From e25090646f6a0ca619bb9faaa7ff6a330c277b0f Mon Sep 17 00:00:00 2001 From: Justin Pryzby Date: Fri, 12 Mar 2021 14:43:53 -0600 Subject: [PATCH v9 7/9] add wal_compression_method: zstd TODO: 9ca40dcd4d0cad43d95a9a253fafaa9a9ba7de24 --- configure | 217 ++++++++++++++++++ configure.ac | 33 +++ doc/src/sgml/config.sgml | 2 +- doc/src/sgml/installation.sgml | 19 ++ src/backend/access/transam/xloginsert.c | 18 +- src/backend/access/transam/xlogreader.c | 18 ++ src/backend/utils/misc/postgresql.conf.sample | 2 +- src/include/access/xlog_internal.h | 1 + src/include/access/xlogrecord.h | 5 +- src/include/pg_config.h.in | 3 + src/tools/msvc/Solution.pm | 1 + src/tools/msvc/config_default.pl | 1 + 12 files changed, 315 insertions(+), 5 deletions(-) diff --git a/configure b/configure index 7038b0727c..72bbd719dc 100755 --- a/configure +++ b/configure @@ -699,6 +699,9 @@ with_gnu_ld LD LDFLAGS_SL LDFLAGS_EX +ZSTD_LIBS +ZSTD_CFLAGS +with_zstd LZ4_LIBS LZ4_CFLAGS with_lz4 @@ -868,6 +871,7 @@ with_libxslt with_system_tzdata with_zlib with_lz4 +with_zstd with_gnu_ld with_ssl with_openssl @@ -897,6 +901,8 @@ XML2_CFLAGS XML2_LIBS LZ4_CFLAGS LZ4_LIBS +ZSTD_CFLAGS +ZSTD_LIBS LDFLAGS_EX LDFLAGS_SL PERL @@ -1576,6 +1582,7 @@ Optional Packages: use system time zone data in DIR --without-zlib do not use Zlib --without-lz4 build without LZ4 support + --with-zstd build with Zstd compression library --with-gnu-ld assume the C compiler uses GNU ld [default=no] --with-ssl=LIB use LIB for SSL/TLS support (openssl) --with-openssl obsolete spelling of --with-ssl=openssl @@ -1605,6 +1612,8 @@ Some influential environment variables: XML2_LIBS linker flags for XML2, overriding pkg-config LZ4_CFLAGS C compiler flags for LZ4, overriding pkg-config LZ4_LIBS linker flags for LZ4, overriding pkg-config + ZSTD_CFLAGS C compiler flags for ZSTD, overriding pkg-config + ZSTD_LIBS linker flags for ZSTD, overriding pkg-config LDFLAGS_EX extra linker flags for linking executables only LDFLAGS_SL extra linker flags for linking shared libraries only PERL Perl program @@ -8715,6 +8724,147 @@ fi done fi +# +# ZSTD +# +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking whether to build with zstd support" >&5 +$as_echo_n "checking whether to build with zstd support... " >&6; } + + + +# Check whether --with-zstd was given. +if test "${with_zstd+set}" = set; then : + withval=$with_zstd; + case $withval in + yes) + +$as_echo "#define USE_ZSTD 1" >>confdefs.h + + ;; + no) + : + ;; + *) + as_fn_error $? "no argument expected for --with-zstd option" "$LINENO" 5 + ;; + esac + +else + with_zstd=no + +fi + + +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $with_zstd" >&5 +$as_echo "$with_zstd" >&6; } + + +if test "$with_zstd" = yes; then + +pkg_failed=no +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for libzstd" >&5 +$as_echo_n "checking for libzstd... " >&6; } + +if test -n "$ZSTD_CFLAGS"; then + pkg_cv_ZSTD_CFLAGS="$ZSTD_CFLAGS" + elif test -n "$PKG_CONFIG"; then + if test -n "$PKG_CONFIG" && \ + { { $as_echo "$as_me:${as_lineno-$LINENO}: \$PKG_CONFIG --exists --print-errors \"libzstd\""; } >&5 + ($PKG_CONFIG --exists --print-errors "libzstd") 2>&5 + ac_status=$? + $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5 + test $ac_status = 0; }; then + pkg_cv_ZSTD_CFLAGS=`$PKG_CONFIG --cflags "libzstd" 2>/dev/null` + test "x$?" != "x0" && pkg_failed=yes +else + pkg_failed=yes +fi + else + pkg_failed=untried +fi +if test -n "$ZSTD_LIBS"; then + pkg_cv_ZSTD_LIBS="$ZSTD_LIBS" + elif test -n "$PKG_CONFIG"; then + if test -n "$PKG_CONFIG" && \ + { { $as_echo "$as_me:${as_lineno-$LINENO}: \$PKG_CONFIG --exists --print-errors \"libzstd\""; } >&5 + ($PKG_CONFIG --exists --print-errors "libzstd") 2>&5 + ac_status=$? + $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5 + test $ac_status = 0; }; then + pkg_cv_ZSTD_LIBS=`$PKG_CONFIG --libs "libzstd" 2>/dev/null` + test "x$?" != "x0" && pkg_failed=yes +else + pkg_failed=yes +fi + else + pkg_failed=untried +fi + + + +if test $pkg_failed = yes; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } + +if $PKG_CONFIG --atleast-pkgconfig-version 0.20; then + _pkg_short_errors_supported=yes +else + _pkg_short_errors_supported=no +fi + if test $_pkg_short_errors_supported = yes; then + ZSTD_PKG_ERRORS=`$PKG_CONFIG --short-errors --print-errors --cflags --libs "libzstd" 2>&1` + else + ZSTD_PKG_ERRORS=`$PKG_CONFIG --print-errors --cflags --libs "libzstd" 2>&1` + fi + # Put the nasty error message in config.log where it belongs + echo "$ZSTD_PKG_ERRORS" >&5 + + as_fn_error $? "Package requirements (libzstd) were not met: + +$ZSTD_PKG_ERRORS + +Consider adjusting the PKG_CONFIG_PATH environment variable if you +installed software in a non-standard prefix. + +Alternatively, you may set the environment variables ZSTD_CFLAGS +and ZSTD_LIBS to avoid the need to call pkg-config. +See the pkg-config man page for more details." "$LINENO" 5 +elif test $pkg_failed = untried; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } + { { $as_echo "$as_me:${as_lineno-$LINENO}: error: in \`$ac_pwd':" >&5 +$as_echo "$as_me: error: in \`$ac_pwd':" >&2;} +as_fn_error $? "The pkg-config script could not be found or is too old. Make sure it +is in your PATH or set the PKG_CONFIG environment variable to the full +path to pkg-config. + +Alternatively, you may set the environment variables ZSTD_CFLAGS +and ZSTD_LIBS to avoid the need to call pkg-config. +See the pkg-config man page for more details. + +To get pkg-config, see . +See \`config.log' for more details" "$LINENO" 5; } +else + ZSTD_CFLAGS=$pkg_cv_ZSTD_CFLAGS + ZSTD_LIBS=$pkg_cv_ZSTD_LIBS + { $as_echo "$as_me:${as_lineno-$LINENO}: result: yes" >&5 +$as_echo "yes" >&6; } + +fi + # We only care about -I, -D, and -L switches; + # note that -lzstd will be added by AC_CHECK_LIB below. + for pgac_option in $ZSTD_CFLAGS; do + case $pgac_option in + -I*|-D*) CPPFLAGS="$CPPFLAGS $pgac_option";; + esac + done + for pgac_option in $ZSTD_LIBS; do + case $pgac_option in + -L*) LDFLAGS="$LDFLAGS $pgac_option";; + esac + done +fi + # # Assignments # @@ -12878,6 +13028,56 @@ fi fi +if test "$with_zstd" = yes ; then + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for ZSTD_compress in -lzstd" >&5 +$as_echo_n "checking for ZSTD_compress in -lzstd... " >&6; } +if ${ac_cv_lib_zstd_ZSTD_compress+:} false; then : + $as_echo_n "(cached) " >&6 +else + ac_check_lib_save_LIBS=$LIBS +LIBS="-lzstd $LIBS" +cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +/* Override any GCC internal prototype to avoid an error. + Use char because int might match the return type of a GCC + builtin and then its argument prototype would still apply. */ +#ifdef __cplusplus +extern "C" +#endif +char ZSTD_compress (); +int +main () +{ +return ZSTD_compress (); + ; + return 0; +} +_ACEOF +if ac_fn_c_try_link "$LINENO"; then : + ac_cv_lib_zstd_ZSTD_compress=yes +else + ac_cv_lib_zstd_ZSTD_compress=no +fi +rm -f core conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext +LIBS=$ac_check_lib_save_LIBS +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_lib_zstd_ZSTD_compress" >&5 +$as_echo "$ac_cv_lib_zstd_ZSTD_compress" >&6; } +if test "x$ac_cv_lib_zstd_ZSTD_compress" = xyes; then : + cat >>confdefs.h <<_ACEOF +#define HAVE_LIBZSTD 1 +_ACEOF + + LIBS="-lzstd $LIBS" + +else + as_fn_error $? "library 'zstd' is required for ZSTD support" "$LINENO" 5 +fi + +fi + # Note: We can test for libldap_r only after we know PTHREAD_LIBS if test "$with_ldap" = yes ; then _LIBS="$LIBS" @@ -13600,6 +13800,23 @@ done fi +if test "$with_zstd" = yes; then + for ac_header in zstd.h +do : + ac_fn_c_check_header_mongrel "$LINENO" "zstd.h" "ac_cv_header_zstd_h" "$ac_includes_default" +if test "x$ac_cv_header_zstd_h" = xyes; then : + cat >>confdefs.h <<_ACEOF +#define HAVE_ZSTD_H 1 +_ACEOF + +else + as_fn_error $? "zstd.h header file is required for zstd" "$LINENO" 5 +fi + +done + +fi + if test "$with_gssapi" = yes ; then for ac_header in gssapi/gssapi.h do : diff --git a/configure.ac b/configure.ac index cb0261f179..c348a3ee91 100644 --- a/configure.ac +++ b/configure.ac @@ -1011,6 +1011,31 @@ if test "$with_lz4" = yes; then done fi +# +# ZSTD +# +AC_MSG_CHECKING([whether to build with zstd support]) +PGAC_ARG_BOOL(with, zstd, no, [build with Zstd compression library], + [AC_DEFINE([USE_ZSTD], 1, [Define to 1 to build with zstd support. (--with-zstd)])]) +AC_MSG_RESULT([$with_zstd]) +AC_SUBST(with_zstd) + +if test "$with_zstd" = yes; then + PKG_CHECK_MODULES(ZSTD, libzstd) + # We only care about -I, -D, and -L switches; + # note that -lzstd will be added by AC_CHECK_LIB below. + for pgac_option in $ZSTD_CFLAGS; do + case $pgac_option in + -I*|-D*) CPPFLAGS="$CPPFLAGS $pgac_option";; + esac + done + for pgac_option in $ZSTD_LIBS; do + case $pgac_option in + -L*) LDFLAGS="$LDFLAGS $pgac_option";; + esac + done +fi + # # Assignments # @@ -1285,6 +1310,10 @@ if test "$with_lz4" = yes ; then AC_CHECK_LIB(lz4, LZ4_compress_default, [], [AC_MSG_ERROR([library 'lz4' is required for LZ4 support])]) fi +if test "$with_zstd" = yes ; then + AC_CHECK_LIB(zstd, ZSTD_compress, [], [AC_MSG_ERROR([library 'zstd' is required for ZSTD support])]) +fi + # Note: We can test for libldap_r only after we know PTHREAD_LIBS if test "$with_ldap" = yes ; then _LIBS="$LIBS" @@ -1443,6 +1472,10 @@ if test "$with_lz4" = yes; then AC_CHECK_HEADERS(lz4.h, [], [AC_MSG_ERROR([lz4.h header file is required for LZ4])]) fi +if test "$with_zstd" = yes; then + AC_CHECK_HEADERS(zstd.h, [], [AC_MSG_ERROR([zstd.h header file is required for zstd])]) +fi + if test "$with_gssapi" = yes ; then AC_CHECK_HEADERS(gssapi/gssapi.h, [], [AC_CHECK_HEADERS(gssapi.h, [], [AC_MSG_ERROR([gssapi.h header file is required for GSSAPI])])]) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index df5ff70d91..ee4c44fb7f 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -3141,7 +3141,7 @@ include_dir 'conf.d' is on or during a base backup. A compressed page image will be decompressed during WAL replay. The supported methods are pglz, zlib, and (if configured when - PostgreSQL was built) lz4. + PostgreSQL was built) lz4 and zstd. The default value is off. Only superusers can change this setting. diff --git a/doc/src/sgml/installation.sgml b/doc/src/sgml/installation.sgml index c7673a4dc8..3e985bbd05 100644 --- a/doc/src/sgml/installation.sgml +++ b/doc/src/sgml/installation.sgml @@ -275,6 +275,14 @@ su - postgres + + + The ZSTD library can be used to enable + compression using that method; see + . + + + To build the PostgreSQL documentation, @@ -986,6 +994,17 @@ build-postgresql: + + + + + Build with ZSTD compression support. + This enables use of ZSTD for + compression of WAL data. + + + + diff --git a/src/backend/access/transam/xloginsert.c b/src/backend/access/transam/xloginsert.c index a8794a941a..96f497d5d6 100644 --- a/src/backend/access/transam/xloginsert.c +++ b/src/backend/access/transam/xloginsert.c @@ -48,10 +48,17 @@ #define LZ4_MAX_BLCKSZ 0 #endif +#ifdef USE_ZSTD +#include "zstd.h" +#define ZSTD_MAX_BLCKSZ ZSTD_COMPRESSBOUND(BLCKSZ) +#else +#define ZSTD_MAX_BLCKSZ 0 +#endif + /* Buffer size required to store a compressed version of backup block image */ #define PGLZ_MAX_BLCKSZ PGLZ_MAX_OUTPUT(BLCKSZ) -#define COMPRESS_BUFSIZE Max(Max(PGLZ_MAX_BLCKSZ, ZLIB_MAX_BLCKSZ), LZ4_MAX_BLCKSZ) +#define COMPRESS_BUFSIZE Max(Max(Max(PGLZ_MAX_BLCKSZ, ZLIB_MAX_BLCKSZ), LZ4_MAX_BLCKSZ), ZSTD_MAX_BLCKSZ) /* * For each block reference registered with XLogRegisterBuffer, we fill in @@ -904,6 +911,15 @@ XLogCompressBackupBlock(char *page, uint16 hole_offset, uint16 hole_length, break; #endif +#ifdef USE_ZSTD + case WAL_COMPRESSION_ZSTD: + len = ZSTD_compress(dest, COMPRESS_BUFSIZE, source, orig_len, + ZSTD_CLEVEL_DEFAULT); + if (ZSTD_isError(len)) + len = -1; + break; +#endif + default: /* * It should be impossible to get here for unsupported algorithms, diff --git a/src/backend/access/transam/xlogreader.c b/src/backend/access/transam/xlogreader.c index e44817fece..1b13d1f660 100644 --- a/src/backend/access/transam/xlogreader.c +++ b/src/backend/access/transam/xlogreader.c @@ -42,6 +42,10 @@ #include "lz4.h" #endif +#ifdef USE_ZSTD +#include "zstd.h" +#endif + static void report_invalid_record(XLogReaderState *state, const char *fmt,...) pg_attribute_printf(2, 3); static bool allocate_recordbuf(XLogReaderState *state, uint32 reclength); @@ -83,6 +87,10 @@ const struct config_enum_entry wal_compression_options[] = { {"lz4", WAL_COMPRESSION_LZ4, false}, #endif +#ifdef USE_ZSTD + {"zstd", WAL_COMPRESSION_ZSTD, false}, +#endif + {NULL, 0, false} }; @@ -1639,6 +1647,16 @@ RestoreBlockImage(XLogReaderState *record, uint8 block_id, char *page) break; #endif +#ifdef USE_ZSTD + case WAL_COMPRESSION_ZSTD: + decomp_result = ZSTD_decompress(tmp.data, BLCKSZ-bkpb->hole_length, + ptr, bkpb->bimg_len); + // XXX: ZSTD_getErrorName + if (ZSTD_isError(decomp_result)) + decomp_result = -1; + break; +#endif + default: report_invalid_record(record, "image at %X/%X is compressed with unsupported codec, block %d (%d/%s)", (uint32) (record->ReadRecPtr >> 32), diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 728acef953..818b26faad 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -218,7 +218,7 @@ #full_page_writes = on # recover from partial page writes #wal_log_hints = off # also do full page writes of non-critical updates # (change requires restart) -#wal_compression = off # enable compression of full-page writes: off, pglz, zlib, lz4 +#wal_compression = off # enable compression of full-page writes: off, pglz, zlib, lz4, zstd #wal_init_zero = on # zero-fill new WAL files #wal_recycle = on # recycle WAL files #wal_buffers = -1 # min 32kB, -1 sets based on shared_buffers diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 0287592cd4..1da965a708 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -331,6 +331,7 @@ typedef enum WalCompression WAL_COMPRESSION_PGLZ, WAL_COMPRESSION_ZLIB, WAL_COMPRESSION_LZ4, + WAL_COMPRESSION_ZSTD, } WalCompression; extern const char *wal_compression_name(WalCompression compression); diff --git a/src/include/access/xlogrecord.h b/src/include/access/xlogrecord.h index abb42b364d..84ffb17596 100644 --- a/src/include/access/xlogrecord.h +++ b/src/include/access/xlogrecord.h @@ -147,12 +147,13 @@ typedef struct XLogRecordBlockImageHeader #define BKPIMAGE_APPLY 0x02 /* page image should be restored during * replay */ #define BKPIMAGE_COMPRESS_METHOD1 0x04 /* bits to encode compression method */ -#define BKPIMAGE_COMPRESS_METHOD2 0x08 /* 0=none, 1=pglz, 2=zlib, 3=lz4 */ +#define BKPIMAGE_COMPRESS_METHOD2 0x08 /* 0=none, 1=pglz, 2=zlib, 3=lz4, 4=zstd */ +#define BKPIMAGE_COMPRESS_METHOD3 0x10 /* How many bits to shift to extract compression */ #define BKPIMAGE_COMPRESS_OFFSET_BITS 2 /* How many bits are for compression */ -#define BKPIMAGE_COMPRESS_BITS 2 +#define BKPIMAGE_COMPRESS_BITS 3 /* Extract the compression from the bimg_info */ #define BKPIMAGE_COMPRESSION(info) ((info >> BKPIMAGE_COMPRESS_OFFSET_BITS) & ((1< undef, USE_LIBXSLT => undef, USE_LZ4 => undef, + USE_ZSTD => $self->{options}->{zstd} ? 1 : undef, USE_LDAP => $self->{options}->{ldap} ? 1 : undef, USE_LLVM => undef, USE_NAMED_POSIX_SEMAPHORES => undef, diff --git a/src/tools/msvc/config_default.pl b/src/tools/msvc/config_default.pl index 460c0375d4..b8a1aac3c2 100644 --- a/src/tools/msvc/config_default.pl +++ b/src/tools/msvc/config_default.pl @@ -26,6 +26,7 @@ our $config = { xslt => undef, # --with-libxslt= iconv => undef, # (not in configure, path to iconv) zlib => undef # --with-zlib= + zstd => undef # --with-zstd= }; 1; -- 2.17.0