fp; } @@ -515,20 +482,21 @@ cfopen_write(const char *path, const char *mode, int compression) * On failure, return NULL with an error code in errno. */ cfp * -cfopen(const char *path, const char *mode, int compression) +cfopen(const char *path, const char *mode, Compress *compression) { - cfp *fp = pg_malloc(sizeof(cfp)); + cfp *fp = pg_malloc0(sizeof(cfp)); - if (compression != 0) + switch (compression->alg) { #ifdef HAVE_LIBZ - if (compression != Z_DEFAULT_COMPRESSION) + case COMPR_ALG_LIBZ: + if (compression->level != Z_DEFAULT_COMPRESSION) { /* user has specified a compression level, so tell zlib to use it */ char mode_compression[32]; snprintf(mode_compression, sizeof(mode_compression), "%s%d", - mode, compression); + mode, compression->level); fp->compressedfp = gzopen(path, mode_compression); } else @@ -537,30 +505,27 @@ cfopen(const char *path, const char *mode, int compression) fp->compressedfp = gzopen(path, mode); } - fp->uncompressedfp = NULL; if (fp->compressedfp == NULL) { free_keep_errno(fp); fp = NULL; } -#else - fatal("not built with zlib support"); -#endif - } - else - { -#ifdef HAVE_LIBZ - fp->compressedfp = NULL; + return fp; #endif + + case COMPR_ALG_NONE: fp->uncompressedfp = fopen(path, mode); if (fp->uncompressedfp == NULL) { free_keep_errno(fp); fp = NULL; } - } + return fp; - return fp; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } } @@ -584,14 +549,13 @@ cfread(void *ptr, int size, cfp *fp) fatal("could not read from input file: %s", errnum == Z_ERRNO ? strerror(errno) : errmsg); } + return ret; } - else #endif - { - ret = fread(ptr, 1, size, fp->uncompressedfp); - if (ret != size && !feof(fp->uncompressedfp)) - READ_ERROR_EXIT(fp->uncompressedfp); - } + + ret = fread(ptr, 1, size, fp->uncompressedfp); + if (ret != size && !feof(fp->uncompressedfp)) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -601,9 +565,8 @@ cfwrite(const void *ptr, int size, cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzwrite(fp->compressedfp, ptr, size); - else #endif - return fwrite(ptr, 1, size, fp->uncompressedfp); + return fwrite(ptr, 1, size, fp->uncompressedfp); } int @@ -622,15 +585,12 @@ cfgetc(cfp *fp) else fatal("could not read from input file: end of file"); } + return ret; } - else #endif - { - ret = fgetc(fp->uncompressedfp); - if (ret == EOF) - READ_ERROR_EXIT(fp->uncompressedfp); - } - + ret = fgetc(fp->uncompressedfp); + if (ret == EOF) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -640,9 +600,8 @@ cfgets(cfp *fp, char *buf, int len) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzgets(fp->compressedfp, buf, len); - else #endif - return fgets(buf, len, fp->uncompressedfp); + return fgets(buf, len, fp->uncompressedfp); } int @@ -660,15 +619,13 @@ cfclose(cfp *fp) { result = gzclose(fp->compressedfp); fp->compressedfp = NULL; + return result; } - else #endif - { - result = fclose(fp->uncompressedfp); - fp->uncompressedfp = NULL; - } - free_keep_errno(fp); + result = fclose(fp->uncompressedfp); + fp->uncompressedfp = NULL; + free_keep_errno(fp); return result; } @@ -678,9 +635,9 @@ cfeof(cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzeof(fp->compressedfp); - else #endif - return feof(fp->uncompressedfp); + + return feof(fp->uncompressedfp); } const char * @@ -699,7 +656,6 @@ get_cfp_error(cfp *fp) return strerror(errno); } -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix) { @@ -714,4 +670,18 @@ hasSuffix(const char *filename, const char *suffix) suffixlen) == 0; } -#endif +/* + * Return a string for the given AH's compression. + * The string is statically allocated. + */ +const char * +compress_suffix(Compress *compression) +{ + switch (compression->alg) + { + case COMPR_ALG_LIBZ: + return ".gz"; + default: + return ""; + } +} diff --git a/src/bin/pg_dump/compress_io.h b/src/bin/pg_dump/compress_io.h index d2e6e1b854..2c073676eb 100644 --- a/src/bin/pg_dump/compress_io.h +++ b/src/bin/pg_dump/compress_io.h @@ -21,12 +21,6 @@ #define ZLIB_OUT_SIZE 4096 #define ZLIB_IN_SIZE 4096 -typedef enum -{ - COMPR_ALG_NONE, - COMPR_ALG_LIBZ -} CompressionAlgorithm; - /* Prototype for callback function to WriteDataToArchive() */ typedef void (*WriteFunc) (ArchiveHandle *AH, const char *buf, size_t len); @@ -46,8 +40,8 @@ typedef size_t (*ReadFunc) (ArchiveHandle *AH, char **buf, size_t *buflen); /* struct definition appears in compress_io.c */ typedef struct CompressorState CompressorState; -extern CompressorState *AllocateCompressor(int compression, WriteFunc writeF); -extern void ReadDataFromArchive(ArchiveHandle *AH, int compression, +extern CompressorState *AllocateCompressor(Compress *compression, WriteFunc writeF); +extern void ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF); extern void WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, const void *data, size_t dLen); @@ -56,9 +50,9 @@ extern void EndCompressor(ArchiveHandle *AH, CompressorState *cs); typedef struct cfp cfp; -extern cfp *cfopen(const char *path, const char *mode, int compression); -extern cfp *cfopen_read(const char *path, const char *mode); -extern cfp *cfopen_write(const char *path, const char *mode, int compression); +extern cfp *cfopen(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_read(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_write(const char *path, const char *mode, Compress *compression); extern int cfread(void *ptr, int size, cfp *fp); extern int cfwrite(const void *ptr, int size, cfp *fp); extern int cfgetc(cfp *fp); @@ -67,4 +61,7 @@ extern int cfclose(cfp *fp); extern int cfeof(cfp *fp); extern const char *get_cfp_error(cfp *fp); +/* also used by tar */ +extern const char * compress_suffix(Compress *compression); + #endif diff --git a/src/bin/pg_dump/pg_backup.h b/src/bin/pg_dump/pg_backup.h index 9d0056a569..f2390b7937 100644 --- a/src/bin/pg_dump/pg_backup.h +++ b/src/bin/pg_dump/pg_backup.h @@ -72,6 +72,25 @@ typedef struct _connParams char *override_dbname; } ConnParams; +typedef enum +{ + COMPR_ALG_DEFAULT = -1, + COMPR_ALG_NONE, + COMPR_ALG_LIBZ, +} CompressionAlgorithm; +/* Should be called "method" or "library" ? */ + +typedef struct Compress { + CompressionAlgorithm alg; + int level; + /* Is a nondefault level set ? This is useful since different compression + * methods have different "default" levels. For now we assume the levels + * are all integer, though. + */ + bool level_set; +} Compress; + + typedef struct _restoreOptions { int createDB; /* Issue commands to create the database */ @@ -125,7 +144,7 @@ typedef struct _restoreOptions int noDataForFailedTables; int exit_on_error; - int compression; + Compress compression; int suppressDumpWarnings; /* Suppress output of WARNING entries * to stderr */ bool single_txn; @@ -281,7 +300,7 @@ extern Archive *OpenArchive(const char *FileSpec, const ArchiveFormat fmt); /* Create a new archive */ extern Archive *CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker); /* The --list option */ diff --git a/src/bin/pg_dump/pg_backup_archiver.c b/src/bin/pg_dump/pg_backup_archiver.c index 1f82c6499b..3eb6c55600 100644 --- a/src/bin/pg_dump/pg_backup_archiver.c +++ b/src/bin/pg_dump/pg_backup_archiver.c @@ -70,7 +70,7 @@ typedef struct _parallelReadyList static ArchiveHandle *_allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr); static void _getObjectDescription(PQExpBuffer buf, TocEntry *te); static void _printTocEntry(ArchiveHandle *AH, TocEntry *te, bool isData); @@ -98,7 +98,7 @@ static int _discoverArchiveFormat(ArchiveHandle *AH); static int RestoringToDB(ArchiveHandle *AH); static void dump_lo_buf(ArchiveHandle *AH); static void dumpTimestamp(ArchiveHandle *AH, const char *msg, time_t tim); -static void SetOutput(ArchiveHandle *AH, const char *filename, int compression); +static void SetOutput(ArchiveHandle *AH, const char *filename, Compress *compress); static OutputContext SaveOutput(ArchiveHandle *AH); static void RestoreOutput(ArchiveHandle *AH, OutputContext savedContext); @@ -238,7 +238,7 @@ setupRestoreWorker(Archive *AHX) /* Public */ Archive * CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker) { @@ -253,7 +253,9 @@ CreateArchive(const char *FileSpec, const ArchiveFormat fmt, Archive * OpenArchive(const char *FileSpec, const ArchiveFormat fmt) { - ArchiveHandle *AH = _allocAH(FileSpec, fmt, 0, true, archModeRead, setupRestoreWorker); + Compress compress = {0}; + ArchiveHandle *AH = _allocAH(FileSpec, fmt, &compress, true, archModeRead, + setupRestoreWorker); return (Archive *) AH; } @@ -382,7 +384,7 @@ RestoreArchive(Archive *AHX) * Make sure we won't need (de)compression we haven't got */ #ifndef HAVE_LIBZ - if (AH->compression != 0 && AH->PrintTocDataPtr != NULL) + if (AH->compression.alg != COMPR_ALG_NONE && AH->PrintTocDataPtr != NULL) { for (te = AH->toc->next; te != AH->toc; te = te->next) { @@ -457,8 +459,8 @@ RestoreArchive(Archive *AHX) * Setup the output file if necessary. */ sav = SaveOutput(AH); - if (ropt->filename || ropt->compression) - SetOutput(AH, ropt->filename, ropt->compression); + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) + SetOutput(AH, ropt->filename, &ropt->compression); ahprintf(AH, "--\n-- PostgreSQL database dump\n--\n\n"); @@ -738,7 +740,7 @@ RestoreArchive(Archive *AHX) */ AH->stage = STAGE_FINALIZING; - if (ropt->filename || ropt->compression) + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) RestoreOutput(AH, sav); if (ropt->useDB) @@ -1123,8 +1125,9 @@ PrintTOCSummary(Archive *AHX) char stamp_str[64]; sav = SaveOutput(AH); + Assert(ropt->compression.alg == COMPR_ALG_NONE); if (ropt->filename) - SetOutput(AH, ropt->filename, 0 /* no compression */ ); + SetOutput(AH, ropt->filename, &ropt->compression); if (strftime(stamp_str, sizeof(stamp_str), PGDUMP_STRFTIME_FMT, localtime(&AH->createDate)) == 0) @@ -1133,7 +1136,7 @@ PrintTOCSummary(Archive *AHX) ahprintf(AH, ";\n; Archive created at %s\n", stamp_str); ahprintf(AH, "; dbname: %s\n; TOC Entries: %d\n; Compression: %d\n", sanitize_line(AH->archdbname, false), - AH->tocCount, AH->compression); + AH->tocCount, AH->compression.alg); switch (AH->format) { @@ -1487,7 +1490,7 @@ archprintf(Archive *AH, const char *fmt,...) *******************************/ static void -SetOutput(ArchiveHandle *AH, const char *filename, int compression) +SetOutput(ArchiveHandle *AH, const char *filename, Compress *compression) { int fn; @@ -1510,12 +1513,12 @@ SetOutput(ArchiveHandle *AH, const char *filename, int compression) /* If compression explicitly requested, use gzopen */ #ifdef HAVE_LIBZ - if (compression != 0) + if (compression->alg != COMPR_ALG_NONE) { char fmode[14]; /* Don't use PG_BINARY_x since this is zlib */ - sprintf(fmode, "wb%d", compression); + sprintf(fmode, "wb%d", compression->level); if (fn >= 0) AH->OF = gzdopen(dup(fn), fmode); else @@ -2259,7 +2262,7 @@ _discoverArchiveFormat(ArchiveHandle *AH) */ static ArchiveHandle * _allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr) { ArchiveHandle *AH; @@ -2310,7 +2313,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, AH->toc->prev = AH->toc; AH->mode = mode; - AH->compression = compression; + AH->compression = *compression; AH->dosync = dosync; memset(&(AH->sqlparse), 0, sizeof(AH->sqlparse)); @@ -2325,7 +2328,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, * Force stdin/stdout into binary mode if that is what we are using. */ #ifdef WIN32 - if ((fmt != archNull || compression != 0) && + if ((fmt != archNull || compression->alg != COMPR_ALG_NONE) && (AH->fSpec == NULL || strcmp(AH->fSpec, "") == 0)) { if (mode == archModeWrite) @@ -3741,7 +3744,7 @@ WriteHead(ArchiveHandle *AH) AH->WriteBytePtr(AH, AH->intSize); AH->WriteBytePtr(AH, AH->offSize); AH->WriteBytePtr(AH, AH->format); - WriteInt(AH, AH->compression); + WriteInt(AH, AH->compression.alg); crtm = *localtime(&AH->createDate); WriteInt(AH, crtm.tm_sec); WriteInt(AH, crtm.tm_min); @@ -3816,15 +3819,15 @@ ReadHead(ArchiveHandle *AH) if (AH->version >= K_VERS_1_2) { if (AH->version < K_VERS_1_4) - AH->compression = AH->ReadBytePtr(AH); + AH->compression.alg = AH->ReadBytePtr(AH); else - AH->compression = ReadInt(AH); + AH->compression.alg = ReadInt(AH); } else - AH->compression = Z_DEFAULT_COMPRESSION; + AH->compression.alg = Z_DEFAULT_COMPRESSION; #ifndef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) pg_log_warning("archive is compressed, but this installation does not support compression -- no data will be available"); #endif diff --git a/src/bin/pg_dump/pg_backup_archiver.h b/src/bin/pg_dump/pg_backup_archiver.h index a8ea5c7eae..6e033d040e 100644 --- a/src/bin/pg_dump/pg_backup_archiver.h +++ b/src/bin/pg_dump/pg_backup_archiver.h @@ -47,7 +47,8 @@ #define GZWRITE(p, s, n, fh) (fwrite(p, s, n, fh) * (s)) #define GZREAD(p, s, n, fh) fread(p, s, n, fh) #define GZEOF(fh) feof(fh) -/* this is just the redefinition of a libz constant */ +/* this is just the redefinition of a libz constant, in case zlib isn't + * available */ #define Z_DEFAULT_COMPRESSION (-1) typedef struct _z_stream @@ -329,14 +330,7 @@ struct _archiveHandle DumpId *tableDataId; /* TABLE DATA ids, indexed by table dumpId */ struct _tocEntry *currToc; /* Used when dumping data */ - int compression; /*--------- - * Compression requested on open(). - * Possible values for compression: - * -1 Z_DEFAULT_COMPRESSION - * 0 COMPRESSION_NONE - * 1-9 levels for gzip compression - *--------- - */ + Compress compression; /* Compression requested on open */ bool dosync; /* data requested to be synced on sight */ ArchiveMode mode; /* File mode - r or w */ void *formatData; /* Header data specific to file format */ diff --git a/src/bin/pg_dump/pg_backup_custom.c b/src/bin/pg_dump/pg_backup_custom.c index 77d402c323..55a887a236 100644 --- a/src/bin/pg_dump/pg_backup_custom.c +++ b/src/bin/pg_dump/pg_backup_custom.c @@ -298,7 +298,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) _WriteByte(AH, BLK_DATA); /* Block type */ WriteInt(AH, te->dumpId); /* For sanity check */ - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -377,7 +377,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) WriteInt(AH, oid); - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -566,7 +566,7 @@ _PrintTocData(ArchiveHandle *AH, TocEntry *te) static void _PrintData(ArchiveHandle *AH) { - ReadDataFromArchive(AH, AH->compression, _CustomReadFunc); + ReadDataFromArchive(AH, _CustomReadFunc); } static void diff --git a/src/bin/pg_dump/pg_backup_directory.c b/src/bin/pg_dump/pg_backup_directory.c index 650b542fce..8bf869c6ca 100644 --- a/src/bin/pg_dump/pg_backup_directory.c +++ b/src/bin/pg_dump/pg_backup_directory.c @@ -202,7 +202,7 @@ InitArchiveFmt_Directory(ArchiveHandle *AH) setFilePath(AH, fname, "toc.dat"); - tocFH = cfopen_read(fname, PG_BINARY_R); + tocFH = cfopen_read(fname, PG_BINARY_R, &AH->compression); if (tocFH == NULL) fatal("could not open input file \"%s\": %m", fname); @@ -327,7 +327,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) setFilePath(AH, fname, tctx->filename); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -388,7 +388,7 @@ _PrintFileData(ArchiveHandle *AH, char *filename) if (!filename) return; - cfp = cfopen_read(filename, PG_BINARY_R); + cfp = cfopen_read(filename, PG_BINARY_R, &AH->compression); if (!cfp) fatal("could not open input file \"%s\": %m", filename); @@ -435,12 +435,13 @@ _LoadBlobs(ArchiveHandle *AH) lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; char line[MAXPGPATH]; + Compress nocompression = {0}; StartRestoreBlobs(AH); setFilePath(AH, fname, "blobs.toc"); - ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R); + ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R, &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open large object TOC file \"%s\" for input: %m", @@ -573,6 +574,7 @@ _CloseArchive(ArchiveHandle *AH) { cfp *tocFH; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "toc.dat"); @@ -580,7 +582,7 @@ _CloseArchive(ArchiveHandle *AH) ctx->pstate = ParallelBackupStart(AH); /* The TOC is always created uncompressed */ - tocFH = cfopen_write(fname, PG_BINARY_W, 0); + tocFH = cfopen_write(fname, PG_BINARY_W, &nocompression); if (tocFH == NULL) fatal("could not open output file \"%s\": %m", fname); ctx->dataFH = tocFH; @@ -639,11 +641,12 @@ _StartBlobs(ArchiveHandle *AH, TocEntry *te) { lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "blobs.toc"); /* The blob TOC file is never compressed */ - ctx->blobsTocFH = cfopen_write(fname, "ab", 0); + ctx->blobsTocFH = cfopen_write(fname, "ab", &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -661,7 +664,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) snprintf(fname, MAXPGPATH, "%s/blob_%u.dat", ctx->directory, oid); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); diff --git a/src/bin/pg_dump/pg_backup_tar.c b/src/bin/pg_dump/pg_backup_tar.c index 61c9c87a9f..4ba79ab924 100644 --- a/src/bin/pg_dump/pg_backup_tar.c +++ b/src/bin/pg_dump/pg_backup_tar.c @@ -39,6 +39,7 @@ #include "pg_backup_archiver.h" #include "pg_backup_tar.h" #include "pg_backup_utils.h" +#include "compress_io.h" #include "pgtar.h" static void _ArchiveEntry(ArchiveHandle *AH, TocEntry *te); @@ -196,10 +197,10 @@ InitArchiveFmt_Tar(ArchiveHandle *AH) /* * We don't support compression because reading the files back is not - * possible since gzdopen uses buffered IO which totally screws file + * possible since gzdopen uses buffered IO which totally screws file XXX * positioning. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) fatal("compression is not supported by tar archive format"); } else @@ -254,14 +255,8 @@ _ArchiveEntry(ArchiveHandle *AH, TocEntry *te) ctx = (lclTocEntry *) pg_malloc0(sizeof(lclTocEntry)); if (te->dataDumper != NULL) { -#ifdef HAVE_LIBZ - if (AH->compression == 0) - sprintf(fn, "%d.dat", te->dumpId); - else - sprintf(fn, "%d.dat.gz", te->dumpId); -#else - sprintf(fn, "%d.dat", te->dumpId); -#endif + const char *suffix = compress_suffix(&AH->compression); + sprintf(fn, "%d.dat%s", te->dumpId, suffix); ctx->filename = pg_strdup(fn); } else @@ -352,7 +347,7 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression == 0) + if (AH->compression.alg == COMPR_ALG_NONE) tm->nFH = ctx->tarFH; else fatal("compression is not supported by tar archive format"); @@ -413,9 +408,9 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) { - sprintf(fmode, "wb%d", AH->compression); + sprintf(fmode, "wb%d", AH->compression.level); tm->zFH = gzdopen(dup(fileno(tm->tmpFH)), fmode); if (tm->zFH == NULL) fatal("could not open temporary file"); @@ -443,7 +438,7 @@ tarClose(ArchiveHandle *AH, TAR_MEMBER *th) /* * Close the GZ file since we dup'd. This will flush the buffers. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) if (GZCLOSE(th->zFH) != 0) fatal("could not close tar member"); @@ -868,7 +863,7 @@ _CloseArchive(ArchiveHandle *AH) memcpy(ropt, AH->public.ropt, sizeof(RestoreOptions)); ropt->filename = NULL; ropt->dropSchema = 1; - ropt->compression = 0; + ropt->compression.alg = COMPR_ALG_NONE; ropt->superuser = NULL; ropt->suppressDumpWarnings = true; @@ -952,16 +947,12 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) lclContext *ctx = (lclContext *) AH->formatData; lclTocEntry *tctx = (lclTocEntry *) te->formatData; char fname[255]; - char *sfx; + const char *sfx; if (oid == 0) fatal("invalid OID for large object (%u)", oid); - if (AH->compression != 0) - sfx = ".gz"; - else - sfx = ""; - + sfx = compress_suffix(&AH->compression); sprintf(fname, "blob_%u.dat%s", oid, sfx); tarPrintf(ctx->blobToc, "%u %s\n", oid, fname); diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c index 1ab98a2286..4cbc79aedc 100644 --- a/src/bin/pg_dump/pg_dump.c +++ b/src/bin/pg_dump/pg_dump.c @@ -59,6 +59,7 @@ #include "getopt_long.h" #include "libpq/libpq-fs.h" #include "parallel.h" +#include "compress_io.h" #include "pg_backup_db.h" #include "pg_backup_utils.h" #include "pg_dump.h" @@ -297,6 +298,82 @@ static void setupDumpWorker(Archive *AHX); static TableInfo *getRootTableInfo(TableInfo *tbinfo); +/* Parse the string into compression options */ +static void +parse_compression(const char *optarg, Compress *compress) +{ + if (optarg[0] == '0' && optarg[1] == '\0') + compress->alg = COMPR_ALG_NONE; + else if ((optarg[0] > '0' && optarg[0] <= '9') || + optarg[0] == '-') + { + compress->alg = COMPR_ALG_LIBZ; + compress->level_set = true; + compress->level = atoi(optarg); + if (optarg[1] != '\0') + { + pg_log_error("compression level must be in range 0..9"); + exit_nicely(1); + } + } + else + { + /* Parse a more flexible string like level=3 alg=zlib opts=long */ + for (;;) + { + char *eq = strchr(optarg, '='); + int len; + + if (eq == NULL) + { + pg_log_error("compression options must be key=value: %s", optarg); + exit_nicely(1); + } + + len = eq - optarg; + if (strncmp(optarg, "alg", len) == 0) + { + if (strchr(eq, ' ')) + len = strchr(eq, ' ') - eq - 1; + else + len = strlen(eq) - len; + if (strncmp(1+eq, "zlib", len) == 0 || + strncmp(1+eq, "libz", len) == 0) + compress->alg = COMPR_ALG_LIBZ; + else + { + pg_log_error("unknown compression algorithm: %s", 1+eq); + exit_nicely(1); + } + } + else if (strncmp(optarg, "level", len) == 0) + { + compress->level = atoi(1+eq); + compress->level_set = true; + } + else + { + pg_log_error("unknown compression setting: %s", optarg); + exit_nicely(1); + } + + optarg = strchr(eq, ' '); + if (!optarg++) + break; + } + + if (!compress->level_set) + { + const int default_compress_level[] = { + 0, /* COMPR_ALG_NONE */ + Z_DEFAULT_COMPRESSION, /* COMPR_ALG_ZLIB */ + }; + + compress->level = default_compress_level[compress->alg]; + } + } +} + int main(int argc, char **argv) { @@ -319,7 +396,7 @@ main(int argc, char **argv) char *use_role = NULL; long rowsPerInsert; int numWorkers = 1; - int compressLevel = -1; + Compress compress = { .alg = COMPR_ALG_DEFAULT }; int plainText = 0; ArchiveFormat archiveFormat = archUnknown; ArchiveMode archiveMode; @@ -532,12 +609,7 @@ main(int argc, char **argv) break; case 'Z': /* Compression Level */ - compressLevel = atoi(optarg); - if (compressLevel < 0 || compressLevel > 9) - { - pg_log_error("compression level must be in range 0..9"); - exit_nicely(1); - } + parse_compression(optarg, &compress); break; case 0: @@ -679,20 +751,28 @@ main(int argc, char **argv) plainText = 1; /* Custom and directory formats are compressed by default, others not */ - if (compressLevel == -1) + if (compress.alg == COMPR_ALG_DEFAULT) { -#ifdef HAVE_LIBZ if (archiveFormat == archCustom || archiveFormat == archDirectory) - compressLevel = Z_DEFAULT_COMPRESSION; - else + { +#ifdef HAVE_LIBZ + compress.alg = COMPR_ALG_LIBZ; + compress.level = Z_DEFAULT_COMPRESSION; #endif - compressLevel = 0; + } + else + { + compress.alg = COMPR_ALG_NONE; + compress.level = 0; + } } #ifndef HAVE_LIBZ - if (compressLevel != 0) + if (compress.alg == COMPR_ALG_LIBZ) + { pg_log_warning("requested compression not available in this installation -- archive will be uncompressed"); - compressLevel = 0; + compress.alg = 0; + } #endif /* @@ -723,7 +803,7 @@ main(int argc, char **argv) fatal("option --index-collation-versions-unknown only works in binary upgrade mode"); /* Open the output file */ - fout = CreateArchive(filename, archiveFormat, compressLevel, dosync, + fout = CreateArchive(filename, archiveFormat, &compress, dosync, archiveMode, setupDumpWorker); /* Make dump options accessible right away */ @@ -957,10 +1037,7 @@ main(int argc, char **argv) ropt->sequence_data = dopt.sequence_data; ropt->binary_upgrade = dopt.binary_upgrade; - if (compressLevel == -1) - ropt->compression = 0; - else - ropt->compression = compressLevel; + ropt->compression = compress; ropt->suppressDumpWarnings = true; /* We've already shown them */ -- 2.17.0 --GRPZ8SYKNexpdSJ7 Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="0004-struct-compressLibs.patch" ^ permalink raw reply [nested|flat] 23+ messages in thread
* [PATCH 03/20] Support multiple compression algs/levels/opts.. @ 2020-12-22 06:23 Justin Pryzby <[email protected]> 0 siblings, 0 replies; 23+ messages in thread From: Justin Pryzby @ 2020-12-22 06:23 UTC (permalink / raw) The existing implementation abtracts compressed and noncompressed I/O. This preliminary commit is intended to also allow for multiple compression algorithms. --- src/bin/pg_dump/compress_io.c | 220 +++++++++++--------------- src/bin/pg_dump/compress_io.h | 19 +-- src/bin/pg_dump/pg_backup.h | 23 ++- src/bin/pg_dump/pg_backup_archiver.c | 45 +++--- src/bin/pg_dump/pg_backup_archiver.h | 12 +- src/bin/pg_dump/pg_backup_custom.c | 6 +- src/bin/pg_dump/pg_backup_directory.c | 17 +- src/bin/pg_dump/pg_backup_tar.c | 33 ++-- src/bin/pg_dump/pg_dump.c | 115 +++++++++++--- 9 files changed, 272 insertions(+), 218 deletions(-) diff --git a/src/bin/pg_dump/compress_io.c b/src/bin/pg_dump/compress_io.c index 6a428978d4..db16fd33f2 100644 --- a/src/bin/pg_dump/compress_io.c +++ b/src/bin/pg_dump/compress_io.c @@ -74,12 +74,9 @@ struct CompressorState #endif }; -static void ParseCompressionOption(int compression, CompressionAlgorithm *alg, - int *level); - /* Routines that support zlib compressed data I/O */ #ifdef HAVE_LIBZ -static void InitCompressorZlib(CompressorState *cs, int level); +static void InitCompressorZlib(CompressorState *cs, Compress *compress); static void DeflateCompressorZlib(ArchiveHandle *AH, CompressorState *cs, bool flush); static void ReadDataFromArchiveZlib(ArchiveHandle *AH, ReadFunc readF); @@ -93,58 +90,36 @@ static void ReadDataFromArchiveNone(ArchiveHandle *AH, ReadFunc readF); static void WriteDataToArchiveNone(ArchiveHandle *AH, CompressorState *cs, const char *data, size_t dLen); -/* - * Interprets a numeric 'compression' value. The algorithm implied by the - * value (zlib or none at the moment), is returned in *alg, and the - * zlib compression level in *level. - */ -static void -ParseCompressionOption(int compression, CompressionAlgorithm *alg, int *level) -{ - if (compression == Z_DEFAULT_COMPRESSION || - (compression > 0 && compression <= 9)) - *alg = COMPR_ALG_LIBZ; - else if (compression == 0) - *alg = COMPR_ALG_NONE; - else - { - fatal("invalid compression code: %d", compression); - *alg = COMPR_ALG_NONE; /* keep compiler quiet */ - } - - /* The level is just the passed-in value. */ - if (level) - *level = compression; -} - /* Public interface routines */ /* Allocate a new compressor */ CompressorState * -AllocateCompressor(int compression, WriteFunc writeF) +AllocateCompressor(Compress *compression, WriteFunc writeF) { CompressorState *cs; - CompressionAlgorithm alg; - int level; - - ParseCompressionOption(compression, &alg, &level); - -#ifndef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - fatal("not built with zlib support"); -#endif cs = (CompressorState *) pg_malloc0(sizeof(CompressorState)); cs->writeF = writeF; - cs->comprAlg = alg; + cs->comprAlg = compression->alg; /* * Perform compression algorithm specific initialization. */ + Assert (compression->alg != COMPR_ALG_DEFAULT); + switch (compression->alg) + { #ifdef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - InitCompressorZlib(cs, level); + case COMPR_ALG_LIBZ: + InitCompressorZlib(cs, compression); + break; #endif + case COMPR_ALG_NONE: + /* Do nothing */ + break; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } return cs; } @@ -154,21 +129,21 @@ AllocateCompressor(int compression, WriteFunc writeF) * out with ahwrite(). */ void -ReadDataFromArchive(ArchiveHandle *AH, int compression, ReadFunc readF) +ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF) { - CompressionAlgorithm alg; - - ParseCompressionOption(compression, &alg, NULL); - - if (alg == COMPR_ALG_NONE) - ReadDataFromArchiveNone(AH, readF); - if (alg == COMPR_ALG_LIBZ) + switch (AH->compression.alg) { + case COMPR_ALG_NONE: + ReadDataFromArchiveNone(AH, readF); + break; #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: ReadDataFromArchiveZlib(AH, readF); -#else - fatal("not built with zlib support"); + break; #endif + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -181,16 +156,18 @@ WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, { switch (cs->comprAlg) { - case COMPR_ALG_LIBZ: #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: WriteDataToArchiveZlib(AH, cs, data, dLen); -#else - fatal("not built with zlib support"); -#endif break; +#endif case COMPR_ALG_NONE: WriteDataToArchiveNone(AH, cs, data, dLen); break; + + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -215,7 +192,7 @@ EndCompressor(ArchiveHandle *AH, CompressorState *cs) */ static void -InitCompressorZlib(CompressorState *cs, int level) +InitCompressorZlib(CompressorState *cs, Compress *compress) { z_streamp zp; @@ -232,7 +209,7 @@ InitCompressorZlib(CompressorState *cs, int level) cs->zlibOut = (char *) pg_malloc(ZLIB_OUT_SIZE + 1); cs->zlibOutSize = ZLIB_OUT_SIZE; - if (deflateInit(zp, level) != Z_OK) + if (deflateInit(zp, compress->level) != Z_OK) fatal("could not initialize compression library: %s", zp->msg); @@ -424,9 +401,7 @@ struct cfp #endif }; -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix); -#endif /* free() without changing errno; useful in several places below */ static void @@ -442,34 +417,31 @@ free_keep_errno(void *p) * Open a file for reading. 'path' is the file to open, and 'mode' should * be either "r" or "rb". * - * If the file at 'path' does not exist, we append the ".gz" suffix (if 'path' - * doesn't already have it) and try again. So if you pass "foo" as 'path', + * If the file at 'path' does not exist, we search with compressed suffix (if 'path' + * doesn't already have one) and try again. So if you pass "foo" as 'path', * this will open either "foo" or "foo.gz". * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_read(const char *path, const char *mode) +cfopen_read(const char *path, const char *mode, Compress *compression) { cfp *fp; -#ifdef HAVE_LIBZ if (hasSuffix(path, ".gz")) - fp = cfopen(path, mode, 1); + fp = cfopen(path, mode, compression); else -#endif { - fp = cfopen(path, mode, 0); -#ifdef HAVE_LIBZ + fp = cfopen(path, mode, compression); if (fp == NULL) { char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); - fp = cfopen(fname, mode, 1); + fname = psprintf("%s%s", path, suffix); + fp = cfopen(fname, mode, compression); free_keep_errno(fname); } -#endif } return fp; } @@ -479,31 +451,26 @@ cfopen_read(const char *path, const char *mode) * be a filemode as accepted by fopen() and gzopen() that indicates writing * ("w", "wb", "a", or "ab"). * - * If 'compression' is non-zero, a gzip compressed stream is opened, and - * 'compression' indicates the compression level used. The ".gz" suffix - * is automatically added to 'path' in that case. + * Use compression if specified. + * The appropriate suffix is automatically added to 'path' in that case. * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_write(const char *path, const char *mode, int compression) +cfopen_write(const char *path, const char *mode, Compress *compression) { cfp *fp; - if (compression == 0) - fp = cfopen(path, mode, 0); + if (compression->alg == COMPR_ALG_NONE) + fp = cfopen(path, mode, compression); else { -#ifdef HAVE_LIBZ char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); + fname = psprintf("%s%s", path, suffix); fp = cfopen(fname, mode, compression); free_keep_errno(fname); -#else - fatal("not built with zlib support"); - fp = NULL; /* keep compiler quiet */ -#endif } return fp; } @@ -515,20 +482,21 @@ cfopen_write(const char *path, const char *mode, int compression) * On failure, return NULL with an error code in errno. */ cfp * -cfopen(const char *path, const char *mode, int compression) +cfopen(const char *path, const char *mode, Compress *compression) { - cfp *fp = pg_malloc(sizeof(cfp)); + cfp *fp = pg_malloc0(sizeof(cfp)); - if (compression != 0) + switch (compression->alg) { #ifdef HAVE_LIBZ - if (compression != Z_DEFAULT_COMPRESSION) + case COMPR_ALG_LIBZ: + if (compression->level != Z_DEFAULT_COMPRESSION) { /* user has specified a compression level, so tell zlib to use it */ char mode_compression[32]; snprintf(mode_compression, sizeof(mode_compression), "%s%d", - mode, compression); + mode, compression->level); fp->compressedfp = gzopen(path, mode_compression); } else @@ -537,30 +505,27 @@ cfopen(const char *path, const char *mode, int compression) fp->compressedfp = gzopen(path, mode); } - fp->uncompressedfp = NULL; if (fp->compressedfp == NULL) { free_keep_errno(fp); fp = NULL; } -#else - fatal("not built with zlib support"); -#endif - } - else - { -#ifdef HAVE_LIBZ - fp->compressedfp = NULL; + return fp; #endif + + case COMPR_ALG_NONE: fp->uncompressedfp = fopen(path, mode); if (fp->uncompressedfp == NULL) { free_keep_errno(fp); fp = NULL; } - } + return fp; - return fp; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } } @@ -584,14 +549,13 @@ cfread(void *ptr, int size, cfp *fp) fatal("could not read from input file: %s", errnum == Z_ERRNO ? strerror(errno) : errmsg); } + return ret; } - else #endif - { - ret = fread(ptr, 1, size, fp->uncompressedfp); - if (ret != size && !feof(fp->uncompressedfp)) - READ_ERROR_EXIT(fp->uncompressedfp); - } + + ret = fread(ptr, 1, size, fp->uncompressedfp); + if (ret != size && !feof(fp->uncompressedfp)) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -601,9 +565,8 @@ cfwrite(const void *ptr, int size, cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzwrite(fp->compressedfp, ptr, size); - else #endif - return fwrite(ptr, 1, size, fp->uncompressedfp); + return fwrite(ptr, 1, size, fp->uncompressedfp); } int @@ -622,15 +585,12 @@ cfgetc(cfp *fp) else fatal("could not read from input file: end of file"); } + return ret; } - else #endif - { - ret = fgetc(fp->uncompressedfp); - if (ret == EOF) - READ_ERROR_EXIT(fp->uncompressedfp); - } - + ret = fgetc(fp->uncompressedfp); + if (ret == EOF) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -640,9 +600,8 @@ cfgets(cfp *fp, char *buf, int len) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzgets(fp->compressedfp, buf, len); - else #endif - return fgets(buf, len, fp->uncompressedfp); + return fgets(buf, len, fp->uncompressedfp); } int @@ -660,15 +619,13 @@ cfclose(cfp *fp) { result = gzclose(fp->compressedfp); fp->compressedfp = NULL; + return result; } - else #endif - { - result = fclose(fp->uncompressedfp); - fp->uncompressedfp = NULL; - } - free_keep_errno(fp); + result = fclose(fp->uncompressedfp); + fp->uncompressedfp = NULL; + free_keep_errno(fp); return result; } @@ -678,9 +635,9 @@ cfeof(cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzeof(fp->compressedfp); - else #endif - return feof(fp->uncompressedfp); + + return feof(fp->uncompressedfp); } const char * @@ -699,7 +656,6 @@ get_cfp_error(cfp *fp) return strerror(errno); } -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix) { @@ -714,4 +670,18 @@ hasSuffix(const char *filename, const char *suffix) suffixlen) == 0; } -#endif +/* + * Return a string for the given AH's compression. + * The string is statically allocated. + */ +const char * +compress_suffix(Compress *compression) +{ + switch (compression->alg) + { + case COMPR_ALG_LIBZ: + return ".gz"; + default: + return ""; + } +} diff --git a/src/bin/pg_dump/compress_io.h b/src/bin/pg_dump/compress_io.h index d2e6e1b854..2c073676eb 100644 --- a/src/bin/pg_dump/compress_io.h +++ b/src/bin/pg_dump/compress_io.h @@ -21,12 +21,6 @@ #define ZLIB_OUT_SIZE 4096 #define ZLIB_IN_SIZE 4096 -typedef enum -{ - COMPR_ALG_NONE, - COMPR_ALG_LIBZ -} CompressionAlgorithm; - /* Prototype for callback function to WriteDataToArchive() */ typedef void (*WriteFunc) (ArchiveHandle *AH, const char *buf, size_t len); @@ -46,8 +40,8 @@ typedef size_t (*ReadFunc) (ArchiveHandle *AH, char **buf, size_t *buflen); /* struct definition appears in compress_io.c */ typedef struct CompressorState CompressorState; -extern CompressorState *AllocateCompressor(int compression, WriteFunc writeF); -extern void ReadDataFromArchive(ArchiveHandle *AH, int compression, +extern CompressorState *AllocateCompressor(Compress *compression, WriteFunc writeF); +extern void ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF); extern void WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, const void *data, size_t dLen); @@ -56,9 +50,9 @@ extern void EndCompressor(ArchiveHandle *AH, CompressorState *cs); typedef struct cfp cfp; -extern cfp *cfopen(const char *path, const char *mode, int compression); -extern cfp *cfopen_read(const char *path, const char *mode); -extern cfp *cfopen_write(const char *path, const char *mode, int compression); +extern cfp *cfopen(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_read(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_write(const char *path, const char *mode, Compress *compression); extern int cfread(void *ptr, int size, cfp *fp); extern int cfwrite(const void *ptr, int size, cfp *fp); extern int cfgetc(cfp *fp); @@ -67,4 +61,7 @@ extern int cfclose(cfp *fp); extern int cfeof(cfp *fp); extern const char *get_cfp_error(cfp *fp); +/* also used by tar */ +extern const char * compress_suffix(Compress *compression); + #endif diff --git a/src/bin/pg_dump/pg_backup.h b/src/bin/pg_dump/pg_backup.h index 9d0056a569..f2390b7937 100644 --- a/src/bin/pg_dump/pg_backup.h +++ b/src/bin/pg_dump/pg_backup.h @@ -72,6 +72,25 @@ typedef struct _connParams char *override_dbname; } ConnParams; +typedef enum +{ + COMPR_ALG_DEFAULT = -1, + COMPR_ALG_NONE, + COMPR_ALG_LIBZ, +} CompressionAlgorithm; +/* Should be called "method" or "library" ? */ + +typedef struct Compress { + CompressionAlgorithm alg; + int level; + /* Is a nondefault level set ? This is useful since different compression + * methods have different "default" levels. For now we assume the levels + * are all integer, though. + */ + bool level_set; +} Compress; + + typedef struct _restoreOptions { int createDB; /* Issue commands to create the database */ @@ -125,7 +144,7 @@ typedef struct _restoreOptions int noDataForFailedTables; int exit_on_error; - int compression; + Compress compression; int suppressDumpWarnings; /* Suppress output of WARNING entries * to stderr */ bool single_txn; @@ -281,7 +300,7 @@ extern Archive *OpenArchive(const char *FileSpec, const ArchiveFormat fmt); /* Create a new archive */ extern Archive *CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker); /* The --list option */ diff --git a/src/bin/pg_dump/pg_backup_archiver.c b/src/bin/pg_dump/pg_backup_archiver.c index 1f82c6499b..3eb6c55600 100644 --- a/src/bin/pg_dump/pg_backup_archiver.c +++ b/src/bin/pg_dump/pg_backup_archiver.c @@ -70,7 +70,7 @@ typedef struct _parallelReadyList static ArchiveHandle *_allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr); static void _getObjectDescription(PQExpBuffer buf, TocEntry *te); static void _printTocEntry(ArchiveHandle *AH, TocEntry *te, bool isData); @@ -98,7 +98,7 @@ static int _discoverArchiveFormat(ArchiveHandle *AH); static int RestoringToDB(ArchiveHandle *AH); static void dump_lo_buf(ArchiveHandle *AH); static void dumpTimestamp(ArchiveHandle *AH, const char *msg, time_t tim); -static void SetOutput(ArchiveHandle *AH, const char *filename, int compression); +static void SetOutput(ArchiveHandle *AH, const char *filename, Compress *compress); static OutputContext SaveOutput(ArchiveHandle *AH); static void RestoreOutput(ArchiveHandle *AH, OutputContext savedContext); @@ -238,7 +238,7 @@ setupRestoreWorker(Archive *AHX) /* Public */ Archive * CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker) { @@ -253,7 +253,9 @@ CreateArchive(const char *FileSpec, const ArchiveFormat fmt, Archive * OpenArchive(const char *FileSpec, const ArchiveFormat fmt) { - ArchiveHandle *AH = _allocAH(FileSpec, fmt, 0, true, archModeRead, setupRestoreWorker); + Compress compress = {0}; + ArchiveHandle *AH = _allocAH(FileSpec, fmt, &compress, true, archModeRead, + setupRestoreWorker); return (Archive *) AH; } @@ -382,7 +384,7 @@ RestoreArchive(Archive *AHX) * Make sure we won't need (de)compression we haven't got */ #ifndef HAVE_LIBZ - if (AH->compression != 0 && AH->PrintTocDataPtr != NULL) + if (AH->compression.alg != COMPR_ALG_NONE && AH->PrintTocDataPtr != NULL) { for (te = AH->toc->next; te != AH->toc; te = te->next) { @@ -457,8 +459,8 @@ RestoreArchive(Archive *AHX) * Setup the output file if necessary. */ sav = SaveOutput(AH); - if (ropt->filename || ropt->compression) - SetOutput(AH, ropt->filename, ropt->compression); + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) + SetOutput(AH, ropt->filename, &ropt->compression); ahprintf(AH, "--\n-- PostgreSQL database dump\n--\n\n"); @@ -738,7 +740,7 @@ RestoreArchive(Archive *AHX) */ AH->stage = STAGE_FINALIZING; - if (ropt->filename || ropt->compression) + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) RestoreOutput(AH, sav); if (ropt->useDB) @@ -1123,8 +1125,9 @@ PrintTOCSummary(Archive *AHX) char stamp_str[64]; sav = SaveOutput(AH); + Assert(ropt->compression.alg == COMPR_ALG_NONE); if (ropt->filename) - SetOutput(AH, ropt->filename, 0 /* no compression */ ); + SetOutput(AH, ropt->filename, &ropt->compression); if (strftime(stamp_str, sizeof(stamp_str), PGDUMP_STRFTIME_FMT, localtime(&AH->createDate)) == 0) @@ -1133,7 +1136,7 @@ PrintTOCSummary(Archive *AHX) ahprintf(AH, ";\n; Archive created at %s\n", stamp_str); ahprintf(AH, "; dbname: %s\n; TOC Entries: %d\n; Compression: %d\n", sanitize_line(AH->archdbname, false), - AH->tocCount, AH->compression); + AH->tocCount, AH->compression.alg); switch (AH->format) { @@ -1487,7 +1490,7 @@ archprintf(Archive *AH, const char *fmt,...) *******************************/ static void -SetOutput(ArchiveHandle *AH, const char *filename, int compression) +SetOutput(ArchiveHandle *AH, const char *filename, Compress *compression) { int fn; @@ -1510,12 +1513,12 @@ SetOutput(ArchiveHandle *AH, const char *filename, int compression) /* If compression explicitly requested, use gzopen */ #ifdef HAVE_LIBZ - if (compression != 0) + if (compression->alg != COMPR_ALG_NONE) { char fmode[14]; /* Don't use PG_BINARY_x since this is zlib */ - sprintf(fmode, "wb%d", compression); + sprintf(fmode, "wb%d", compression->level); if (fn >= 0) AH->OF = gzdopen(dup(fn), fmode); else @@ -2259,7 +2262,7 @@ _discoverArchiveFormat(ArchiveHandle *AH) */ static ArchiveHandle * _allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr) { ArchiveHandle *AH; @@ -2310,7 +2313,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, AH->toc->prev = AH->toc; AH->mode = mode; - AH->compression = compression; + AH->compression = *compression; AH->dosync = dosync; memset(&(AH->sqlparse), 0, sizeof(AH->sqlparse)); @@ -2325,7 +2328,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, * Force stdin/stdout into binary mode if that is what we are using. */ #ifdef WIN32 - if ((fmt != archNull || compression != 0) && + if ((fmt != archNull || compression->alg != COMPR_ALG_NONE) && (AH->fSpec == NULL || strcmp(AH->fSpec, "") == 0)) { if (mode == archModeWrite) @@ -3741,7 +3744,7 @@ WriteHead(ArchiveHandle *AH) AH->WriteBytePtr(AH, AH->intSize); AH->WriteBytePtr(AH, AH->offSize); AH->WriteBytePtr(AH, AH->format); - WriteInt(AH, AH->compression); + WriteInt(AH, AH->compression.alg); crtm = *localtime(&AH->createDate); WriteInt(AH, crtm.tm_sec); WriteInt(AH, crtm.tm_min); @@ -3816,15 +3819,15 @@ ReadHead(ArchiveHandle *AH) if (AH->version >= K_VERS_1_2) { if (AH->version < K_VERS_1_4) - AH->compression = AH->ReadBytePtr(AH); + AH->compression.alg = AH->ReadBytePtr(AH); else - AH->compression = ReadInt(AH); + AH->compression.alg = ReadInt(AH); } else - AH->compression = Z_DEFAULT_COMPRESSION; + AH->compression.alg = Z_DEFAULT_COMPRESSION; #ifndef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) pg_log_warning("archive is compressed, but this installation does not support compression -- no data will be available"); #endif diff --git a/src/bin/pg_dump/pg_backup_archiver.h b/src/bin/pg_dump/pg_backup_archiver.h index a8ea5c7eae..6e033d040e 100644 --- a/src/bin/pg_dump/pg_backup_archiver.h +++ b/src/bin/pg_dump/pg_backup_archiver.h @@ -47,7 +47,8 @@ #define GZWRITE(p, s, n, fh) (fwrite(p, s, n, fh) * (s)) #define GZREAD(p, s, n, fh) fread(p, s, n, fh) #define GZEOF(fh) feof(fh) -/* this is just the redefinition of a libz constant */ +/* this is just the redefinition of a libz constant, in case zlib isn't + * available */ #define Z_DEFAULT_COMPRESSION (-1) typedef struct _z_stream @@ -329,14 +330,7 @@ struct _archiveHandle DumpId *tableDataId; /* TABLE DATA ids, indexed by table dumpId */ struct _tocEntry *currToc; /* Used when dumping data */ - int compression; /*--------- - * Compression requested on open(). - * Possible values for compression: - * -1 Z_DEFAULT_COMPRESSION - * 0 COMPRESSION_NONE - * 1-9 levels for gzip compression - *--------- - */ + Compress compression; /* Compression requested on open */ bool dosync; /* data requested to be synced on sight */ ArchiveMode mode; /* File mode - r or w */ void *formatData; /* Header data specific to file format */ diff --git a/src/bin/pg_dump/pg_backup_custom.c b/src/bin/pg_dump/pg_backup_custom.c index 77d402c323..55a887a236 100644 --- a/src/bin/pg_dump/pg_backup_custom.c +++ b/src/bin/pg_dump/pg_backup_custom.c @@ -298,7 +298,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) _WriteByte(AH, BLK_DATA); /* Block type */ WriteInt(AH, te->dumpId); /* For sanity check */ - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -377,7 +377,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) WriteInt(AH, oid); - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -566,7 +566,7 @@ _PrintTocData(ArchiveHandle *AH, TocEntry *te) static void _PrintData(ArchiveHandle *AH) { - ReadDataFromArchive(AH, AH->compression, _CustomReadFunc); + ReadDataFromArchive(AH, _CustomReadFunc); } static void diff --git a/src/bin/pg_dump/pg_backup_directory.c b/src/bin/pg_dump/pg_backup_directory.c index 650b542fce..8bf869c6ca 100644 --- a/src/bin/pg_dump/pg_backup_directory.c +++ b/src/bin/pg_dump/pg_backup_directory.c @@ -202,7 +202,7 @@ InitArchiveFmt_Directory(ArchiveHandle *AH) setFilePath(AH, fname, "toc.dat"); - tocFH = cfopen_read(fname, PG_BINARY_R); + tocFH = cfopen_read(fname, PG_BINARY_R, &AH->compression); if (tocFH == NULL) fatal("could not open input file \"%s\": %m", fname); @@ -327,7 +327,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) setFilePath(AH, fname, tctx->filename); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -388,7 +388,7 @@ _PrintFileData(ArchiveHandle *AH, char *filename) if (!filename) return; - cfp = cfopen_read(filename, PG_BINARY_R); + cfp = cfopen_read(filename, PG_BINARY_R, &AH->compression); if (!cfp) fatal("could not open input file \"%s\": %m", filename); @@ -435,12 +435,13 @@ _LoadBlobs(ArchiveHandle *AH) lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; char line[MAXPGPATH]; + Compress nocompression = {0}; StartRestoreBlobs(AH); setFilePath(AH, fname, "blobs.toc"); - ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R); + ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R, &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open large object TOC file \"%s\" for input: %m", @@ -573,6 +574,7 @@ _CloseArchive(ArchiveHandle *AH) { cfp *tocFH; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "toc.dat"); @@ -580,7 +582,7 @@ _CloseArchive(ArchiveHandle *AH) ctx->pstate = ParallelBackupStart(AH); /* The TOC is always created uncompressed */ - tocFH = cfopen_write(fname, PG_BINARY_W, 0); + tocFH = cfopen_write(fname, PG_BINARY_W, &nocompression); if (tocFH == NULL) fatal("could not open output file \"%s\": %m", fname); ctx->dataFH = tocFH; @@ -639,11 +641,12 @@ _StartBlobs(ArchiveHandle *AH, TocEntry *te) { lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "blobs.toc"); /* The blob TOC file is never compressed */ - ctx->blobsTocFH = cfopen_write(fname, "ab", 0); + ctx->blobsTocFH = cfopen_write(fname, "ab", &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -661,7 +664,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) snprintf(fname, MAXPGPATH, "%s/blob_%u.dat", ctx->directory, oid); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); diff --git a/src/bin/pg_dump/pg_backup_tar.c b/src/bin/pg_dump/pg_backup_tar.c index 61c9c87a9f..4ba79ab924 100644 --- a/src/bin/pg_dump/pg_backup_tar.c +++ b/src/bin/pg_dump/pg_backup_tar.c @@ -39,6 +39,7 @@ #include "pg_backup_archiver.h" #include "pg_backup_tar.h" #include "pg_backup_utils.h" +#include "compress_io.h" #include "pgtar.h" static void _ArchiveEntry(ArchiveHandle *AH, TocEntry *te); @@ -196,10 +197,10 @@ InitArchiveFmt_Tar(ArchiveHandle *AH) /* * We don't support compression because reading the files back is not - * possible since gzdopen uses buffered IO which totally screws file + * possible since gzdopen uses buffered IO which totally screws file XXX * positioning. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) fatal("compression is not supported by tar archive format"); } else @@ -254,14 +255,8 @@ _ArchiveEntry(ArchiveHandle *AH, TocEntry *te) ctx = (lclTocEntry *) pg_malloc0(sizeof(lclTocEntry)); if (te->dataDumper != NULL) { -#ifdef HAVE_LIBZ - if (AH->compression == 0) - sprintf(fn, "%d.dat", te->dumpId); - else - sprintf(fn, "%d.dat.gz", te->dumpId); -#else - sprintf(fn, "%d.dat", te->dumpId); -#endif + const char *suffix = compress_suffix(&AH->compression); + sprintf(fn, "%d.dat%s", te->dumpId, suffix); ctx->filename = pg_strdup(fn); } else @@ -352,7 +347,7 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression == 0) + if (AH->compression.alg == COMPR_ALG_NONE) tm->nFH = ctx->tarFH; else fatal("compression is not supported by tar archive format"); @@ -413,9 +408,9 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) { - sprintf(fmode, "wb%d", AH->compression); + sprintf(fmode, "wb%d", AH->compression.level); tm->zFH = gzdopen(dup(fileno(tm->tmpFH)), fmode); if (tm->zFH == NULL) fatal("could not open temporary file"); @@ -443,7 +438,7 @@ tarClose(ArchiveHandle *AH, TAR_MEMBER *th) /* * Close the GZ file since we dup'd. This will flush the buffers. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) if (GZCLOSE(th->zFH) != 0) fatal("could not close tar member"); @@ -868,7 +863,7 @@ _CloseArchive(ArchiveHandle *AH) memcpy(ropt, AH->public.ropt, sizeof(RestoreOptions)); ropt->filename = NULL; ropt->dropSchema = 1; - ropt->compression = 0; + ropt->compression.alg = COMPR_ALG_NONE; ropt->superuser = NULL; ropt->suppressDumpWarnings = true; @@ -952,16 +947,12 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) lclContext *ctx = (lclContext *) AH->formatData; lclTocEntry *tctx = (lclTocEntry *) te->formatData; char fname[255]; - char *sfx; + const char *sfx; if (oid == 0) fatal("invalid OID for large object (%u)", oid); - if (AH->compression != 0) - sfx = ".gz"; - else - sfx = ""; - + sfx = compress_suffix(&AH->compression); sprintf(fname, "blob_%u.dat%s", oid, sfx); tarPrintf(ctx->blobToc, "%u %s\n", oid, fname); diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c index 1ab98a2286..4cbc79aedc 100644 --- a/src/bin/pg_dump/pg_dump.c +++ b/src/bin/pg_dump/pg_dump.c @@ -59,6 +59,7 @@ #include "getopt_long.h" #include "libpq/libpq-fs.h" #include "parallel.h" +#include "compress_io.h" #include "pg_backup_db.h" #include "pg_backup_utils.h" #include "pg_dump.h" @@ -297,6 +298,82 @@ static void setupDumpWorker(Archive *AHX); static TableInfo *getRootTableInfo(TableInfo *tbinfo); +/* Parse the string into compression options */ +static void +parse_compression(const char *optarg, Compress *compress) +{ + if (optarg[0] == '0' && optarg[1] == '\0') + compress->alg = COMPR_ALG_NONE; + else if ((optarg[0] > '0' && optarg[0] <= '9') || + optarg[0] == '-') + { + compress->alg = COMPR_ALG_LIBZ; + compress->level_set = true; + compress->level = atoi(optarg); + if (optarg[1] != '\0') + { + pg_log_error("compression level must be in range 0..9"); + exit_nicely(1); + } + } + else + { + /* Parse a more flexible string like level=3 alg=zlib opts=long */ + for (;;) + { + char *eq = strchr(optarg, '='); + int len; + + if (eq == NULL) + { + pg_log_error("compression options must be key=value: %s", optarg); + exit_nicely(1); + } + + len = eq - optarg; + if (strncmp(optarg, "alg", len) == 0) + { + if (strchr(eq, ' ')) + len = strchr(eq, ' ') - eq - 1; + else + len = strlen(eq) - len; + if (strncmp(1+eq, "zlib", len) == 0 || + strncmp(1+eq, "libz", len) == 0) + compress->alg = COMPR_ALG_LIBZ; + else + { + pg_log_error("unknown compression algorithm: %s", 1+eq); + exit_nicely(1); + } + } + else if (strncmp(optarg, "level", len) == 0) + { + compress->level = atoi(1+eq); + compress->level_set = true; + } + else + { + pg_log_error("unknown compression setting: %s", optarg); + exit_nicely(1); + } + + optarg = strchr(eq, ' '); + if (!optarg++) + break; + } + + if (!compress->level_set) + { + const int default_compress_level[] = { + 0, /* COMPR_ALG_NONE */ + Z_DEFAULT_COMPRESSION, /* COMPR_ALG_ZLIB */ + }; + + compress->level = default_compress_level[compress->alg]; + } + } +} + int main(int argc, char **argv) { @@ -319,7 +396,7 @@ main(int argc, char **argv) char *use_role = NULL; long rowsPerInsert; int numWorkers = 1; - int compressLevel = -1; + Compress compress = { .alg = COMPR_ALG_DEFAULT }; int plainText = 0; ArchiveFormat archiveFormat = archUnknown; ArchiveMode archiveMode; @@ -532,12 +609,7 @@ main(int argc, char **argv) break; case 'Z': /* Compression Level */ - compressLevel = atoi(optarg); - if (compressLevel < 0 || compressLevel > 9) - { - pg_log_error("compression level must be in range 0..9"); - exit_nicely(1); - } + parse_compression(optarg, &compress); break; case 0: @@ -679,20 +751,28 @@ main(int argc, char **argv) plainText = 1; /* Custom and directory formats are compressed by default, others not */ - if (compressLevel == -1) + if (compress.alg == COMPR_ALG_DEFAULT) { -#ifdef HAVE_LIBZ if (archiveFormat == archCustom || archiveFormat == archDirectory) - compressLevel = Z_DEFAULT_COMPRESSION; - else + { +#ifdef HAVE_LIBZ + compress.alg = COMPR_ALG_LIBZ; + compress.level = Z_DEFAULT_COMPRESSION; #endif - compressLevel = 0; + } + else + { + compress.alg = COMPR_ALG_NONE; + compress.level = 0; + } } #ifndef HAVE_LIBZ - if (compressLevel != 0) + if (compress.alg == COMPR_ALG_LIBZ) + { pg_log_warning("requested compression not available in this installation -- archive will be uncompressed"); - compressLevel = 0; + compress.alg = 0; + } #endif /* @@ -723,7 +803,7 @@ main(int argc, char **argv) fatal("option --index-collation-versions-unknown only works in binary upgrade mode"); /* Open the output file */ - fout = CreateArchive(filename, archiveFormat, compressLevel, dosync, + fout = CreateArchive(filename, archiveFormat, &compress, dosync, archiveMode, setupDumpWorker); /* Make dump options accessible right away */ @@ -957,10 +1037,7 @@ main(int argc, char **argv) ropt->sequence_data = dopt.sequence_data; ropt->binary_upgrade = dopt.binary_upgrade; - if (compressLevel == -1) - ropt->compression = 0; - else - ropt->compression = compressLevel; + ropt->compression = compress; ropt->suppressDumpWarnings = true; /* We've already shown them */ -- 2.17.0 --GRPZ8SYKNexpdSJ7 Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="0004-struct-compressLibs.patch" ^ permalink raw reply [nested|flat] 23+ messages in thread
* [PATCH 03/20] Support multiple compression algs/levels/opts.. @ 2020-12-22 06:23 Justin Pryzby <[email protected]> 0 siblings, 0 replies; 23+ messages in thread From: Justin Pryzby @ 2020-12-22 06:23 UTC (permalink / raw) The existing implementation abtracts compressed and noncompressed I/O. This preliminary commit is intended to also allow for multiple compression algorithms. --- src/bin/pg_dump/compress_io.c | 220 +++++++++++--------------- src/bin/pg_dump/compress_io.h | 19 +-- src/bin/pg_dump/pg_backup.h | 23 ++- src/bin/pg_dump/pg_backup_archiver.c | 45 +++--- src/bin/pg_dump/pg_backup_archiver.h | 12 +- src/bin/pg_dump/pg_backup_custom.c | 6 +- src/bin/pg_dump/pg_backup_directory.c | 17 +- src/bin/pg_dump/pg_backup_tar.c | 33 ++-- src/bin/pg_dump/pg_dump.c | 115 +++++++++++--- 9 files changed, 272 insertions(+), 218 deletions(-) diff --git a/src/bin/pg_dump/compress_io.c b/src/bin/pg_dump/compress_io.c index 6a428978d4..db16fd33f2 100644 --- a/src/bin/pg_dump/compress_io.c +++ b/src/bin/pg_dump/compress_io.c @@ -74,12 +74,9 @@ struct CompressorState #endif }; -static void ParseCompressionOption(int compression, CompressionAlgorithm *alg, - int *level); - /* Routines that support zlib compressed data I/O */ #ifdef HAVE_LIBZ -static void InitCompressorZlib(CompressorState *cs, int level); +static void InitCompressorZlib(CompressorState *cs, Compress *compress); static void DeflateCompressorZlib(ArchiveHandle *AH, CompressorState *cs, bool flush); static void ReadDataFromArchiveZlib(ArchiveHandle *AH, ReadFunc readF); @@ -93,58 +90,36 @@ static void ReadDataFromArchiveNone(ArchiveHandle *AH, ReadFunc readF); static void WriteDataToArchiveNone(ArchiveHandle *AH, CompressorState *cs, const char *data, size_t dLen); -/* - * Interprets a numeric 'compression' value. The algorithm implied by the - * value (zlib or none at the moment), is returned in *alg, and the - * zlib compression level in *level. - */ -static void -ParseCompressionOption(int compression, CompressionAlgorithm *alg, int *level) -{ - if (compression == Z_DEFAULT_COMPRESSION || - (compression > 0 && compression <= 9)) - *alg = COMPR_ALG_LIBZ; - else if (compression == 0) - *alg = COMPR_ALG_NONE; - else - { - fatal("invalid compression code: %d", compression); - *alg = COMPR_ALG_NONE; /* keep compiler quiet */ - } - - /* The level is just the passed-in value. */ - if (level) - *level = compression; -} - /* Public interface routines */ /* Allocate a new compressor */ CompressorState * -AllocateCompressor(int compression, WriteFunc writeF) +AllocateCompressor(Compress *compression, WriteFunc writeF) { CompressorState *cs; - CompressionAlgorithm alg; - int level; - - ParseCompressionOption(compression, &alg, &level); - -#ifndef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - fatal("not built with zlib support"); -#endif cs = (CompressorState *) pg_malloc0(sizeof(CompressorState)); cs->writeF = writeF; - cs->comprAlg = alg; + cs->comprAlg = compression->alg; /* * Perform compression algorithm specific initialization. */ + Assert (compression->alg != COMPR_ALG_DEFAULT); + switch (compression->alg) + { #ifdef HAVE_LIBZ - if (alg == COMPR_ALG_LIBZ) - InitCompressorZlib(cs, level); + case COMPR_ALG_LIBZ: + InitCompressorZlib(cs, compression); + break; #endif + case COMPR_ALG_NONE: + /* Do nothing */ + break; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } return cs; } @@ -154,21 +129,21 @@ AllocateCompressor(int compression, WriteFunc writeF) * out with ahwrite(). */ void -ReadDataFromArchive(ArchiveHandle *AH, int compression, ReadFunc readF) +ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF) { - CompressionAlgorithm alg; - - ParseCompressionOption(compression, &alg, NULL); - - if (alg == COMPR_ALG_NONE) - ReadDataFromArchiveNone(AH, readF); - if (alg == COMPR_ALG_LIBZ) + switch (AH->compression.alg) { + case COMPR_ALG_NONE: + ReadDataFromArchiveNone(AH, readF); + break; #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: ReadDataFromArchiveZlib(AH, readF); -#else - fatal("not built with zlib support"); + break; #endif + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -181,16 +156,18 @@ WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, { switch (cs->comprAlg) { - case COMPR_ALG_LIBZ: #ifdef HAVE_LIBZ + case COMPR_ALG_LIBZ: WriteDataToArchiveZlib(AH, cs, data, dLen); -#else - fatal("not built with zlib support"); -#endif break; +#endif case COMPR_ALG_NONE: WriteDataToArchiveNone(AH, cs, data, dLen); break; + + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); } } @@ -215,7 +192,7 @@ EndCompressor(ArchiveHandle *AH, CompressorState *cs) */ static void -InitCompressorZlib(CompressorState *cs, int level) +InitCompressorZlib(CompressorState *cs, Compress *compress) { z_streamp zp; @@ -232,7 +209,7 @@ InitCompressorZlib(CompressorState *cs, int level) cs->zlibOut = (char *) pg_malloc(ZLIB_OUT_SIZE + 1); cs->zlibOutSize = ZLIB_OUT_SIZE; - if (deflateInit(zp, level) != Z_OK) + if (deflateInit(zp, compress->level) != Z_OK) fatal("could not initialize compression library: %s", zp->msg); @@ -424,9 +401,7 @@ struct cfp #endif }; -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix); -#endif /* free() without changing errno; useful in several places below */ static void @@ -442,34 +417,31 @@ free_keep_errno(void *p) * Open a file for reading. 'path' is the file to open, and 'mode' should * be either "r" or "rb". * - * If the file at 'path' does not exist, we append the ".gz" suffix (if 'path' - * doesn't already have it) and try again. So if you pass "foo" as 'path', + * If the file at 'path' does not exist, we search with compressed suffix (if 'path' + * doesn't already have one) and try again. So if you pass "foo" as 'path', * this will open either "foo" or "foo.gz". * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_read(const char *path, const char *mode) +cfopen_read(const char *path, const char *mode, Compress *compression) { cfp *fp; -#ifdef HAVE_LIBZ if (hasSuffix(path, ".gz")) - fp = cfopen(path, mode, 1); + fp = cfopen(path, mode, compression); else -#endif { - fp = cfopen(path, mode, 0); -#ifdef HAVE_LIBZ + fp = cfopen(path, mode, compression); if (fp == NULL) { char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); - fp = cfopen(fname, mode, 1); + fname = psprintf("%s%s", path, suffix); + fp = cfopen(fname, mode, compression); free_keep_errno(fname); } -#endif } return fp; } @@ -479,31 +451,26 @@ cfopen_read(const char *path, const char *mode) * be a filemode as accepted by fopen() and gzopen() that indicates writing * ("w", "wb", "a", or "ab"). * - * If 'compression' is non-zero, a gzip compressed stream is opened, and - * 'compression' indicates the compression level used. The ".gz" suffix - * is automatically added to 'path' in that case. + * Use compression if specified. + * The appropriate suffix is automatically added to 'path' in that case. * * On failure, return NULL with an error code in errno. */ cfp * -cfopen_write(const char *path, const char *mode, int compression) +cfopen_write(const char *path, const char *mode, Compress *compression) { cfp *fp; - if (compression == 0) - fp = cfopen(path, mode, 0); + if (compression->alg == COMPR_ALG_NONE) + fp = cfopen(path, mode, compression); else { -#ifdef HAVE_LIBZ char *fname; + const char *suffix = compress_suffix(compression); - fname = psprintf("%s.gz", path); + fname = psprintf("%s%s", path, suffix); fp = cfopen(fname, mode, compression); free_keep_errno(fname); -#else - fatal("not built with zlib support"); - fp = NULL; /* keep compiler quiet */ -#endif } return fp; } @@ -515,20 +482,21 @@ cfopen_write(const char *path, const char *mode, int compression) * On failure, return NULL with an error code in errno. */ cfp * -cfopen(const char *path, const char *mode, int compression) +cfopen(const char *path, const char *mode, Compress *compression) { - cfp *fp = pg_malloc(sizeof(cfp)); + cfp *fp = pg_malloc0(sizeof(cfp)); - if (compression != 0) + switch (compression->alg) { #ifdef HAVE_LIBZ - if (compression != Z_DEFAULT_COMPRESSION) + case COMPR_ALG_LIBZ: + if (compression->level != Z_DEFAULT_COMPRESSION) { /* user has specified a compression level, so tell zlib to use it */ char mode_compression[32]; snprintf(mode_compression, sizeof(mode_compression), "%s%d", - mode, compression); + mode, compression->level); fp->compressedfp = gzopen(path, mode_compression); } else @@ -537,30 +505,27 @@ cfopen(const char *path, const char *mode, int compression) fp->compressedfp = gzopen(path, mode); } - fp->uncompressedfp = NULL; if (fp->compressedfp == NULL) { free_keep_errno(fp); fp = NULL; } -#else - fatal("not built with zlib support"); -#endif - } - else - { -#ifdef HAVE_LIBZ - fp->compressedfp = NULL; + return fp; #endif + + case COMPR_ALG_NONE: fp->uncompressedfp = fopen(path, mode); if (fp->uncompressedfp == NULL) { free_keep_errno(fp); fp = NULL; } - } + return fp; - return fp; + default: + /* Should not happen */ + fatal("requested compression not available in this installation"); + } } @@ -584,14 +549,13 @@ cfread(void *ptr, int size, cfp *fp) fatal("could not read from input file: %s", errnum == Z_ERRNO ? strerror(errno) : errmsg); } + return ret; } - else #endif - { - ret = fread(ptr, 1, size, fp->uncompressedfp); - if (ret != size && !feof(fp->uncompressedfp)) - READ_ERROR_EXIT(fp->uncompressedfp); - } + + ret = fread(ptr, 1, size, fp->uncompressedfp); + if (ret != size && !feof(fp->uncompressedfp)) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -601,9 +565,8 @@ cfwrite(const void *ptr, int size, cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzwrite(fp->compressedfp, ptr, size); - else #endif - return fwrite(ptr, 1, size, fp->uncompressedfp); + return fwrite(ptr, 1, size, fp->uncompressedfp); } int @@ -622,15 +585,12 @@ cfgetc(cfp *fp) else fatal("could not read from input file: end of file"); } + return ret; } - else #endif - { - ret = fgetc(fp->uncompressedfp); - if (ret == EOF) - READ_ERROR_EXIT(fp->uncompressedfp); - } - + ret = fgetc(fp->uncompressedfp); + if (ret == EOF) + READ_ERROR_EXIT(fp->uncompressedfp); return ret; } @@ -640,9 +600,8 @@ cfgets(cfp *fp, char *buf, int len) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzgets(fp->compressedfp, buf, len); - else #endif - return fgets(buf, len, fp->uncompressedfp); + return fgets(buf, len, fp->uncompressedfp); } int @@ -660,15 +619,13 @@ cfclose(cfp *fp) { result = gzclose(fp->compressedfp); fp->compressedfp = NULL; + return result; } - else #endif - { - result = fclose(fp->uncompressedfp); - fp->uncompressedfp = NULL; - } - free_keep_errno(fp); + result = fclose(fp->uncompressedfp); + fp->uncompressedfp = NULL; + free_keep_errno(fp); return result; } @@ -678,9 +635,9 @@ cfeof(cfp *fp) #ifdef HAVE_LIBZ if (fp->compressedfp) return gzeof(fp->compressedfp); - else #endif - return feof(fp->uncompressedfp); + + return feof(fp->uncompressedfp); } const char * @@ -699,7 +656,6 @@ get_cfp_error(cfp *fp) return strerror(errno); } -#ifdef HAVE_LIBZ static int hasSuffix(const char *filename, const char *suffix) { @@ -714,4 +670,18 @@ hasSuffix(const char *filename, const char *suffix) suffixlen) == 0; } -#endif +/* + * Return a string for the given AH's compression. + * The string is statically allocated. + */ +const char * +compress_suffix(Compress *compression) +{ + switch (compression->alg) + { + case COMPR_ALG_LIBZ: + return ".gz"; + default: + return ""; + } +} diff --git a/src/bin/pg_dump/compress_io.h b/src/bin/pg_dump/compress_io.h index d2e6e1b854..2c073676eb 100644 --- a/src/bin/pg_dump/compress_io.h +++ b/src/bin/pg_dump/compress_io.h @@ -21,12 +21,6 @@ #define ZLIB_OUT_SIZE 4096 #define ZLIB_IN_SIZE 4096 -typedef enum -{ - COMPR_ALG_NONE, - COMPR_ALG_LIBZ -} CompressionAlgorithm; - /* Prototype for callback function to WriteDataToArchive() */ typedef void (*WriteFunc) (ArchiveHandle *AH, const char *buf, size_t len); @@ -46,8 +40,8 @@ typedef size_t (*ReadFunc) (ArchiveHandle *AH, char **buf, size_t *buflen); /* struct definition appears in compress_io.c */ typedef struct CompressorState CompressorState; -extern CompressorState *AllocateCompressor(int compression, WriteFunc writeF); -extern void ReadDataFromArchive(ArchiveHandle *AH, int compression, +extern CompressorState *AllocateCompressor(Compress *compression, WriteFunc writeF); +extern void ReadDataFromArchive(ArchiveHandle *AH, ReadFunc readF); extern void WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs, const void *data, size_t dLen); @@ -56,9 +50,9 @@ extern void EndCompressor(ArchiveHandle *AH, CompressorState *cs); typedef struct cfp cfp; -extern cfp *cfopen(const char *path, const char *mode, int compression); -extern cfp *cfopen_read(const char *path, const char *mode); -extern cfp *cfopen_write(const char *path, const char *mode, int compression); +extern cfp *cfopen(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_read(const char *path, const char *mode, Compress *compression); +extern cfp *cfopen_write(const char *path, const char *mode, Compress *compression); extern int cfread(void *ptr, int size, cfp *fp); extern int cfwrite(const void *ptr, int size, cfp *fp); extern int cfgetc(cfp *fp); @@ -67,4 +61,7 @@ extern int cfclose(cfp *fp); extern int cfeof(cfp *fp); extern const char *get_cfp_error(cfp *fp); +/* also used by tar */ +extern const char * compress_suffix(Compress *compression); + #endif diff --git a/src/bin/pg_dump/pg_backup.h b/src/bin/pg_dump/pg_backup.h index 9d0056a569..f2390b7937 100644 --- a/src/bin/pg_dump/pg_backup.h +++ b/src/bin/pg_dump/pg_backup.h @@ -72,6 +72,25 @@ typedef struct _connParams char *override_dbname; } ConnParams; +typedef enum +{ + COMPR_ALG_DEFAULT = -1, + COMPR_ALG_NONE, + COMPR_ALG_LIBZ, +} CompressionAlgorithm; +/* Should be called "method" or "library" ? */ + +typedef struct Compress { + CompressionAlgorithm alg; + int level; + /* Is a nondefault level set ? This is useful since different compression + * methods have different "default" levels. For now we assume the levels + * are all integer, though. + */ + bool level_set; +} Compress; + + typedef struct _restoreOptions { int createDB; /* Issue commands to create the database */ @@ -125,7 +144,7 @@ typedef struct _restoreOptions int noDataForFailedTables; int exit_on_error; - int compression; + Compress compression; int suppressDumpWarnings; /* Suppress output of WARNING entries * to stderr */ bool single_txn; @@ -281,7 +300,7 @@ extern Archive *OpenArchive(const char *FileSpec, const ArchiveFormat fmt); /* Create a new archive */ extern Archive *CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker); /* The --list option */ diff --git a/src/bin/pg_dump/pg_backup_archiver.c b/src/bin/pg_dump/pg_backup_archiver.c index 1f82c6499b..3eb6c55600 100644 --- a/src/bin/pg_dump/pg_backup_archiver.c +++ b/src/bin/pg_dump/pg_backup_archiver.c @@ -70,7 +70,7 @@ typedef struct _parallelReadyList static ArchiveHandle *_allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr); static void _getObjectDescription(PQExpBuffer buf, TocEntry *te); static void _printTocEntry(ArchiveHandle *AH, TocEntry *te, bool isData); @@ -98,7 +98,7 @@ static int _discoverArchiveFormat(ArchiveHandle *AH); static int RestoringToDB(ArchiveHandle *AH); static void dump_lo_buf(ArchiveHandle *AH); static void dumpTimestamp(ArchiveHandle *AH, const char *msg, time_t tim); -static void SetOutput(ArchiveHandle *AH, const char *filename, int compression); +static void SetOutput(ArchiveHandle *AH, const char *filename, Compress *compress); static OutputContext SaveOutput(ArchiveHandle *AH); static void RestoreOutput(ArchiveHandle *AH, OutputContext savedContext); @@ -238,7 +238,7 @@ setupRestoreWorker(Archive *AHX) /* Public */ Archive * CreateArchive(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupDumpWorker) { @@ -253,7 +253,9 @@ CreateArchive(const char *FileSpec, const ArchiveFormat fmt, Archive * OpenArchive(const char *FileSpec, const ArchiveFormat fmt) { - ArchiveHandle *AH = _allocAH(FileSpec, fmt, 0, true, archModeRead, setupRestoreWorker); + Compress compress = {0}; + ArchiveHandle *AH = _allocAH(FileSpec, fmt, &compress, true, archModeRead, + setupRestoreWorker); return (Archive *) AH; } @@ -382,7 +384,7 @@ RestoreArchive(Archive *AHX) * Make sure we won't need (de)compression we haven't got */ #ifndef HAVE_LIBZ - if (AH->compression != 0 && AH->PrintTocDataPtr != NULL) + if (AH->compression.alg != COMPR_ALG_NONE && AH->PrintTocDataPtr != NULL) { for (te = AH->toc->next; te != AH->toc; te = te->next) { @@ -457,8 +459,8 @@ RestoreArchive(Archive *AHX) * Setup the output file if necessary. */ sav = SaveOutput(AH); - if (ropt->filename || ropt->compression) - SetOutput(AH, ropt->filename, ropt->compression); + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) + SetOutput(AH, ropt->filename, &ropt->compression); ahprintf(AH, "--\n-- PostgreSQL database dump\n--\n\n"); @@ -738,7 +740,7 @@ RestoreArchive(Archive *AHX) */ AH->stage = STAGE_FINALIZING; - if (ropt->filename || ropt->compression) + if (ropt->filename || ropt->compression.alg != COMPR_ALG_NONE) RestoreOutput(AH, sav); if (ropt->useDB) @@ -1123,8 +1125,9 @@ PrintTOCSummary(Archive *AHX) char stamp_str[64]; sav = SaveOutput(AH); + Assert(ropt->compression.alg == COMPR_ALG_NONE); if (ropt->filename) - SetOutput(AH, ropt->filename, 0 /* no compression */ ); + SetOutput(AH, ropt->filename, &ropt->compression); if (strftime(stamp_str, sizeof(stamp_str), PGDUMP_STRFTIME_FMT, localtime(&AH->createDate)) == 0) @@ -1133,7 +1136,7 @@ PrintTOCSummary(Archive *AHX) ahprintf(AH, ";\n; Archive created at %s\n", stamp_str); ahprintf(AH, "; dbname: %s\n; TOC Entries: %d\n; Compression: %d\n", sanitize_line(AH->archdbname, false), - AH->tocCount, AH->compression); + AH->tocCount, AH->compression.alg); switch (AH->format) { @@ -1487,7 +1490,7 @@ archprintf(Archive *AH, const char *fmt,...) *******************************/ static void -SetOutput(ArchiveHandle *AH, const char *filename, int compression) +SetOutput(ArchiveHandle *AH, const char *filename, Compress *compression) { int fn; @@ -1510,12 +1513,12 @@ SetOutput(ArchiveHandle *AH, const char *filename, int compression) /* If compression explicitly requested, use gzopen */ #ifdef HAVE_LIBZ - if (compression != 0) + if (compression->alg != COMPR_ALG_NONE) { char fmode[14]; /* Don't use PG_BINARY_x since this is zlib */ - sprintf(fmode, "wb%d", compression); + sprintf(fmode, "wb%d", compression->level); if (fn >= 0) AH->OF = gzdopen(dup(fn), fmode); else @@ -2259,7 +2262,7 @@ _discoverArchiveFormat(ArchiveHandle *AH) */ static ArchiveHandle * _allocAH(const char *FileSpec, const ArchiveFormat fmt, - const int compression, bool dosync, ArchiveMode mode, + Compress *compression, bool dosync, ArchiveMode mode, SetupWorkerPtrType setupWorkerPtr) { ArchiveHandle *AH; @@ -2310,7 +2313,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, AH->toc->prev = AH->toc; AH->mode = mode; - AH->compression = compression; + AH->compression = *compression; AH->dosync = dosync; memset(&(AH->sqlparse), 0, sizeof(AH->sqlparse)); @@ -2325,7 +2328,7 @@ _allocAH(const char *FileSpec, const ArchiveFormat fmt, * Force stdin/stdout into binary mode if that is what we are using. */ #ifdef WIN32 - if ((fmt != archNull || compression != 0) && + if ((fmt != archNull || compression->alg != COMPR_ALG_NONE) && (AH->fSpec == NULL || strcmp(AH->fSpec, "") == 0)) { if (mode == archModeWrite) @@ -3741,7 +3744,7 @@ WriteHead(ArchiveHandle *AH) AH->WriteBytePtr(AH, AH->intSize); AH->WriteBytePtr(AH, AH->offSize); AH->WriteBytePtr(AH, AH->format); - WriteInt(AH, AH->compression); + WriteInt(AH, AH->compression.alg); crtm = *localtime(&AH->createDate); WriteInt(AH, crtm.tm_sec); WriteInt(AH, crtm.tm_min); @@ -3816,15 +3819,15 @@ ReadHead(ArchiveHandle *AH) if (AH->version >= K_VERS_1_2) { if (AH->version < K_VERS_1_4) - AH->compression = AH->ReadBytePtr(AH); + AH->compression.alg = AH->ReadBytePtr(AH); else - AH->compression = ReadInt(AH); + AH->compression.alg = ReadInt(AH); } else - AH->compression = Z_DEFAULT_COMPRESSION; + AH->compression.alg = Z_DEFAULT_COMPRESSION; #ifndef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) pg_log_warning("archive is compressed, but this installation does not support compression -- no data will be available"); #endif diff --git a/src/bin/pg_dump/pg_backup_archiver.h b/src/bin/pg_dump/pg_backup_archiver.h index a8ea5c7eae..6e033d040e 100644 --- a/src/bin/pg_dump/pg_backup_archiver.h +++ b/src/bin/pg_dump/pg_backup_archiver.h @@ -47,7 +47,8 @@ #define GZWRITE(p, s, n, fh) (fwrite(p, s, n, fh) * (s)) #define GZREAD(p, s, n, fh) fread(p, s, n, fh) #define GZEOF(fh) feof(fh) -/* this is just the redefinition of a libz constant */ +/* this is just the redefinition of a libz constant, in case zlib isn't + * available */ #define Z_DEFAULT_COMPRESSION (-1) typedef struct _z_stream @@ -329,14 +330,7 @@ struct _archiveHandle DumpId *tableDataId; /* TABLE DATA ids, indexed by table dumpId */ struct _tocEntry *currToc; /* Used when dumping data */ - int compression; /*--------- - * Compression requested on open(). - * Possible values for compression: - * -1 Z_DEFAULT_COMPRESSION - * 0 COMPRESSION_NONE - * 1-9 levels for gzip compression - *--------- - */ + Compress compression; /* Compression requested on open */ bool dosync; /* data requested to be synced on sight */ ArchiveMode mode; /* File mode - r or w */ void *formatData; /* Header data specific to file format */ diff --git a/src/bin/pg_dump/pg_backup_custom.c b/src/bin/pg_dump/pg_backup_custom.c index 77d402c323..55a887a236 100644 --- a/src/bin/pg_dump/pg_backup_custom.c +++ b/src/bin/pg_dump/pg_backup_custom.c @@ -298,7 +298,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) _WriteByte(AH, BLK_DATA); /* Block type */ WriteInt(AH, te->dumpId); /* For sanity check */ - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -377,7 +377,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) WriteInt(AH, oid); - ctx->cs = AllocateCompressor(AH->compression, _CustomWriteFunc); + ctx->cs = AllocateCompressor(&AH->compression, _CustomWriteFunc); } /* @@ -566,7 +566,7 @@ _PrintTocData(ArchiveHandle *AH, TocEntry *te) static void _PrintData(ArchiveHandle *AH) { - ReadDataFromArchive(AH, AH->compression, _CustomReadFunc); + ReadDataFromArchive(AH, _CustomReadFunc); } static void diff --git a/src/bin/pg_dump/pg_backup_directory.c b/src/bin/pg_dump/pg_backup_directory.c index 650b542fce..8bf869c6ca 100644 --- a/src/bin/pg_dump/pg_backup_directory.c +++ b/src/bin/pg_dump/pg_backup_directory.c @@ -202,7 +202,7 @@ InitArchiveFmt_Directory(ArchiveHandle *AH) setFilePath(AH, fname, "toc.dat"); - tocFH = cfopen_read(fname, PG_BINARY_R); + tocFH = cfopen_read(fname, PG_BINARY_R, &AH->compression); if (tocFH == NULL) fatal("could not open input file \"%s\": %m", fname); @@ -327,7 +327,7 @@ _StartData(ArchiveHandle *AH, TocEntry *te) setFilePath(AH, fname, tctx->filename); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -388,7 +388,7 @@ _PrintFileData(ArchiveHandle *AH, char *filename) if (!filename) return; - cfp = cfopen_read(filename, PG_BINARY_R); + cfp = cfopen_read(filename, PG_BINARY_R, &AH->compression); if (!cfp) fatal("could not open input file \"%s\": %m", filename); @@ -435,12 +435,13 @@ _LoadBlobs(ArchiveHandle *AH) lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; char line[MAXPGPATH]; + Compress nocompression = {0}; StartRestoreBlobs(AH); setFilePath(AH, fname, "blobs.toc"); - ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R); + ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R, &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open large object TOC file \"%s\" for input: %m", @@ -573,6 +574,7 @@ _CloseArchive(ArchiveHandle *AH) { cfp *tocFH; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "toc.dat"); @@ -580,7 +582,7 @@ _CloseArchive(ArchiveHandle *AH) ctx->pstate = ParallelBackupStart(AH); /* The TOC is always created uncompressed */ - tocFH = cfopen_write(fname, PG_BINARY_W, 0); + tocFH = cfopen_write(fname, PG_BINARY_W, &nocompression); if (tocFH == NULL) fatal("could not open output file \"%s\": %m", fname); ctx->dataFH = tocFH; @@ -639,11 +641,12 @@ _StartBlobs(ArchiveHandle *AH, TocEntry *te) { lclContext *ctx = (lclContext *) AH->formatData; char fname[MAXPGPATH]; + Compress nocompression = {0}; setFilePath(AH, fname, "blobs.toc"); /* The blob TOC file is never compressed */ - ctx->blobsTocFH = cfopen_write(fname, "ab", 0); + ctx->blobsTocFH = cfopen_write(fname, "ab", &nocompression); if (ctx->blobsTocFH == NULL) fatal("could not open output file \"%s\": %m", fname); } @@ -661,7 +664,7 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) snprintf(fname, MAXPGPATH, "%s/blob_%u.dat", ctx->directory, oid); - ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression); + ctx->dataFH = cfopen_write(fname, PG_BINARY_W, &AH->compression); if (ctx->dataFH == NULL) fatal("could not open output file \"%s\": %m", fname); diff --git a/src/bin/pg_dump/pg_backup_tar.c b/src/bin/pg_dump/pg_backup_tar.c index 61c9c87a9f..4ba79ab924 100644 --- a/src/bin/pg_dump/pg_backup_tar.c +++ b/src/bin/pg_dump/pg_backup_tar.c @@ -39,6 +39,7 @@ #include "pg_backup_archiver.h" #include "pg_backup_tar.h" #include "pg_backup_utils.h" +#include "compress_io.h" #include "pgtar.h" static void _ArchiveEntry(ArchiveHandle *AH, TocEntry *te); @@ -196,10 +197,10 @@ InitArchiveFmt_Tar(ArchiveHandle *AH) /* * We don't support compression because reading the files back is not - * possible since gzdopen uses buffered IO which totally screws file + * possible since gzdopen uses buffered IO which totally screws file XXX * positioning. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) fatal("compression is not supported by tar archive format"); } else @@ -254,14 +255,8 @@ _ArchiveEntry(ArchiveHandle *AH, TocEntry *te) ctx = (lclTocEntry *) pg_malloc0(sizeof(lclTocEntry)); if (te->dataDumper != NULL) { -#ifdef HAVE_LIBZ - if (AH->compression == 0) - sprintf(fn, "%d.dat", te->dumpId); - else - sprintf(fn, "%d.dat.gz", te->dumpId); -#else - sprintf(fn, "%d.dat", te->dumpId); -#endif + const char *suffix = compress_suffix(&AH->compression); + sprintf(fn, "%d.dat%s", te->dumpId, suffix); ctx->filename = pg_strdup(fn); } else @@ -352,7 +347,7 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression == 0) + if (AH->compression.alg == COMPR_ALG_NONE) tm->nFH = ctx->tarFH; else fatal("compression is not supported by tar archive format"); @@ -413,9 +408,9 @@ tarOpen(ArchiveHandle *AH, const char *filename, char mode) #ifdef HAVE_LIBZ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) { - sprintf(fmode, "wb%d", AH->compression); + sprintf(fmode, "wb%d", AH->compression.level); tm->zFH = gzdopen(dup(fileno(tm->tmpFH)), fmode); if (tm->zFH == NULL) fatal("could not open temporary file"); @@ -443,7 +438,7 @@ tarClose(ArchiveHandle *AH, TAR_MEMBER *th) /* * Close the GZ file since we dup'd. This will flush the buffers. */ - if (AH->compression != 0) + if (AH->compression.alg != COMPR_ALG_NONE) if (GZCLOSE(th->zFH) != 0) fatal("could not close tar member"); @@ -868,7 +863,7 @@ _CloseArchive(ArchiveHandle *AH) memcpy(ropt, AH->public.ropt, sizeof(RestoreOptions)); ropt->filename = NULL; ropt->dropSchema = 1; - ropt->compression = 0; + ropt->compression.alg = COMPR_ALG_NONE; ropt->superuser = NULL; ropt->suppressDumpWarnings = true; @@ -952,16 +947,12 @@ _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid) lclContext *ctx = (lclContext *) AH->formatData; lclTocEntry *tctx = (lclTocEntry *) te->formatData; char fname[255]; - char *sfx; + const char *sfx; if (oid == 0) fatal("invalid OID for large object (%u)", oid); - if (AH->compression != 0) - sfx = ".gz"; - else - sfx = ""; - + sfx = compress_suffix(&AH->compression); sprintf(fname, "blob_%u.dat%s", oid, sfx); tarPrintf(ctx->blobToc, "%u %s\n", oid, fname); diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c index 1ab98a2286..4cbc79aedc 100644 --- a/src/bin/pg_dump/pg_dump.c +++ b/src/bin/pg_dump/pg_dump.c @@ -59,6 +59,7 @@ #include "getopt_long.h" #include "libpq/libpq-fs.h" #include "parallel.h" +#include "compress_io.h" #include "pg_backup_db.h" #include "pg_backup_utils.h" #include "pg_dump.h" @@ -297,6 +298,82 @@ static void setupDumpWorker(Archive *AHX); static TableInfo *getRootTableInfo(TableInfo *tbinfo); +/* Parse the string into compression options */ +static void +parse_compression(const char *optarg, Compress *compress) +{ + if (optarg[0] == '0' && optarg[1] == '\0') + compress->alg = COMPR_ALG_NONE; + else if ((optarg[0] > '0' && optarg[0] <= '9') || + optarg[0] == '-') + { + compress->alg = COMPR_ALG_LIBZ; + compress->level_set = true; + compress->level = atoi(optarg); + if (optarg[1] != '\0') + { + pg_log_error("compression level must be in range 0..9"); + exit_nicely(1); + } + } + else + { + /* Parse a more flexible string like level=3 alg=zlib opts=long */ + for (;;) + { + char *eq = strchr(optarg, '='); + int len; + + if (eq == NULL) + { + pg_log_error("compression options must be key=value: %s", optarg); + exit_nicely(1); + } + + len = eq - optarg; + if (strncmp(optarg, "alg", len) == 0) + { + if (strchr(eq, ' ')) + len = strchr(eq, ' ') - eq - 1; + else + len = strlen(eq) - len; + if (strncmp(1+eq, "zlib", len) == 0 || + strncmp(1+eq, "libz", len) == 0) + compress->alg = COMPR_ALG_LIBZ; + else + { + pg_log_error("unknown compression algorithm: %s", 1+eq); + exit_nicely(1); + } + } + else if (strncmp(optarg, "level", len) == 0) + { + compress->level = atoi(1+eq); + compress->level_set = true; + } + else + { + pg_log_error("unknown compression setting: %s", optarg); + exit_nicely(1); + } + + optarg = strchr(eq, ' '); + if (!optarg++) + break; + } + + if (!compress->level_set) + { + const int default_compress_level[] = { + 0, /* COMPR_ALG_NONE */ + Z_DEFAULT_COMPRESSION, /* COMPR_ALG_ZLIB */ + }; + + compress->level = default_compress_level[compress->alg]; + } + } +} + int main(int argc, char **argv) { @@ -319,7 +396,7 @@ main(int argc, char **argv) char *use_role = NULL; long rowsPerInsert; int numWorkers = 1; - int compressLevel = -1; + Compress compress = { .alg = COMPR_ALG_DEFAULT }; int plainText = 0; ArchiveFormat archiveFormat = archUnknown; ArchiveMode archiveMode; @@ -532,12 +609,7 @@ main(int argc, char **argv) break; case 'Z': /* Compression Level */ - compressLevel = atoi(optarg); - if (compressLevel < 0 || compressLevel > 9) - { - pg_log_error("compression level must be in range 0..9"); - exit_nicely(1); - } + parse_compression(optarg, &compress); break; case 0: @@ -679,20 +751,28 @@ main(int argc, char **argv) plainText = 1; /* Custom and directory formats are compressed by default, others not */ - if (compressLevel == -1) + if (compress.alg == COMPR_ALG_DEFAULT) { -#ifdef HAVE_LIBZ if (archiveFormat == archCustom || archiveFormat == archDirectory) - compressLevel = Z_DEFAULT_COMPRESSION; - else + { +#ifdef HAVE_LIBZ + compress.alg = COMPR_ALG_LIBZ; + compress.level = Z_DEFAULT_COMPRESSION; #endif - compressLevel = 0; + } + else + { + compress.alg = COMPR_ALG_NONE; + compress.level = 0; + } } #ifndef HAVE_LIBZ - if (compressLevel != 0) + if (compress.alg == COMPR_ALG_LIBZ) + { pg_log_warning("requested compression not available in this installation -- archive will be uncompressed"); - compressLevel = 0; + compress.alg = 0; + } #endif /* @@ -723,7 +803,7 @@ main(int argc, char **argv) fatal("option --index-collation-versions-unknown only works in binary upgrade mode"); /* Open the output file */ - fout = CreateArchive(filename, archiveFormat, compressLevel, dosync, + fout = CreateArchive(filename, archiveFormat, &compress, dosync, archiveMode, setupDumpWorker); /* Make dump options accessible right away */ @@ -957,10 +1037,7 @@ main(int argc, char **argv) ropt->sequence_data = dopt.sequence_data; ropt->binary_upgrade = dopt.binary_upgrade; - if (compressLevel == -1) - ropt->compression = 0; - else - ropt->compression = compressLevel; + ropt->compression = compress; ropt->suppressDumpWarnings = true; /* We've already shown them */ -- 2.17.0 --GRPZ8SYKNexpdSJ7 Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="0004-struct-compressLibs.patch" ^ permalink raw reply [nested|flat] 23+ messages in thread
* Re: O(n) tasks cause lengthy startups and checkpoints @ 2023-02-17 23:43 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 23+ messages in thread From: Nathan Bossart @ 2023-02-17 23:43 UTC (permalink / raw) To: Bharath Rupireddy <[email protected]>; +Cc: Simon Riggs <[email protected]>; Robert Haas <[email protected]>; Andres Freund <[email protected]>; Bossart, Nathan <[email protected]>; Maxim Orlov <[email protected]>; Amul Sul <[email protected]>; Bruce Momjian <[email protected]>; pgsql-hackers On Thu, Feb 02, 2023 at 09:48:08PM -0800, Nathan Bossart wrote: > rebased for cfbot another rebase for cfbot -- Nathan Bossart Amazon Web Services: https://aws.amazon.com Attachments: [text/x-diff] v20-0001-Introduce-custodian.patch (26.4K, ../../20230217234344.GA3357392@nathanxps13/2-v20-0001-Introduce-custodian.patch) download | inline diff: From 1c9b95cae7adcc57b7544a44ff16a26e71c6c736 Mon Sep 17 00:00:00 2001 From: Nathan Bossart <[email protected]> Date: Wed, 5 Jan 2022 19:24:22 +0000 Subject: [PATCH v20 1/4] Introduce custodian. The custodian process is a new auxiliary process that is intended to help offload tasks could otherwise delay startup and checkpointing. This commit simply adds the new process; it does not yet do anything useful. --- doc/src/sgml/glossary.sgml | 11 + src/backend/postmaster/Makefile | 1 + src/backend/postmaster/auxprocess.c | 8 + src/backend/postmaster/custodian.c | 377 ++++++++++++++++++++++++ src/backend/postmaster/meson.build | 1 + src/backend/postmaster/postmaster.c | 38 ++- src/backend/storage/ipc/ipci.c | 3 + src/backend/storage/lmgr/proc.c | 1 + src/backend/utils/activity/pgstat_io.c | 4 +- src/backend/utils/activity/wait_event.c | 3 + src/backend/utils/init/miscinit.c | 3 + src/include/miscadmin.h | 3 + src/include/postmaster/custodian.h | 32 ++ src/include/storage/proc.h | 11 +- src/include/utils/wait_event.h | 1 + 15 files changed, 491 insertions(+), 6 deletions(-) create mode 100644 src/backend/postmaster/custodian.c create mode 100644 src/include/postmaster/custodian.h diff --git a/doc/src/sgml/glossary.sgml b/doc/src/sgml/glossary.sgml index 7c01a541fe..ad3f53e2a3 100644 --- a/doc/src/sgml/glossary.sgml +++ b/doc/src/sgml/glossary.sgml @@ -144,6 +144,7 @@ (but not the autovacuum workers), the <glossterm linkend="glossary-background-writer">background writer</glossterm>, the <glossterm linkend="glossary-checkpointer">checkpointer</glossterm>, + the <glossterm linkend="glossary-custodian">custodian</glossterm>, the <glossterm linkend="glossary-logger">logger</glossterm>, the <glossterm linkend="glossary-startup-process">startup process</glossterm>, the <glossterm linkend="glossary-wal-archiver">WAL archiver</glossterm>, @@ -484,6 +485,16 @@ </glossdef> </glossentry> + <glossentry id="glossary-custodian"> + <glossterm>Custodian (process)</glossterm> + <glossdef> + <para> + An <glossterm linkend="glossary-auxiliary-proc">auxiliary process</glossterm> + that is responsible for executing assorted cleanup tasks. + </para> + </glossdef> + </glossentry> + <glossentry> <glossterm>Data area</glossterm> <glosssee otherterm="glossary-data-directory" /> diff --git a/src/backend/postmaster/Makefile b/src/backend/postmaster/Makefile index 047448b34e..5f4dde85cf 100644 --- a/src/backend/postmaster/Makefile +++ b/src/backend/postmaster/Makefile @@ -18,6 +18,7 @@ OBJS = \ bgworker.o \ bgwriter.o \ checkpointer.o \ + custodian.o \ fork_process.o \ interrupt.o \ pgarch.o \ diff --git a/src/backend/postmaster/auxprocess.c b/src/backend/postmaster/auxprocess.c index cae6feb356..a1f042f13a 100644 --- a/src/backend/postmaster/auxprocess.c +++ b/src/backend/postmaster/auxprocess.c @@ -20,6 +20,7 @@ #include "pgstat.h" #include "postmaster/auxprocess.h" #include "postmaster/bgwriter.h" +#include "postmaster/custodian.h" #include "postmaster/startup.h" #include "postmaster/walwriter.h" #include "replication/walreceiver.h" @@ -74,6 +75,9 @@ AuxiliaryProcessMain(AuxProcType auxtype) case CheckpointerProcess: MyBackendType = B_CHECKPOINTER; break; + case CustodianProcess: + MyBackendType = B_CUSTODIAN; + break; case WalWriterProcess: MyBackendType = B_WAL_WRITER; break; @@ -153,6 +157,10 @@ AuxiliaryProcessMain(AuxProcType auxtype) CheckpointerMain(); proc_exit(1); + case CustodianProcess: + CustodianMain(); + proc_exit(1); + case WalWriterProcess: WalWriterMain(); proc_exit(1); diff --git a/src/backend/postmaster/custodian.c b/src/backend/postmaster/custodian.c new file mode 100644 index 0000000000..98bb9efcfd --- /dev/null +++ b/src/backend/postmaster/custodian.c @@ -0,0 +1,377 @@ +/*------------------------------------------------------------------------- + * + * custodian.c + * + * The custodian process handles a variety of non-critical tasks that might + * otherwise delay startup, checkpointing, etc. Offloaded tasks should not + * be synchronous (e.g., checkpointing shouldn't wait for the custodian to + * complete a task before proceeding). However, tasks can be synchronously + * executed when necessary (e.g., single-user mode). The custodian is not + * an essential process and can shutdown quickly when requested. The + * custodian only wakes up to perform its tasks when its latch is set. + * + * + * Copyright (c) 2022, PostgreSQL Global Development Group + * + * + * IDENTIFICATION + * src/backend/postmaster/custodian.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "libpq/pqsignal.h" +#include "pgstat.h" +#include "postmaster/custodian.h" +#include "postmaster/interrupt.h" +#include "storage/bufmgr.h" +#include "storage/condition_variable.h" +#include "storage/fd.h" +#include "storage/proc.h" +#include "storage/procsignal.h" +#include "storage/smgr.h" +#include "utils/memutils.h" + +static void DoCustodianTasks(void); +static CustodianTask CustodianGetNextTask(void); +static void CustodianEnqueueTask(CustodianTask task); +static const struct cust_task_funcs_entry *LookupCustodianFunctions(CustodianTask task); + +typedef struct +{ + slock_t cust_lck; + + CustodianTask task_queue_elems[NUM_CUSTODIAN_TASKS]; + int task_queue_head; +} CustodianShmemStruct; + +static CustodianShmemStruct *CustodianShmem; + +typedef void (*CustodianTaskFunction) (void); +typedef void (*CustodianTaskHandleArg) (Datum arg); + +struct cust_task_funcs_entry +{ + CustodianTask task; + CustodianTaskFunction task_func; /* performs task */ + CustodianTaskHandleArg handle_arg_func; /* handles additional info in request */ +}; + +/* + * Add new tasks here. + * + * task_func is the logic that will be executed via DoCustodianTasks() when the + * matching task is requested via RequestCustodian(). handle_arg_func is an + * optional function for providing extra information for the next invocation of + * the task. Typically, the extra information should be stored in shared + * memory for access from the custodian process. handle_arg_func is invoked + * before enqueueing the task, and it will still be invoked regardless of + * whether the task is already enqueued. + */ +static const struct cust_task_funcs_entry cust_task_functions[] = { + {INVALID_CUSTODIAN_TASK, NULL, NULL} /* must be last */ +}; + +/* + * Main entry point for custodian process + * + * This is invoked from AuxiliaryProcessMain, which has already created the + * basic execution environment, but not enabled signals yet. + */ +void +CustodianMain(void) +{ + sigjmp_buf local_sigjmp_buf; + MemoryContext custodian_context; + + /* + * Properly accept or ignore signals that might be sent to us. + */ + pqsignal(SIGHUP, SignalHandlerForConfigReload); + pqsignal(SIGINT, SignalHandlerForShutdownRequest); + pqsignal(SIGTERM, SignalHandlerForShutdownRequest); + /* SIGQUIT handler was already set up by InitPostmasterChild */ + pqsignal(SIGALRM, SIG_IGN); + pqsignal(SIGPIPE, SIG_IGN); + pqsignal(SIGUSR1, procsignal_sigusr1_handler); + pqsignal(SIGUSR2, SIG_IGN); + + /* + * Reset some signals that are accepted by postmaster but not here + */ + pqsignal(SIGCHLD, SIG_DFL); + + /* + * Create a memory context that we will do all our work in. We do this so + * that we can reset the context during error recovery and thereby avoid + * possible memory leaks. + */ + custodian_context = AllocSetContextCreate(TopMemoryContext, + "Custodian", + ALLOCSET_DEFAULT_SIZES); + MemoryContextSwitchTo(custodian_context); + + /* + * If an exception is encountered, processing resumes here. As with other + * auxiliary processes, we cannot use PG_TRY because this is the bottom of + * the exception stack. + */ + if (sigsetjmp(local_sigjmp_buf, 1) != 0) + { + /* Since not using PG_TRY, must reset error stack by hand */ + error_context_stack = NULL; + + /* Prevent interrupts while cleaning up */ + HOLD_INTERRUPTS(); + + /* Report the error to the server log */ + EmitErrorReport(); + + /* + * These operations are really just a minimal subset of + * AbortTransaction(). We don't have very many resources to worry + * about. + */ + LWLockReleaseAll(); + ConditionVariableCancelSleep(); + ReleaseAuxProcessResources(false); + AtEOXact_Files(false); + + /* + * Now return to normal top-level context and clear ErrorContext for + * next time. + */ + MemoryContextSwitchTo(custodian_context); + FlushErrorState(); + + /* Flush any leaked data in the top-level context */ + MemoryContextResetAndDeleteChildren(custodian_context); + + /* Now we can allow interrupts again */ + RESUME_INTERRUPTS(); + + /* + * Sleep at least 1 second after any error. A write error is likely + * to be repeated, and we don't want to be filling the error logs as + * fast as we can. + */ + pg_usleep(1000000L); + + /* + * Close all open files after any error. This is helpful on Windows, + * where holding deleted files open causes various strange errors. + * It's not clear we need it elsewhere, but shouldn't hurt. + */ + smgrcloseall(); + + /* Report wait end here, when there is no further possibility of wait */ + pgstat_report_wait_end(); + } + + /* We can now handle ereport(ERROR) */ + PG_exception_stack = &local_sigjmp_buf; + + /* + * Unblock signals (they were blocked when the postmaster forked us) + */ + sigprocmask(SIG_SETMASK, &UnBlockSig, NULL); + + /* + * Advertise our latch that backends can use to wake us up while we're + * sleeping. + */ + ProcGlobal->custodianLatch = &MyProc->procLatch; + + /* + * Loop forever + */ + for (;;) + { + /* Clear any already-pending wakeups */ + ResetLatch(MyLatch); + + HandleMainLoopInterrupts(); + + DoCustodianTasks(); + + (void) WaitLatch(MyLatch, WL_LATCH_SET | WL_EXIT_ON_PM_DEATH, 0, + WAIT_EVENT_CUSTODIAN_MAIN); + } + + pg_unreachable(); +} + +/* + * DoCustodianTasks + * Perform requested custodian tasks + * + * If we are not in a standalone backend, the custodian will re-enqueue the + * currently running task if an exception is encountered. + */ +static void +DoCustodianTasks(void) +{ + CustodianTask task; + + while ((task = CustodianGetNextTask()) != INVALID_CUSTODIAN_TASK) + { + CustodianTaskFunction func = (LookupCustodianFunctions(task))->task_func; + + PG_TRY(); + { + (*func) (); + } + PG_CATCH(); + { + if (IsPostmasterEnvironment) + CustodianEnqueueTask(task); + + PG_RE_THROW(); + } + PG_END_TRY(); + } +} + +Size +CustodianShmemSize(void) +{ + return sizeof(CustodianShmemStruct); +} + +void +CustodianShmemInit(void) +{ + Size size = CustodianShmemSize(); + bool found; + + CustodianShmem = (CustodianShmemStruct *) + ShmemInitStruct("Custodian Data", size, &found); + + if (!found) + { + memset(CustodianShmem, 0, size); + SpinLockInit(&CustodianShmem->cust_lck); + for (int i = 0; i < NUM_CUSTODIAN_TASKS; i++) + CustodianShmem->task_queue_elems[i] = INVALID_CUSTODIAN_TASK; + } +} + +/* + * RequestCustodian + * Called to request a custodian task. + * + * In standalone backends, the task is performed immediately in the current + * process, and this function will not return until it completes. Otherwise, + * the task is added to the custodian's queue if it is not already enqueued, + * and this function returns without waiting for the task to complete. + * + * arg can be used to provide additional information to the custodian that is + * necessary for the task. Typically, the handling function should store this + * information in shared memory for later use by the custodian. Note that the + * task's handling function for arg is invoked before enqueueing the task, and + * it will still be invoked regardless of whether the task is already enqueued. + */ +void +RequestCustodian(CustodianTask requested, Datum arg) +{ + CustodianTaskHandleArg arg_func = (LookupCustodianFunctions(requested))->handle_arg_func; + + /* First process any extra information provided in the request. */ + if (arg_func) + (*arg_func) (arg); + + CustodianEnqueueTask(requested); + + if (!IsPostmasterEnvironment) + DoCustodianTasks(); + else if (ProcGlobal->custodianLatch) + SetLatch(ProcGlobal->custodianLatch); +} + +/* + * CustodianEnqueueTask + * Add a task to the custodian's queue + * + * If the task is already in the queue, this function has no effect. + */ +static void +CustodianEnqueueTask(CustodianTask task) +{ + Assert(task >= 0 && task < NUM_CUSTODIAN_TASKS); + + SpinLockAcquire(&CustodianShmem->cust_lck); + + for (int i = 0; i < NUM_CUSTODIAN_TASKS; i++) + { + int idx = (CustodianShmem->task_queue_head + i) % NUM_CUSTODIAN_TASKS; + CustodianTask *elem = &CustodianShmem->task_queue_elems[idx]; + + /* + * If the task is already queued in this slot or the slot is empty, + * enqueue the task here and return. + */ + if (*elem == INVALID_CUSTODIAN_TASK || *elem == task) + { + *elem = task; + SpinLockRelease(&CustodianShmem->cust_lck); + return; + } + } + + /* We should never run out of space in the queue. */ + elog(ERROR, "could not enqueue custodian task %d", task); + pg_unreachable(); +} + +/* + * CustodianGetNextTask + * Retrieve the next task that the custodian should execute + * + * The returned task is dequeued from the custodian's queue. If no tasks are + * queued, INVALID_CUSTODIAN_TASK is returned. + */ +static CustodianTask +CustodianGetNextTask(void) +{ + CustodianTask next_task; + CustodianTask *elem; + + SpinLockAcquire(&CustodianShmem->cust_lck); + + elem = &CustodianShmem->task_queue_elems[CustodianShmem->task_queue_head]; + + next_task = *elem; + *elem = INVALID_CUSTODIAN_TASK; + + CustodianShmem->task_queue_head++; + CustodianShmem->task_queue_head %= NUM_CUSTODIAN_TASKS; + + SpinLockRelease(&CustodianShmem->cust_lck); + + return next_task; +} + +/* + * LookupCustodianFunctions + * Given a custodian task, look up its function pointers. + */ +static const struct cust_task_funcs_entry * +LookupCustodianFunctions(CustodianTask task) +{ + const struct cust_task_funcs_entry *entry; + + Assert(task >= 0 && task < NUM_CUSTODIAN_TASKS); + + for (entry = cust_task_functions; + entry && entry->task != INVALID_CUSTODIAN_TASK; + entry++) + { + if (entry->task == task) + return entry; + } + + /* All tasks must have an entry. */ + elog(ERROR, "could not lookup functions for custodian task %d", task); + pg_unreachable(); +} diff --git a/src/backend/postmaster/meson.build b/src/backend/postmaster/meson.build index cda921fd10..faaaba6a21 100644 --- a/src/backend/postmaster/meson.build +++ b/src/backend/postmaster/meson.build @@ -6,6 +6,7 @@ backend_sources += files( 'bgworker.c', 'bgwriter.c', 'checkpointer.c', + 'custodian.c', 'fork_process.c', 'interrupt.c', 'pgarch.c', diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 2552327d90..e3aef4081e 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -249,6 +249,7 @@ bool send_abort_for_kill = false; static pid_t StartupPID = 0, BgWriterPID = 0, CheckpointerPID = 0, + CustodianPID = 0, WalWriterPID = 0, WalReceiverPID = 0, AutoVacPID = 0, @@ -560,6 +561,7 @@ static void ShmemBackendArrayRemove(Backend *bn); #define StartArchiver() StartChildProcess(ArchiverProcess) #define StartBackgroundWriter() StartChildProcess(BgWriterProcess) #define StartCheckpointer() StartChildProcess(CheckpointerProcess) +#define StartCustodian() StartChildProcess(CustodianProcess) #define StartWalWriter() StartChildProcess(WalWriterProcess) #define StartWalReceiver() StartChildProcess(WalReceiverProcess) @@ -1795,13 +1797,16 @@ ServerLoop(void) /* * If no background writer process is running, and we are not in a * state that prevents it, start one. It doesn't matter if this - * fails, we'll just try again later. Likewise for the checkpointer. + * fails, we'll just try again later. Likewise for the checkpointer + * and custodian. */ if (pmState == PM_RUN || pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY || pmState == PM_STARTUP) { if (CheckpointerPID == 0) CheckpointerPID = StartCheckpointer(); + if (CustodianPID == 0) + CustodianPID = StartCustodian(); if (BgWriterPID == 0) BgWriterPID = StartBackgroundWriter(); } @@ -2732,6 +2737,8 @@ process_pm_reload_request(void) signal_child(BgWriterPID, SIGHUP); if (CheckpointerPID != 0) signal_child(CheckpointerPID, SIGHUP); + if (CustodianPID != 0) + signal_child(CustodianPID, SIGHUP); if (WalWriterPID != 0) signal_child(WalWriterPID, SIGHUP); if (WalReceiverPID != 0) @@ -3085,6 +3092,8 @@ process_pm_child_exit(void) */ if (CheckpointerPID == 0) CheckpointerPID = StartCheckpointer(); + if (CustodianPID == 0) + CustodianPID = StartCustodian(); if (BgWriterPID == 0) BgWriterPID = StartBackgroundWriter(); if (WalWriterPID == 0) @@ -3178,6 +3187,20 @@ process_pm_child_exit(void) continue; } + /* + * Was it the custodian? Normal exit can be ignored; we'll start a + * new one at the next iteration of the postmaster's main loop, if + * necessary. Any other exit condition is treated as a crash. + */ + if (pid == CustodianPID) + { + CustodianPID = 0; + if (!EXIT_STATUS_0(exitstatus)) + HandleChildCrash(pid, exitstatus, + _("custodian process")); + continue; + } + /* * Was it the wal writer? Normal exit can be ignored; we'll start a * new one at the next iteration of the postmaster's main loop, if @@ -3590,6 +3613,12 @@ HandleChildCrash(int pid, int exitstatus, const char *procname) else if (CheckpointerPID != 0 && take_action) sigquit_child(CheckpointerPID); + /* Take care of the custodian too */ + if (pid == CustodianPID) + CustodianPID = 0; + else if (CustodianPID != 0 && take_action) + sigquit_child(CustodianPID); + /* Take care of the walwriter too */ if (pid == WalWriterPID) WalWriterPID = 0; @@ -3744,6 +3773,9 @@ PostmasterStateMachine(void) /* and the bgwriter too */ if (BgWriterPID != 0) signal_child(BgWriterPID, SIGTERM); + /* and the custodian too */ + if (CustodianPID != 0) + signal_child(CustodianPID, SIGTERM); /* and the walwriter too */ if (WalWriterPID != 0) signal_child(WalWriterPID, SIGTERM); @@ -3781,6 +3813,7 @@ PostmasterStateMachine(void) BgWriterPID == 0 && (CheckpointerPID == 0 || (!FatalError && Shutdown < ImmediateShutdown)) && + CustodianPID == 0 && WalWriterPID == 0 && AutoVacPID == 0) { @@ -3877,6 +3910,7 @@ PostmasterStateMachine(void) Assert(WalReceiverPID == 0); Assert(BgWriterPID == 0); Assert(CheckpointerPID == 0); + Assert(CustodianPID == 0); Assert(WalWriterPID == 0); Assert(AutoVacPID == 0); /* syslogger is not considered here */ @@ -4092,6 +4126,8 @@ TerminateChildren(int signal) signal_child(BgWriterPID, signal); if (CheckpointerPID != 0) signal_child(CheckpointerPID, signal); + if (CustodianPID != 0) + signal_child(CustodianPID, signal); if (WalWriterPID != 0) signal_child(WalWriterPID, signal); if (WalReceiverPID != 0) diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 8f1ded7338..4268a941ad 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -30,6 +30,7 @@ #include "postmaster/autovacuum.h" #include "postmaster/bgworker_internals.h" #include "postmaster/bgwriter.h" +#include "postmaster/custodian.h" #include "postmaster/postmaster.h" #include "replication/logicallauncher.h" #include "replication/origin.h" @@ -130,6 +131,7 @@ CalculateShmemSize(int *num_semaphores) size = add_size(size, PMSignalShmemSize()); size = add_size(size, ProcSignalShmemSize()); size = add_size(size, CheckpointerShmemSize()); + size = add_size(size, CustodianShmemSize()); size = add_size(size, AutoVacuumShmemSize()); size = add_size(size, ReplicationSlotsShmemSize()); size = add_size(size, ReplicationOriginShmemSize()); @@ -278,6 +280,7 @@ CreateSharedMemoryAndSemaphores(void) PMSignalShmemInit(); ProcSignalShmemInit(); CheckpointerShmemInit(); + CustodianShmemInit(); AutoVacuumShmemInit(); ReplicationSlotsShmemInit(); ReplicationOriginShmemInit(); diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 22b4278610..40a83636fe 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -178,6 +178,7 @@ InitProcGlobal(void) ProcGlobal->startupBufferPinWaitBufId = -1; ProcGlobal->walwriterLatch = NULL; ProcGlobal->checkpointerLatch = NULL; + ProcGlobal->custodianLatch = NULL; pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO); pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO); diff --git a/src/backend/utils/activity/pgstat_io.c b/src/backend/utils/activity/pgstat_io.c index 0e07e0848d..f05590f2c4 100644 --- a/src/backend/utils/activity/pgstat_io.c +++ b/src/backend/utils/activity/pgstat_io.c @@ -224,7 +224,8 @@ pgstat_io_snapshot_cb(void) * - Syslogger because it is not connected to shared memory * - Archiver because most relevant archiving IO is delegated to a * specialized command or module -* - WAL Receiver and WAL Writer IO is not tracked in pg_stat_io for now +* - WAL Receiver, WAL Writer, and Custodian IO is not tracked in pg_stat_io for +* now * * Function returns true if BackendType participates in the cumulative stats * subsystem for IO and false if it does not. @@ -243,6 +244,7 @@ pgstat_tracks_io_bktype(BackendType bktype) { case B_INVALID: case B_ARCHIVER: + case B_CUSTODIAN: case B_LOGGER: case B_WAL_RECEIVER: case B_WAL_WRITER: diff --git a/src/backend/utils/activity/wait_event.c b/src/backend/utils/activity/wait_event.c index cb99cc6339..6ca751dd1f 100644 --- a/src/backend/utils/activity/wait_event.c +++ b/src/backend/utils/activity/wait_event.c @@ -224,6 +224,9 @@ pgstat_get_wait_activity(WaitEventActivity w) case WAIT_EVENT_CHECKPOINTER_MAIN: event_name = "CheckpointerMain"; break; + case WAIT_EVENT_CUSTODIAN_MAIN: + event_name = "CustodianMain"; + break; case WAIT_EVENT_LOGICAL_APPLY_MAIN: event_name = "LogicalApplyMain"; break; diff --git a/src/backend/utils/init/miscinit.c b/src/backend/utils/init/miscinit.c index 59532bbd80..25c2ba97b8 100644 --- a/src/backend/utils/init/miscinit.c +++ b/src/backend/utils/init/miscinit.c @@ -283,6 +283,9 @@ GetBackendTypeDesc(BackendType backendType) case B_CHECKPOINTER: backendDesc = "checkpointer"; break; + case B_CUSTODIAN: + backendDesc = "custodian"; + break; case B_LOGGER: backendDesc = "logger"; break; diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h index c309e0233d..50f407a0bf 100644 --- a/src/include/miscadmin.h +++ b/src/include/miscadmin.h @@ -324,6 +324,7 @@ typedef enum BackendType B_BG_WORKER, B_BG_WRITER, B_CHECKPOINTER, + B_CUSTODIAN, B_LOGGER, B_STANDALONE_BACKEND, B_STARTUP, @@ -432,6 +433,7 @@ typedef enum BgWriterProcess, ArchiverProcess, CheckpointerProcess, + CustodianProcess, WalWriterProcess, WalReceiverProcess, @@ -444,6 +446,7 @@ extern PGDLLIMPORT AuxProcType MyAuxProcType; #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess) #define AmArchiverProcess() (MyAuxProcType == ArchiverProcess) #define AmCheckpointerProcess() (MyAuxProcType == CheckpointerProcess) +#define AmCustodianProcess() (MyAuxProcType == CustodianProcess) #define AmWalWriterProcess() (MyAuxProcType == WalWriterProcess) #define AmWalReceiverProcess() (MyAuxProcType == WalReceiverProcess) diff --git a/src/include/postmaster/custodian.h b/src/include/postmaster/custodian.h new file mode 100644 index 0000000000..73d0bc5f02 --- /dev/null +++ b/src/include/postmaster/custodian.h @@ -0,0 +1,32 @@ +/*------------------------------------------------------------------------- + * + * custodian.h + * Exports from postmaster/custodian.c. + * + * Copyright (c) 2022, PostgreSQL Global Development Group + * + * src/include/postmaster/custodian.h + * + *------------------------------------------------------------------------- + */ +#ifndef _CUSTODIAN_H +#define _CUSTODIAN_H + +/* + * If you add a new task here, be sure to add its corresponding function + * pointers to cust_task_functions in custodian.c. + */ +typedef enum CustodianTask +{ + FAKE_TASK, /* placeholder until we have a real task */ + + NUM_CUSTODIAN_TASKS, /* new tasks go above */ + INVALID_CUSTODIAN_TASK +} CustodianTask; + +extern void CustodianMain(void) pg_attribute_noreturn(); +extern Size CustodianShmemSize(void); +extern void CustodianShmemInit(void); +extern void RequestCustodian(CustodianTask task, Datum arg); + +#endif /* _CUSTODIAN_H */ diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 4258cd92c9..25e00a14ff 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -400,6 +400,8 @@ typedef struct PROC_HDR Latch *walwriterLatch; /* Checkpointer process's latch */ Latch *checkpointerLatch; + /* Custodian process's latch */ + Latch *custodianLatch; /* Current shared estimate of appropriate spins_per_delay value */ int spins_per_delay; /* Buffer id of the buffer that Startup process waits for pin on, or -1 */ @@ -417,11 +419,12 @@ extern PGDLLIMPORT PGPROC *PreparedXactProcs; * We set aside some extra PGPROC structures for auxiliary processes, * ie things that aren't full-fledged backends but need shmem access. * - * Background writer, checkpointer, WAL writer and archiver run during normal - * operation. Startup process and WAL receiver also consume 2 slots, but WAL - * writer is launched only after startup has exited, so we only need 5 slots. + * Background writer, checkpointer, custodian, WAL writer and archiver run + * during normal operation. Startup process and WAL receiver also consume 2 + * slots, but WAL writer is launched only after startup has exited, so we only + * need 6 slots. */ -#define NUM_AUXILIARY_PROCS 5 +#define NUM_AUXILIARY_PROCS 6 /* configurable options */ extern PGDLLIMPORT int DeadlockTimeout; diff --git a/src/include/utils/wait_event.h b/src/include/utils/wait_event.h index 9ab23e1c4a..a100dbca3b 100644 --- a/src/include/utils/wait_event.h +++ b/src/include/utils/wait_event.h @@ -40,6 +40,7 @@ typedef enum WAIT_EVENT_BGWRITER_HIBERNATE, WAIT_EVENT_BGWRITER_MAIN, WAIT_EVENT_CHECKPOINTER_MAIN, + WAIT_EVENT_CUSTODIAN_MAIN, WAIT_EVENT_LOGICAL_APPLY_MAIN, WAIT_EVENT_LOGICAL_LAUNCHER_MAIN, WAIT_EVENT_LOGICAL_PARALLEL_APPLY_MAIN, -- 2.25.1 [text/x-diff] v20-0002-Move-removal-of-old-serialized-snapshots-to-cust.patch (6.3K, ../../20230217234344.GA3357392@nathanxps13/3-v20-0002-Move-removal-of-old-serialized-snapshots-to-cust.patch) download | inline diff: From 02258dd4551c0a2ee9e7357eb9899b9f290f0b06 Mon Sep 17 00:00:00 2001 From: Nathan Bossart <[email protected]> Date: Sun, 5 Dec 2021 22:02:40 -0800 Subject: [PATCH v20 2/4] Move removal of old serialized snapshots to custodian. This was only done during checkpoints because it was a convenient place to put it. However, if there are many snapshots to remove, it can significantly extend checkpoint time. To avoid this, move this work to the newly-introduced custodian process. --- contrib/test_decoding/expected/rewrite.out | 21 +++++++++++++++++++++ contrib/test_decoding/sql/rewrite.sql | 17 +++++++++++++++++ src/backend/access/transam/xlog.c | 6 ++++-- src/backend/postmaster/custodian.c | 2 ++ src/backend/replication/logical/snapbuild.c | 9 ++++----- src/include/postmaster/custodian.h | 2 +- src/include/replication/snapbuild.h | 2 +- 7 files changed, 50 insertions(+), 9 deletions(-) diff --git a/contrib/test_decoding/expected/rewrite.out b/contrib/test_decoding/expected/rewrite.out index b30999c436..8b97f15f6f 100644 --- a/contrib/test_decoding/expected/rewrite.out +++ b/contrib/test_decoding/expected/rewrite.out @@ -162,3 +162,24 @@ DROP TABLE IF EXISTS replication_example; DROP FUNCTION iamalongfunction(); DROP FUNCTION exec(text); DROP ROLE regress_justforcomments; +-- make sure custodian cleans up files +CHECKPOINT; +DO $$ +DECLARE + snaps_removed bool; + loops int := 0; +BEGIN + LOOP + snaps_removed := count(*) = 0 FROM pg_ls_logicalsnapdir(); + IF snaps_removed OR loops > 120 * 100 THEN EXIT; END IF; + PERFORM pg_sleep(0.01); + loops := loops + 1; + END LOOP; +END +$$; +SELECT count(*) = 0 FROM pg_ls_logicalsnapdir(); + ?column? +---------- + t +(1 row) + diff --git a/contrib/test_decoding/sql/rewrite.sql b/contrib/test_decoding/sql/rewrite.sql index 62dead3a9b..d268fa559a 100644 --- a/contrib/test_decoding/sql/rewrite.sql +++ b/contrib/test_decoding/sql/rewrite.sql @@ -105,3 +105,20 @@ DROP TABLE IF EXISTS replication_example; DROP FUNCTION iamalongfunction(); DROP FUNCTION exec(text); DROP ROLE regress_justforcomments; + +-- make sure custodian cleans up files +CHECKPOINT; +DO $$ +DECLARE + snaps_removed bool; + loops int := 0; +BEGIN + LOOP + snaps_removed := count(*) = 0 FROM pg_ls_logicalsnapdir(); + IF snaps_removed OR loops > 120 * 100 THEN EXIT; END IF; + PERFORM pg_sleep(0.01); + loops := loops + 1; + END LOOP; +END +$$; +SELECT count(*) = 0 FROM pg_ls_logicalsnapdir(); diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f9f0f6db8d..7da9461048 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -76,12 +76,12 @@ #include "port/atomics.h" #include "port/pg_iovec.h" #include "postmaster/bgwriter.h" +#include "postmaster/custodian.h" #include "postmaster/startup.h" #include "postmaster/walwriter.h" #include "replication/logical.h" #include "replication/origin.h" #include "replication/slot.h" -#include "replication/snapbuild.h" #include "replication/walreceiver.h" #include "replication/walsender.h" #include "storage/bufmgr.h" @@ -6994,10 +6994,12 @@ CheckPointGuts(XLogRecPtr checkPointRedo, int flags) { CheckPointRelationMap(); CheckPointReplicationSlots(); - CheckPointSnapBuild(); CheckPointLogicalRewriteHeap(); CheckPointReplicationOrigin(); + /* tasks offloaded to custodian */ + RequestCustodian(CUSTODIAN_REMOVE_SERIALIZED_SNAPSHOTS, (Datum) 0); + /* Write out all dirty data in SLRUs and the main buffer pool */ TRACE_POSTGRESQL_BUFFER_CHECKPOINT_START(flags); CheckpointStats.ckpt_write_t = GetCurrentTimestamp(); diff --git a/src/backend/postmaster/custodian.c b/src/backend/postmaster/custodian.c index 98bb9efcfd..4e0ce1f7b3 100644 --- a/src/backend/postmaster/custodian.c +++ b/src/backend/postmaster/custodian.c @@ -25,6 +25,7 @@ #include "pgstat.h" #include "postmaster/custodian.h" #include "postmaster/interrupt.h" +#include "replication/snapbuild.h" #include "storage/bufmgr.h" #include "storage/condition_variable.h" #include "storage/fd.h" @@ -70,6 +71,7 @@ struct cust_task_funcs_entry * whether the task is already enqueued. */ static const struct cust_task_funcs_entry cust_task_functions[] = { + {CUSTODIAN_REMOVE_SERIALIZED_SNAPSHOTS, RemoveOldSerializedSnapshots, NULL}, {INVALID_CUSTODIAN_TASK, NULL, NULL} /* must be last */ }; diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 62542827e4..f940bb5930 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -2036,14 +2036,13 @@ SnapBuildRestoreContents(int fd, char *dest, Size size, const char *path) /* * Remove all serialized snapshots that are not required anymore because no - * slot can need them. This doesn't actually have to run during a checkpoint, - * but it's a convenient point to schedule this. + * slot can need them. * - * NB: We run this during checkpoints even if logical decoding is disabled so - * we cleanup old slots at some point after it got disabled. + * NB: We run this even if logical decoding is disabled so we cleanup old slots + * at some point after it got disabled. */ void -CheckPointSnapBuild(void) +RemoveOldSerializedSnapshots(void) { XLogRecPtr cutoff; XLogRecPtr redo; diff --git a/src/include/postmaster/custodian.h b/src/include/postmaster/custodian.h index 73d0bc5f02..ab6d4283b9 100644 --- a/src/include/postmaster/custodian.h +++ b/src/include/postmaster/custodian.h @@ -18,7 +18,7 @@ */ typedef enum CustodianTask { - FAKE_TASK, /* placeholder until we have a real task */ + CUSTODIAN_REMOVE_SERIALIZED_SNAPSHOTS, NUM_CUSTODIAN_TASKS, /* new tasks go above */ INVALID_CUSTODIAN_TASK diff --git a/src/include/replication/snapbuild.h b/src/include/replication/snapbuild.h index f49b941b53..5f1ba3842c 100644 --- a/src/include/replication/snapbuild.h +++ b/src/include/replication/snapbuild.h @@ -57,7 +57,7 @@ struct ReorderBuffer; struct xl_heap_new_cid; struct xl_running_xacts; -extern void CheckPointSnapBuild(void); +extern void RemoveOldSerializedSnapshots(void); extern SnapBuild *AllocateSnapshotBuilder(struct ReorderBuffer *reorder, TransactionId xmin_horizon, XLogRecPtr start_lsn, -- 2.25.1 [text/x-diff] v20-0003-Move-removal-of-old-logical-rewrite-mapping-file.patch (10.6K, ../../20230217234344.GA3357392@nathanxps13/4-v20-0003-Move-removal-of-old-logical-rewrite-mapping-file.patch) download | inline diff: From e4800e6c85c562ac3856a65e2838fbc3e5a79b63 Mon Sep 17 00:00:00 2001 From: Nathan Bossart <[email protected]> Date: Sun, 12 Dec 2021 22:07:11 -0800 Subject: [PATCH v20 3/4] Move removal of old logical rewrite mapping files to custodian. If there are many such files to remove, checkpoints can take much longer. To avoid this, move this work to the newly-introduced custodian process. Since the mapping files include 32-bit transaction IDs, there is a risk of wraparound if the files are not cleaned up fast enough. Removing these files in checkpoints offered decent wraparound protection simply due to the relatively high frequency of checkpointing. With this change, servers should still clean up mappings files with decently high frequency, but in theory the wraparound risk might worsen for some (e.g., if the custodian is spending a lot of time on a different task). Given this is an existing problem, this change makes no effort to handle the wraparound risk, and it is left as a future exercise. --- contrib/test_decoding/expected/rewrite.out | 19 ++++++ contrib/test_decoding/sql/rewrite.sql | 14 ++++ src/backend/access/heap/rewriteheap.c | 78 +++++++++++++++++++--- src/backend/postmaster/custodian.c | 43 ++++++++++++ src/include/access/rewriteheap.h | 1 + src/include/postmaster/custodian.h | 4 ++ 6 files changed, 149 insertions(+), 10 deletions(-) diff --git a/contrib/test_decoding/expected/rewrite.out b/contrib/test_decoding/expected/rewrite.out index 8b97f15f6f..214a514a0a 100644 --- a/contrib/test_decoding/expected/rewrite.out +++ b/contrib/test_decoding/expected/rewrite.out @@ -183,3 +183,22 @@ SELECT count(*) = 0 FROM pg_ls_logicalsnapdir(); t (1 row) +DO $$ +DECLARE + mappings_removed bool; + loops int := 0; +BEGIN + LOOP + mappings_removed := count(*) = 0 FROM pg_ls_logicalmapdir(); + IF mappings_removed OR loops > 120 * 100 THEN EXIT; END IF; + PERFORM pg_sleep(0.01); + loops := loops + 1; + END LOOP; +END +$$; +SELECT count(*) = 0 FROM pg_ls_logicalmapdir(); + ?column? +---------- + t +(1 row) + diff --git a/contrib/test_decoding/sql/rewrite.sql b/contrib/test_decoding/sql/rewrite.sql index d268fa559a..d66f70f837 100644 --- a/contrib/test_decoding/sql/rewrite.sql +++ b/contrib/test_decoding/sql/rewrite.sql @@ -122,3 +122,17 @@ BEGIN END $$; SELECT count(*) = 0 FROM pg_ls_logicalsnapdir(); +DO $$ +DECLARE + mappings_removed bool; + loops int := 0; +BEGIN + LOOP + mappings_removed := count(*) = 0 FROM pg_ls_logicalmapdir(); + IF mappings_removed OR loops > 120 * 100 THEN EXIT; END IF; + PERFORM pg_sleep(0.01); + loops := loops + 1; + END LOOP; +END +$$; +SELECT count(*) = 0 FROM pg_ls_logicalmapdir(); diff --git a/src/backend/access/heap/rewriteheap.c b/src/backend/access/heap/rewriteheap.c index 8993c1ed5a..9ea0f81ac3 100644 --- a/src/backend/access/heap/rewriteheap.c +++ b/src/backend/access/heap/rewriteheap.c @@ -116,6 +116,7 @@ #include "lib/ilist.h" #include "miscadmin.h" #include "pgstat.h" +#include "postmaster/custodian.h" #include "replication/logical.h" #include "replication/slot.h" #include "storage/bufmgr.h" @@ -123,6 +124,7 @@ #include "storage/procarray.h" #include "storage/smgr.h" #include "utils/memutils.h" +#include "utils/pg_lsn.h" #include "utils/rel.h" /* @@ -1179,7 +1181,8 @@ heap_xlog_logical_rewrite(XLogReaderState *r) * Perform a checkpoint for logical rewrite mappings * * This serves two tasks: - * 1) Remove all mappings not needed anymore based on the logical restart LSN + * 1) Alert the custodian to remove all mappings not needed anymore based on the + * logical restart LSN * 2) Flush all remaining mappings to disk, so that replay after a checkpoint * only has to deal with the parts of a mapping that have been written out * after the checkpoint started. @@ -1207,6 +1210,9 @@ CheckPointLogicalRewriteHeap(void) if (cutoff != InvalidXLogRecPtr && redo < cutoff) cutoff = redo; + /* let the custodian know what it can remove */ + RequestCustodian(CUSTODIAN_REMOVE_REWRITE_MAPPINGS, LSNGetDatum(cutoff)); + mappings_dir = AllocateDir("pg_logical/mappings"); while ((mapping_de = ReadDir(mappings_dir, "pg_logical/mappings")) != NULL) { @@ -1239,15 +1245,7 @@ CheckPointLogicalRewriteHeap(void) lsn = ((uint64) hi) << 32 | lo; - if (lsn < cutoff || cutoff == InvalidXLogRecPtr) - { - elog(DEBUG1, "removing logical rewrite file \"%s\"", path); - if (unlink(path) < 0) - ereport(ERROR, - (errcode_for_file_access(), - errmsg("could not remove file \"%s\": %m", path))); - } - else + if (lsn >= cutoff && cutoff != InvalidXLogRecPtr) { /* on some operating systems fsyncing a file requires O_RDWR */ int fd = OpenTransientFile(path, O_RDWR | PG_BINARY); @@ -1285,3 +1283,63 @@ CheckPointLogicalRewriteHeap(void) /* persist directory entries to disk */ fsync_fname("pg_logical/mappings", true); } + +/* + * Remove all mappings not needed anymore based on the logical restart LSN saved + * by the checkpointer. We use this saved value instead of calling + * ReplicationSlotsComputeLogicalRestartLSN() so that we don't try to remove + * files that a concurrent call to CheckPointLogicalRewriteHeap() is trying to + * flush to disk. + */ +void +RemoveOldLogicalRewriteMappings(void) +{ + XLogRecPtr cutoff; + DIR *mappings_dir; + struct dirent *mapping_de; + char path[MAXPGPATH + 20]; + + cutoff = CustodianGetLogicalRewriteCutoff(); + + mappings_dir = AllocateDir("pg_logical/mappings"); + while ((mapping_de = ReadDir(mappings_dir, "pg_logical/mappings")) != NULL) + { + Oid dboid; + Oid relid; + XLogRecPtr lsn; + TransactionId rewrite_xid; + TransactionId create_xid; + uint32 hi, + lo; + PGFileType de_type; + + if (strcmp(mapping_de->d_name, ".") == 0 || + strcmp(mapping_de->d_name, "..") == 0) + continue; + + snprintf(path, sizeof(path), "pg_logical/mappings/%s", mapping_de->d_name); + de_type = get_dirent_type(path, mapping_de, false, DEBUG1); + + if (de_type != PGFILETYPE_ERROR && de_type != PGFILETYPE_REG) + continue; + + /* Skip over files that cannot be ours. */ + if (strncmp(mapping_de->d_name, "map-", 4) != 0) + continue; + + if (sscanf(mapping_de->d_name, LOGICAL_REWRITE_FORMAT, + &dboid, &relid, &hi, &lo, &rewrite_xid, &create_xid) != 6) + elog(ERROR, "could not parse filename \"%s\"", mapping_de->d_name); + + lsn = ((uint64) hi) << 32 | lo; + if (lsn >= cutoff && cutoff != InvalidXLogRecPtr) + continue; + + elog(DEBUG1, "removing logical rewrite file \"%s\"", path); + if (unlink(path) < 0) + ereport(ERROR, + (errcode_for_file_access(), + errmsg("could not remove file \"%s\": %m", path))); + } + FreeDir(mappings_dir); +} diff --git a/src/backend/postmaster/custodian.c b/src/backend/postmaster/custodian.c index 4e0ce1f7b3..4cbd89fae9 100644 --- a/src/backend/postmaster/custodian.c +++ b/src/backend/postmaster/custodian.c @@ -21,6 +21,7 @@ */ #include "postgres.h" +#include "access/rewriteheap.h" #include "libpq/pqsignal.h" #include "pgstat.h" #include "postmaster/custodian.h" @@ -33,11 +34,13 @@ #include "storage/procsignal.h" #include "storage/smgr.h" #include "utils/memutils.h" +#include "utils/pg_lsn.h" static void DoCustodianTasks(void); static CustodianTask CustodianGetNextTask(void); static void CustodianEnqueueTask(CustodianTask task); static const struct cust_task_funcs_entry *LookupCustodianFunctions(CustodianTask task); +static void CustodianSetLogicalRewriteCutoff(Datum arg); typedef struct { @@ -45,6 +48,8 @@ typedef struct CustodianTask task_queue_elems[NUM_CUSTODIAN_TASKS]; int task_queue_head; + + XLogRecPtr logical_rewrite_mappings_cutoff; /* can remove older mappings */ } CustodianShmemStruct; static CustodianShmemStruct *CustodianShmem; @@ -72,6 +77,7 @@ struct cust_task_funcs_entry */ static const struct cust_task_funcs_entry cust_task_functions[] = { {CUSTODIAN_REMOVE_SERIALIZED_SNAPSHOTS, RemoveOldSerializedSnapshots, NULL}, + {CUSTODIAN_REMOVE_REWRITE_MAPPINGS, RemoveOldLogicalRewriteMappings, CustodianSetLogicalRewriteCutoff}, {INVALID_CUSTODIAN_TASK, NULL, NULL} /* must be last */ }; @@ -377,3 +383,40 @@ LookupCustodianFunctions(CustodianTask task) elog(ERROR, "could not lookup functions for custodian task %d", task); pg_unreachable(); } + +/* + * Stores the provided cutoff LSN in the custodian's shared memory. + * + * It's okay if the cutoff LSN is updated before a previously set cutoff has + * been used for cleaning up files. If that happens, it just means that the + * next invocation of RemoveOldLogicalRewriteMappings() will use a more accurate + * cutoff. + */ +static void +CustodianSetLogicalRewriteCutoff(Datum arg) +{ + SpinLockAcquire(&CustodianShmem->cust_lck); + CustodianShmem->logical_rewrite_mappings_cutoff = DatumGetLSN(arg); + SpinLockRelease(&CustodianShmem->cust_lck); + + /* if pass-by-ref, free Datum memory */ +#ifndef USE_FLOAT8_BYVAL + pfree(DatumGetPointer(arg)); +#endif +} + +/* + * Used by the custodian to determine which logical rewrite mapping files it can + * remove. + */ +XLogRecPtr +CustodianGetLogicalRewriteCutoff(void) +{ + XLogRecPtr cutoff; + + SpinLockAcquire(&CustodianShmem->cust_lck); + cutoff = CustodianShmem->logical_rewrite_mappings_cutoff; + SpinLockRelease(&CustodianShmem->cust_lck); + + return cutoff; +} diff --git a/src/include/access/rewriteheap.h b/src/include/access/rewriteheap.h index 1125457053..dc3eb3e308 100644 --- a/src/include/access/rewriteheap.h +++ b/src/include/access/rewriteheap.h @@ -53,5 +53,6 @@ typedef struct LogicalRewriteMappingData */ #define LOGICAL_REWRITE_FORMAT "map-%x-%x-%X_%X-%x-%x" extern void CheckPointLogicalRewriteHeap(void); +extern void RemoveOldLogicalRewriteMappings(void); #endif /* REWRITE_HEAP_H */ diff --git a/src/include/postmaster/custodian.h b/src/include/postmaster/custodian.h index ab6d4283b9..00280c203b 100644 --- a/src/include/postmaster/custodian.h +++ b/src/include/postmaster/custodian.h @@ -12,6 +12,8 @@ #ifndef _CUSTODIAN_H #define _CUSTODIAN_H +#include "access/xlogdefs.h" + /* * If you add a new task here, be sure to add its corresponding function * pointers to cust_task_functions in custodian.c. @@ -19,6 +21,7 @@ typedef enum CustodianTask { CUSTODIAN_REMOVE_SERIALIZED_SNAPSHOTS, + CUSTODIAN_REMOVE_REWRITE_MAPPINGS, NUM_CUSTODIAN_TASKS, /* new tasks go above */ INVALID_CUSTODIAN_TASK @@ -28,5 +31,6 @@ extern void CustodianMain(void) pg_attribute_noreturn(); extern Size CustodianShmemSize(void); extern void CustodianShmemInit(void); extern void RequestCustodian(CustodianTask task, Datum arg); +extern XLogRecPtr CustodianGetLogicalRewriteCutoff(void); #endif /* _CUSTODIAN_H */ -- 2.25.1 [text/x-diff] v20-0004-Do-not-delay-shutdown-due-to-long-running-custod.patch (2.9K, ../../20230217234344.GA3357392@nathanxps13/5-v20-0004-Do-not-delay-shutdown-due-to-long-running-custod.patch) download | inline diff: From 5dd4a58a87005d440b905c4e4b6a16fd7622f4b5 Mon Sep 17 00:00:00 2001 From: Nathan Bossart <[email protected]> Date: Mon, 28 Nov 2022 15:15:37 -0800 Subject: [PATCH v20 4/4] Do not delay shutdown due to long-running custodian tasks. These tasks are not essential enough to delay shutdown and can be retried the next time the server is running. --- src/backend/access/heap/rewriteheap.c | 9 +++++++++ src/backend/postmaster/custodian.c | 8 ++++++++ src/backend/replication/logical/snapbuild.c | 9 +++++++++ 3 files changed, 26 insertions(+) diff --git a/src/backend/access/heap/rewriteheap.c b/src/backend/access/heap/rewriteheap.c index 9ea0f81ac3..3ee635fe77 100644 --- a/src/backend/access/heap/rewriteheap.c +++ b/src/backend/access/heap/rewriteheap.c @@ -117,6 +117,7 @@ #include "miscadmin.h" #include "pgstat.h" #include "postmaster/custodian.h" +#include "postmaster/interrupt.h" #include "replication/logical.h" #include "replication/slot.h" #include "storage/bufmgr.h" @@ -1313,6 +1314,14 @@ RemoveOldLogicalRewriteMappings(void) lo; PGFileType de_type; + /* + * This task is not essential enough to delay shutdown, so bail out if + * there's a pending shutdown request. We'll try again the next time + * the server is running. + */ + if (ShutdownRequestPending) + break; + if (strcmp(mapping_de->d_name, ".") == 0 || strcmp(mapping_de->d_name, "..") == 0) continue; diff --git a/src/backend/postmaster/custodian.c b/src/backend/postmaster/custodian.c index 4cbd89fae9..274b2d4a79 100644 --- a/src/backend/postmaster/custodian.c +++ b/src/backend/postmaster/custodian.c @@ -226,6 +226,14 @@ DoCustodianTasks(void) { CustodianTaskFunction func = (LookupCustodianFunctions(task))->task_func; + /* + * Custodian tasks are not essential enough to delay shutdown, so bail + * out if there's a pending shutdown request. Tasks should be + * requested again and retried the next time the server is running. + */ + if (ShutdownRequestPending) + break; + PG_TRY(); { (*func) (); diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index f940bb5930..ca2e2a3e5b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -126,6 +126,7 @@ #include "common/file_utils.h" #include "miscadmin.h" #include "pgstat.h" +#include "postmaster/interrupt.h" #include "replication/logical.h" #include "replication/reorderbuffer.h" #include "replication/snapbuild.h" @@ -2072,6 +2073,14 @@ RemoveOldSerializedSnapshots(void) XLogRecPtr lsn; PGFileType de_type; + /* + * This task is not essential enough to delay shutdown, so bail out if + * there's a pending shutdown request. We'll try again the next time + * the server is running. + */ + if (ShutdownRequestPending) + break; + if (strcmp(snap_de->d_name, ".") == 0 || strcmp(snap_de->d_name, "..") == 0) continue; -- 2.25.1 ^ permalink raw reply [nested|flat] 23+ messages in thread
end of thread, other threads:[~2023-02-17 23:43 UTC | newest] Thread overview: 23+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2020-12-22 06:23 [PATCH 03/20] Support multiple compression algs/levels/opts.. Justin Pryzby <[email protected]> 2020-12-22 06:23 [PATCH 03/20] Support multiple compression algs/levels/opts.. Justin Pryzby <[email protected]> 2020-12-22 06:23 [PATCH 03/20] Support multiple compression algs/levels/opts.. Justin Pryzby <[email protected]> 2020-12-22 06:23 [PATCH 03/20] Support multiple compression algs/levels/opts.. Justin Pryzby <[email protected]> 2020-12-22 06:23 [PATCH 03/20] Support multiple compression algs/levels/opts.. Justin Pryzby <[email protected]> 2020-12-22 06:23 [PATCH 03/20] Support multiple compression algs/levels/opts.. Justin Pryzby <[email protected]> 2020-12-22 06:23 [PATCH 03/20] Support multiple compression algs/levels/opts.. Justin Pryzby <[email protected]> 2020-12-22 06:23 [PATCH 03/20] Support multiple compression algs/levels/opts.. Justin Pryzby <[email protected]> 2020-12-22 06:23 [PATCH 03/20] Support multiple compression algs/levels/opts.. Justin Pryzby <[email protected]> 2020-12-22 06:23 [PATCH 03/20] Support multiple compression algs/levels/opts.. Justin Pryzby <[email protected]> 2020-12-22 06:23 [PATCH 03/20] Support multiple compression algs/levels/opts.. Justin Pryzby <[email protected]> 2020-12-22 06:23 [PATCH 03/20] Support multiple compression algs/levels/opts.. Justin Pryzby <[email protected]> 2020-12-22 06:23 [PATCH 03/20] Support multiple compression algs/levels/opts.. Justin Pryzby <[email protected]> 2020-12-22 06:23 [PATCH 03/20] Support multiple compression algs/levels/opts.. Justin Pryzby <[email protected]> 2020-12-22 06:23 [PATCH 03/20] Support multiple compression algs/levels/opts.. Justin Pryzby <[email protected]> 2020-12-22 06:23 [PATCH 03/20] Support multiple compression algs/levels/opts.. Justin Pryzby <[email protected]> 2020-12-22 06:23 [PATCH 03/20] Support multiple compression algs/levels/opts.. Justin Pryzby <[email protected]> 2020-12-22 06:23 [PATCH 03/20] Support multiple compression algs/levels/opts.. Justin Pryzby <[email protected]> 2020-12-22 06:23 [PATCH 03/20] Support multiple compression algs/levels/opts.. Justin Pryzby <[email protected]> 2020-12-22 06:23 [PATCH 03/20] Support multiple compression algs/levels/opts.. Justin Pryzby <[email protected]> 2020-12-22 06:23 [PATCH 03/20] Support multiple compression algs/levels/opts.. Justin Pryzby <[email protected]> 2020-12-22 06:23 [PATCH 03/20] Support multiple compression algs/levels/opts.. Justin Pryzby <[email protected]> 2023-02-17 23:43 Re: O(n) tasks cause lengthy startups and checkpoints Nathan Bossart <[email protected]>
This inbox is served by agora; see mirroring instructions for how to clone and mirror all data and code used for this inbox