public inbox for [email protected]help / color / mirror / Atom feed
[PATCH 1/5] Built-in compression method 2+ messages / 2 participants [nested] [flat]
* [PATCH 1/5] Built-in compression method @ 2021-03-05 04:03 Dilip Kumar <[email protected]> 0 siblings, 0 replies; 2+ messages in thread From: Dilip Kumar @ 2021-03-05 04:03 UTC (permalink / raw) Add syntax allowing a compression method to be specified. As of now there is only 2 option for build-in compression method (pglz, lz4) which can be set while creating a table or adding a new column. No option for altering the compression method for an existing column. Dilip Kumar based on the patches from Ildus Kurbangaliev. Design input from Robert Haas and Tomas Vondra. Reviewed by Robert Haas, Tomas Vondra, Alexander Korotkov and Justin Pryzby Discussions: https://www.postgresql.org/message-id/[email protected] https://www.postgresql.org/message-id/CA%2BTgmoaKDW1Oi9V%3Djc9hOGyf77NbkNEABuqgHD1Cq%3D%3D1QsOcxg%40... https://www.postgresql.org/message-id/CA%2BTgmobSDVgUage9qQ5P_%3DF_9jaMkCgyKxUQGtFQU7oN4kX-AA%40mail... https://www.postgresql.org/message-id/20201005160355.byp74sh3ejsv7wrj%40development https://www.postgresql.org/message-id/CAFiTN-tzTTT2oqWdRGLv1dvvS5MC1W%2BLE%2B3bqWPJUZj4GnHOJg%40mail... --- configure | 118 +++++++ configure.ac | 18 + doc/src/sgml/catalogs.sgml | 10 + doc/src/sgml/ref/create_table.sgml | 33 +- doc/src/sgml/ref/psql-ref.sgml | 11 + src/backend/access/brin/brin_tuple.c | 5 +- src/backend/access/common/Makefile | 1 + src/backend/access/common/detoast.c | 71 ++-- src/backend/access/common/indextuple.c | 3 +- src/backend/access/common/toast_compression.c | 308 ++++++++++++++++++ src/backend/access/common/toast_internals.c | 54 ++- src/backend/access/common/tupdesc.c | 8 + src/backend/access/table/toast_helper.c | 5 +- src/backend/bootstrap/bootstrap.c | 5 + src/backend/catalog/genbki.pl | 3 + src/backend/catalog/heap.c | 4 + src/backend/catalog/index.c | 1 + src/backend/catalog/toasting.c | 6 + src/backend/commands/tablecmds.c | 110 +++++++ src/backend/nodes/copyfuncs.c | 1 + src/backend/nodes/equalfuncs.c | 1 + src/backend/nodes/nodeFuncs.c | 2 + src/backend/nodes/outfuncs.c | 1 + src/backend/parser/gram.y | 26 +- src/backend/parser/parse_utilcmd.c | 9 + src/backend/utils/adt/varlena.c | 41 +++ src/bin/pg_dump/pg_backup.h | 1 + src/bin/pg_dump/pg_dump.c | 39 +++ src/bin/pg_dump/pg_dump.h | 1 + src/bin/pg_dump/t/002_pg_dump.pl | 12 +- src/bin/psql/describe.c | 31 +- src/bin/psql/help.c | 2 + src/bin/psql/settings.h | 1 + src/bin/psql/startup.c | 10 + src/include/access/detoast.h | 8 + src/include/access/toast_compression.h | 119 +++++++ src/include/access/toast_helper.h | 1 + src/include/access/toast_internals.h | 20 +- src/include/catalog/pg_attribute.h | 8 +- src/include/catalog/pg_proc.dat | 4 + src/include/nodes/parsenodes.h | 2 + src/include/parser/kwlist.h | 1 + src/include/pg_config.h.in | 3 + src/include/postgres.h | 14 +- src/test/regress/expected/compression.out | 247 ++++++++++++++ src/test/regress/expected/compression_1.out | 240 ++++++++++++++ src/test/regress/parallel_schedule | 2 +- src/test/regress/pg_regress_main.c | 4 +- src/test/regress/serial_schedule | 1 + src/test/regress/sql/compression.sql | 102 ++++++ src/tools/msvc/Solution.pm | 1 + src/tools/pgindent/typedefs.list | 1 + 52 files changed, 1645 insertions(+), 85 deletions(-) create mode 100644 src/backend/access/common/toast_compression.c create mode 100644 src/include/access/toast_compression.h create mode 100644 src/test/regress/expected/compression.out create mode 100644 src/test/regress/expected/compression_1.out create mode 100644 src/test/regress/sql/compression.sql diff --git a/configure b/configure index fad817bb38..761a27965d 100755 --- a/configure +++ b/configure @@ -699,6 +699,7 @@ with_gnu_ld LD LDFLAGS_SL LDFLAGS_EX +with_lz4 with_zlib with_system_tzdata with_libxslt @@ -864,6 +865,7 @@ with_libxml with_libxslt with_system_tzdata with_zlib +with_lz4 with_gnu_ld with_ssl with_openssl @@ -1569,6 +1571,7 @@ Optional Packages: --with-system-tzdata=DIR use system time zone data in DIR --without-zlib do not use Zlib + --with-lz4 build with LZ4 support --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 @@ -8563,6 +8566,41 @@ fi +# +# LZ4 +# +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking whether to build with LZ4 support" >&5 +$as_echo_n "checking whether to build with LZ4 support... " >&6; } + + + +# Check whether --with-lz4 was given. +if test "${with_lz4+set}" = set; then : + withval=$with_lz4; + case $withval in + yes) + +$as_echo "#define USE_LZ4 1" >>confdefs.h + + ;; + no) + : + ;; + *) + as_fn_error $? "no argument expected for --with-lz4 option" "$LINENO" 5 + ;; + esac + +else + with_lz4=no + +fi + + +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $with_lz4" >&5 +$as_echo "$with_lz4" >&6; } + + # # Assignments # @@ -12110,6 +12148,56 @@ fi fi +if test "$with_lz4" = yes ; then + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for LZ4_compress in -llz4" >&5 +$as_echo_n "checking for LZ4_compress in -llz4... " >&6; } +if ${ac_cv_lib_lz4_LZ4_compress+:} false; then : + $as_echo_n "(cached) " >&6 +else + ac_check_lib_save_LIBS=$LIBS +LIBS="-llz4 $LIBS" +cat confdefs.h - <<_ACEOF >conftest.$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 LZ4_compress (); +int +main () +{ +return LZ4_compress (); + ; + return 0; +} +_ACEOF +if ac_fn_c_try_link "$LINENO"; then : + ac_cv_lib_lz4_LZ4_compress=yes +else + ac_cv_lib_lz4_LZ4_compress=no +fi +rm -f core conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext +LIBS=$ac_check_lib_save_LIBS +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_lib_lz4_LZ4_compress" >&5 +$as_echo "$ac_cv_lib_lz4_LZ4_compress" >&6; } +if test "x$ac_cv_lib_lz4_LZ4_compress" = xyes; then : + cat >>confdefs.h <<_ACEOF +#define HAVE_LIBLZ4 1 +_ACEOF + + LIBS="-llz4 $LIBS" + +else + as_fn_error $? "library 'lz4' is required for LZ4 support" "$LINENO" 5 +fi + +fi + if test "$enable_spinlocks" = yes; then $as_echo "#define HAVE_SPINLOCKS 1" >>confdefs.h @@ -13376,6 +13464,36 @@ Use --without-zlib to disable zlib support." "$LINENO" 5 fi +fi + +if test "$with_lz4" = yes ; then + for ac_header in lz4/lz4.h +do : + ac_fn_c_check_header_mongrel "$LINENO" "lz4/lz4.h" "ac_cv_header_lz4_lz4_h" "$ac_includes_default" +if test "x$ac_cv_header_lz4_lz4_h" = xyes; then : + cat >>confdefs.h <<_ACEOF +#define HAVE_LZ4_LZ4_H 1 +_ACEOF + +else + for ac_header in lz4.h +do : + ac_fn_c_check_header_mongrel "$LINENO" "lz4.h" "ac_cv_header_lz4_h" "$ac_includes_default" +if test "x$ac_cv_header_lz4_h" = xyes; then : + cat >>confdefs.h <<_ACEOF +#define HAVE_LZ4_H 1 +_ACEOF + +else + as_fn_error $? "lz4.h header file is required for LZ4" "$LINENO" 5 +fi + +done + +fi + +done + fi if test "$with_gssapi" = yes ; then diff --git a/configure.ac b/configure.ac index 0ed53571dd..616ce5e1a2 100644 --- a/configure.ac +++ b/configure.ac @@ -986,6 +986,15 @@ PGAC_ARG_BOOL(with, zlib, yes, [do not use Zlib]) AC_SUBST(with_zlib) +# +# LZ4 +# +AC_MSG_CHECKING([whether to build with LZ4 support]) +PGAC_ARG_BOOL(with, lz4, no, [build with LZ4 support], + [AC_DEFINE([USE_LZ4], 1, [Define to 1 to build with LZ4 support. (--with-lz4)])]) +AC_MSG_RESULT([$with_lz4]) +AC_SUBST(with_lz4) + # # Assignments # @@ -1174,6 +1183,10 @@ failure. It is possible the compiler isn't looking in the proper directory. Use --without-zlib to disable zlib support.])]) fi +if test "$with_lz4" = yes ; then + AC_CHECK_LIB(lz4, LZ4_compress, [], [AC_MSG_ERROR([library 'lz4' is required for LZ4 support])]) +fi + if test "$enable_spinlocks" = yes; then AC_DEFINE(HAVE_SPINLOCKS, 1, [Define to 1 if you have spinlocks.]) else @@ -1407,6 +1420,11 @@ failure. It is possible the compiler isn't looking in the proper directory. Use --without-zlib to disable zlib support.])]) fi +if test "$with_lz4" = yes ; then + AC_CHECK_HEADERS(lz4/lz4.h, [], + [AC_CHECK_HEADERS(lz4.h, [], [AC_MSG_ERROR([lz4.h header file is required for LZ4])])]) +fi + if test "$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/catalogs.sgml b/doc/src/sgml/catalogs.sgml index b1de6d0674..5fdc80ff3d 100644 --- a/doc/src/sgml/catalogs.sgml +++ b/doc/src/sgml/catalogs.sgml @@ -1355,6 +1355,16 @@ </para></entry> </row> + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>attcompression</structfield> <type>char</type> + </para> + <para> + The current compression method of the column. Must be <literal>InvalidCompressionMethod</literal> + if and only if typstorage is 'plain' or 'external'. + </para></entry> + </row> + <row> <entry role="catalog_table_entry"><para role="column_definition"> <structfield>attacl</structfield> <type>aclitem[]</type> diff --git a/doc/src/sgml/ref/create_table.sgml b/doc/src/sgml/ref/create_table.sgml index 3b2b227683..7c8fc77983 100644 --- a/doc/src/sgml/ref/create_table.sgml +++ b/doc/src/sgml/ref/create_table.sgml @@ -22,7 +22,7 @@ PostgreSQL documentation <refsynopsisdiv> <synopsis> CREATE [ [ GLOBAL | LOCAL ] { TEMPORARY | TEMP } | UNLOGGED ] TABLE [ IF NOT EXISTS ] <replaceable class="parameter">table_name</replaceable> ( [ - { <replaceable class="parameter">column_name</replaceable> <replaceable class="parameter">data_type</replaceable> [ COLLATE <replaceable>collation</replaceable> ] [ <replaceable class="parameter">column_constraint</replaceable> [ ... ] ] + { <replaceable class="parameter">column_name</replaceable> <replaceable class="parameter">data_type</replaceable> [ COLLATE <replaceable>collation</replaceable> ] [ COMPRESSION <replaceable>compression_method</replaceable> ] [ <replaceable class="parameter">column_constraint</replaceable> [ ... ] ] | <replaceable>table_constraint</replaceable> | LIKE <replaceable>source_table</replaceable> [ <replaceable>like_option</replaceable> ... ] } [, ... ] @@ -288,6 +288,26 @@ WITH ( MODULUS <replaceable class="parameter">numeric_literal</replaceable>, REM </listitem> </varlistentry> + <varlistentry> + <term><literal>COMPRESSION <replaceable class="parameter">compression_method</replaceable></literal></term> + <listitem> + <para> + The <literal>COMPRESSION</literal> clause sets the compression method + for a column. Compression is supported only for variable-width data + types, and is used only for columns whose storage type is main or + extended. (See <xref linkend="sql-altertable"/> for information on + column storage types.) Setting this property for a partitioned table + has no direct effect, because such tables have no storage of their own, + but the configured value is inherited by newly-created partitions. + The supported compression methods are <literal>pglz</literal> and + <literal>lz4</literal>. <literal>lz4</literal> is available only if + <literal>--with-lz4</literal> was used when building + <productname>PostgreSQL</productname>. The default + is <literal>pglz</literal>. + </para> + </listitem> + </varlistentry> + <varlistentry> <term><literal>INHERITS ( <replaceable>parent_table</replaceable> [, ... ] )</literal></term> <listitem> @@ -605,6 +625,17 @@ WITH ( MODULUS <replaceable class="parameter">numeric_literal</replaceable>, REM </listitem> </varlistentry> + <varlistentry> + <term><literal>INCLUDING COMPRESSION</literal></term> + <listitem> + <para> + Compression method of the columns will be copied. The default + behavior is to exclude compression methods, resulting in columns + having the default compression method. + </para> + </listitem> + </varlistentry> + <varlistentry> <term><literal>INCLUDING CONSTRAINTS</literal></term> <listitem> diff --git a/doc/src/sgml/ref/psql-ref.sgml b/doc/src/sgml/ref/psql-ref.sgml index 13c1edfa4d..01ec9b8b0a 100644 --- a/doc/src/sgml/ref/psql-ref.sgml +++ b/doc/src/sgml/ref/psql-ref.sgml @@ -3863,6 +3863,17 @@ bar </listitem> </varlistentry> + <varlistentry> + <term><varname>HIDE_TOAST_COMPRESSION</varname></term> + <listitem> + <para> + If this variable is set to <literal>true</literal>, column + compression method details are not displayed. This is mainly + useful for regression tests. + </para> + </listitem> + </varlistentry> + <varlistentry> <term><varname>HIDE_TABLEAM</varname></term> <listitem> diff --git a/src/backend/access/brin/brin_tuple.c b/src/backend/access/brin/brin_tuple.c index a7eb1c9473..0ab5712c71 100644 --- a/src/backend/access/brin/brin_tuple.c +++ b/src/backend/access/brin/brin_tuple.c @@ -213,7 +213,10 @@ brin_form_tuple(BrinDesc *brdesc, BlockNumber blkno, BrinMemTuple *tuple, (atttype->typstorage == TYPSTORAGE_EXTENDED || atttype->typstorage == TYPSTORAGE_MAIN)) { - Datum cvalue = toast_compress_datum(value); + Form_pg_attribute att = TupleDescAttr(brdesc->bd_tupdesc, + keyno); + Datum cvalue = toast_compress_datum(value, + att->attcompression); if (DatumGetPointer(cvalue) != NULL) { diff --git a/src/backend/access/common/Makefile b/src/backend/access/common/Makefile index 5a007d63f1..b9aff0ccfd 100644 --- a/src/backend/access/common/Makefile +++ b/src/backend/access/common/Makefile @@ -25,6 +25,7 @@ OBJS = \ scankey.o \ session.o \ syncscan.o \ + toast_compression.o \ toast_internals.o \ tupconvert.o \ tupdesc.o diff --git a/src/backend/access/common/detoast.c b/src/backend/access/common/detoast.c index d1cdbaf648..031d20d5fc 100644 --- a/src/backend/access/common/detoast.c +++ b/src/backend/access/common/detoast.c @@ -13,6 +13,7 @@ #include "postgres.h" +#include "access/toast_compression.h" #include "access/detoast.h" #include "access/table.h" #include "access/tableam.h" @@ -456,6 +457,37 @@ toast_fetch_datum_slice(struct varlena *attr, int32 sliceoffset, return result; } +/* ---------- + * toast_get_compression_method + * + * Returns compression method for the compressed varlena. If it is not + * compressed then returns InvalidCompressionMethod. + */ +char +toast_get_compression_method(struct varlena *attr) +{ + if (VARATT_IS_EXTERNAL_ONDISK(attr)) + { + struct varatt_external toast_pointer; + + VARATT_EXTERNAL_GET_POINTER(toast_pointer, attr); + + /* fast path for non-compressed external datums */ + if (!VARATT_EXTERNAL_IS_COMPRESSED(toast_pointer)) + return InvalidCompressionMethod; + + /* + * Fetch just enough of the value to examine the compression header, + * so that we can find out the compression method. + */ + attr = toast_fetch_datum_slice(attr, 0, VARHDRSZ); + } + else if (!VARATT_IS_COMPRESSED(attr)) + return InvalidCompressionMethod; + + return CompressionIdToMethod(TOAST_COMPRESS_METHOD(attr)); +} + /* ---------- * toast_decompress_datum - * @@ -464,21 +496,18 @@ toast_fetch_datum_slice(struct varlena *attr, int32 sliceoffset, static struct varlena * toast_decompress_datum(struct varlena *attr) { - struct varlena *result; + const CompressionRoutine *cmroutine; Assert(VARATT_IS_COMPRESSED(attr)); - result = (struct varlena *) - palloc(TOAST_COMPRESS_RAWSIZE(attr) + VARHDRSZ); - SET_VARSIZE(result, TOAST_COMPRESS_RAWSIZE(attr) + VARHDRSZ); - - if (pglz_decompress(TOAST_COMPRESS_RAWDATA(attr), - TOAST_COMPRESS_SIZE(attr), - VARDATA(result), - TOAST_COMPRESS_RAWSIZE(attr), true) < 0) - elog(ERROR, "compressed data is corrupted"); + /* + * Get compression handler routines, using the compression id stored in the + * toast header. + */ + cmroutine = GetCompressionRoutines( + CompressionIdToMethod(TOAST_COMPRESS_METHOD(attr))); - return result; + return cmroutine->datum_decompress(attr); } @@ -492,22 +521,18 @@ toast_decompress_datum(struct varlena *attr) static struct varlena * toast_decompress_datum_slice(struct varlena *attr, int32 slicelength) { - struct varlena *result; - int32 rawsize; + const CompressionRoutine *cmroutine; Assert(VARATT_IS_COMPRESSED(attr)); - result = (struct varlena *) palloc(slicelength + VARHDRSZ); - - rawsize = pglz_decompress(TOAST_COMPRESS_RAWDATA(attr), - VARSIZE(attr) - TOAST_COMPRESS_HDRSZ, - VARDATA(result), - slicelength, false); - if (rawsize < 0) - elog(ERROR, "compressed data is corrupted"); + /* + * Get compression handler routines, using the compression id stored in the + * toast header. + */ + cmroutine = GetCompressionRoutines( + CompressionIdToMethod(TOAST_COMPRESS_METHOD(attr))); - SET_VARSIZE(result, rawsize + VARHDRSZ); - return result; + return cmroutine->datum_decompress_slice(attr, slicelength); } /* ---------- diff --git a/src/backend/access/common/indextuple.c b/src/backend/access/common/indextuple.c index b72a138497..1f6b7b77d4 100644 --- a/src/backend/access/common/indextuple.c +++ b/src/backend/access/common/indextuple.c @@ -103,7 +103,8 @@ index_form_tuple(TupleDesc tupleDescriptor, (att->attstorage == TYPSTORAGE_EXTENDED || att->attstorage == TYPSTORAGE_MAIN)) { - Datum cvalue = toast_compress_datum(untoasted_values[i]); + Datum cvalue = toast_compress_datum(untoasted_values[i], + att->attcompression); if (DatumGetPointer(cvalue) != NULL) { diff --git a/src/backend/access/common/toast_compression.c b/src/backend/access/common/toast_compression.c new file mode 100644 index 0000000000..3463b42438 --- /dev/null +++ b/src/backend/access/common/toast_compression.c @@ -0,0 +1,308 @@ +/*------------------------------------------------------------------------- + * + * toast_compression.c + * Functions for toast compression. + * + * Copyright (c) 2021, PostgreSQL Global Development Group + * + * + * IDENTIFICATION + * src/backend/access/common/toast_compression.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#ifdef HAVE_LIBLZ4 +#include <lz4.h> +#endif + +#include "access/toast_compression.h" +#include "common/pg_lzcompress.h" +#include "fmgr.h" +#include "utils/builtins.h" + +static struct varlena *pglz_cmcompress(const struct varlena *value); +static struct varlena *pglz_cmdecompress(const struct varlena *value); +static struct varlena *pglz_cmdecompress_slice(const struct varlena *value, + int32 slicelength); +static struct varlena *lz4_cmcompress(const struct varlena *value); +static struct varlena *lz4_cmdecompress(const struct varlena *value); +static struct varlena *lz4_cmdecompress_slice(const struct varlena *value, + int32 slicelength); + +#define NO_LZ4_SUPPORT() \ + ereport(ERROR, \ + (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), \ + errmsg("unsupported LZ4 compression method"), \ + errdetail("This functionality requires the server to be built with lz4 support."), \ + errhint("You need to rebuild PostgreSQL using --with-lz4."))) + +/* handler routines for pglz and lz4 built-in compression methods */ +const CompressionRoutine toast_compression[] = +{ + { + .cmname = "pglz", + .datum_compress = pglz_cmcompress, + .datum_decompress = pglz_cmdecompress, + .datum_decompress_slice = pglz_cmdecompress_slice + }, + { + .cmname = "lz4", + .datum_compress = lz4_cmcompress, + .datum_decompress = lz4_cmdecompress, + .datum_decompress_slice = lz4_cmdecompress_slice + } +}; + +/* + * pglz_cmcompress - compression routine for pglz compression method + * + * Compresses source into dest using the default strategy. Returns the + * compressed varlena, or NULL if compression fails. + */ +static struct varlena * +pglz_cmcompress(const struct varlena *value) +{ + int32 valsize, + len; + struct varlena *tmp = NULL; + + valsize = VARSIZE_ANY_EXHDR(DatumGetPointer(value)); + + /* + * No point in wasting a palloc cycle if value size is outside the allowed + * range for compression. + */ + if (valsize < PGLZ_strategy_default->min_input_size || + valsize > PGLZ_strategy_default->max_input_size) + return NULL; + + /* + * Figure out the maximum possible size of the pglz output, add the bytes + * that will be needed for varlena overhead, and allocate that amount. + */ + tmp = (struct varlena *) palloc(PGLZ_MAX_OUTPUT(valsize) + + VARHDRSZ_COMPRESS); + + len = pglz_compress(VARDATA_ANY(value), + valsize, + (char *) tmp + VARHDRSZ_COMPRESS, + NULL); + if (len < 0) + { + pfree(tmp); + return NULL; + } + + SET_VARSIZE_COMPRESSED(tmp, len + VARHDRSZ_COMPRESS); + + return tmp; +} + +/* + * pglz_cmdecompress - decompression routine for pglz compression method + * + * Returns the decompressed varlena. + */ +static struct varlena * +pglz_cmdecompress(const struct varlena *value) +{ + struct varlena *result; + int32 rawsize; + + /* allocate memory for the uncompressed data */ + result = (struct varlena *) palloc(VARRAWSIZE_4B_C(value) + VARHDRSZ); + + /* decompress the data */ + rawsize = pglz_decompress((char *) value + VARHDRSZ_COMPRESS, + VARSIZE(value) - VARHDRSZ_COMPRESS, + VARDATA(result), + VARRAWSIZE_4B_C(value), true); + if (rawsize < 0) + ereport(ERROR, + (errcode(ERRCODE_DATA_CORRUPTED), + errmsg_internal("compressed pglz data is corrupt"))); + + SET_VARSIZE(result, rawsize + VARHDRSZ); + + return result; +} + +/* + * pglz_decompress - slice decompression routine for pglz compression method + * + * Decompresses part of the data. Returns the decompressed varlena. + */ +static struct varlena * +pglz_cmdecompress_slice(const struct varlena *value, + int32 slicelength) +{ + struct varlena *result; + int32 rawsize; + + /* allocate memory for the uncompressed data */ + result = (struct varlena *) palloc(slicelength + VARHDRSZ); + + /* decompress the data */ + rawsize = pglz_decompress((char *) value + VARHDRSZ_COMPRESS, + VARSIZE(value) - VARHDRSZ_COMPRESS, + VARDATA(result), + slicelength, false); + if (rawsize < 0) + ereport(ERROR, + (errcode(ERRCODE_DATA_CORRUPTED), + errmsg_internal("compressed pglz data is corrupt"))); + + SET_VARSIZE(result, rawsize + VARHDRSZ); + + return result; +} + +/* + * lz4_cmcompress - compression routine for lz4 compression method + * + * Compresses source into dest using the LZ4 defaults. Returns the + * compressed varlena, or NULL if compression fails. + */ +static struct varlena * +lz4_cmcompress(const struct varlena *value) +{ +#ifndef HAVE_LIBLZ4 + NO_LZ4_SUPPORT(); +#else + int32 valsize; + int32 len; + int32 max_size; + struct varlena *tmp = NULL; + + valsize = VARSIZE_ANY_EXHDR(value); + + /* + * Figure out the maximum possible size of the LZ4 output, add the bytes + * that will be needed for varlena overhead, and allocate that amount. + */ + max_size = LZ4_compressBound(valsize); + tmp = (struct varlena *) palloc(max_size + VARHDRSZ_COMPRESS); + + len = LZ4_compress_default(VARDATA_ANY(value), + (char *) tmp + VARHDRSZ_COMPRESS, + valsize, max_size); + if (len <= 0) + elog(ERROR, "could not compress data with lz4"); + + /* data is incompressible so just free the memory and return NULL */ + if (len > valsize) + { + pfree(tmp); + return NULL; + } + + SET_VARSIZE_COMPRESSED(tmp, len + VARHDRSZ_COMPRESS); + + return tmp; +#endif +} + +/* + * lz4_cmdecompress - decompression routine for lz4 compression method + * + * Returns the decompressed varlena. + */ +static struct varlena * +lz4_cmdecompress(const struct varlena *value) +{ +#ifndef HAVE_LIBLZ4 + NO_LZ4_SUPPORT(); +#else + int32 rawsize; + struct varlena *result; + + /* allocate memory for the uncompressed data */ + result = (struct varlena *) palloc(VARRAWSIZE_4B_C(value) + VARHDRSZ); + + /* decompress the data */ + rawsize = LZ4_decompress_safe((char *) value + VARHDRSZ_COMPRESS, + VARDATA(result), + VARSIZE(value) - VARHDRSZ_COMPRESS, + VARRAWSIZE_4B_C(value)); + if (rawsize < 0) + ereport(ERROR, + (errcode(ERRCODE_DATA_CORRUPTED), + errmsg_internal("compressed lz4 data is corrupt"))); + + + SET_VARSIZE(result, rawsize + VARHDRSZ); + + return result; +#endif +} + +/* + * lz4_cmdecompress_slice - slice decompression routine for lz4 compression + * + * Decompresses part of the data. Returns the decompressed varlena. + */ +static struct varlena * +lz4_cmdecompress_slice(const struct varlena *value, int32 slicelength) +{ +#ifndef HAVE_LIBLZ4 + NO_LZ4_SUPPORT(); +#elif LZ4_VERSION_NUMBER < 10803 + return lz4_cmdecompress(value); +#else + int32 rawsize; + struct varlena *result; + + /* allocate memory for the uncompressed data */ + result = (struct varlena *) palloc(slicelength + VARHDRSZ); + + /* decompress the data */ + rawsize = LZ4_decompress_safe_partial((char *) value + VARHDRSZ_COMPRESS, + VARDATA(result), + VARSIZE(value) - VARHDRSZ_COMPRESS, + slicelength, + slicelength); + if (rawsize < 0) + ereport(ERROR, + (errcode(ERRCODE_DATA_CORRUPTED), + errmsg_internal("compressed lz4 data is corrupt"))); + + SET_VARSIZE(result, rawsize + VARHDRSZ); + + return result; +#endif +} + +/* + * CompressionNameToMethod - Get compression method from compression name + * + * Search in the available built-in methods. If the compression not found + * in the built-in methods then return InvalidCompressionMethod. + */ +char +CompressionNameToMethod(char *compression) +{ + if (strcmp(toast_compression[PGLZ_COMPRESSION_ID].cmname, + compression) == 0) + return PGLZ_COMPRESSION; + else if (strcmp(toast_compression[LZ4_COMPRESSION_ID].cmname, + compression) == 0) + { +#ifndef HAVE_LIBLZ4 + NO_LZ4_SUPPORT(); +#endif + return LZ4_COMPRESSION; + } + + return InvalidCompressionMethod; +} + +/* + * GetCompressionRoutines - Get compression handler routines + */ +const CompressionRoutine* +GetCompressionRoutines(char method) +{ + return &toast_compression[CompressionMethodToId(method)]; +} diff --git a/src/backend/access/common/toast_internals.c b/src/backend/access/common/toast_internals.c index 9b9da0f41b..69dd9492f6 100644 --- a/src/backend/access/common/toast_internals.c +++ b/src/backend/access/common/toast_internals.c @@ -44,46 +44,42 @@ static bool toastid_valueid_exists(Oid toastrelid, Oid valueid); * ---------- */ Datum -toast_compress_datum(Datum value) +toast_compress_datum(Datum value, char cmethod) { - struct varlena *tmp; - int32 valsize = VARSIZE_ANY_EXHDR(DatumGetPointer(value)); - int32 len; + struct varlena *tmp = NULL; + int32 valsize; + const CompressionRoutine *cmroutine = NULL; Assert(!VARATT_IS_EXTERNAL(DatumGetPointer(value))); Assert(!VARATT_IS_COMPRESSED(DatumGetPointer(value))); - /* - * No point in wasting a palloc cycle if value size is out of the allowed - * range for compression - */ - if (valsize < PGLZ_strategy_default->min_input_size || - valsize > PGLZ_strategy_default->max_input_size) - return PointerGetDatum(NULL); + Assert(CompressionMethodIsValid(cmethod)); - tmp = (struct varlena *) palloc(PGLZ_MAX_OUTPUT(valsize) + - TOAST_COMPRESS_HDRSZ); + /* get the handler routines for the compression method */ + cmroutine = GetCompressionRoutines(cmethod); + + /* call the actual compression function */ + tmp = cmroutine->datum_compress((const struct varlena *) value); + if (!tmp) + return PointerGetDatum(NULL); /* - * We recheck the actual size even if pglz_compress() reports success, - * because it might be satisfied with having saved as little as one byte - * in the compressed data --- which could turn into a net loss once you - * consider header and alignment padding. Worst case, the compressed - * format might require three padding bytes (plus header, which is - * included in VARSIZE(tmp)), whereas the uncompressed format would take - * only one header byte and no padding if the value is short enough. So - * we insist on a savings of more than 2 bytes to ensure we have a gain. + * We recheck the actual size even if compression reports success, because + * it might be satisfied with having saved as little as one byte in the + * compressed data --- which could turn into a net loss once you consider + * header and alignment padding. Worst case, the compressed format might + * require three padding bytes (plus header, which is included in + * VARSIZE(tmp)), whereas the uncompressed format would take only one + * header byte and no padding if the value is short enough. So we insist + * on a savings of more than 2 bytes to ensure we have a gain. */ - len = pglz_compress(VARDATA_ANY(DatumGetPointer(value)), - valsize, - TOAST_COMPRESS_RAWDATA(tmp), - PGLZ_strategy_default); - if (len >= 0 && - len + TOAST_COMPRESS_HDRSZ < valsize - 2) + valsize = VARSIZE_ANY_EXHDR(DatumGetPointer(value)); + + if (VARSIZE(tmp) < valsize - 2) { - TOAST_COMPRESS_SET_RAWSIZE(tmp, valsize); - SET_VARSIZE_COMPRESSED(tmp, len + TOAST_COMPRESS_HDRSZ); /* successful compression */ + TOAST_COMPRESS_SET_SIZE_AND_METHOD(tmp, valsize, + CompressionMethodToId(cmethod)); return PointerGetDatum(tmp); } else diff --git a/src/backend/access/common/tupdesc.c b/src/backend/access/common/tupdesc.c index 902f59440c..503d64df38 100644 --- a/src/backend/access/common/tupdesc.c +++ b/src/backend/access/common/tupdesc.c @@ -19,6 +19,7 @@ #include "postgres.h" +#include "access/toast_compression.h" #include "access/htup_details.h" #include "access/tupdesc_details.h" #include "catalog/pg_collation.h" @@ -470,6 +471,8 @@ equalTupleDescs(TupleDesc tupdesc1, TupleDesc tupdesc2) return false; if (attr1->attcollation != attr2->attcollation) return false; + if (attr1->attcompression != attr2->attcompression) + return false; /* attacl, attoptions and attfdwoptions are not even present... */ } @@ -664,6 +667,11 @@ TupleDescInitEntry(TupleDesc desc, att->attstorage = typeForm->typstorage; att->attcollation = typeForm->typcollation; + if (IsStorageCompressible(typeForm->typstorage)) + att->attcompression = DefaultCompressionMethod; + else + att->attcompression = InvalidCompressionMethod; + ReleaseSysCache(tuple); } diff --git a/src/backend/access/table/toast_helper.c b/src/backend/access/table/toast_helper.c index fb36151ce5..53f78f9c3e 100644 --- a/src/backend/access/table/toast_helper.c +++ b/src/backend/access/table/toast_helper.c @@ -54,6 +54,7 @@ toast_tuple_init(ToastTupleContext *ttc) ttc->ttc_attr[i].tai_colflags = 0; ttc->ttc_attr[i].tai_oldexternal = NULL; + ttc->ttc_attr[i].tai_compression = att->attcompression; if (ttc->ttc_oldvalues != NULL) { @@ -226,9 +227,11 @@ void toast_tuple_try_compression(ToastTupleContext *ttc, int attribute) { Datum *value = &ttc->ttc_values[attribute]; - Datum new_value = toast_compress_datum(*value); + Datum new_value; ToastAttrInfo *attr = &ttc->ttc_attr[attribute]; + new_value = toast_compress_datum(*value, attr->tai_compression); + if (DatumGetPointer(new_value) != NULL) { /* successful compression */ diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..45e1cfa56c 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -17,6 +17,7 @@ #include <unistd.h> #include <signal.h> +#include "access/toast_compression.h" #include "access/genam.h" #include "access/heapam.h" #include "access/htup_details.h" @@ -731,6 +732,10 @@ DefineAttr(char *name, char *type, int attnum, int nullness) attrtypes[attnum]->attcacheoff = -1; attrtypes[attnum]->atttypmod = -1; attrtypes[attnum]->attislocal = true; + if (IsStorageCompressible(attrtypes[attnum]->attstorage)) + attrtypes[attnum]->attcompression = DefaultCompressionMethod; + else + attrtypes[attnum]->attcompression = InvalidCompressionMethod; if (nullness == BOOTCOL_NULL_FORCE_NOT_NULL) { diff --git a/src/backend/catalog/genbki.pl b/src/backend/catalog/genbki.pl index b159958112..9586c29ad0 100644 --- a/src/backend/catalog/genbki.pl +++ b/src/backend/catalog/genbki.pl @@ -906,6 +906,9 @@ sub morph_row_for_pgattr $row->{attcollation} = $type->{typcollation} ne '0' ? $C_COLLATION_OID : 0; + $row->{attcompression} = + $type->{typstorage} ne 'p' && $type->{typstorage} ne 'e' ? 'p' : '\0'; + if (defined $attr->{forcenotnull}) { $row->{attnotnull} = 't'; diff --git a/src/backend/catalog/heap.c b/src/backend/catalog/heap.c index 9abc4a1f55..d8b71e5bc3 100644 --- a/src/backend/catalog/heap.c +++ b/src/backend/catalog/heap.c @@ -29,6 +29,7 @@ */ #include "postgres.h" +#include "access/toast_compression.h" #include "access/genam.h" #include "access/htup_details.h" #include "access/multixact.h" @@ -789,6 +790,7 @@ InsertPgAttributeTuples(Relation pg_attribute_rel, slot[slotCount]->tts_values[Anum_pg_attribute_attislocal - 1] = BoolGetDatum(attrs->attislocal); slot[slotCount]->tts_values[Anum_pg_attribute_attinhcount - 1] = Int32GetDatum(attrs->attinhcount); slot[slotCount]->tts_values[Anum_pg_attribute_attcollation - 1] = ObjectIdGetDatum(attrs->attcollation); + slot[slotCount]->tts_values[Anum_pg_attribute_attcompression - 1] = CharGetDatum(attrs->attcompression); if (attoptions && attoptions[natts] != (Datum) 0) slot[slotCount]->tts_values[Anum_pg_attribute_attoptions - 1] = attoptions[natts]; else @@ -1715,6 +1717,8 @@ RemoveAttributeById(Oid relid, AttrNumber attnum) /* Unset this so no one tries to look up the generation expression */ attStruct->attgenerated = '\0'; + attStruct->attcompression = InvalidCompressionMethod; + /* * Change the column name to something that isn't likely to conflict */ diff --git a/src/backend/catalog/index.c b/src/backend/catalog/index.c index 4ef61b5efd..397d70d226 100644 --- a/src/backend/catalog/index.c +++ b/src/backend/catalog/index.c @@ -348,6 +348,7 @@ ConstructTupleDescriptor(Relation heapRelation, to->attbyval = from->attbyval; to->attstorage = from->attstorage; to->attalign = from->attalign; + to->attcompression = from->attcompression; } else { diff --git a/src/backend/catalog/toasting.c b/src/backend/catalog/toasting.c index d7b806020d..2196b44aae 100644 --- a/src/backend/catalog/toasting.c +++ b/src/backend/catalog/toasting.c @@ -14,6 +14,7 @@ */ #include "postgres.h" +#include "access/toast_compression.h" #include "access/heapam.h" #include "access/xact.h" #include "catalog/binary_upgrade.h" @@ -220,6 +221,11 @@ create_toast_table(Relation rel, Oid toastOid, Oid toastIndexOid, TupleDescAttr(tupdesc, 1)->attstorage = TYPSTORAGE_PLAIN; TupleDescAttr(tupdesc, 2)->attstorage = TYPSTORAGE_PLAIN; + /* Toast field should not be compressed */ + TupleDescAttr(tupdesc, 0)->attcompression = InvalidCompressionMethod; + TupleDescAttr(tupdesc, 1)->attcompression = InvalidCompressionMethod; + TupleDescAttr(tupdesc, 2)->attcompression = InvalidCompressionMethod; + /* * Toast tables for regular relations go in pg_toast; those for temp * relations go into the per-backend temp-toast-table namespace. diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c index 559fa1d2e5..d295d85cd2 100644 --- a/src/backend/commands/tablecmds.c +++ b/src/backend/commands/tablecmds.c @@ -15,6 +15,7 @@ #include "postgres.h" #include "access/attmap.h" +#include "access/toast_compression.h" #include "access/genam.h" #include "access/heapam.h" #include "access/heapam_xlog.h" @@ -558,6 +559,7 @@ static void refuseDupeIndexAttach(Relation parentIdx, Relation partIdx, static List *GetParentedForeignKeyRefs(Relation partition); static void ATDetachCheckNoForeignKeyRefs(Relation partition); static void ATExecAlterCollationRefreshVersion(Relation rel, List *coll); +static char GetAttributeCompression(Form_pg_attribute att, char *compression); /* ---------------------------------------------------------------- @@ -852,6 +854,18 @@ DefineRelation(CreateStmt *stmt, char relkind, Oid ownerId, if (colDef->generated) attr->attgenerated = colDef->generated; + + /* + * lookup attribute's compression method and store it in the + * attr->attcompression. + */ + if (relkind == RELKIND_RELATION || + relkind == RELKIND_PARTITIONED_TABLE || + relkind == RELKIND_MATVIEW) + attr->attcompression = + GetAttributeCompression(attr, colDef->compression); + else + attr->attcompression = InvalidCompressionMethod; } /* @@ -2396,6 +2410,22 @@ MergeAttributes(List *schema, List *supers, char relpersistence, storage_name(def->storage), storage_name(attribute->attstorage)))); + /* Copy/check compression parameter */ + if (CompressionMethodIsValid(attribute->attcompression)) + { + const char *compression = GetCompressionMethodName( + attribute->attcompression); + + if (def->compression == NULL) + def->compression = pstrdup(compression); + else if (strcmp(def->compression, compression) != 0) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("column \"%s\" has a compression method conflict", + attributeName), + errdetail("%s versus %s", def->compression, compression))); + } + def->inhcount++; /* Merge of NOT NULL constraints = OR 'em together */ def->is_not_null |= attribute->attnotnull; @@ -2430,6 +2460,11 @@ MergeAttributes(List *schema, List *supers, char relpersistence, def->collOid = attribute->attcollation; def->constraints = NIL; def->location = -1; + if (CompressionMethodIsValid(attribute->attcompression)) + def->compression = pstrdup(GetCompressionMethodName( + attribute->attcompression)); + else + def->compression = NULL; inhSchema = lappend(inhSchema, def); newattmap->attnums[parent_attno - 1] = ++child_attno; } @@ -2675,6 +2710,19 @@ MergeAttributes(List *schema, List *supers, char relpersistence, storage_name(def->storage), storage_name(newdef->storage)))); + /* Copy compression parameter */ + if (def->compression == NULL) + def->compression = newdef->compression; + else if (newdef->compression != NULL) + { + if (strcmp(def->compression, newdef->compression) != 0) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("column \"%s\" has a compression method conflict", + attributeName), + errdetail("%s versus %s", def->compression, newdef->compression))); + } + /* Mark the column as locally defined */ def->is_local = true; /* Merge of NOT NULL constraints = OR 'em together */ @@ -6340,6 +6388,18 @@ ATExecAddColumn(List **wqueue, AlteredTableInfo *tab, Relation rel, attribute.attislocal = colDef->is_local; attribute.attinhcount = colDef->inhcount; attribute.attcollation = collOid; + + /* + * lookup attribute's compression method and store it in the + * attr->attcompression. + */ + if (rel->rd_rel->relkind == RELKIND_RELATION || + rel->rd_rel->relkind == RELKIND_PARTITIONED_TABLE) + attribute.attcompression = GetAttributeCompression(&attribute, + colDef->compression); + else + attribute.attcompression = InvalidCompressionMethod; + /* attribute.attacl is handled by InsertPgAttributeTuples() */ ReleaseSysCache(typeTuple); @@ -11859,6 +11919,23 @@ ATExecAlterColumnType(AlteredTableInfo *tab, Relation rel, ReleaseSysCache(typeTuple); + /* Setup attribute compression */ + if (rel->rd_rel->relkind == RELKIND_RELATION || + rel->rd_rel->relkind == RELKIND_PARTITIONED_TABLE) + { + /* + * No compression for plain/external storage, otherwise, default + * compression method if it is not already set, refer comments atop + * attcompression parameter in pg_attribute.h. + */ + if (!IsStorageCompressible(tform->typstorage)) + attTup->attcompression = InvalidCompressionMethod; + else if (!CompressionMethodIsValid(attTup->attcompression)) + attTup->attcompression = DefaultCompressionMethod; + } + else + attTup->attcompression = InvalidCompressionMethod; + CatalogTupleUpdate(attrelation, &heapTup->t_self, heapTup); table_close(attrelation, RowExclusiveLock); @@ -17641,3 +17718,36 @@ ATExecAlterCollationRefreshVersion(Relation rel, List *coll) index_update_collation_versions(rel->rd_id, get_collation_oid(coll, false)); CacheInvalidateRelcache(rel); } + +/* + * resolve column compression specification to compression method. + */ +static char +GetAttributeCompression(Form_pg_attribute att, char *compression) +{ + char typstorage = get_typstorage(att->atttypid); + char cmethod; + + /* + * No compression for plain/external storage, refer comments atop + * attcompression parameter in pg_attribute.h + */ + if (!IsStorageCompressible(typstorage)) + { + if (compression == NULL) + return InvalidCompressionMethod; + + ereport(ERROR, + (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("column data type %s does not support compression", + format_type_be(att->atttypid)))); + } + + /* fallback to default compression if it's not specified */ + if (compression == NULL) + return DefaultCompressionMethod; + + cmethod = CompressionNameToMethod(compression); + + return cmethod; +} diff --git a/src/backend/nodes/copyfuncs.c b/src/backend/nodes/copyfuncs.c index da91cbd2b1..0d3b923a38 100644 --- a/src/backend/nodes/copyfuncs.c +++ b/src/backend/nodes/copyfuncs.c @@ -2988,6 +2988,7 @@ _copyColumnDef(const ColumnDef *from) COPY_STRING_FIELD(colname); COPY_NODE_FIELD(typeName); + COPY_STRING_FIELD(compression); COPY_SCALAR_FIELD(inhcount); COPY_SCALAR_FIELD(is_local); COPY_SCALAR_FIELD(is_not_null); diff --git a/src/backend/nodes/equalfuncs.c b/src/backend/nodes/equalfuncs.c index c2d73626fc..f3592003da 100644 --- a/src/backend/nodes/equalfuncs.c +++ b/src/backend/nodes/equalfuncs.c @@ -2599,6 +2599,7 @@ _equalColumnDef(const ColumnDef *a, const ColumnDef *b) { COMPARE_STRING_FIELD(colname); COMPARE_NODE_FIELD(typeName); + COMPARE_STRING_FIELD(compression); COMPARE_SCALAR_FIELD(inhcount); COMPARE_SCALAR_FIELD(is_local); COMPARE_SCALAR_FIELD(is_not_null); diff --git a/src/backend/nodes/nodeFuncs.c b/src/backend/nodes/nodeFuncs.c index 49357ac5c2..38226530c6 100644 --- a/src/backend/nodes/nodeFuncs.c +++ b/src/backend/nodes/nodeFuncs.c @@ -3897,6 +3897,8 @@ raw_expression_tree_walker(Node *node, if (walker(coldef->typeName, context)) return true; + if (walker(coldef->compression, context)) + return true; if (walker(coldef->raw_default, context)) return true; if (walker(coldef->collClause, context)) diff --git a/src/backend/nodes/outfuncs.c b/src/backend/nodes/outfuncs.c index 6493a03ff8..75343b8aaf 100644 --- a/src/backend/nodes/outfuncs.c +++ b/src/backend/nodes/outfuncs.c @@ -2876,6 +2876,7 @@ _outColumnDef(StringInfo str, const ColumnDef *node) WRITE_STRING_FIELD(colname); WRITE_NODE_FIELD(typeName); + WRITE_STRING_FIELD(compression); WRITE_INT_FIELD(inhcount); WRITE_BOOL_FIELD(is_local); WRITE_BOOL_FIELD(is_not_null); diff --git a/src/backend/parser/gram.y b/src/backend/parser/gram.y index 652be0b96d..9d923b5d95 100644 --- a/src/backend/parser/gram.y +++ b/src/backend/parser/gram.y @@ -596,6 +596,8 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query); %type <list> hash_partbound %type <defelt> hash_partbound_elem +%type <str> optColumnCompression + /* * Non-keyword token types. These are hard-wired into the "flex" lexer. * They must be listed first so that their numeric codes do not depend on @@ -631,9 +633,9 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query); CACHE CALL CALLED CASCADE CASCADED CASE CAST CATALOG_P CHAIN CHAR_P CHARACTER CHARACTERISTICS CHECK CHECKPOINT CLASS CLOSE CLUSTER COALESCE COLLATE COLLATION COLUMN COLUMNS COMMENT COMMENTS COMMIT - COMMITTED CONCURRENTLY CONFIGURATION CONFLICT CONNECTION CONSTRAINT - CONSTRAINTS CONTENT_P CONTINUE_P CONVERSION_P COPY COST CREATE - CROSS CSV CUBE CURRENT_P + COMMITTED COMPRESSION CONCURRENTLY CONFIGURATION CONFLICT + CONNECTION CONSTRAINT CONSTRAINTS CONTENT_P CONTINUE_P CONVERSION_P COPY + COST CREATE CROSS CSV CUBE CURRENT_P CURRENT_CATALOG CURRENT_DATE CURRENT_ROLE CURRENT_SCHEMA CURRENT_TIME CURRENT_TIMESTAMP CURRENT_USER CURSOR CYCLE @@ -3421,11 +3423,12 @@ TypedTableElement: | TableConstraint { $$ = $1; } ; -columnDef: ColId Typename create_generic_options ColQualList +columnDef: ColId Typename optColumnCompression create_generic_options ColQualList { ColumnDef *n = makeNode(ColumnDef); n->colname = $1; n->typeName = $2; + n->compression = $3; n->inhcount = 0; n->is_local = true; n->is_not_null = false; @@ -3434,8 +3437,8 @@ columnDef: ColId Typename create_generic_options ColQualList n->raw_default = NULL; n->cooked_default = NULL; n->collOid = InvalidOid; - n->fdwoptions = $3; - SplitColQualList($4, &n->constraints, &n->collClause, + n->fdwoptions = $4; + SplitColQualList($5, &n->constraints, &n->collClause, yyscanner); n->location = @1; $$ = (Node *)n; @@ -3480,6 +3483,14 @@ columnOptions: ColId ColQualList } ; +optColumnCompression: + COMPRESSION name + { + $$ = $2; + } + | /*EMPTY*/ { $$ = NULL; } + ; + ColQualList: ColQualList ColConstraint { $$ = lappend($1, $2); } | /*EMPTY*/ { $$ = NIL; } @@ -3710,6 +3721,7 @@ TableLikeOption: | INDEXES { $$ = CREATE_TABLE_LIKE_INDEXES; } | STATISTICS { $$ = CREATE_TABLE_LIKE_STATISTICS; } | STORAGE { $$ = CREATE_TABLE_LIKE_STORAGE; } + | COMPRESSION { $$ = CREATE_TABLE_LIKE_COMPRESSION; } | ALL { $$ = CREATE_TABLE_LIKE_ALL; } ; @@ -15296,6 +15308,7 @@ unreserved_keyword: | COMMENTS | COMMIT | COMMITTED + | COMPRESSION | CONFIGURATION | CONFLICT | CONNECTION @@ -15816,6 +15829,7 @@ bare_label_keyword: | COMMENTS | COMMIT | COMMITTED + | COMPRESSION | CONCURRENTLY | CONFIGURATION | CONFLICT diff --git a/src/backend/parser/parse_utilcmd.c b/src/backend/parser/parse_utilcmd.c index 75266caeb4..af772ba6bc 100644 --- a/src/backend/parser/parse_utilcmd.c +++ b/src/backend/parser/parse_utilcmd.c @@ -27,6 +27,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/toast_compression.h" #include "access/htup_details.h" #include "access/relation.h" #include "access/reloptions.h" @@ -1082,6 +1083,14 @@ transformTableLikeClause(CreateStmtContext *cxt, TableLikeClause *table_like_cla else def->storage = 0; + /* Likewise, copy compression if requested */ + if ((table_like_clause->options & CREATE_TABLE_LIKE_COMPRESSION) != 0 + && CompressionMethodIsValid(attribute->attcompression)) + def->compression = + pstrdup(GetCompressionMethodName(attribute->attcompression)); + else + def->compression = NULL; + /* Likewise, copy comment if requested */ if ((table_like_clause->options & CREATE_TABLE_LIKE_COMMENTS) && (comment = GetComment(attribute->attrelid, diff --git a/src/backend/utils/adt/varlena.c b/src/backend/utils/adt/varlena.c index 479ed9ae54..37876a8cb7 100644 --- a/src/backend/utils/adt/varlena.c +++ b/src/backend/utils/adt/varlena.c @@ -17,6 +17,7 @@ #include <ctype.h> #include <limits.h> +#include "access/toast_compression.h" #include "access/detoast.h" #include "catalog/pg_collation.h" #include "catalog/pg_type.h" @@ -5299,6 +5300,46 @@ pg_column_size(PG_FUNCTION_ARGS) PG_RETURN_INT32(result); } +/* + * Return the compression method stored in the compressed attribute. Return + * NULL for non varlena type or uncompressed data. + */ +Datum +pg_column_compression(PG_FUNCTION_ARGS) +{ + Datum value = PG_GETARG_DATUM(0); + int typlen; + char method; + + /* On first call, get the input type's typlen, and save at *fn_extra */ + if (fcinfo->flinfo->fn_extra == NULL) + { + /* Lookup the datatype of the supplied argument */ + Oid argtypeid = get_fn_expr_argtype(fcinfo->flinfo, 0); + + typlen = get_typlen(argtypeid); + if (typlen == 0) /* should not happen */ + elog(ERROR, "cache lookup failed for type %u", argtypeid); + + fcinfo->flinfo->fn_extra = MemoryContextAlloc(fcinfo->flinfo->fn_mcxt, + sizeof(int)); + *((int *) fcinfo->flinfo->fn_extra) = typlen; + } + else + typlen = *((int *) fcinfo->flinfo->fn_extra); + + if (typlen != -1) + PG_RETURN_NULL(); + + method = toast_get_compression_method( + (struct varlena *) DatumGetPointer(value)); + + if (!CompressionMethodIsValid(method)) + PG_RETURN_NULL(); + else + PG_RETURN_TEXT_P(cstring_to_text(GetCompressionMethodName(method))); +} + /* * string_agg - Concatenates values and returns string. * diff --git a/src/bin/pg_dump/pg_backup.h b/src/bin/pg_dump/pg_backup.h index eea9f30a79..0296b9bb5e 100644 --- a/src/bin/pg_dump/pg_backup.h +++ b/src/bin/pg_dump/pg_backup.h @@ -160,6 +160,7 @@ typedef struct _dumpOptions int no_subscriptions; int no_synchronized_snapshots; int no_unlogged_table_data; + int no_toast_compression; int serializable_deferrable; int disable_triggers; int outputNoTablespaces; diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c index eb988d7eb4..cef9bbd76a 100644 --- a/src/bin/pg_dump/pg_dump.c +++ b/src/bin/pg_dump/pg_dump.c @@ -387,6 +387,7 @@ main(int argc, char **argv) {"no-synchronized-snapshots", no_argument, &dopt.no_synchronized_snapshots, 1}, {"no-unlogged-table-data", no_argument, &dopt.no_unlogged_table_data, 1}, {"no-subscriptions", no_argument, &dopt.no_subscriptions, 1}, + {"no-toast-compression", no_argument, &dopt.no_toast_compression, 1}, {"no-sync", no_argument, NULL, 7}, {"on-conflict-do-nothing", no_argument, &dopt.do_nothing, 1}, {"rows-per-insert", required_argument, NULL, 10}, @@ -1047,6 +1048,7 @@ help(const char *progname) printf(_(" --no-publications do not dump publications\n")); printf(_(" --no-security-labels do not dump security label assignments\n")); printf(_(" --no-subscriptions do not dump subscriptions\n")); + printf(_(" --no-toast-compression do not dump toast compression methods\n")); printf(_(" --no-synchronized-snapshots do not use synchronized snapshots in parallel jobs\n")); printf(_(" --no-tablespaces do not dump tablespace assignments\n")); printf(_(" --no-unlogged-table-data do not dump unlogged table data\n")); @@ -8617,6 +8619,7 @@ getTableAttrs(Archive *fout, TableInfo *tblinfo, int numTables) { DumpOptions *dopt = fout->dopt; PQExpBuffer q = createPQExpBuffer(); + bool createWithCompression; for (int i = 0; i < numTables; i++) { @@ -8702,6 +8705,15 @@ getTableAttrs(Archive *fout, TableInfo *tblinfo, int numTables) appendPQExpBufferStr(q, "'' AS attidentity,\n"); + createWithCompression = (fout->remoteVersion >= 140000); + + if (createWithCompression) + appendPQExpBuffer(q, + "a.attcompression AS attcompression,\n"); + else + appendPQExpBuffer(q, + "NULL AS attcmname,\n"); + if (fout->remoteVersion >= 110000) appendPQExpBufferStr(q, "CASE WHEN a.atthasmissing AND NOT a.attisdropped " @@ -8747,6 +8759,7 @@ getTableAttrs(Archive *fout, TableInfo *tblinfo, int numTables) tbinfo->attcollation = (Oid *) pg_malloc(ntups * sizeof(Oid)); tbinfo->attfdwoptions = (char **) pg_malloc(ntups * sizeof(char *)); tbinfo->attmissingval = (char **) pg_malloc(ntups * sizeof(char *)); + tbinfo->attcompression = (char *) pg_malloc(ntups * sizeof(char *)); tbinfo->notnull = (bool *) pg_malloc(ntups * sizeof(bool)); tbinfo->inhNotNull = (bool *) pg_malloc(ntups * sizeof(bool)); tbinfo->attrdefs = (AttrDefInfo **) pg_malloc(ntups * sizeof(AttrDefInfo *)); @@ -8775,6 +8788,7 @@ getTableAttrs(Archive *fout, TableInfo *tblinfo, int numTables) tbinfo->attcollation[j] = atooid(PQgetvalue(res, j, PQfnumber(res, "attcollation"))); tbinfo->attfdwoptions[j] = pg_strdup(PQgetvalue(res, j, PQfnumber(res, "attfdwoptions"))); tbinfo->attmissingval[j] = pg_strdup(PQgetvalue(res, j, PQfnumber(res, "attmissingval"))); + tbinfo->attcompression[j] = *(PQgetvalue(res, j, PQfnumber(res, "attcompression"))); tbinfo->attrdefs[j] = NULL; /* fix below */ if (PQgetvalue(res, j, PQfnumber(res, "atthasdef"))[0] == 't') hasdefaults = true; @@ -15891,6 +15905,31 @@ dumpTableSchema(Archive *fout, const TableInfo *tbinfo) tbinfo->atttypnames[j]); } + /* + * Attribute compression + */ + if (!dopt->no_toast_compression && + tbinfo->attcompression[j] && + tbinfo->attcompression[j] != '\0') + { + char *cmname; + + switch (tbinfo->attcompression[j]) + { + case 'p': + cmname = "pglz"; + break; + case 'l': + cmname = "lz4"; + break; + default: + cmname = NULL; + } + + if (cmname != NULL) + appendPQExpBuffer(q, " COMPRESSION %s", cmname); + } + if (print_default) { if (tbinfo->attgenerated[j] == ATTRIBUTE_GENERATED_STORED) diff --git a/src/bin/pg_dump/pg_dump.h b/src/bin/pg_dump/pg_dump.h index 0a2213fb06..d956b035f3 100644 --- a/src/bin/pg_dump/pg_dump.h +++ b/src/bin/pg_dump/pg_dump.h @@ -326,6 +326,7 @@ typedef struct _tableInfo char *partbound; /* partition bound definition */ bool needs_override; /* has GENERATED ALWAYS AS IDENTITY */ char *amname; /* relation access method */ + char *attcompression; /* per-attribute current compression method */ /* * Stuff computed only for dumpable tables. diff --git a/src/bin/pg_dump/t/002_pg_dump.pl b/src/bin/pg_dump/t/002_pg_dump.pl index 737e46464a..bc91bb12ac 100644 --- a/src/bin/pg_dump/t/002_pg_dump.pl +++ b/src/bin/pg_dump/t/002_pg_dump.pl @@ -2284,9 +2284,9 @@ my %tests = ( regexp => qr/^ \QCREATE TABLE dump_test.test_table (\E\n \s+\Qcol1 integer NOT NULL,\E\n - \s+\Qcol2 text,\E\n - \s+\Qcol3 text,\E\n - \s+\Qcol4 text,\E\n + \s+\Qcol2 text COMPRESSION\E\D*,\n + \s+\Qcol3 text COMPRESSION\E\D*,\n + \s+\Qcol4 text COMPRESSION\E\D*,\n \s+\QCONSTRAINT test_table_col1_check CHECK ((col1 <= 1000))\E\n \Q)\E\n \QWITH (autovacuum_enabled='false', fillfactor='80');\E\n/xm, @@ -2326,7 +2326,7 @@ my %tests = ( regexp => qr/^ \QCREATE TABLE dump_test.test_second_table (\E \n\s+\Qcol1 integer,\E - \n\s+\Qcol2 text\E + \n\s+\Qcol2 text COMPRESSION\E\D* \n\); /xm, like => @@ -2441,7 +2441,7 @@ my %tests = ( \n\s+\Qcol1 integer,\E \n\s+\Qcol2 boolean,\E \n\s+\Qcol3 boolean,\E - \n\s+\Qcol4 bit(5),\E + \n\s+\Qcol4 bit(5) COMPRESSION\E\D*, \n\s+\Qcol5 double precision\E \n\); /xm, @@ -2459,7 +2459,7 @@ my %tests = ( regexp => qr/^ \QCREATE TABLE dump_test.test_table_identity (\E\n \s+\Qcol1 integer NOT NULL,\E\n - \s+\Qcol2 text\E\n + \s+\Qcol2 text COMPRESSION\E\D*\n \); .* \QALTER TABLE dump_test.test_table_identity ALTER COLUMN col1 ADD GENERATED ALWAYS AS IDENTITY (\E\n diff --git a/src/bin/psql/describe.c b/src/bin/psql/describe.c index 20af5a92b4..b284113d55 100644 --- a/src/bin/psql/describe.c +++ b/src/bin/psql/describe.c @@ -1459,7 +1459,7 @@ describeOneTableDetails(const char *schemaname, bool printTableInitialized = false; int i; char *view_def = NULL; - char *headers[11]; + char *headers[12]; PQExpBufferData title; PQExpBufferData tmpbuf; int cols; @@ -1475,7 +1475,8 @@ describeOneTableDetails(const char *schemaname, fdwopts_col = -1, attstorage_col = -1, attstattarget_col = -1, - attdescr_col = -1; + attdescr_col = -1, + attcompression_col = -1; int numrows; struct { @@ -1892,6 +1893,17 @@ describeOneTableDetails(const char *schemaname, appendPQExpBufferStr(&buf, ",\n a.attstorage"); attstorage_col = cols++; + /* compresssion info */ + if (pset.sversion >= 140000 && + !pset.hide_compression && + (tableinfo.relkind == RELKIND_RELATION || + tableinfo.relkind == RELKIND_PARTITIONED_TABLE || + tableinfo.relkind == RELKIND_MATVIEW)) + { + appendPQExpBufferStr(&buf, ",\n a.attcompression AS attcompression"); + attcompression_col = cols++; + } + /* stats target, if relevant to relkind */ if (tableinfo.relkind == RELKIND_RELATION || tableinfo.relkind == RELKIND_INDEX || @@ -2018,6 +2030,8 @@ describeOneTableDetails(const char *schemaname, headers[cols++] = gettext_noop("FDW options"); if (attstorage_col >= 0) headers[cols++] = gettext_noop("Storage"); + if (attcompression_col >= 0) + headers[cols++] = gettext_noop("Compression"); if (attstattarget_col >= 0) headers[cols++] = gettext_noop("Stats target"); if (attdescr_col >= 0) @@ -2097,6 +2111,19 @@ describeOneTableDetails(const char *schemaname, false, false); } + /* Column compression. */ + if (attcompression_col >= 0) + { + char *compression = PQgetvalue(res, i, attcompression_col); + + /* these strings are literal in our syntax, so not translated. */ + printTableAddCell(&cont, (compression[0] == 'p' ? "pglz" : + (compression[0] == 'l' ? "lz4" : + (compression[0] == '\0' ? "" : + "???"))), + false, false); + } + /* Statistics target, if the relkind supports this feature */ if (attstattarget_col >= 0) printTableAddCell(&cont, PQgetvalue(res, i, attstattarget_col), diff --git a/src/bin/psql/help.c b/src/bin/psql/help.c index daa5081eac..99a59470c5 100644 --- a/src/bin/psql/help.c +++ b/src/bin/psql/help.c @@ -372,6 +372,8 @@ helpVariables(unsigned short int pager) " true if last query failed, else false\n")); fprintf(output, _(" FETCH_COUNT\n" " the number of result rows to fetch and display at a time (0 = unlimited)\n")); + fprintf(output, _(" HIDE_TOAST_COMPRESSION\n" + " if set, compression methods are not displayed\n")); fprintf(output, _(" HIDE_TABLEAM\n" " if set, table access methods are not displayed\n")); fprintf(output, _(" HISTCONTROL\n" diff --git a/src/bin/psql/settings.h b/src/bin/psql/settings.h index d65990059d..83f2e6f254 100644 --- a/src/bin/psql/settings.h +++ b/src/bin/psql/settings.h @@ -134,6 +134,7 @@ typedef struct _psqlSettings bool quiet; bool singleline; bool singlestep; + bool hide_compression; bool hide_tableam; int fetch_count; int histsize; diff --git a/src/bin/psql/startup.c b/src/bin/psql/startup.c index 780479c8d7..110906a4e9 100644 --- a/src/bin/psql/startup.c +++ b/src/bin/psql/startup.c @@ -1159,6 +1159,13 @@ show_context_hook(const char *newval) return true; } +static bool +hide_compression_hook(const char *newval) +{ + return ParseVariableBool(newval, "HIDE_TOAST_COMPRESSION", + &pset.hide_compression); +} + static bool hide_tableam_hook(const char *newval) { @@ -1227,6 +1234,9 @@ EstablishVariableSpace(void) SetVariableHooks(pset.vars, "SHOW_CONTEXT", show_context_substitute_hook, show_context_hook); + SetVariableHooks(pset.vars, "HIDE_TOAST_COMPRESSION", + bool_substitute_hook, + hide_compression_hook); SetVariableHooks(pset.vars, "HIDE_TABLEAM", bool_substitute_hook, hide_tableam_hook); diff --git a/src/include/access/detoast.h b/src/include/access/detoast.h index 0adf53c77b..9a428aae2d 100644 --- a/src/include/access/detoast.h +++ b/src/include/access/detoast.h @@ -89,4 +89,12 @@ extern Size toast_raw_datum_size(Datum value); */ extern Size toast_datum_size(Datum value); +/* ---------- + * toast_get_compression_method - + * + * Return the compression method from the compressed value + * ---------- + */ +extern char toast_get_compression_method(struct varlena *attr); + #endif /* DETOAST_H */ diff --git a/src/include/access/toast_compression.h b/src/include/access/toast_compression.h new file mode 100644 index 0000000000..38800cb97a --- /dev/null +++ b/src/include/access/toast_compression.h @@ -0,0 +1,119 @@ +/*------------------------------------------------------------------------- + * + * toast_compression.h + * Functions for toast compression. + * + * Copyright (c) 2021, PostgreSQL Global Development Group + * + * src/include/access/toast_compression.h + * + *------------------------------------------------------------------------- + */ + +#ifndef TOAST_COMPRESSION_H +#define TOAST_COMPRESSION_H + +#include "postgres.h" + +/* + * Built-in compression methods. pg_attribute will store this in the + * attcompression column. + */ +#define PGLZ_COMPRESSION 'p' +#define LZ4_COMPRESSION 'l' + +#define InvalidCompressionMethod '\0' +#define CompressionMethodIsValid(cm) ((bool) ((cm) != InvalidCompressionMethod)) + +/* + * Built-in compression method-id. The toast compression header will store + * this in the first 2 bits of the raw length. These built-in compression + * method-id are directly mapped to the built-in compression methods. + */ +typedef enum CompressionId +{ + PGLZ_COMPRESSION_ID = 0, + LZ4_COMPRESSION_ID = 1 +} CompressionId; + +/* use default compression method if it is not specified. */ +#define DefaultCompressionMethod PGLZ_COMPRESSION +#define IsValidCompression(cm) ((cm) != InvalidCompressionMethod) + +#define IsStorageCompressible(storage) ((storage) != TYPSTORAGE_PLAIN && \ + (storage) != TYPSTORAGE_EXTERNAL) + +/* compression handler routines */ +typedef struct varlena *(*cmcompress_function) (const struct varlena *value); +typedef struct varlena *(*cmdecompress_function) (const struct varlena *value); +typedef struct varlena *(*cmdecompress_slice_function) + (const struct varlena *value, int32 slicelength); + +/* + * API struct for a compression routines. + * + * 'cmname' - name of the compression method + * 'datum_compress' - varlena compression function. + * 'datum_decompress' - varlena decompression function. + * 'datum_decompress_slice' - varlena slice decompression functions. + */ +typedef struct CompressionRoutine +{ + char cmname[64]; + cmcompress_function datum_compress; + cmdecompress_function datum_decompress; + cmdecompress_slice_function datum_decompress_slice; +} CompressionRoutine; + +extern char CompressionNameToMethod(char *compression); +extern const CompressionRoutine *GetCompressionRoutines(char method); + +/* + * CompressionMethodToId - Convert compression method to compression id. + * + * For more details refer comment atop CompressionId in toast_compression.h + */ +static inline CompressionId +CompressionMethodToId(char method) +{ + switch (method) + { + case PGLZ_COMPRESSION: + return PGLZ_COMPRESSION_ID; + case LZ4_COMPRESSION: + return LZ4_COMPRESSION_ID; + default: + elog(ERROR, "invalid compression method %c", method); + } +} + +/* + * CompressionIdToMethod - Convert compression id to compression method + * + * For more details refer comment atop CompressionId in toast_compression.h + */ +static inline Oid +CompressionIdToMethod(CompressionId cmid) +{ + switch (cmid) + { + case PGLZ_COMPRESSION_ID: + return PGLZ_COMPRESSION; + case LZ4_COMPRESSION_ID: + return LZ4_COMPRESSION; + default: + elog(ERROR, "invalid compression method id %d", cmid); + } +} + +/* + * GetCompressionMethodName - Get compression method name + */ +static inline const char* +GetCompressionMethodName(char method) +{ + return GetCompressionRoutines(method)->cmname; +} + + +#endif /* TOAST_COMPRESSION_H */ diff --git a/src/include/access/toast_helper.h b/src/include/access/toast_helper.h index a9a6d644bc..05104ce237 100644 --- a/src/include/access/toast_helper.h +++ b/src/include/access/toast_helper.h @@ -32,6 +32,7 @@ typedef struct struct varlena *tai_oldexternal; int32 tai_size; uint8 tai_colflags; + char tai_compression; } ToastAttrInfo; /* diff --git a/src/include/access/toast_internals.h b/src/include/access/toast_internals.h index cedfb890d8..284a15761a 100644 --- a/src/include/access/toast_internals.h +++ b/src/include/access/toast_internals.h @@ -12,6 +12,7 @@ #ifndef TOAST_INTERNALS_H #define TOAST_INTERNALS_H +#include "access/toast_compression.h" #include "storage/lockdefs.h" #include "utils/relcache.h" #include "utils/snapshot.h" @@ -22,22 +23,23 @@ typedef struct toast_compress_header { int32 vl_len_; /* varlena header (do not touch directly!) */ - int32 rawsize; + uint32 tcinfo; /* 2 bits for compression method and 30 bits + * rawsize */ } toast_compress_header; /* * Utilities for manipulation of header information for compressed * toast entries. */ -#define TOAST_COMPRESS_HDRSZ ((int32) sizeof(toast_compress_header)) -#define TOAST_COMPRESS_RAWSIZE(ptr) (((toast_compress_header *) (ptr))->rawsize) -#define TOAST_COMPRESS_SIZE(ptr) ((int32) VARSIZE_ANY(ptr) - TOAST_COMPRESS_HDRSZ) -#define TOAST_COMPRESS_RAWDATA(ptr) \ - (((char *) (ptr)) + TOAST_COMPRESS_HDRSZ) -#define TOAST_COMPRESS_SET_RAWSIZE(ptr, len) \ - (((toast_compress_header *) (ptr))->rawsize = (len)) +#define TOAST_COMPRESS_METHOD(ptr) (((toast_compress_header *) (ptr))->tcinfo >> VARLENA_RAWSIZE_BITS) +#define TOAST_COMPRESS_SET_SIZE_AND_METHOD(ptr, len, cm_method) \ + do { \ + Assert((len) > 0 && (len) <= VARLENA_RAWSIZE_MASK); \ + Assert((cm_method) >= PGLZ_COMPRESSION_ID && (cm_method) <= LZ4_COMPRESSION_ID); \ + ((toast_compress_header *) (ptr))->tcinfo = ((len) | (cm_method) << VARLENA_RAWSIZE_BITS); \ + } while (0) -extern Datum toast_compress_datum(Datum value); +extern Datum toast_compress_datum(Datum value, char cmethod); extern Oid toast_get_valid_index(Oid toastoid, LOCKMODE lock); extern void toast_delete_datum(Relation rel, Datum value, bool is_speculative); diff --git a/src/include/catalog/pg_attribute.h b/src/include/catalog/pg_attribute.h index 3db42abf08..560f8f00bb 100644 --- a/src/include/catalog/pg_attribute.h +++ b/src/include/catalog/pg_attribute.h @@ -160,6 +160,12 @@ CATALOG(pg_attribute,1249,AttributeRelationId) BKI_BOOTSTRAP BKI_ROWTYPE_OID(75, /* attribute's collation, if any */ Oid attcollation BKI_LOOKUP_OPT(pg_collation); + /* + * compression method. Must be InvalidCompressionMethod if and only if + * typstorage is 'plain' or 'external'. + */ + char attcompression BKI_DEFAULT('\0'); + #ifdef CATALOG_VARLEN /* variable-length fields start here */ /* NOTE: The following fields are not present in tuple descriptors. */ @@ -187,7 +193,7 @@ CATALOG(pg_attribute,1249,AttributeRelationId) BKI_BOOTSTRAP BKI_ROWTYPE_OID(75, * can access fields beyond attcollation except in a real tuple! */ #define ATTRIBUTE_FIXED_PART_SIZE \ - (offsetof(FormData_pg_attribute,attcollation) + sizeof(Oid)) + (offsetof(FormData_pg_attribute,attcompression) + sizeof(char)) /* ---------------- * Form_pg_attribute corresponds to a pointer to a tuple with diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index c7619f8cd3..91c1c5b720 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -7099,6 +7099,10 @@ descr => 'bytes required to store the value, perhaps with compression', proname => 'pg_column_size', provolatile => 's', prorettype => 'int4', proargtypes => 'any', prosrc => 'pg_column_size' }, +{ oid => '2121', + descr => 'compression method for the compressed datum', + proname => 'pg_column_compression', provolatile => 's', prorettype => 'text', + proargtypes => 'any', prosrc => 'pg_column_compression' }, { oid => '2322', descr => 'total disk space usage for the specified tablespace', proname => 'pg_tablespace_size', provolatile => 'v', prorettype => 'int8', diff --git a/src/include/nodes/parsenodes.h b/src/include/nodes/parsenodes.h index 236832a2ca..19d2ba26bf 100644 --- a/src/include/nodes/parsenodes.h +++ b/src/include/nodes/parsenodes.h @@ -646,6 +646,7 @@ typedef struct ColumnDef NodeTag type; char *colname; /* name of column */ TypeName *typeName; /* type of column */ + char *compression; /* compression method for column */ int inhcount; /* number of times column is inherited */ bool is_local; /* column has local (non-inherited) def'n */ bool is_not_null; /* NOT NULL constraint specified? */ @@ -685,6 +686,7 @@ typedef enum TableLikeOption CREATE_TABLE_LIKE_INDEXES = 1 << 5, CREATE_TABLE_LIKE_STATISTICS = 1 << 6, CREATE_TABLE_LIKE_STORAGE = 1 << 7, + CREATE_TABLE_LIKE_COMPRESSION = 1 << 8, CREATE_TABLE_LIKE_ALL = PG_INT32_MAX } TableLikeOption; diff --git a/src/include/parser/kwlist.h b/src/include/parser/kwlist.h index 28083aaac9..ca1f950cbe 100644 --- a/src/include/parser/kwlist.h +++ b/src/include/parser/kwlist.h @@ -88,6 +88,7 @@ PG_KEYWORD("comment", COMMENT, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("comments", COMMENTS, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("commit", COMMIT, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("committed", COMMITTED, UNRESERVED_KEYWORD, BARE_LABEL) +PG_KEYWORD("compression", COMPRESSION, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("concurrently", CONCURRENTLY, TYPE_FUNC_NAME_KEYWORD, BARE_LABEL) PG_KEYWORD("configuration", CONFIGURATION, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("conflict", CONFLICT, UNRESERVED_KEYWORD, BARE_LABEL) diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in index 7a7cc21d8d..6007d72a73 100644 --- a/src/include/pg_config.h.in +++ b/src/include/pg_config.h.in @@ -346,6 +346,9 @@ /* Define to 1 if you have the `z' library (-lz). */ #undef HAVE_LIBZ +/* Define to 1 if you have the `lz4' library (-llz4). */ +#undef HAVE_LIBLZ4 + /* Define to 1 if you have the `link' function. */ #undef HAVE_LINK diff --git a/src/include/postgres.h b/src/include/postgres.h index 2ed572004d..e98af05b30 100644 --- a/src/include/postgres.h +++ b/src/include/postgres.h @@ -145,7 +145,8 @@ typedef union struct /* Compressed-in-line format */ { uint32 va_header; - uint32 va_rawsize; /* Original data size (excludes header) */ + uint32 va_tcinfo; /* Original data size (excludes header) and + * compression method */ char va_data[FLEXIBLE_ARRAY_MEMBER]; /* Compressed data */ } va_compressed; } varattrib_4b; @@ -274,14 +275,23 @@ typedef struct (VARSIZE(PTR) - VARHDRSZ + VARHDRSZ_SHORT) #define VARHDRSZ_EXTERNAL offsetof(varattrib_1b_e, va_data) +#define VARHDRSZ_COMPRESS offsetof(varattrib_4b, va_compressed.va_data) #define VARDATA_4B(PTR) (((varattrib_4b *) (PTR))->va_4byte.va_data) #define VARDATA_4B_C(PTR) (((varattrib_4b *) (PTR))->va_compressed.va_data) #define VARDATA_1B(PTR) (((varattrib_1b *) (PTR))->va_data) #define VARDATA_1B_E(PTR) (((varattrib_1b_e *) (PTR))->va_data) +#define VARLENA_RAWSIZE_BITS 30 +#define VARLENA_RAWSIZE_MASK ((1U << VARLENA_RAWSIZE_BITS) - 1) + +/* + * va_tcinfo in va_compress contains raw size of datum and compression method. + */ #define VARRAWSIZE_4B_C(PTR) \ - (((varattrib_4b *) (PTR))->va_compressed.va_rawsize) + (((varattrib_4b *) (PTR))->va_compressed.va_tcinfo & VARLENA_RAWSIZE_MASK) +#define VARCOMPRESS_4B_C(PTR) \ + (((varattrib_4b *) (PTR))->va_compressed.va_tcinfo >> VARLENA_RAWSIZE_BITS) /* Externally visible macros */ diff --git a/src/test/regress/expected/compression.out b/src/test/regress/expected/compression.out new file mode 100644 index 0000000000..1de3ae2646 --- /dev/null +++ b/src/test/regress/expected/compression.out @@ -0,0 +1,247 @@ +\set HIDE_TOAST_COMPRESSION false +-- test creating table with compression method +CREATE TABLE cmdata(f1 text COMPRESSION pglz); +CREATE INDEX idx ON cmdata(f1); +INSERT INTO cmdata VALUES(repeat('1234567890',1000)); +\d+ cmdata + Table "public.cmdata" + Column | Type | Collation | Nullable | Default | Storage | Compression | Stats target | Description +--------+------+-----------+----------+---------+----------+-------------+--------------+------------- + f1 | text | | | | extended | pglz | | +Indexes: + "idx" btree (f1) + +CREATE TABLE cmdata1(f1 TEXT COMPRESSION lz4); +INSERT INTO cmdata1 VALUES(repeat('1234567890',1004)); +\d+ cmdata1 + Table "public.cmdata1" + Column | Type | Collation | Nullable | Default | Storage | Compression | Stats target | Description +--------+------+-----------+----------+---------+----------+-------------+--------------+------------- + f1 | text | | | | extended | lz4 | | + +-- try setting compression for incompressible data type +CREATE TABLE cmdata2 (f1 int COMPRESSION pglz); +ERROR: column data type integer does not support compression +-- verify stored compression method +SELECT pg_column_compression(f1) FROM cmdata; + pg_column_compression +----------------------- + pglz +(1 row) + +SELECT pg_column_compression(f1) FROM cmdata1; + pg_column_compression +----------------------- + lz4 +(1 row) + +-- decompress data slice +SELECT SUBSTR(f1, 200, 5) FROM cmdata; + substr +-------- + 01234 +(1 row) + +SELECT SUBSTR(f1, 2000, 50) FROM cmdata1; + substr +---------------------------------------------------- + 01234567890123456789012345678901234567890123456789 +(1 row) + +-- copy with table creation +SELECT * INTO cmmove1 FROM cmdata; +SELECT pg_column_compression(f1) FROM cmmove1; + pg_column_compression +----------------------- + pglz +(1 row) + +-- update using datum from different table +CREATE TABLE cmmove2(f1 text COMPRESSION pglz); +INSERT INTO cmmove2 VALUES (repeat('1234567890',1004)); +SELECT pg_column_compression(f1) FROM cmmove2; + pg_column_compression +----------------------- + pglz +(1 row) + +UPDATE cmmove2 SET f1 = cmdata.f1 FROM cmdata; +SELECT pg_column_compression(f1) FROM cmmove2; + pg_column_compression +----------------------- + pglz +(1 row) + +UPDATE cmmove2 SET f1 = cmdata1.f1 FROM cmdata1; +SELECT pg_column_compression(f1) FROM cmmove2; + pg_column_compression +----------------------- + lz4 +(1 row) + +-- copy to existing table +CREATE TABLE cmmove3(f1 text COMPRESSION pglz); +INSERT INTO cmmove3 SELECT * FROM cmdata; +INSERT INTO cmmove3 SELECT * FROM cmdata1; +SELECT pg_column_compression(f1) FROM cmmove2; + pg_column_compression +----------------------- + lz4 +(1 row) + +-- test external compressed data +CREATE OR REPLACE FUNCTION large_val() RETURNS TEXT LANGUAGE SQL AS +'select array_agg(md5(g::text))::text from generate_series(1, 256) g'; +CREATE TABLE cmdata2 (f1 text COMPRESSION pglz); +INSERT INTO cmdata2 select large_val() || repeat('a', 4000); +SELECT pg_column_compression(f1) FROM cmdata2; + pg_column_compression +----------------------- + pglz +(1 row) + +INSERT INTO cmdata1 SELECT * FROM cmdata2; +SELECT pg_column_compression(f1) FROM cmdata1; + pg_column_compression +----------------------- + lz4 + pglz +(2 rows) + +DROP TABLE cmdata2; +-- test LIKE INCLUDING COMPRESSION +CREATE TABLE cmdata2 (LIKE cmdata1 INCLUDING COMPRESSION); +\d+ cmdata2 + Table "public.cmdata2" + Column | Type | Collation | Nullable | Default | Storage | Compression | Stats target | Description +--------+------+-----------+----------+---------+----------+-------------+--------------+------------- + f1 | text | | | | extended | lz4 | | + +DROP TABLE cmdata2; +--test column type update varlena/non-varlena +CREATE TABLE cmdata2 (f1 int); +\d+ cmdata2 + Table "public.cmdata2" + Column | Type | Collation | Nullable | Default | Storage | Compression | Stats target | Description +--------+---------+-----------+----------+---------+---------+-------------+--------------+------------- + f1 | integer | | | | plain | | | + +ALTER TABLE cmdata2 ALTER COLUMN f1 TYPE varchar; +\d+ cmdata2 + Table "public.cmdata2" + Column | Type | Collation | Nullable | Default | Storage | Compression | Stats target | Description +--------+-------------------+-----------+----------+---------+----------+-------------+--------------+------------- + f1 | character varying | | | | extended | pglz | | + +ALTER TABLE cmdata2 ALTER COLUMN f1 TYPE int USING f1::integer; +\d+ cmdata2 + Table "public.cmdata2" + Column | Type | Collation | Nullable | Default | Storage | Compression | Stats target | Description +--------+---------+-----------+----------+---------+---------+-------------+--------------+------------- + f1 | integer | | | | plain | | | + +--changing column storage should not impact the compression method +--but the data should not be compressed +ALTER TABLE cmdata2 ALTER COLUMN f1 TYPE varchar; +\d+ cmdata2 + Table "public.cmdata2" + Column | Type | Collation | Nullable | Default | Storage | Compression | Stats target | Description +--------+-------------------+-----------+----------+---------+----------+-------------+--------------+------------- + f1 | character varying | | | | extended | pglz | | + +ALTER TABLE cmdata2 ALTER COLUMN f1 SET STORAGE plain; +\d+ cmdata2 + Table "public.cmdata2" + Column | Type | Collation | Nullable | Default | Storage | Compression | Stats target | Description +--------+-------------------+-----------+----------+---------+---------+-------------+--------------+------------- + f1 | character varying | | | | plain | pglz | | + +INSERT INTO cmdata2 VALUES (repeat('123456789', 800)); +SELECT pg_column_compression(f1) FROM cmdata2; + pg_column_compression +----------------------- + +(1 row) + +-- test compression with materialized view +CREATE MATERIALIZED VIEW mv(x) AS SELECT * FROM cmdata1; +\d+ mv + Materialized view "public.mv" + Column | Type | Collation | Nullable | Default | Storage | Compression | Stats target | Description +--------+------+-----------+----------+---------+----------+-------------+--------------+------------- + x | text | | | | extended | pglz | | +View definition: + SELECT cmdata1.f1 AS x + FROM cmdata1; + +SELECT pg_column_compression(f1) FROM cmdata1; + pg_column_compression +----------------------- + lz4 + pglz +(2 rows) + +SELECT pg_column_compression(x) FROM mv; + pg_column_compression +----------------------- + lz4 + pglz +(2 rows) + +-- test compression with partition +CREATE TABLE cmpart(f1 text COMPRESSION lz4) PARTITION BY HASH(f1); +CREATE TABLE cmpart1 PARTITION OF cmpart FOR VALUES WITH (MODULUS 2, REMAINDER 0); +CREATE TABLE cmpart2(f1 text COMPRESSION pglz); +ALTER TABLE cmpart ATTACH PARTITION cmpart2 FOR VALUES WITH (MODULUS 2, REMAINDER 1); +INSERT INTO cmpart VALUES (repeat('123456789',1004)); +INSERT INTO cmpart VALUES (repeat('123456789',4004)); +SELECT pg_column_compression(f1) FROM cmpart; + pg_column_compression +----------------------- + lz4 + pglz +(2 rows) + +-- test compression with inheritence, error +CREATE TABLE cminh() INHERITS(cmdata, cmdata1); +NOTICE: merging multiple inherited definitions of column "f1" +ERROR: column "f1" has a compression method conflict +DETAIL: pglz versus lz4 +CREATE TABLE cminh(f1 TEXT COMPRESSION lz4) INHERITS(cmdata); +NOTICE: merging column "f1" with inherited definition +ERROR: column "f1" has a compression method conflict +DETAIL: pglz versus lz4 +-- check data is ok +SELECT length(f1) FROM cmdata; + length +-------- + 10000 +(1 row) + +SELECT length(f1) FROM cmdata1; + length +-------- + 10040 + 12449 +(2 rows) + +SELECT length(f1) FROM cmmove1; + length +-------- + 10000 +(1 row) + +SELECT length(f1) FROM cmmove2; + length +-------- + 10040 +(1 row) + +SELECT length(f1) FROM cmmove3; + length +-------- + 10000 + 10040 +(2 rows) + +\set HIDE_TOAST_COMPRESSION true diff --git a/src/test/regress/expected/compression_1.out b/src/test/regress/expected/compression_1.out new file mode 100644 index 0000000000..2999b3bb79 --- /dev/null +++ b/src/test/regress/expected/compression_1.out @@ -0,0 +1,240 @@ +\set HIDE_TOAST_COMPRESSION false +-- test creating table with compression method +CREATE TABLE cmdata(f1 text COMPRESSION pglz); +CREATE INDEX idx ON cmdata(f1); +INSERT INTO cmdata VALUES(repeat('1234567890',1000)); +\d+ cmdata + Table "public.cmdata" + Column | Type | Collation | Nullable | Default | Storage | Compression | Stats target | Description +--------+------+-----------+----------+---------+----------+-------------+--------------+------------- + f1 | text | | | | extended | pglz | | +Indexes: + "idx" btree (f1) + +CREATE TABLE cmdata1(f1 TEXT COMPRESSION lz4); +ERROR: unsupported LZ4 compression method +DETAIL: This functionality requires the server to be built with lz4 support. +HINT: You need to rebuild PostgreSQL using --with-lz4. +INSERT INTO cmdata1 VALUES(repeat('1234567890',1004)); +ERROR: relation "cmdata1" does not exist +LINE 1: INSERT INTO cmdata1 VALUES(repeat('1234567890',1004)); + ^ +\d+ cmdata1 +-- try setting compression for incompressible data type +CREATE TABLE cmdata2 (f1 int COMPRESSION pglz); +ERROR: column data type integer does not support compression +-- verify stored compression method +SELECT pg_column_compression(f1) FROM cmdata; + pg_column_compression +----------------------- + pglz +(1 row) + +SELECT pg_column_compression(f1) FROM cmdata1; +ERROR: relation "cmdata1" does not exist +LINE 1: SELECT pg_column_compression(f1) FROM cmdata1; + ^ +-- decompress data slice +SELECT SUBSTR(f1, 200, 5) FROM cmdata; + substr +-------- + 01234 +(1 row) + +SELECT SUBSTR(f1, 2000, 50) FROM cmdata1; +ERROR: relation "cmdata1" does not exist +LINE 1: SELECT SUBSTR(f1, 2000, 50) FROM cmdata1; + ^ +-- copy with table creation +SELECT * INTO cmmove1 FROM cmdata; +SELECT pg_column_compression(f1) FROM cmmove1; + pg_column_compression +----------------------- + pglz +(1 row) + +-- update using datum from different table +CREATE TABLE cmmove2(f1 text COMPRESSION pglz); +INSERT INTO cmmove2 VALUES (repeat('1234567890',1004)); +SELECT pg_column_compression(f1) FROM cmmove2; + pg_column_compression +----------------------- + pglz +(1 row) + +UPDATE cmmove2 SET f1 = cmdata.f1 FROM cmdata; +SELECT pg_column_compression(f1) FROM cmmove2; + pg_column_compression +----------------------- + pglz +(1 row) + +UPDATE cmmove2 SET f1 = cmdata1.f1 FROM cmdata1; +ERROR: relation "cmdata1" does not exist +LINE 1: UPDATE cmmove2 SET f1 = cmdata1.f1 FROM cmdata1; + ^ +SELECT pg_column_compression(f1) FROM cmmove2; + pg_column_compression +----------------------- + pglz +(1 row) + +-- copy to existing table +CREATE TABLE cmmove3(f1 text COMPRESSION pglz); +INSERT INTO cmmove3 SELECT * FROM cmdata; +INSERT INTO cmmove3 SELECT * FROM cmdata1; +ERROR: relation "cmdata1" does not exist +LINE 1: INSERT INTO cmmove3 SELECT * FROM cmdata1; + ^ +SELECT pg_column_compression(f1) FROM cmmove2; + pg_column_compression +----------------------- + pglz +(1 row) + +-- test external compressed data +CREATE OR REPLACE FUNCTION large_val() RETURNS TEXT LANGUAGE SQL AS +'select array_agg(md5(g::text))::text from generate_series(1, 256) g'; +CREATE TABLE cmdata2 (f1 text COMPRESSION pglz); +INSERT INTO cmdata2 select large_val() || repeat('a', 4000); +SELECT pg_column_compression(f1) FROM cmdata2; + pg_column_compression +----------------------- + pglz +(1 row) + +INSERT INTO cmdata1 SELECT * FROM cmdata2; +ERROR: relation "cmdata1" does not exist +LINE 1: INSERT INTO cmdata1 SELECT * FROM cmdata2; + ^ +SELECT pg_column_compression(f1) FROM cmdata1; +ERROR: relation "cmdata1" does not exist +LINE 1: SELECT pg_column_compression(f1) FROM cmdata1; + ^ +DROP TABLE cmdata2; +-- test LIKE INCLUDING COMPRESSION +CREATE TABLE cmdata2 (LIKE cmdata1 INCLUDING COMPRESSION); +ERROR: relation "cmdata1" does not exist +LINE 1: CREATE TABLE cmdata2 (LIKE cmdata1 INCLUDING COMPRESSION); + ^ +\d+ cmdata2 +DROP TABLE cmdata2; +ERROR: table "cmdata2" does not exist +--test column type update varlena/non-varlena +CREATE TABLE cmdata2 (f1 int); +\d+ cmdata2 + Table "public.cmdata2" + Column | Type | Collation | Nullable | Default | Storage | Compression | Stats target | Description +--------+---------+-----------+----------+---------+---------+-------------+--------------+------------- + f1 | integer | | | | plain | | | + +ALTER TABLE cmdata2 ALTER COLUMN f1 TYPE varchar; +\d+ cmdata2 + Table "public.cmdata2" + Column | Type | Collation | Nullable | Default | Storage | Compression | Stats target | Description +--------+-------------------+-----------+----------+---------+----------+-------------+--------------+------------- + f1 | character varying | | | | extended | pglz | | + +ALTER TABLE cmdata2 ALTER COLUMN f1 TYPE int USING f1::integer; +\d+ cmdata2 + Table "public.cmdata2" + Column | Type | Collation | Nullable | Default | Storage | Compression | Stats target | Description +--------+---------+-----------+----------+---------+---------+-------------+--------------+------------- + f1 | integer | | | | plain | | | + +--changing column storage should not impact the compression method +--but the data should not be compressed +ALTER TABLE cmdata2 ALTER COLUMN f1 TYPE varchar; +\d+ cmdata2 + Table "public.cmdata2" + Column | Type | Collation | Nullable | Default | Storage | Compression | Stats target | Description +--------+-------------------+-----------+----------+---------+----------+-------------+--------------+------------- + f1 | character varying | | | | extended | pglz | | + +ALTER TABLE cmdata2 ALTER COLUMN f1 SET STORAGE plain; +\d+ cmdata2 + Table "public.cmdata2" + Column | Type | Collation | Nullable | Default | Storage | Compression | Stats target | Description +--------+-------------------+-----------+----------+---------+---------+-------------+--------------+------------- + f1 | character varying | | | | plain | pglz | | + +INSERT INTO cmdata2 VALUES (repeat('123456789', 800)); +SELECT pg_column_compression(f1) FROM cmdata2; + pg_column_compression +----------------------- + +(1 row) + +-- test compression with materialized view +CREATE MATERIALIZED VIEW mv(x) AS SELECT * FROM cmdata1; +ERROR: relation "cmdata1" does not exist +LINE 1: CREATE MATERIALIZED VIEW mv(x) AS SELECT * FROM cmdata1; + ^ +\d+ mv +SELECT pg_column_compression(f1) FROM cmdata1; +ERROR: relation "cmdata1" does not exist +LINE 1: SELECT pg_column_compression(f1) FROM cmdata1; + ^ +SELECT pg_column_compression(x) FROM mv; +ERROR: relation "mv" does not exist +LINE 1: SELECT pg_column_compression(x) FROM mv; + ^ +-- test compression with partition +CREATE TABLE cmpart(f1 text COMPRESSION lz4) PARTITION BY HASH(f1); +ERROR: unsupported LZ4 compression method +DETAIL: This functionality requires the server to be built with lz4 support. +HINT: You need to rebuild PostgreSQL using --with-lz4. +CREATE TABLE cmpart1 PARTITION OF cmpart FOR VALUES WITH (MODULUS 2, REMAINDER 0); +ERROR: relation "cmpart" does not exist +CREATE TABLE cmpart2(f1 text COMPRESSION pglz); +ALTER TABLE cmpart ATTACH PARTITION cmpart2 FOR VALUES WITH (MODULUS 2, REMAINDER 1); +ERROR: relation "cmpart" does not exist +INSERT INTO cmpart VALUES (repeat('123456789',1004)); +ERROR: relation "cmpart" does not exist +LINE 1: INSERT INTO cmpart VALUES (repeat('123456789',1004)); + ^ +INSERT INTO cmpart VALUES (repeat('123456789',4004)); +ERROR: relation "cmpart" does not exist +LINE 1: INSERT INTO cmpart VALUES (repeat('123456789',4004)); + ^ +SELECT pg_column_compression(f1) FROM cmpart; +ERROR: relation "cmpart" does not exist +LINE 1: SELECT pg_column_compression(f1) FROM cmpart; + ^ +-- test compression with inheritence, error +CREATE TABLE cminh() INHERITS(cmdata, cmdata1); +ERROR: relation "cmdata1" does not exist +CREATE TABLE cminh(f1 TEXT COMPRESSION lz4) INHERITS(cmdata); +NOTICE: merging column "f1" with inherited definition +ERROR: column "f1" has a compression method conflict +DETAIL: pglz versus lz4 +-- check data is ok +SELECT length(f1) FROM cmdata; + length +-------- + 10000 +(1 row) + +SELECT length(f1) FROM cmdata1; +ERROR: relation "cmdata1" does not exist +LINE 1: SELECT length(f1) FROM cmdata1; + ^ +SELECT length(f1) FROM cmmove1; + length +-------- + 10000 +(1 row) + +SELECT length(f1) FROM cmmove2; + length +-------- + 10000 +(1 row) + +SELECT length(f1) FROM cmmove3; + length +-------- + 10000 +(1 row) + +\set HIDE_TOAST_COMPRESSION true diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e280198b17..70c38309d7 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -115,7 +115,7 @@ test: plancache limit plpgsql copy2 temp domain rangefuncs prepare conversion tr # ---------- # Another group of parallel tests # ---------- -test: partition_join partition_prune reloptions hash_part indexing partition_aggregate partition_info tuplesort explain +test: partition_join partition_prune reloptions hash_part indexing partition_aggregate partition_info tuplesort explain compression # event triggers cannot run concurrently with any test that runs DDL # oidjoins is read-only, though, and should run late for best coverage diff --git a/src/test/regress/pg_regress_main.c b/src/test/regress/pg_regress_main.c index 8dc4941c24..1524676f3b 100644 --- a/src/test/regress/pg_regress_main.c +++ b/src/test/regress/pg_regress_main.c @@ -78,11 +78,11 @@ psql_start_test(const char *testname, * against different AMs without unnecessary differences. */ offset += snprintf(psql_cmd + offset, sizeof(psql_cmd) - offset, - "\"%s%spsql\" -X -a -q -d \"%s\" -v %s < \"%s\" > \"%s\" 2>&1", + "\"%s%spsql\" -X -a -q -d \"%s\" %s < \"%s\" > \"%s\" 2>&1", bindir ? bindir : "", bindir ? "/" : "", dblist->str, - "HIDE_TABLEAM=\"on\"", + "-v HIDE_TABLEAM=on -v HIDE_TOAST_COMPRESSION=on", infile, outfile); if (offset >= sizeof(psql_cmd)) diff --git a/src/test/regress/serial_schedule b/src/test/regress/serial_schedule index 6a57e889a1..d81d04136c 100644 --- a/src/test/regress/serial_schedule +++ b/src/test/regress/serial_schedule @@ -201,6 +201,7 @@ test: partition_aggregate test: partition_info test: tuplesort test: explain +test: compression test: event_trigger test: oidjoins test: fast_default diff --git a/src/test/regress/sql/compression.sql b/src/test/regress/sql/compression.sql new file mode 100644 index 0000000000..ab35f3b4ae --- /dev/null +++ b/src/test/regress/sql/compression.sql @@ -0,0 +1,102 @@ +\set HIDE_TOAST_COMPRESSION false +-- test creating table with compression method +CREATE TABLE cmdata(f1 text COMPRESSION pglz); +CREATE INDEX idx ON cmdata(f1); +INSERT INTO cmdata VALUES(repeat('1234567890',1000)); +\d+ cmdata + +CREATE TABLE cmdata1(f1 TEXT COMPRESSION lz4); +INSERT INTO cmdata1 VALUES(repeat('1234567890',1004)); +\d+ cmdata1 + +-- try setting compression for incompressible data type +CREATE TABLE cmdata2 (f1 int COMPRESSION pglz); + +-- verify stored compression method +SELECT pg_column_compression(f1) FROM cmdata; +SELECT pg_column_compression(f1) FROM cmdata1; + +-- decompress data slice +SELECT SUBSTR(f1, 200, 5) FROM cmdata; +SELECT SUBSTR(f1, 2000, 50) FROM cmdata1; + +-- copy with table creation +SELECT * INTO cmmove1 FROM cmdata; +SELECT pg_column_compression(f1) FROM cmmove1; + +-- update using datum from different table +CREATE TABLE cmmove2(f1 text COMPRESSION pglz); +INSERT INTO cmmove2 VALUES (repeat('1234567890',1004)); +SELECT pg_column_compression(f1) FROM cmmove2; + +UPDATE cmmove2 SET f1 = cmdata.f1 FROM cmdata; +SELECT pg_column_compression(f1) FROM cmmove2; +UPDATE cmmove2 SET f1 = cmdata1.f1 FROM cmdata1; +SELECT pg_column_compression(f1) FROM cmmove2; + +-- copy to existing table +CREATE TABLE cmmove3(f1 text COMPRESSION pglz); +INSERT INTO cmmove3 SELECT * FROM cmdata; +INSERT INTO cmmove3 SELECT * FROM cmdata1; +SELECT pg_column_compression(f1) FROM cmmove2; + +-- test external compressed data +CREATE OR REPLACE FUNCTION large_val() RETURNS TEXT LANGUAGE SQL AS +'select array_agg(md5(g::text))::text from generate_series(1, 256) g'; +CREATE TABLE cmdata2 (f1 text COMPRESSION pglz); +INSERT INTO cmdata2 select large_val() || repeat('a', 4000); +SELECT pg_column_compression(f1) FROM cmdata2; +INSERT INTO cmdata1 SELECT * FROM cmdata2; +SELECT pg_column_compression(f1) FROM cmdata1; +DROP TABLE cmdata2; + +-- test LIKE INCLUDING COMPRESSION +CREATE TABLE cmdata2 (LIKE cmdata1 INCLUDING COMPRESSION); +\d+ cmdata2 +DROP TABLE cmdata2; + +--test column type update varlena/non-varlena +CREATE TABLE cmdata2 (f1 int); +\d+ cmdata2 +ALTER TABLE cmdata2 ALTER COLUMN f1 TYPE varchar; +\d+ cmdata2 +ALTER TABLE cmdata2 ALTER COLUMN f1 TYPE int USING f1::integer; +\d+ cmdata2 + +--changing column storage should not impact the compression method +--but the data should not be compressed +ALTER TABLE cmdata2 ALTER COLUMN f1 TYPE varchar; +\d+ cmdata2 +ALTER TABLE cmdata2 ALTER COLUMN f1 SET STORAGE plain; +\d+ cmdata2 +INSERT INTO cmdata2 VALUES (repeat('123456789', 800)); +SELECT pg_column_compression(f1) FROM cmdata2; + +-- test compression with materialized view +CREATE MATERIALIZED VIEW mv(x) AS SELECT * FROM cmdata1; +\d+ mv +SELECT pg_column_compression(f1) FROM cmdata1; +SELECT pg_column_compression(x) FROM mv; + +-- test compression with partition +CREATE TABLE cmpart(f1 text COMPRESSION lz4) PARTITION BY HASH(f1); +CREATE TABLE cmpart1 PARTITION OF cmpart FOR VALUES WITH (MODULUS 2, REMAINDER 0); +CREATE TABLE cmpart2(f1 text COMPRESSION pglz); + +ALTER TABLE cmpart ATTACH PARTITION cmpart2 FOR VALUES WITH (MODULUS 2, REMAINDER 1); +INSERT INTO cmpart VALUES (repeat('123456789',1004)); +INSERT INTO cmpart VALUES (repeat('123456789',4004)); +SELECT pg_column_compression(f1) FROM cmpart; + +-- test compression with inheritence, error +CREATE TABLE cminh() INHERITS(cmdata, cmdata1); +CREATE TABLE cminh(f1 TEXT COMPRESSION lz4) INHERITS(cmdata); + +-- check data is ok +SELECT length(f1) FROM cmdata; +SELECT length(f1) FROM cmdata1; +SELECT length(f1) FROM cmmove1; +SELECT length(f1) FROM cmmove2; +SELECT length(f1) FROM cmmove3; + +\set HIDE_TOAST_COMPRESSION true diff --git a/src/tools/msvc/Solution.pm b/src/tools/msvc/Solution.pm index a4f5cc4bdb..5f39a92111 100644 --- a/src/tools/msvc/Solution.pm +++ b/src/tools/msvc/Solution.pm @@ -307,6 +307,7 @@ sub GenerateFiles HAVE_LIBXML2 => undef, HAVE_LIBXSLT => undef, HAVE_LIBZ => $self->{options}->{zlib} ? 1 : undef, + HAVE_LIBLZ4 => undef, HAVE_LINK => undef, HAVE_LOCALE_T => 1, HAVE_LONG_INT_64 => undef, diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 574a8a94fa..e6cb35a16f 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -395,6 +395,7 @@ CompositeIOData CompositeTypeStmt CompoundAffixFlag CompressionAlgorithm +CompressionRoutine CompressorState ComputeXidHorizonsResult ConditionVariable -- 2.17.0 --nHwqXXcoX0o6fKCv Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="0002-f-use-pkgconfig.patch" ^ permalink raw reply [nested|flat] 2+ messages in thread
* [PATCH 1/6] Add REPACK command @ 2026-01-12 16:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 2+ messages in thread From: Antonin Houska @ 2026-01-12 16:30 UTC (permalink / raw) REPACK absorbs the functionality of VACUUM FULL and CLUSTER in a single command. Because this functionality is completely different from regular VACUUM, having it separate from VACUUM makes it easier for users to understand; as for CLUSTER, the term is heavily overloaded in the IT world and even in Postgres itself, so it's good that we can avoid it. This also adds pg_repackdb, a new utility that can invoke the new commands. This is heavily based on vacuumdb. Author: Antonin Houska <[email protected]> Co-authored-by: =C3=81lvaro Herrera <[email protected]> Reviewed-by: Mihail Nikalayeu <[email protected]> Reviewed-by: Robert Treat <[email protected]> Reviewed-by: Euler Taveira <[email protected]> Reviewed-by: Matheus Alcantara <[email protected]> Reviewed-by: Junwang Zhao <[email protected]> Reviewed-by: jian he <[email protected]> Discussion: https://postgr.es/m/82651.1720540558@antos Discussion: https://postgr.es/m/[email protected] --- doc/src/sgml/monitoring.sgml | 223 +++++- doc/src/sgml/ref/allfiles.sgml | 2 + doc/src/sgml/ref/cluster.sgml | 97 +-- doc/src/sgml/ref/clusterdb.sgml | 5 + doc/src/sgml/ref/pg_repackdb.sgml | 488 +++++++++++++ doc/src/sgml/ref/repack.sgml | 328 +++++++++ doc/src/sgml/ref/vacuum.sgml | 33 +- doc/src/sgml/reference.sgml | 2 + src/backend/access/heap/heapam_handler.c | 32 +- src/backend/catalog/index.c | 2 +- src/backend/catalog/system_views.sql | 29 +- src/backend/commands/cluster.c | 842 +++++++++++++++-------- src/backend/commands/vacuum.c | 6 +- src/backend/parser/gram.y | 86 ++- src/backend/tcop/utility.c | 23 +- src/backend/utils/adt/pgstatfuncs.c | 4 +- src/bin/psql/tab-complete.in.c | 42 +- src/bin/scripts/Makefile | 3 + src/bin/scripts/meson.build | 2 + src/bin/scripts/pg_repackdb.c | 240 +++++++ src/bin/scripts/t/103_repackdb.pl | 47 ++ src/bin/scripts/vacuuming.c | 102 ++- src/bin/scripts/vacuuming.h | 3 + src/include/commands/cluster.h | 8 +- src/include/commands/progress.h | 50 +- src/include/nodes/parsenodes.h | 35 +- src/include/parser/kwlist.h | 1 + src/include/tcop/cmdtaglist.h | 1 + src/include/utils/backend_progress.h | 2 +- src/test/regress/expected/cluster.out | 134 +++- src/test/regress/expected/rules.out | 72 +- src/test/regress/sql/cluster.sql | 70 +- src/tools/pgindent/typedefs.list | 2 + 33 files changed, 2480 insertions(+), 536 deletions(-) create mode 100644 doc/src/sgml/ref/pg_repackdb.sgml create mode 100644 doc/src/sgml/ref/repack.sgml create mode 100644 src/bin/scripts/pg_repackdb.c create mode 100644 src/bin/scripts/t/103_repackdb.pl diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 817fd9f4ca7..b07fe3294cd 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -405,6 +405,14 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss = 11:34 0:00 postgres: ser </entry> </row> =20 + <row> + <entry><structname>pg_stat_progress_repack</structname><indexterm><p= rimary>pg_stat_progress_repack</primary></indexterm></entry> + <entry>One row for each backend running + <command>REPACK</command>, showing current progress. See + <xref linkend=3D"repack-progress-reporting"/>. + </entry> + </row> + <row> <entry><structname>pg_stat_progress_basebackup</structname><indexter= m><primary>pg_stat_progress_basebackup</primary></indexterm></entry> <entry>One row for each WAL sender process streaming a base backup, @@ -5609,7 +5617,8 @@ FROM pg_stat_get_backend_idset() AS backendid; certain commands during command execution. Currently, the only commands which support progress reporting are <command>ANALYZE</command>, <command>CLUSTER</command>, - <command>CREATE INDEX</command>, <command>VACUUM</command>, + <command>CREATE INDEX</command>, <command>REPACK</command>, + <command>VACUUM</command>, <command>COPY</command>, and <xref linkend=3D"protocol-replication-base-backup"/> (i.e., replica= tion command that <xref linkend=3D"app-pgbasebackup"/> issues to take @@ -6093,6 +6102,218 @@ FROM pg_stat_get_backend_idset() AS backendid; </table> </sect2> =20 + <sect2 id=3D"repack-progress-reporting"> + <title>REPACK Progress Reporting</title> + + <indexterm> + <primary>pg_stat_progress_repack</primary> + </indexterm> + + <para> + Whenever <command>REPACK</command> is running, + the <structname>pg_stat_progress_repack</structname> view will contain a + row for each backend that is currently running the command. The tables + below describe the information that will be reported and provide + information about how to interpret it. + </para> + + <table id=3D"pg-stat-progress-repack-view" xreflabel=3D"pg_stat_progress= _repack"> + <title><structname>pg_stat_progress_repack</structname> View</title> + <tgroup cols=3D"1"> + <thead> + <row> + <entry role=3D"catalog_table_entry"><para role=3D"column_definition"> + Column Type + </para> + <para> + Description + </para></entry> + </row> + </thead> + + <tbody> + <row> + <entry role=3D"catalog_table_entry"><para role=3D"column_definition"> + <structfield>pid</structfield> <type>integer</type> + </para> + <para> + Process ID of backend. + </para></entry> + </row> + + <row> + <entry role=3D"catalog_table_entry"><para role=3D"column_definition"> + <structfield>datid</structfield> <type>oid</type> + </para> + <para> + OID of the database to which this backend is connected. + </para></entry> + </row> + + <row> + <entry role=3D"catalog_table_entry"><para role=3D"column_definition"> + <structfield>datname</structfield> <type>name</type> + </para> + <para> + Name of the database to which this backend is connected. + </para></entry> + </row> + + <row> + <entry role=3D"catalog_table_entry"><para role=3D"column_definition"> + <structfield>relid</structfield> <type>oid</type> + </para> + <para> + OID of the table being repacked. + </para></entry> + </row> + + <row> + <entry role=3D"catalog_table_entry"><para role=3D"column_definition"> + <structfield>phase</structfield> <type>text</type> + </para> + <para> + Current processing phase. See <xref linkend=3D"repack-phases"/>. + </para></entry> + </row> + + <row> + <entry role=3D"catalog_table_entry"><para role=3D"column_definition"> + <structfield>repack_index_relid</structfield> <type>oid</type> + </para> + <para> + If the table is being scanned using an index, this is the OID of the + index being used; otherwise, it is zero. + </para></entry> + </row> + + <row> + <entry role=3D"catalog_table_entry"><para role=3D"column_definition"> + <structfield>heap_tuples_scanned</structfield> <type>bigint</type> + </para> + <para> + Number of heap tuples scanned. + This counter only advances when the phase is + <literal>seq scanning heap</literal>, + <literal>index scanning heap</literal> + or <literal>writing new heap</literal>. + </para></entry> + </row> + + <row> + <entry role=3D"catalog_table_entry"><para role=3D"column_definition"> + <structfield>heap_tuples_written</structfield> <type>bigint</type> + </para> + <para> + Number of heap tuples written. + This counter only advances when the phase is + <literal>seq scanning heap</literal>, + <literal>index scanning heap</literal> + or <literal>writing new heap</literal>. + </para></entry> + </row> + + <row> + <entry role=3D"catalog_table_entry"><para role=3D"column_definition"> + <structfield>heap_blks_total</structfield> <type>bigint</type> + </para> + <para> + Total number of heap blocks in the table. This number is reported + as of the beginning of <literal>seq scanning heap</literal>. + </para></entry> + </row> + + <row> + <entry role=3D"catalog_table_entry"><para role=3D"column_definition"> + <structfield>heap_blks_scanned</structfield> <type>bigint</type> + </para> + <para> + Number of heap blocks scanned. This counter only advances when the + phase is <literal>seq scanning heap</literal>. + </para></entry> + </row> + + <row> + <entry role=3D"catalog_table_entry"><para role=3D"column_definition"> + <structfield>index_rebuild_count</structfield> <type>bigint</type> + </para> + <para> + Number of indexes rebuilt. This counter only advances when the pha= se + is <literal>rebuilding index</literal>. + </para></entry> + </row> + </tbody> + </tgroup> + </table> + + <table id=3D"repack-phases"> + <title>REPACK Phases</title> + <tgroup cols=3D"2"> + <colspec colname=3D"col1" colwidth=3D"1*"/> + <colspec colname=3D"col2" colwidth=3D"2*"/> + <thead> + <row> + <entry>Phase</entry> + <entry>Description</entry> + </row> + </thead> + + <tbody> + <row> + <entry><literal>initializing</literal></entry> + <entry> + The command is preparing to begin scanning the heap. This phase is + expected to be very brief. + </entry> + </row> + <row> + <entry><literal>seq scanning heap</literal></entry> + <entry> + The command is currently scanning the table using a sequential scan. + </entry> + </row> + <row> + <entry><literal>index scanning heap</literal></entry> + <entry> + <command>REPACK</command> is currently scanning the table using an = index scan. + </entry> + </row> + <row> + <entry><literal>sorting tuples</literal></entry> + <entry> + <command>REPACK</command> is currently sorting tuples. + </entry> + </row> + <row> + <entry><literal>writing new heap</literal></entry> + <entry> + <command>REPACK</command> is currently writing the new heap. + </entry> + </row> + <row> + <entry><literal>swapping relation files</literal></entry> + <entry> + The command is currently swapping newly-built files into place. + </entry> + </row> + <row> + <entry><literal>rebuilding index</literal></entry> + <entry> + The command is currently rebuilding an index. + </entry> + </row> + <row> + <entry><literal>performing final cleanup</literal></entry> + <entry> + The command is performing final cleanup. When this phase is + completed, <command>REPACK</command> will end. + </entry> + </row> + </tbody> + </tgroup> + </table> + </sect2> + <sect2 id=3D"copy-progress-reporting"> <title>COPY Progress Reporting</title> =20 diff --git a/doc/src/sgml/ref/allfiles.sgml b/doc/src/sgml/ref/allfiles.sgml index e167406c744..5df944d13ca 100644 --- a/doc/src/sgml/ref/allfiles.sgml +++ b/doc/src/sgml/ref/allfiles.sgml @@ -167,6 +167,7 @@ Complete list of usable sgml source files in this direc= tory. <!ENTITY refreshMaterializedView SYSTEM "refresh_materialized_view.sgml"> <!ENTITY reindex SYSTEM "reindex.sgml"> <!ENTITY releaseSavepoint SYSTEM "release_savepoint.sgml"> +<!ENTITY repack SYSTEM "repack.sgml"> <!ENTITY reset SYSTEM "reset.sgml"> <!ENTITY revoke SYSTEM "revoke.sgml"> <!ENTITY rollback SYSTEM "rollback.sgml"> @@ -213,6 +214,7 @@ Complete list of usable sgml source files in this direc= tory. <!ENTITY pgIsready SYSTEM "pg_isready.sgml"> <!ENTITY pgReceivewal SYSTEM "pg_receivewal.sgml"> <!ENTITY pgRecvlogical SYSTEM "pg_recvlogical.sgml"> +<!ENTITY pgRepackdb SYSTEM "pg_repackdb.sgml"> <!ENTITY pgResetwal SYSTEM "pg_resetwal.sgml"> <!ENTITY pgRestore SYSTEM "pg_restore.sgml"> <!ENTITY pgRewind SYSTEM "pg_rewind.sgml"> diff --git a/doc/src/sgml/ref/cluster.sgml b/doc/src/sgml/ref/cluster.sgml index 0b47460080b..2cda711bc9f 100644 --- a/doc/src/sgml/ref/cluster.sgml +++ b/doc/src/sgml/ref/cluster.sgml @@ -33,51 +33,13 @@ CLUSTER [ ( <replaceable class=3D"parameter">option</re= placeable> [, ...] ) ] [ <r <title>Description</title> =20 <para> - <command>CLUSTER</command> instructs <productname>PostgreSQL</productna= me> - to cluster the table specified - by <replaceable class=3D"parameter">table_name</replaceable> - based on the index specified by - <replaceable class=3D"parameter">index_name</replaceable>. The index mu= st - already have been defined on - <replaceable class=3D"parameter">table_name</replaceable>. + The <command>CLUSTER</command> command is equivalent to + <xref linkend=3D"sql-repack"/> with an <literal>USING INDEX</literal> + clause. See there for more details. </para> =20 - <para> - When a table is clustered, it is physically reordered - based on the index information. Clustering is a one-time operation: - when the table is subsequently updated, the changes are - not clustered. That is, no attempt is made to store new or - updated rows according to their index order. (If one wishes, one can - periodically recluster by issuing the command again. Also, setting - the table's <literal>fillfactor</literal> storage parameter to less than - 100% can aid in preserving cluster ordering during updates, since updat= ed - rows are kept on the same page if enough space is available there.) - </para> - - <para> - When a table is clustered, <productname>PostgreSQL</productname> - remembers which index it was clustered by. The form - <command>CLUSTER <replaceable class=3D"parameter">table_name</replaceab= le></command> - reclusters the table using the same index as before. You can also - use the <literal>CLUSTER</literal> or <literal>SET WITHOUT CLUSTER</lit= eral> - forms of <link linkend=3D"sql-altertable"><command>ALTER TABLE</command= ></link> to set the index to be used for - future cluster operations, or to clear any previous setting. - </para> - - <para> - <command>CLUSTER</command> without a - <replaceable class=3D"parameter">table_name</replaceable> reclusters al= l the - previously-clustered tables in the current database that the calling us= er - has privileges for. This form of <command>CLUSTER</command> cannot be - executed inside a transaction block. - </para> +<!-- Do we need to describe exactly which options map to what? They seem = obvious to me. --> =20 - <para> - When a table is being clustered, an <literal>ACCESS - EXCLUSIVE</literal> lock is acquired on it. This prevents any other - database operations (both reads and writes) from operating on the - table until the <command>CLUSTER</command> is finished. - </para> </refsect1> =20 <refsect1> @@ -136,63 +98,12 @@ CLUSTER [ ( <replaceable class=3D"parameter">option</r= eplaceable> [, ...] ) ] [ <r on the table. </para> =20 - <para> - In cases where you are accessing single rows randomly - within a table, the actual order of the data in the - table is unimportant. However, if you tend to access some - data more than others, and there is an index that groups - them together, you will benefit from using <command>CLUSTER</command>. - If you are requesting a range of indexed values from a table, or a - single indexed value that has multiple rows that match, - <command>CLUSTER</command> will help because once the index identifies= the - table page for the first row that matches, all other rows - that match are probably already on the same table page, - and so you save disk accesses and speed up the query. - </para> - - <para> - <command>CLUSTER</command> can re-sort the table using either an index= scan - on the specified index, or (if the index is a b-tree) a sequential - scan followed by sorting. It will attempt to choose the method that - will be faster, based on planner cost parameters and available statist= ical - information. - </para> - <para> While <command>CLUSTER</command> is running, the <xref linkend=3D"guc-search-path"/> is temporarily changed to <literal>pg_ca= talog, pg_temp</literal>. </para> =20 - <para> - When an index scan is used, a temporary copy of the table is created t= hat - contains the table data in the index order. Temporary copies of each - index on the table are created as well. Therefore, you need free spac= e on - disk at least equal to the sum of the table size and the index sizes. - </para> - - <para> - When a sequential scan and sort is used, a temporary sort file is - also created, so that the peak temporary space requirement is as much - as double the table size, plus the index sizes. This method is often - faster than the index scan method, but if the disk space requirement is - intolerable, you can disable this choice by temporarily setting <xref - linkend=3D"guc-enable-sort"/> to <literal>off</literal>. - </para> - - <para> - It is advisable to set <xref linkend=3D"guc-maintenance-work-mem"/> to - a reasonably large value (but not more than the amount of RAM you can - dedicate to the <command>CLUSTER</command> operation) before clusterin= g. - </para> - - <para> - Because the planner records statistics about the ordering of - tables, it is advisable to run <link linkend=3D"sql-analyze"><command>= ANALYZE</command></link> - on the newly clustered table. - Otherwise, the planner might make poor choices of query plans. - </para> - <para> Because <command>CLUSTER</command> remembers which indexes are cluster= ed, one can cluster the tables one wants clustered manually the first time, diff --git a/doc/src/sgml/ref/clusterdb.sgml b/doc/src/sgml/ref/clusterdb.s= gml index 0d2051bf6f1..b50c9581a98 100644 --- a/doc/src/sgml/ref/clusterdb.sgml +++ b/doc/src/sgml/ref/clusterdb.sgml @@ -64,6 +64,11 @@ PostgreSQL documentation this utility and via other methods for accessing the server. </para> =20 + <para> + <application>clusterdb</application> has been superseded by + <application>pg_repackdb</application>. + </para> + </refsect1> =20 =20 diff --git a/doc/src/sgml/ref/pg_repackdb.sgml b/doc/src/sgml/ref/pg_repack= db.sgml new file mode 100644 index 00000000000..a5ea513c6b1 --- /dev/null +++ b/doc/src/sgml/ref/pg_repackdb.sgml @@ -0,0 +1,488 @@ +<!-- +doc/src/sgml/ref/pg_repackdb.sgml +PostgreSQL documentation +--> + +<refentry id=3D"app-pgrepackdb"> + <indexterm zone=3D"app-pgrepackdb"> + <primary>pg_repackdb</primary> + </indexterm> + + <refmeta> + <refentrytitle><application>pg_repackdb</application></refentrytitle> + <manvolnum>1</manvolnum> + <refmiscinfo>Application</refmiscinfo> + </refmeta> + + <refnamediv> + <refname>pg_repackdb</refname> + <refpurpose>repack and analyze a <productname>PostgreSQL</productname> + database</refpurpose> + </refnamediv> + + <refsynopsisdiv> + <cmdsynopsis> + <command>pg_repackdb</command> + <arg rep=3D"repeat"><replaceable>connection-option</replaceable></arg> + <arg rep=3D"repeat"><replaceable>option</replaceable></arg> + + <arg choice=3D"plain" rep=3D"repeat"> + <arg choice=3D"opt"> + <group choice=3D"plain"> + <arg choice=3D"plain"><option>-t</option></arg> + <arg choice=3D"plain"><option>--table</option></arg> + </group> + <replaceable>table</replaceable> + <arg choice=3D"opt">( <replaceable class=3D"parameter">column</replac= eable> [,...] )</arg> + </arg> + </arg> + + <arg choice=3D"opt"> + <group choice=3D"plain"> + <arg choice=3D"plain"><replaceable>dbname</replaceable></arg> + <arg choice=3D"plain"><option>-a</option></arg> + <arg choice=3D"plain"><option>--all</option></arg> + </group> + </arg> + </cmdsynopsis> + + <cmdsynopsis> + <command>pg_repackdb</command> + <arg rep=3D"repeat"><replaceable>connection-option</replaceable></arg> + <arg rep=3D"repeat"><replaceable>option</replaceable></arg> + + <arg choice=3D"plain" rep=3D"repeat"> + <arg choice=3D"opt"> + <group choice=3D"plain"> + <arg choice=3D"plain"><option>-n</option></arg> + <arg choice=3D"plain"><option>--schema</option></arg> + </group> + <replaceable>schema</replaceable> + </arg> + </arg> + + <arg choice=3D"opt"> + <group choice=3D"plain"> + <arg choice=3D"plain"><replaceable>dbname</replaceable></arg> + <arg choice=3D"plain"><option>-a</option></arg> + <arg choice=3D"plain"><option>--all</option></arg> + </group> + </arg> + </cmdsynopsis> + + <cmdsynopsis> + <command>pg_repackdb</command> + <arg rep=3D"repeat"><replaceable>connection-option</replaceable></arg> + <arg rep=3D"repeat"><replaceable>option</replaceable></arg> + + <arg choice=3D"plain" rep=3D"repeat"> + <arg choice=3D"opt"> + <group choice=3D"plain"> + <arg choice=3D"plain"><option>-N</option></arg> + <arg choice=3D"plain"><option>--exclude-schema</option></arg> + </group> + <replaceable>schema</replaceable> + </arg> + </arg> + + <arg choice=3D"opt"> + <group choice=3D"plain"> + <arg choice=3D"plain"><replaceable>dbname</replaceable></arg> + <arg choice=3D"plain"><option>-a</option></arg> + <arg choice=3D"plain"><option>--all</option></arg> + </group> + </arg> + </cmdsynopsis> + </refsynopsisdiv> + + <refsect1> + <title>Description</title> + + <para> + <application>pg_repackdb</application> is a utility for repacking a + <productname>PostgreSQL</productname> database. + <application>pg_repackdb</application> will also generate internal + statistics used by the <productname>PostgreSQL</productname> query + optimizer. + </para> + + <para> + <application>pg_repackdb</application> is a wrapper around the SQL + command <link linkend=3D"sql-repack"><command>REPACK</command></link>. = There + is no effective difference between repacking and analyzing databases via + this utility and via other methods for accessing the server. + </para> + </refsect1> + + <refsect1> + <title>Options</title> + + <para> + <application>pg_repackdb</application> accepts the following command-l= ine arguments: + <variablelist> + <varlistentry> + <term><option>-a</option></term> + <term><option>--all</option></term> + <listitem> + <para> + Repack all databases. + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><option><optional>-d</optional> <replaceable class=3D"paramete= r">dbname</replaceable></option></term> + <term><option><optional>--dbname=3D</optional><replaceable class=3D"= parameter">dbname</replaceable></option></term> + <listitem> + <para> + Specifies the name of the database to be repacked or analyzed, + when <option>-a</option>/<option>--all</option> is not used. If t= his + is not specified, the database name is read from the environment + variable <envar>PGDATABASE</envar>. If that is not set, the user = name + specified for the connection is used. + The <replaceable>dbname</replaceable> can be + a <link linkend=3D"libpq-connstring">connection string</link>. If= so, + connection string parameters will override any conflicting command + line options. + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><option>-e</option></term> + <term><option>--echo</option></term> + <listitem> + <para> + Echo the commands that <application>pg_repackdb</application> + generates and sends to the server. + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><option>--index<optional>=3D<replaceable class=3D"parameter">i= ndex_name</replaceable></optional></option></term> + <listitem> + <para> + Pass the <literal>USING INDEX</literal> clause to <literal>REPACK<= /literal>, + and optionally the index name to specify. + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><option>-j <replaceable class=3D"parameter">njobs</replaceable= ></option></term> + <term><option>--jobs=3D<replaceable class=3D"parameter">njobs</repla= ceable></option></term> + <listitem> + <para> + Execute the repack or analyze commands in parallel by running + <replaceable class=3D"parameter">njobs</replaceable> + commands simultaneously. This option may reduce the processing ti= me + but it also increases the load on the database server. + </para> + <para> + <application>pg_repackdb</application> will open + <replaceable class=3D"parameter">njobs</replaceable> connections t= o the + database, so make sure your <xref linkend=3D"guc-max-connections"/> + setting is high enough to accommodate all connections. + </para> + <para> + Note that using this mode might cause deadlock failures if certain + system catalogs are processed in parallel. + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><option>-n <replaceable class=3D"parameter">schema</replaceabl= e></option></term> + <term><option>--schema=3D<replaceable class=3D"parameter">schema</re= placeable></option></term> + <listitem> + <para> + Repack or analyze all tables in + <replaceable class=3D"parameter">schema</replaceable> only. Multi= ple + schemas can be repacked by writing multiple <option>-n</option> + switches. + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><option>-N <replaceable class=3D"parameter">schema</replaceabl= e></option></term> + <term><option>--exclude-schema=3D<replaceable class=3D"parameter">sc= hema</replaceable></option></term> + <listitem> + <para> + Do not repack or analyze any tables in + <replaceable class=3D"parameter">schema</replaceable>. Multiple s= chemas + can be excluded by writing multiple <option>-N</option> switches. + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><option>-q</option></term> + <term><option>--quiet</option></term> + <listitem> + <para> + Do not display progress messages. + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><option>-t <replaceable class=3D"parameter">table</replaceable= > [ (<replaceable class=3D"parameter">column</replaceable> [,...]) ]</optio= n></term> + <term><option>--table=3D<replaceable class=3D"parameter">table</repl= aceable> [ (<replaceable class=3D"parameter">column</replaceable> [,...]) ]= </option></term> + <listitem> + <para> + Repack or analyze <replaceable class=3D"parameter">table</replacea= ble> + only. Column names can be specified only in conjunction with + the <option>--analyze</option> option. Multiple tables can be + repacked by writing multiple + <option>-t</option> switches. + </para> + <tip> + <para> + If you specify columns, you probably have to escape the parenthes= es + from the shell. (See examples below.) + </para> + </tip> + </listitem> + </varlistentry> + + <varlistentry> + <term><option>-v</option></term> + <term><option>--verbose</option></term> + <listitem> + <para> + Print detailed information during processing. + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><option>-V</option></term> + <term><option>--version</option></term> + <listitem> + <para> + Print the <application>pg_repackdb</application> version and exit. + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><option>-z</option></term> + <term><option>--analyze</option></term> + <listitem> + <para> + Also calculate statistics for use by the optimizer. If a column n= ame + list is given, only compute statistics for those columns. + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><option>-?</option></term> + <term><option>--help</option></term> + <listitem> + <para> + Show help about <application>pg_repackdb</application> command line + arguments, and exit. + </para> + </listitem> + </varlistentry> + + </variablelist> + </para> + + <para> + <application>pg_repackdb</application> also accepts + the following command-line arguments for connection parameters: + <variablelist> + <varlistentry> + <term><option>-h <replaceable class=3D"parameter">host</replaceable>= </option></term> + <term><option>--host=3D<replaceable class=3D"parameter">host</replac= eable></option></term> + <listitem> + <para> + Specifies the host name of the machine on which the server + is running. If the value begins with a slash, it is used + as the directory for the Unix domain socket. + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><option>-p <replaceable class=3D"parameter">port</replaceable>= </option></term> + <term><option>--port=3D<replaceable class=3D"parameter">port</replac= eable></option></term> + <listitem> + <para> + Specifies the TCP port or local Unix domain socket file + extension on which the server + is listening for connections. + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><option>-U <replaceable class=3D"parameter">username</replacea= ble></option></term> + <term><option>--username=3D<replaceable class=3D"parameter">username= </replaceable></option></term> + <listitem> + <para> + User name to connect as. + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><option>-w</option></term> + <term><option>--no-password</option></term> + <listitem> + <para> + Never issue a password prompt. If the server requires + password authentication and a password is not available by + other means such as a <filename>.pgpass</filename> file, the + connection attempt will fail. This option can be useful in + batch jobs and scripts where no user is present to enter a + password. + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><option>-W</option></term> + <term><option>--password</option></term> + <listitem> + <para> + Force <application>pg_repackdb</application> to prompt for a + password before connecting to a database. + </para> + + <para> + This option is never essential, since + <application>pg_repackdb</application> will automatically prompt + for a password if the server demands password authentication. + However, <application>pg_repackdb</application> will waste a + connection attempt finding out that the server wants a password. + In some cases it is worth typing <option>-W</option> to avoid the = extra + connection attempt. + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><option>--maintenance-db=3D<replaceable class=3D"parameter">db= name</replaceable></option></term> + <listitem> + <para> + When the <option>-a</option>/<option>--all</option> is used, conne= ct + to this database to gather the list of databases to repack. + If not specified, the <literal>postgres</literal> database will be= used, + or if that does not exist, <literal>template1</literal> will be us= ed. + This can be a <link linkend=3D"libpq-connstring">connection + string</link>. If so, connection string parameters will override = any + conflicting command line options. Also, connection string paramet= ers + other than the database name itself will be re-used when connecting + to other databases. + </para> + </listitem> + </varlistentry> + </variablelist> + </para> + </refsect1> + + + <refsect1> + <title>Environment</title> + + <variablelist> + <varlistentry> + <term><envar>PGDATABASE</envar></term> + <term><envar>PGHOST</envar></term> + <term><envar>PGPORT</envar></term> + <term><envar>PGUSER</envar></term> + + <listitem> + <para> + Default connection parameters + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><envar>PG_COLOR</envar></term> + <listitem> + <para> + Specifies whether to use color in diagnostic messages. Possible valu= es + are <literal>always</literal>, <literal>auto</literal> and + <literal>never</literal>. + </para> + </listitem> + </varlistentry> + </variablelist> + + <para> + This utility, like most other <productname>PostgreSQL</productname> uti= lities, + also uses the environment variables supported by <application>libpq</ap= plication> + (see <xref linkend=3D"libpq-envars"/>). + </para> + + </refsect1> + + + <refsect1> + <title>Diagnostics</title> + + <para> + In case of difficulty, see + <xref linkend=3D"sql-repack"/> and <xref linkend=3D"app-psql"/> for + discussions of potential problems and error messages. + The database server must be running at the + targeted host. Also, any default connection settings and environment + variables used by the <application>libpq</application> front-end + library will apply. + </para> + + </refsect1> + + <refsect1> + <title>Examples</title> + + <para> + To repack the database <literal>test</literal>: +<screen> +<prompt>$ </prompt><userinput>pg_repackdb test</userinput> +</screen> + </para> + + <para> + To repack and analyze for the optimizer a database named + <literal>bigdb</literal>: +<screen> +<prompt>$ </prompt><userinput>pg_repackdb --analyze bigdb</userinput> +</screen> + </para> + + <para> + To repack a single table + <literal>foo</literal> in a database named + <literal>xyzzy</literal>, and analyze a single column + <literal>bar</literal> of the table for the optimizer: +<screen> +<prompt>$ </prompt><userinput>pg_repackdb --analyze --verbose --table=3D'f= oo(bar)' xyzzy</userinput> +</screen></para> + + <para> + To repack all tables in the <literal>foo</literal> and <literal>bar</l= iteral> schemas + in a database named <literal>xyzzy</literal>: +<screen> +<prompt>$ </prompt><userinput>pg_repackdb --schema=3D'foo' --schema=3D'bar= ' xyzzy</userinput> +</screen></para> + + + </refsect1> + + <refsect1> + <title>See Also</title> + + <simplelist type=3D"inline"> + <member><xref linkend=3D"sql-repack"/></member> + </simplelist> + </refsect1> + +</refentry> diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml new file mode 100644 index 00000000000..61d5c2cdef1 --- /dev/null +++ b/doc/src/sgml/ref/repack.sgml @@ -0,0 +1,328 @@ +<!-- +doc/src/sgml/ref/repack.sgml +PostgreSQL documentation +--> + +<refentry id=3D"sql-repack"> + <indexterm zone=3D"sql-repack"> + <primary>REPACK</primary> + </indexterm> + + <refmeta> + <refentrytitle>REPACK</refentrytitle> + <manvolnum>7</manvolnum> + <refmiscinfo>SQL - Language Statements</refmiscinfo> + </refmeta> + + <refnamediv> + <refname>REPACK</refname> + <refpurpose>rewrite a table to reclaim disk space</refpurpose> + </refnamediv> + + <refsynopsisdiv> +<synopsis> +REPACK [ ( <replaceable class=3D"parameter">option</replaceable> [, ...] )= ] [ <replaceable class=3D"parameter">table_and_columns</replaceable> [ USI= NG INDEX [ <replaceable class=3D"parameter">index_name</replaceable> ] ] ] +REPACK [ ( <replaceable class=3D"parameter">option</replaceable> [, ...] )= ] USING INDEX + +<phrase>where <replaceable class=3D"parameter">option</replaceable> can be= one of:</phrase> + + VERBOSE [ <replaceable class=3D"parameter">boolean</replaceable> ] + ANALYZE [ <replaceable class=3D"parameter">boolean</replaceable> ] + +<phrase>and <replaceable class=3D"parameter">table_and_columns</replaceabl= e> is:</phrase> + + <replaceable class=3D"parameter">table_name</replaceable> [ ( <replace= able class=3D"parameter">column_name</replaceable> [, ...] ) ] +</synopsis> + </refsynopsisdiv> + + <refsect1> + <title>Description</title> + + <para> + <command>REPACK</command> reclaims storage occupied by dead + tuples. Unlike <command>VACUUM</command>, it does so by rewriting the + entire contents of the table specified + by <replaceable class=3D"parameter">table_name</replaceable> into a new= disk + file with no extra space (except for the space guaranteed by + the <literal>fillfactor</literal> storage parameter), allowing unused s= pace + to be returned to the operating system. + </para> + + <para> + Without + a <replaceable class=3D"parameter">table_name</replaceable>, <command>R= EPACK</command> + processes every table and materialized view in the current database that + the current user has the <literal>MAINTAIN</literal> privilege on. This + form of <command>REPACK</command> cannot be executed inside a transacti= on + block. + </para> + + <para> + If a <literal>USING INDEX</literal> clause is specified, the rows are + physically reordered based on information from an index. Please see the + notes on clustering below. + </para> + + <para> + When a table is being repacked, an <literal>ACCESS EXCLUSIVE</literal> = lock + is acquired on it. This prevents any other database operations (both re= ads + and writes) from operating on the table until the <command>REPACK</comm= and> + is finished. + </para> + + <refsect2 id=3D"sql-repack-notes-on-clustering" xreflabel=3D"Notes on Cl= ustering"> + <title>Notes on Clustering</title> + + <para> + If the <literal>USING INDEX</literal> clause is specified, the rows in + the table are physically reordered following an index: if an index name + is specified in the command, then that index is used; if no index name + is specified, then the index that has been configured as the index to + cluster on. If no index has been configured in this way, an error is + thrown. The index given in the <literal>USING INDEX</literal> clause + is configured as the index to cluster on, as well as an index given + to the <command>CLUSTER</command> command. An index can be set + manually using <command>ALTER TABLE ... CLUSTER ON</command>, and reset + with <command>ALTER TABLE ... SET WITHOUT CLUSTER</command>. + </para> + + <para> + If no table name is specified in <command>REPACK USING INDEX</command>, + all tables which have a clustering index defined and which the calling + user has privileges for are processed. + </para> + + <para> + Clustering is a one-time operation: when the table is + subsequently updated, the changes are not clustered. That is, no atte= mpt + is made to store new or updated rows according to their index order. = (If + one wishes, one can periodically recluster by issuing the command agai= n. + Also, setting the table's <literal>fillfactor</literal> storage parame= ter + to less than 100% can aid in preserving cluster ordering during update= s, + since updated rows are kept on the same page if enough space is availa= ble + there.) + </para> + + <para> + In cases where you are accessing single rows randomly within a table, = the + actual order of the data in the table is unimportant. However, if you = tend + to access some data more than others, and there is an index that groups + them together, you will benefit from using clustering. If + you are requesting a range of indexed values from a table, or a single + indexed value that has multiple rows that match, + <command>REPACK</command> will help because once the index identifies = the + table page for the first row that matches, all other rows that match a= re + probably already on the same table page, and so you save disk accesses= and + speed up the query. + </para> + + <para> + <command>REPACK</command> can re-sort the table using either an index = scan + on the specified index (if the index is a b-tree), or a sequential scan + followed by sorting. It will attempt to choose the method that will be + faster, based on planner cost parameters and available statistical + information. + </para> + + <para> + Because the planner records statistics about the ordering of tables, i= t is + advisable to + run <link linkend=3D"sql-analyze"><command>ANALYZE</command></link> on= the + newly repacked table. Otherwise, the planner might make poor choices = of + query plans. + </para> + </refsect2> + + <refsect2 id=3D"sql-repack-notes-on-resources" xreflabel=3D"Notes on Res= ources"> + <title>Notes on Resources</title> + + <para> + When an index scan or a sequential scan without sort is used, a tempor= ary + copy of the table is created that contains the table data in the index + order. Temporary copies of each index on the table are created as wel= l. + Therefore, you need free space on disk at least equal to the sum of the + table size and the index sizes. + </para> + + <para> + When a sequential scan and sort is used, a temporary sort file is also + created, so that the peak temporary space requirement is as much as do= uble + the table size, plus the index sizes. This method is often faster than + the index scan method, but if the disk space requirement is intolerabl= e, + you can disable this choice by temporarily setting + <xref linkend=3D"guc-enable-sort"/> to <literal>off</literal>. + </para> + + <para> + It is advisable to set <xref linkend=3D"guc-maintenance-work-mem"/> to= a + reasonably large value (but not more than the amount of RAM you can + dedicate to the <command>REPACK</command> operation) before repacking. + </para> + </refsect2> + + </refsect1> + + <refsect1> + <title>Parameters</title> + + <variablelist> + <varlistentry> + <term><replaceable class=3D"parameter">table_name</replaceable></term> + <listitem> + <para> + The name (possibly schema-qualified) of a table. + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><replaceable class=3D"parameter">column_name</replaceable></term> + <listitem> + <para> + The name of a specific column to analyze. Defaults to all columns. + If a column list is specific, <literal>ANALYZE</literal> must also + be specified. + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><replaceable class=3D"parameter">index_name</replaceable></term> + <listitem> + <para> + The name of an index. + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><literal>VERBOSE</literal></term> + <listitem> + <para> + Prints a progress report as each table is repacked + at <literal>INFO</literal> level. + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><literal>ANALYZE</literal></term> + <term><literal>ANALYSE</literal></term> + <listitem> + <para> + Applies <xref linkend=3D"sql-analyze"/> on the table after repacking= . This is + currently only supported when a single (non-partitioned) table is sp= ecified. + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><replaceable class=3D"parameter">boolean</replaceable></term> + <listitem> + <para> + Specifies whether the selected option should be turned on or off. + You can write <literal>TRUE</literal>, <literal>ON</literal>, or + <literal>1</literal> to enable the option, and <literal>FALSE</liter= al>, + <literal>OFF</literal>, or <literal>0</literal> to disable it. The + <replaceable class=3D"parameter">boolean</replaceable> value can also + be omitted, in which case <literal>TRUE</literal> is assumed. + </para> + </listitem> + </varlistentry> + </variablelist> + </refsect1> + + <refsect1> + <title>Notes</title> + + <para> + To repack a table, one must have the <literal>MAINTAIN</literal> privi= lege + on the table. + </para> + + <para> + While <command>REPACK</command> is running, the <xref + linkend=3D"guc-search-path"/> is temporarily changed to <literal>pg_ca= talog, + pg_temp</literal>. + </para> + + <para> + Each backend running <command>REPACK</command> will report its progress + in the <structname>pg_stat_progress_repack</structname> view. See + <xref linkend=3D"repack-progress-reporting"/> for details. + </para> + + <para> + Repacking a partitioned table repacks each of its partitions. If an in= dex + is specified, each partition is repacked using the partition of that + index. <command>REPACK</command> on a partitioned table cannot be exec= uted + inside a transaction block. + </para> + + </refsect1> + + <refsect1> + <title>Examples</title> + + <para> + Repack the table <literal>employees</literal>: +<programlisting> +REPACK employees; +</programlisting> + </para> + + <para> + Repack the table <literal>employees</literal> on the basis of its + index <literal>employees_ind</literal> (Since index is used here, this = is + effectively clustering): +<programlisting> +REPACK employees USING INDEX employees_ind; +</programlisting> + </para> + + <para> + Repack the table <literal>cases</literal> on physical ordering, + running an <command>ANALYZE</command> on the given columns once + repacking is done, showing informational messages: +<programlisting> +REPACK (ANALYZE, VERBOSE) cases (district, case_nr); +</programlisting> + </para> + + <para> + Repack all tables in the database on which you have + the <literal>MAINTAIN</literal> privilege: +<programlisting> +REPACK; +</programlisting> + </para> + + <para> + Repack all tables for which a clustering index has previously been + configured on which you have the <literal>MAINTAIN</literal> privilege, + showing informational messages: +<programlisting> +REPACK (VERBOSE) USING INDEX; +</programlisting> + </para> + + </refsect1> + + <refsect1> + <title>Compatibility</title> + + <para> + There is no <command>REPACK</command> statement in the SQL standard. + </para> + </refsect1> + + <refsect1> + <title>See Also</title> + + <simplelist type=3D"inline"> + <member><xref linkend=3D"app-pgrepackdb"/></member> + <member><xref linkend=3D"repack-progress-reporting"/></member> + </simplelist> + </refsect1> + +</refentry> diff --git a/doc/src/sgml/ref/vacuum.sgml b/doc/src/sgml/ref/vacuum.sgml index 6d0fdd43cfb..ac5d083d468 100644 --- a/doc/src/sgml/ref/vacuum.sgml +++ b/doc/src/sgml/ref/vacuum.sgml @@ -25,7 +25,6 @@ VACUUM [ ( <replaceable class=3D"parameter">option</repla= ceable> [, ...] ) ] [ <re =20 <phrase>where <replaceable class=3D"parameter">option</replaceable> can be= one of:</phrase> =20 - FULL [ <replaceable class=3D"parameter">boolean</replaceable> ] FREEZE [ <replaceable class=3D"parameter">boolean</replaceable> ] VERBOSE [ <replaceable class=3D"parameter">boolean</replaceable> ] ANALYZE [ <replaceable class=3D"parameter">boolean</replaceable> ] @@ -39,6 +38,7 @@ VACUUM [ ( <replaceable class=3D"parameter">option</repla= ceable> [, ...] ) ] [ <re SKIP_DATABASE_STATS [ <replaceable class=3D"parameter">boolean</replac= eable> ] ONLY_DATABASE_STATS [ <replaceable class=3D"parameter">boolean</replac= eable> ] BUFFER_USAGE_LIMIT <replaceable class=3D"parameter">size</replaceable> + FULL [ <replaceable class=3D"parameter">boolean</replaceable> ] =20 <phrase>and <replaceable class=3D"parameter">table_and_columns</replaceabl= e> is:</phrase> =20 @@ -95,20 +95,6 @@ VACUUM [ ( <replaceable class=3D"parameter">option</repl= aceable> [, ...] ) ] [ <re <title>Parameters</title> =20 <variablelist> - <varlistentry> - <term><literal>FULL</literal></term> - <listitem> - <para> - Selects <quote>full</quote> vacuum, which can reclaim more - space, but takes much longer and exclusively locks the table. - This method also requires extra disk space, since it writes a - new copy of the table and doesn't release the old copy until - the operation is complete. Usually this should only be used when a - significant amount of space needs to be reclaimed from within the ta= ble. - </para> - </listitem> - </varlistentry> - <varlistentry> <term><literal>FREEZE</literal></term> <listitem> @@ -362,6 +348,23 @@ VACUUM [ ( <replaceable class=3D"parameter">option</re= placeable> [, ...] ) ] [ <re </listitem> </varlistentry> =20 + <varlistentry> + <term><literal>FULL</literal></term> + <listitem> + <para> + This option, which is deprecated, makes <command>VACUUM</command> + behave like <command>REPACK</command> without a + <literal>USING INDEX</literal> clause. + This method of compacting the table takes much longer than + <command>VACUUM</command> and exclusively locks the table. + This method also requires extra disk space, since it writes a + new copy of the table and doesn't release the old copy until + the operation is complete. Usually this should only be used when a + significant amount of space needs to be reclaimed from within the ta= ble. + </para> + </listitem> + </varlistentry> + <varlistentry> <term><replaceable class=3D"parameter">boolean</replaceable></term> <listitem> diff --git a/doc/src/sgml/reference.sgml b/doc/src/sgml/reference.sgml index 2cf02c37b17..5d9a8a25a02 100644 --- a/doc/src/sgml/reference.sgml +++ b/doc/src/sgml/reference.sgml @@ -195,6 +195,7 @@ &refreshMaterializedView; &reindex; &releaseSavepoint; + &repack; &reset; &revoke; &rollback; @@ -258,6 +259,7 @@ &pgIsready; &pgReceivewal; &pgRecvlogical; + &pgRepackdb; &pgRestore; &pgVerifyBackup; &psqlRef; diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/= heap/heapam_handler.c index 09a456e9966..778377b9866 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -741,13 +741,13 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Re= lation NewHeap, if (OldIndex !=3D NULL && !use_sort) { const int ci_index[] =3D { - PROGRESS_CLUSTER_PHASE, - PROGRESS_CLUSTER_INDEX_RELID + PROGRESS_REPACK_PHASE, + PROGRESS_REPACK_INDEX_RELID }; int64 ci_val[2]; =20 /* Set phase and OIDOldIndex to columns */ - ci_val[0] =3D PROGRESS_CLUSTER_PHASE_INDEX_SCAN_HEAP; + ci_val[0] =3D PROGRESS_REPACK_PHASE_INDEX_SCAN_HEAP; ci_val[1] =3D RelationGetRelid(OldIndex); pgstat_progress_update_multi_param(2, ci_index, ci_val); =20 @@ -759,15 +759,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Re= lation NewHeap, else { /* In scan-and-sort mode and also VACUUM FULL, set phase */ - pgstat_progress_update_param(PROGRESS_CLUSTER_PHASE, - PROGRESS_CLUSTER_PHASE_SEQ_SCAN_HEAP); + pgstat_progress_update_param(PROGRESS_REPACK_PHASE, + PROGRESS_REPACK_PHASE_SEQ_SCAN_HEAP); =20 tableScan =3D table_beginscan(OldHeap, SnapshotAny, 0, (ScanKey) NULL); heapScan =3D (HeapScanDesc) tableScan; indexScan =3D NULL; =20 /* Set total heap blocks */ - pgstat_progress_update_param(PROGRESS_CLUSTER_TOTAL_HEAP_BLKS, + pgstat_progress_update_param(PROGRESS_REPACK_TOTAL_HEAP_BLKS, heapScan->rs_nblocks); } =20 @@ -809,7 +809,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Rela= tion NewHeap, * is manually updated to the correct value when the table * scan finishes. */ - pgstat_progress_update_param(PROGRESS_CLUSTER_HEAP_BLKS_SCANNED, + pgstat_progress_update_param(PROGRESS_REPACK_HEAP_BLKS_SCANNED, heapScan->rs_nblocks); break; } @@ -825,7 +825,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Rela= tion NewHeap, */ if (prev_cblock !=3D heapScan->rs_cblock) { - pgstat_progress_update_param(PROGRESS_CLUSTER_HEAP_BLKS_SCANNED, + pgstat_progress_update_param(PROGRESS_REPACK_HEAP_BLKS_SCANNED, (heapScan->rs_cblock + heapScan->rs_nblocks - heapScan->rs_startblock @@ -912,14 +912,14 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Re= lation NewHeap, * In scan-and-sort mode, report increase in number of tuples * scanned */ - pgstat_progress_update_param(PROGRESS_CLUSTER_HEAP_TUPLES_SCANNED, + pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_SCANNED, *num_tuples); } else { const int ct_index[] =3D { - PROGRESS_CLUSTER_HEAP_TUPLES_SCANNED, - PROGRESS_CLUSTER_HEAP_TUPLES_WRITTEN + PROGRESS_REPACK_HEAP_TUPLES_SCANNED, + PROGRESS_REPACK_HEAP_TUPLES_WRITTEN }; int64 ct_val[2]; =20 @@ -952,14 +952,14 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Re= lation NewHeap, double n_tuples =3D 0; =20 /* Report that we are now sorting tuples */ - pgstat_progress_update_param(PROGRESS_CLUSTER_PHASE, - PROGRESS_CLUSTER_PHASE_SORT_TUPLES); + pgstat_progress_update_param(PROGRESS_REPACK_PHASE, + PROGRESS_REPACK_PHASE_SORT_TUPLES); =20 tuplesort_performsort(tuplesort); =20 /* Report that we are now writing new heap */ - pgstat_progress_update_param(PROGRESS_CLUSTER_PHASE, - PROGRESS_CLUSTER_PHASE_WRITE_NEW_HEAP); + pgstat_progress_update_param(PROGRESS_REPACK_PHASE, + PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); =20 for (;;) { @@ -977,7 +977,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Rela= tion NewHeap, values, isnull, rwstate); /* Report n_tuples */ - pgstat_progress_update_param(PROGRESS_CLUSTER_HEAP_TUPLES_WRITTEN, + pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_WRITTEN, n_tuples); } =20 diff --git a/src/backend/catalog/index.c b/src/backend/catalog/index.c index 43de42ce39e..5ee6389d39c 100644 --- a/src/backend/catalog/index.c +++ b/src/backend/catalog/index.c @@ -4077,7 +4077,7 @@ reindex_relation(const ReindexStmt *stmt, Oid relid, = int flags, Assert(!ReindexIsProcessingIndex(indexOid)); =20 /* Set index rebuild count */ - pgstat_progress_update_param(PROGRESS_CLUSTER_INDEX_REBUILD_COUNT, + pgstat_progress_update_param(PROGRESS_REPACK_INDEX_REBUILD_COUNT, i); i++; } diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/sys= tem_views.sql index 7553f31fef0..3f05ba3083a 100644 --- a/src/backend/catalog/system_views.sql +++ b/src/backend/catalog/system_views.sql @@ -1283,14 +1283,15 @@ CREATE VIEW pg_stat_progress_vacuum AS FROM pg_stat_get_progress_info('VACUUM') AS S LEFT JOIN pg_database D ON S.datid =3D D.oid; =20 -CREATE VIEW pg_stat_progress_cluster AS +CREATE VIEW pg_stat_progress_repack AS SELECT S.pid AS pid, S.datid AS datid, D.datname AS datname, S.relid AS relid, CASE S.param1 WHEN 1 THEN 'CLUSTER' - WHEN 2 THEN 'VACUUM FULL' + WHEN 2 THEN 'REPACK' + WHEN 3 THEN 'VACUUM FULL' END AS command, CASE S.param2 WHEN 0 THEN 'initializing' WHEN 1 THEN 'seq scanning heap' @@ -1301,15 +1302,35 @@ CREATE VIEW pg_stat_progress_cluster AS WHEN 6 THEN 'rebuilding index' WHEN 7 THEN 'performing final cleanup' END AS phase, - CAST(S.param3 AS oid) AS cluster_index_relid, + CAST(S.param3 AS oid) AS repack_index_relid, S.param4 AS heap_tuples_scanned, S.param5 AS heap_tuples_written, S.param6 AS heap_blks_total, S.param7 AS heap_blks_scanned, S.param8 AS index_rebuild_count - FROM pg_stat_get_progress_info('CLUSTER') AS S + FROM pg_stat_get_progress_info('REPACK') AS S LEFT JOIN pg_database D ON S.datid =3D D.oid; =20 +-- This view is as the one above, except for renaming a column and avoiding +-- 'REPACK' as a command name to report. +CREATE VIEW pg_stat_progress_cluster AS + SELECT + pid, + datid, + datname, + relid, + CASE WHEN command IN ('CLUSTER', 'VACUUM FULL') THEN command + WHEN repack_index_relid =3D 0 THEN 'VACUUM FULL' + ELSE 'CLUSTER' END AS command, + phase, + repack_index_relid AS cluster_index_relid, + heap_tuples_scanned, + heap_tuples_written, + heap_blks_total, + heap_blks_scanned, + index_rebuild_count + FROM pg_stat_progress_repack; + CREATE VIEW pg_stat_progress_create_index AS SELECT S.pid AS pid, S.datid AS datid, D.datname AS datname, diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 60a4617a585..e19675a6d05 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1,7 +1,8 @@ /*------------------------------------------------------------------------- * * cluster.c - * CLUSTER a table on an index. This is now also used for VACUUM FULL. + * CLUSTER a table on an index. This is now also used for VACUUM FULL a= nd + * REPACK. * * There is hardly anything left of Paul Brown's original implementation... * @@ -67,27 +68,35 @@ typedef struct Oid indexOid; } RelToCluster; =20 - -static void cluster_multiple_rels(List *rtcs, ClusterParams *params); +static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, + Oid indexOid, Oid userid, int options); static void rebuild_relation(Relation OldHeap, Relation index, bool verbos= e); static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation O= ldIndex, bool verbose, bool *pSwapToastByContent, TransactionId *pFreezeXid, MultiXactId *pCutoffMulti); -static List *get_tables_to_cluster(MemoryContext cluster_context); -static List *get_tables_to_cluster_partitioned(MemoryContext cluster_conte= xt, - Oid indexOid); -static bool cluster_is_permitted_for_relation(Oid relid, Oid userid); +static List *get_tables_to_repack(RepackCommand cmd, bool usingindex, + MemoryContext permcxt); +static List *get_tables_to_repack_partitioned(RepackCommand cmd, + Oid relid, bool rel_is_index, + MemoryContext permcxt); +static bool cluster_is_permitted_for_relation(RepackCommand cmd, + Oid relid, Oid userid); +static Relation process_single_relation(RepackStmt *stmt, + ClusterParams *params); +static Oid determine_clustered_index(Relation rel, bool usingindex, + const char *indexname); +static const char *RepackCommandAsString(RepackCommand cmd); =20 =20 -/*------------------------------------------------------------------------= --- - * This cluster code allows for clustering multiple tables at once. Because +/* + * The repack code allows for processing multiple tables at once. Because * of this, we cannot just run everything on a single transaction, or we * would be forced to acquire exclusive locks on all the tables being * clustered, simultaneously --- very likely leading to deadlock. * - * To solve this we follow a similar strategy to VACUUM code, - * clustering each relation in a separate transaction. For this to work, - * we need to: + * To solve this we follow a similar strategy to VACUUM code, processing e= ach + * relation in a separate transaction. For this to work, we need to: + * * - provide a separate memory context so that we can pass information in * a way that survives across transactions * - start a new transaction every time a new relation is clustered @@ -98,197 +107,166 @@ static bool cluster_is_permitted_for_relation(Oid re= lid, Oid userid); * * The single-relation case does not have any such overhead. * - * We also allow a relation to be specified without index. In that case, - * the indisclustered bit will be looked up, and an ERROR will be thrown - * if there is no index with the bit set. - *------------------------------------------------------------------------= --- + * We also allow a relation to be repacked following an index, but without + * naming a specific one. In that case, the indisclustered bit will be + * looked up, and an ERROR will be thrown if no so-marked index is found. */ void -cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel) +ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) { - ListCell *lc; ClusterParams params =3D {0}; - bool verbose =3D false; Relation rel =3D NULL; - Oid indexOid =3D InvalidOid; - MemoryContext cluster_context; + MemoryContext repack_context; List *rtcs; =20 /* Parse option list */ - foreach(lc, stmt->params) + foreach_node(DefElem, opt, stmt->params) { - DefElem *opt =3D (DefElem *) lfirst(lc); - if (strcmp(opt->defname, "verbose") =3D=3D 0) - verbose =3D defGetBoolean(opt); + params.options |=3D defGetBoolean(opt) ? CLUOPT_VERBOSE : 0; + else if (strcmp(opt->defname, "analyze") =3D=3D 0 || + strcmp(opt->defname, "analyse") =3D=3D 0) + params.options |=3D defGetBoolean(opt) ? CLUOPT_ANALYZE : 0; else ereport(ERROR, - (errcode(ERRCODE_SYNTAX_ERROR), - errmsg("unrecognized %s option \"%s\"", - "CLUSTER", opt->defname), - parser_errposition(pstate, opt->location))); + errcode(ERRCODE_SYNTAX_ERROR), + errmsg("unrecognized %s option \"%s\"", + RepackCommandAsString(stmt->command), + opt->defname), + parser_errposition(pstate, opt->location)); } =20 - params.options =3D (verbose ? CLUOPT_VERBOSE : 0); - + /* + * If a single relation is specified, process it and we're done ... unless + * the relation is a partitioned table, in which case we fall through. + */ if (stmt->relation !=3D NULL) { - /* This is the single-relation case. */ - Oid tableOid; - - /* - * Find, lock, and check permissions on the table. We obtain - * AccessExclusiveLock right away to avoid lock-upgrade hazard in the - * single-transaction case. - */ - tableOid =3D RangeVarGetRelidExtended(stmt->relation, - AccessExclusiveLock, - 0, - RangeVarCallbackMaintainsTable, - NULL); - rel =3D table_open(tableOid, NoLock); - - /* - * Reject clustering a remote temp table ... their local buffer - * manager is not going to cope. - */ - if (RELATION_IS_OTHER_TEMP(rel)) - ereport(ERROR, - (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), - errmsg("cannot cluster temporary tables of other sessions"))); - - if (stmt->indexname =3D=3D NULL) - { - ListCell *index; - - /* We need to find the index that has indisclustered set. */ - foreach(index, RelationGetIndexList(rel)) - { - indexOid =3D lfirst_oid(index); - if (get_index_isclustered(indexOid)) - break; - indexOid =3D InvalidOid; - } - - if (!OidIsValid(indexOid)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("there is no previously clustered index for table \"%s\"", - stmt->relation->relname))); - } - else - { - /* - * The index is expected to be in the same namespace as the - * relation. - */ - indexOid =3D get_relname_relid(stmt->indexname, - rel->rd_rel->relnamespace); - if (!OidIsValid(indexOid)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("index \"%s\" for table \"%s\" does not exist", - stmt->indexname, stmt->relation->relname))); - } - - /* For non-partitioned tables, do what we came here to do. */ - if (rel->rd_rel->relkind !=3D RELKIND_PARTITIONED_TABLE) - { - cluster_rel(rel, indexOid, ¶ms); - /* cluster_rel closes the relation, but keeps lock */ - - return; - } + rel =3D process_single_relation(stmt, ¶ms); + if (rel =3D=3D NULL) + return; /* all done */ } =20 + /* + * Don't allow ANALYZE in the multiple-relation case for now. Maybe we + * can add support for this later. + */ + if (params.options & CLUOPT_ANALYZE) + ereport(ERROR, + errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("cannot %s multiple tables", "REPACK (ANALYZE)")); + /* * By here, we know we are in a multi-table situation. In order to avoid * holding locks for too long, we want to process each table in its own * transaction. This forces us to disallow running inside a user * transaction block. */ - PreventInTransactionBlock(isTopLevel, "CLUSTER"); + PreventInTransactionBlock(isTopLevel, RepackCommandAsString(stmt->command= )); =20 /* Also, we need a memory context to hold our list of relations */ - cluster_context =3D AllocSetContextCreate(PortalContext, - "Cluster", - ALLOCSET_DEFAULT_SIZES); + repack_context =3D AllocSetContextCreate(PortalContext, + "Repack", + ALLOCSET_DEFAULT_SIZES); + + params.options |=3D CLUOPT_RECHECK; =20 /* - * Either we're processing a partitioned table, or we were not given any - * table name at all. In either case, obtain a list of relations to - * process. - * - * In the former case, an index name must have been given, so we don't - * need to recheck its "indisclustered" bit, but we have to check that it - * is an index that we can cluster on. In the latter case, we set the - * option bit to have indisclustered verified. - * - * Rechecking the relation itself is necessary here in all cases. + * If we don't have a relation yet, determine a relation list. If we do, + * then it must be a partitioned table, and we want to process its + * partitions. */ - params.options |=3D CLUOPT_RECHECK; - if (rel !=3D NULL) + if (rel =3D=3D NULL) { - Assert(rel->rd_rel->relkind =3D=3D RELKIND_PARTITIONED_TABLE); - check_index_is_clusterable(rel, indexOid, AccessShareLock); - rtcs =3D get_tables_to_cluster_partitioned(cluster_context, indexOid); - - /* close relation, releasing lock on parent table */ - table_close(rel, AccessExclusiveLock); + Assert(stmt->indexname =3D=3D NULL); + rtcs =3D get_tables_to_repack(stmt->command, stmt->usingindex, + repack_context); + params.options |=3D CLUOPT_RECHECK_ISCLUSTERED; } else { - rtcs =3D get_tables_to_cluster(cluster_context); - params.options |=3D CLUOPT_RECHECK_ISCLUSTERED; - } + Oid relid; + bool rel_is_index; =20 - /* Do the job. */ - cluster_multiple_rels(rtcs, ¶ms); + Assert(rel->rd_rel->relkind =3D=3D RELKIND_PARTITIONED_TABLE); =20 - /* Start a new transaction for the cleanup work. */ - StartTransactionCommand(); + /* + * If USING INDEX was specified, resolve the index name now and pass + * it down. + */ + if (stmt->usingindex) + { + /* + * If no index name was specified when repacking a partitioned + * table, punt for now. Maybe we can improve this later. + */ + if (!stmt->indexname) + ereport(ERROR, + errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("there is no previously clustered index for table \"%s\"", + RelationGetRelationName(rel))); + + relid =3D determine_clustered_index(rel, stmt->usingindex, + stmt->indexname); + if (!OidIsValid(relid)) + elog(ERROR, "unable to determine index to cluster on"); + /* XXX is this the right place for this check? */ + check_index_is_clusterable(rel, relid, AccessExclusiveLock); + rel_is_index =3D true; + } + else + { + relid =3D RelationGetRelid(rel); + rel_is_index =3D false; + } =20 - /* Clean up working storage */ - MemoryContextDelete(cluster_context); -} + rtcs =3D get_tables_to_repack_partitioned(stmt->command, + relid, rel_is_index, + repack_context); =20 -/* - * Given a list of relations to cluster, process each of them in a separate - * transaction. - * - * We expect to be in a transaction at start, but there isn't one when we - * return. - */ -static void -cluster_multiple_rels(List *rtcs, ClusterParams *params) -{ - ListCell *lc; + /* close parent relation, releasing lock on it */ + table_close(rel, AccessExclusiveLock); + rel =3D NULL; + } =20 /* Commit to get out of starting transaction */ PopActiveSnapshot(); CommitTransactionCommand(); =20 /* Cluster the tables, each in a separate transaction */ - foreach(lc, rtcs) + Assert(rel =3D=3D NULL); + foreach_ptr(RelToCluster, rtc, rtcs) { - RelToCluster *rtc =3D (RelToCluster *) lfirst(lc); - Relation rel; - /* Start a new transaction for each relation. */ StartTransactionCommand(); =20 + /* + * Open the target table, coping with the case where it has been + * dropped. + */ + rel =3D try_table_open(rtc->tableOid, AccessExclusiveLock); + if (rel =3D=3D NULL) + { + CommitTransactionCommand(); + continue; + } + /* functions in indexes may want a snapshot set */ PushActiveSnapshot(GetTransactionSnapshot()); =20 - rel =3D table_open(rtc->tableOid, AccessExclusiveLock); - /* Process this table */ - cluster_rel(rel, rtc->indexOid, params); + cluster_rel(stmt->command, rel, rtc->indexOid, ¶ms); /* cluster_rel closes the relation, but keeps lock */ =20 PopActiveSnapshot(); CommitTransactionCommand(); } + + /* Start a new transaction for the cleanup work. */ + StartTransactionCommand(); + + /* Clean up working storage */ + MemoryContextDelete(repack_context); } =20 /* @@ -304,11 +282,14 @@ cluster_multiple_rels(List *rtcs, ClusterParams *para= ms) * them incrementally while we load the table. * * If indexOid is InvalidOid, the table will be rewritten in physical order - * instead of index order. This is the new implementation of VACUUM FULL, - * and error messages should refer to the operation as VACUUM not CLUSTER. + * instead of index order. + * + * 'cmd' indicates which command is being executed, to be used for error + * messages. */ void -cluster_rel(Relation OldHeap, Oid indexOid, ClusterParams *params) +cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, + ClusterParams *params) { Oid tableOid =3D RelationGetRelid(OldHeap); Oid save_userid; @@ -323,13 +304,8 @@ cluster_rel(Relation OldHeap, Oid indexOid, ClusterPar= ams *params) /* Check for user-requested abort. */ CHECK_FOR_INTERRUPTS(); =20 - pgstat_progress_start_command(PROGRESS_COMMAND_CLUSTER, tableOid); - if (OidIsValid(indexOid)) - pgstat_progress_update_param(PROGRESS_CLUSTER_COMMAND, - PROGRESS_CLUSTER_COMMAND_CLUSTER); - else - pgstat_progress_update_param(PROGRESS_CLUSTER_COMMAND, - PROGRESS_CLUSTER_COMMAND_VACUUM_FULL); + pgstat_progress_start_command(PROGRESS_COMMAND_REPACK, tableOid); + pgstat_progress_update_param(PROGRESS_REPACK_COMMAND, cmd); =20 /* * Switch to the table owner's userid, so that any index functions are run @@ -350,86 +326,38 @@ cluster_rel(Relation OldHeap, Oid indexOid, ClusterPa= rams *params) * *must* skip the one on indisclustered since it would reject an attempt * to cluster a not-previously-clustered index. */ - if (recheck) - { - /* Check that the user still has privileges for the relation */ - if (!cluster_is_permitted_for_relation(tableOid, save_userid)) - { - relation_close(OldHeap, AccessExclusiveLock); - goto out; - } - - /* - * Silently skip a temp table for a remote session. Only doing this - * check in the "recheck" case is appropriate (which currently means - * somebody is executing a database-wide CLUSTER or on a partitioned - * table), because there is another check in cluster() which will stop - * any attempt to cluster remote temp tables by name. There is - * another check in cluster_rel which is redundant, but we leave it - * for extra safety. - */ - if (RELATION_IS_OTHER_TEMP(OldHeap)) - { - relation_close(OldHeap, AccessExclusiveLock); - goto out; - } - - if (OidIsValid(indexOid)) - { - /* - * Check that the index still exists - */ - if (!SearchSysCacheExists1(RELOID, ObjectIdGetDatum(indexOid))) - { - relation_close(OldHeap, AccessExclusiveLock); - goto out; - } - - /* - * Check that the index is still the one with indisclustered set, - * if needed. - */ - if ((params->options & CLUOPT_RECHECK_ISCLUSTERED) !=3D 0 && - !get_index_isclustered(indexOid)) - { - relation_close(OldHeap, AccessExclusiveLock); - goto out; - } - } - } + if (recheck && + !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, + params->options)) + goto out; =20 /* - * We allow VACUUM FULL, but not CLUSTER, on shared catalogs. CLUSTER - * would work in most respects, but the index would only get marked as - * indisclustered in the current database, leading to unexpected behavior - * if CLUSTER were later invoked in another database. + * We allow repacking shared catalogs only when not using an index. It + * would work to use an index in most respects, but the index would only + * get marked as indisclustered in the current database, leading to + * unexpected behavior if CLUSTER were later invoked in another database. */ if (OidIsValid(indexOid) && OldHeap->rd_rel->relisshared) ereport(ERROR, - (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), - errmsg("cannot cluster a shared catalog"))); + errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("cannot run %s on a shared catalog", + RepackCommandAsString(cmd))); =20 /* * Don't process temp tables of other backends ... their local buffer * manager is not going to cope. */ if (RELATION_IS_OTHER_TEMP(OldHeap)) - { - if (OidIsValid(indexOid)) - ereport(ERROR, - (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), - errmsg("cannot cluster temporary tables of other sessions"))); - else - ereport(ERROR, - (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), - errmsg("cannot vacuum temporary tables of other sessions"))); - } + ereport(ERROR, + errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("cannot run %s on temporary tables of other sessions", + RepackCommandAsString(cmd))); =20 /* * Also check for active uses of the relation in the current transaction, * including open scans and pending AFTER trigger events. */ - CheckTableNotInUse(OldHeap, OidIsValid(indexOid) ? "CLUSTER" : "VACUUM"); + CheckTableNotInUse(OldHeap, RepackCommandAsString(cmd)); =20 /* Check heap and index are valid to cluster on */ if (OidIsValid(indexOid)) @@ -442,6 +370,24 @@ cluster_rel(Relation OldHeap, Oid indexOid, ClusterPar= ams *params) else index =3D NULL; =20 + /* + * When allow_system_table_mods is turned off, we disallow repacking a + * catalog on a particular index unless that's already the clustered index + * for that catalog. + * + * XXX We don't check for this in CLUSTER, because it's historically been + * allowed. + */ + if (cmd !=3D REPACK_COMMAND_CLUSTER && + !allowSystemTableMods && OidIsValid(indexOid) && + IsCatalogRelation(OldHeap) && !index->rd_index->indisclustered) + ereport(ERROR, + errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + errmsg("permission denied: \"%s\" is a system catalog", + RelationGetRelationName(OldHeap)), + errdetail("System catalogs can only be clustered by the index they're = already clustered on, if any, unless \"%s\" is enabled.", + "allow_system_table_mods")); + /* * Quietly ignore the request if this is a materialized view which has not * been populated from its query. No harm is done because there is no data @@ -482,6 +428,63 @@ out: pgstat_progress_end_command(); } =20 +/* + * Check if the table (and its index) still meets the requirements of + * cluster_rel(). + */ +static bool +cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, + Oid userid, int options) +{ + Oid tableOid =3D RelationGetRelid(OldHeap); + + /* Check that the user still has privileges for the relation */ + if (!cluster_is_permitted_for_relation(cmd, tableOid, userid)) + { + relation_close(OldHeap, AccessExclusiveLock); + return false; + } + + /* + * Silently skip a temp table for a remote session. Only doing this check + * in the "recheck" case is appropriate (which currently means somebody is + * executing a database-wide CLUSTER or on a partitioned table), because + * there is another check in cluster() which will stop any attempt to + * cluster remote temp tables by name. There is another check in + * cluster_rel which is redundant, but we leave it for extra safety. + */ + if (RELATION_IS_OTHER_TEMP(OldHeap)) + { + relation_close(OldHeap, AccessExclusiveLock); + return false; + } + + if (OidIsValid(indexOid)) + { + /* + * Check that the index still exists + */ + if (!SearchSysCacheExists1(RELOID, ObjectIdGetDatum(indexOid))) + { + relation_close(OldHeap, AccessExclusiveLock); + return false; + } + + /* + * Check that the index is still the one with indisclustered set, if + * needed. + */ + if ((options & CLUOPT_RECHECK_ISCLUSTERED) !=3D 0 && + !get_index_isclustered(indexOid)) + { + relation_close(OldHeap, AccessExclusiveLock); + return false; + } + } + + return true; +} + /* * Verify that the specified heap and index are valid to cluster on * @@ -642,8 +645,8 @@ rebuild_relation(Relation OldHeap, Relation index, bool= verbose) Assert(CheckRelationLockedByMe(OldHeap, AccessExclusiveLock, false) && (index =3D=3D NULL || CheckRelationLockedByMe(index, AccessExclusiveL= ock, false))); =20 - if (index) - /* Mark the correct index as clustered */ + /* for CLUSTER or REPACK USING INDEX, mark the index as the one to use */ + if (index !=3D NULL) mark_index_clustered(OldHeap, RelationGetRelid(index), true); =20 /* Remember info about rel before closing OldHeap */ @@ -958,20 +961,20 @@ copy_table_data(Relation NewHeap, Relation OldHeap, R= elation OldIndex, bool verb /* Log what we're doing */ if (OldIndex !=3D NULL && !use_sort) ereport(elevel, - (errmsg("clustering \"%s.%s\" using index scan on \"%s\"", - nspname, - RelationGetRelationName(OldHeap), - RelationGetRelationName(OldIndex)))); + errmsg("repacking \"%s.%s\" using index scan on \"%s\"", + nspname, + RelationGetRelationName(OldHeap), + RelationGetRelationName(OldIndex))); else if (use_sort) ereport(elevel, - (errmsg("clustering \"%s.%s\" using sequential scan and sort", - nspname, - RelationGetRelationName(OldHeap)))); + errmsg("repacking \"%s.%s\" using sequential scan and sort", + nspname, + RelationGetRelationName(OldHeap))); else ereport(elevel, - (errmsg("vacuuming \"%s.%s\"", - nspname, - RelationGetRelationName(OldHeap)))); + errmsg("repacking \"%s.%s\" in physical order", + nspname, + RelationGetRelationName(OldHeap))); =20 /* * Hand off the actual copying to AM specific function, the generic code @@ -1458,8 +1461,8 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, int i; =20 /* Report that we are now swapping relation files */ - pgstat_progress_update_param(PROGRESS_CLUSTER_PHASE, - PROGRESS_CLUSTER_PHASE_SWAP_REL_FILES); + pgstat_progress_update_param(PROGRESS_REPACK_PHASE, + PROGRESS_REPACK_PHASE_SWAP_REL_FILES); =20 /* Zero out possible results from swapped_relation_files */ memset(mapped_tables, 0, sizeof(mapped_tables)); @@ -1509,14 +1512,14 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, reindex_flags |=3D REINDEX_REL_FORCE_INDEXES_PERMANENT; =20 /* Report that we are now reindexing relations */ - pgstat_progress_update_param(PROGRESS_CLUSTER_PHASE, - PROGRESS_CLUSTER_PHASE_REBUILD_INDEX); + pgstat_progress_update_param(PROGRESS_REPACK_PHASE, + PROGRESS_REPACK_PHASE_REBUILD_INDEX); =20 reindex_relation(NULL, OIDOldHeap, reindex_flags, &reindex_params); =20 /* Report that we are now doing clean up */ - pgstat_progress_update_param(PROGRESS_CLUSTER_PHASE, - PROGRESS_CLUSTER_PHASE_FINAL_CLEANUP); + pgstat_progress_update_param(PROGRESS_REPACK_PHASE, + PROGRESS_REPACK_PHASE_FINAL_CLEANUP); =20 /* * If the relation being rebuilt is pg_class, swap_relation_files() @@ -1632,106 +1635,191 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, } } =20 - /* - * Get a list of tables that the current user has privileges on and - * have indisclustered set. Return the list in a List * of RelToCluster - * (stored in the specified memory context), each one giving the tableOid - * and the indexOid on which the table is already clustered. + * Determine which relations to process, when REPACK/CLUSTER is called + * without specifying a table name. The exact process depends on whether + * USING INDEX was given or not, and in any case we only return tables and + * materialized views that the current user has privileges to repack/clust= er. + * + * If USING INDEX was given, we scan pg_index to find those that have + * indisclustered set; if it was not given, scan pg_class and return all + * tables. + * + * Return it as a list of RelToCluster in the given memory context. */ static List * -get_tables_to_cluster(MemoryContext cluster_context) +get_tables_to_repack(RepackCommand cmd, bool usingindex, MemoryContext per= mcxt) { - Relation indRelation; + Relation catalog; TableScanDesc scan; - ScanKeyData entry; - HeapTuple indexTuple; - Form_pg_index index; - MemoryContext old_context; + HeapTuple tuple; List *rtcs =3D NIL; =20 - /* - * Get all indexes that have indisclustered set and that the current user - * has the appropriate privileges for. - */ - indRelation =3D table_open(IndexRelationId, AccessShareLock); - ScanKeyInit(&entry, - Anum_pg_index_indisclustered, - BTEqualStrategyNumber, F_BOOLEQ, - BoolGetDatum(true)); - scan =3D table_beginscan_catalog(indRelation, 1, &entry); - while ((indexTuple =3D heap_getnext(scan, ForwardScanDirection)) !=3D NUL= L) + if (usingindex) { - RelToCluster *rtc; + ScanKeyData entry; + + catalog =3D table_open(IndexRelationId, AccessShareLock); + ScanKeyInit(&entry, + Anum_pg_index_indisclustered, + BTEqualStrategyNumber, F_BOOLEQ, + BoolGetDatum(true)); + scan =3D table_beginscan_catalog(catalog, 1, &entry); + while ((tuple =3D heap_getnext(scan, ForwardScanDirection)) !=3D NULL) + { + RelToCluster *rtc; + Form_pg_index index; + MemoryContext oldcxt; =20 - index =3D (Form_pg_index) GETSTRUCT(indexTuple); + index =3D (Form_pg_index) GETSTRUCT(tuple); =20 - if (!cluster_is_permitted_for_relation(index->indrelid, GetUserId())) - continue; + /* + * Try to obtain a light lock on the index's table, to ensure it + * doesn't go away while we collect the list. If we cannot, just + * disregard it. + */ + if (!ConditionalLockRelationOid(index->indrelid, AccessShareLock)) + continue; =20 - /* Use a permanent memory context for the result list */ - old_context =3D MemoryContextSwitchTo(cluster_context); + /* Verify that the table still exists */ + if (!SearchSysCacheExists1(RELOID, ObjectIdGetDatum(index->indrelid))) + { + /* Release useless lock */ + UnlockRelationOid(index->indrelid, AccessShareLock); + continue; + } =20 - rtc =3D palloc_object(RelToCluster); - rtc->tableOid =3D index->indrelid; - rtc->indexOid =3D index->indexrelid; - rtcs =3D lappend(rtcs, rtc); + if (!cluster_is_permitted_for_relation(cmd, index->indrelid, + GetUserId())) + continue; + + /* Use a permanent memory context for the result list */ + oldcxt =3D MemoryContextSwitchTo(permcxt); + rtc =3D palloc_object(RelToCluster); + rtc->tableOid =3D index->indrelid; + rtc->indexOid =3D index->indexrelid; + rtcs =3D lappend(rtcs, rtc); + MemoryContextSwitchTo(oldcxt); + } + } + else + { + catalog =3D table_open(RelationRelationId, AccessShareLock); + scan =3D table_beginscan_catalog(catalog, 0, NULL); + + while ((tuple =3D heap_getnext(scan, ForwardScanDirection)) !=3D NULL) + { + RelToCluster *rtc; + Form_pg_class class; + MemoryContext oldcxt; + + class =3D (Form_pg_class) GETSTRUCT(tuple); + + /* + * Try to obtain a light lock on the table, to ensure it doesn't + * go away while we collect the list. If we cannot, just + * disregard the table. + */ + if (!ConditionalLockRelationOid(class->oid, AccessShareLock)) + continue; =20 - MemoryContextSwitchTo(old_context); + /* Verify that the table still exists */ + if (!SearchSysCacheExists1(RELOID, ObjectIdGetDatum(class->oid))) + { + /* Release useless lock */ + UnlockRelationOid(class->oid, AccessShareLock); + continue; + } + + /* Can only process plain tables and matviews */ + if (class->relkind !=3D RELKIND_RELATION && + class->relkind !=3D RELKIND_MATVIEW) + continue; + + /* noisily skip rels which the user can't process */ + if (!cluster_is_permitted_for_relation(cmd, class->oid, + GetUserId())) + continue; + + /* Use a permanent memory context for the result list */ + oldcxt =3D MemoryContextSwitchTo(permcxt); + rtc =3D palloc_object(RelToCluster); + rtc->tableOid =3D class->oid; + rtc->indexOid =3D InvalidOid; + rtcs =3D lappend(rtcs, rtc); + MemoryContextSwitchTo(oldcxt); + } } - table_endscan(scan); =20 - relation_close(indRelation, AccessShareLock); + table_endscan(scan); + relation_close(catalog, AccessShareLock); =20 return rtcs; } =20 /* - * Given an index on a partitioned table, return a list of RelToCluster for + * Given a partitioned table or its index, return a list of RelToCluster f= or * all the children leaves tables/indexes. * * Like expand_vacuum_rel, but here caller must hold AccessExclusiveLock * on the table containing the index. + * + * 'rel_is_index' tells whether 'relid' is that of an index (true) or of t= he + * owning relation. */ static List * -get_tables_to_cluster_partitioned(MemoryContext cluster_context, Oid index= Oid) +get_tables_to_repack_partitioned(RepackCommand cmd, Oid relid, + bool rel_is_index, MemoryContext permcxt) { List *inhoids; - ListCell *lc; List *rtcs =3D NIL; - MemoryContext old_context; - - /* Do not lock the children until they're processed */ - inhoids =3D find_all_inheritors(indexOid, NoLock, NULL); =20 - foreach(lc, inhoids) + /* + * Do not lock the children until they're processed. Note that we do hold + * a lock on the parent partitioned table. + */ + inhoids =3D find_all_inheritors(relid, NoLock, NULL); + foreach_oid(child_oid, inhoids) { - Oid indexrelid =3D lfirst_oid(lc); - Oid relid =3D IndexGetRelation(indexrelid, false); + Oid table_oid, + index_oid; RelToCluster *rtc; + MemoryContext oldcxt; =20 - /* consider only leaf indexes */ - if (get_rel_relkind(indexrelid) !=3D RELKIND_INDEX) - continue; + if (rel_is_index) + { + /* consider only leaf indexes */ + if (get_rel_relkind(child_oid) !=3D RELKIND_INDEX) + continue; + + table_oid =3D IndexGetRelation(child_oid, false); + index_oid =3D child_oid; + } + else + { + /* consider only leaf relations */ + if (get_rel_relkind(child_oid) !=3D RELKIND_RELATION) + continue; + + table_oid =3D child_oid; + index_oid =3D InvalidOid; + } =20 /* * It's possible that the user does not have privileges to CLUSTER the - * leaf partition despite having such privileges on the partitioned - * table. We skip any partitions which the user is not permitted to - * CLUSTER. + * leaf partition despite having them on the partitioned table. Skip + * if so. */ - if (!cluster_is_permitted_for_relation(relid, GetUserId())) + if (!cluster_is_permitted_for_relation(cmd, table_oid, GetUserId())) continue; =20 /* Use a permanent memory context for the result list */ - old_context =3D MemoryContextSwitchTo(cluster_context); - + oldcxt =3D MemoryContextSwitchTo(permcxt); rtc =3D palloc_object(RelToCluster); - rtc->tableOid =3D relid; - rtc->indexOid =3D indexrelid; + rtc->tableOid =3D table_oid; + rtc->indexOid =3D index_oid; rtcs =3D lappend(rtcs, rtc); - - MemoryContextSwitchTo(old_context); + MemoryContextSwitchTo(oldcxt); } =20 return rtcs; @@ -1742,13 +1830,167 @@ get_tables_to_cluster_partitioned(MemoryContext cl= uster_context, Oid indexOid) * function emits a WARNING. */ static bool -cluster_is_permitted_for_relation(Oid relid, Oid userid) +cluster_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid) { + Assert(cmd =3D=3D REPACK_COMMAND_CLUSTER || cmd =3D=3D REPACK_COMMAND_REP= ACK); + if (pg_class_aclcheck(relid, userid, ACL_MAINTAIN) =3D=3D ACLCHECK_OK) return true; =20 ereport(WARNING, - (errmsg("permission denied to cluster \"%s\", skipping it", - get_rel_name(relid)))); + errmsg("permission denied to execute %s on \"%s\", skipping it", + RepackCommandAsString(cmd), + get_rel_name(relid))); + return false; } + + +/* + * Given a RepackStmt with an indicated relation name, resolve the relation + * name, obtain lock on it, then determine what to do based on the relation + * type: if it's table and not partitioned, repack it as indicated (using = an + * existing clustered index, or following the given one), and return NULL. + * + * On the other hand, if the table is partitioned, do nothing further and + * instead return the opened and locked relcache entry, so that caller can + * process the partitions using the multiple-table handling code. In this + * case, if an index name is given, it's up to the caller to resolve it. + */ +static Relation +process_single_relation(RepackStmt *stmt, ClusterParams *params) +{ + Relation rel; + Oid tableOid; + + Assert(stmt->relation !=3D NULL); + Assert(stmt->command =3D=3D REPACK_COMMAND_CLUSTER || + stmt->command =3D=3D REPACK_COMMAND_REPACK); + + /* + * Find, lock, and check permissions on the table. We obtain + * AccessExclusiveLock right away to avoid lock-upgrade hazard in the + * single-transaction case. + */ + tableOid =3D RangeVarGetRelidExtended(stmt->relation->relation, + AccessExclusiveLock, + 0, + RangeVarCallbackMaintainsTable, + NULL); + rel =3D table_open(tableOid, NoLock); + + /* + * Reject clustering a remote temp table ... their local buffer manager is + * not going to cope. + */ + if (RELATION_IS_OTHER_TEMP(rel)) + ereport(ERROR, + errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("cannot execute %s on temporary tables of other sessions", + RepackCommandAsString(stmt->command))); + + /* + * Make sure ANALYZE is specified if a column list is present. + */ + if ((params->options & CLUOPT_ANALYZE) =3D=3D 0 && stmt->relation->va_col= s !=3D NIL) + ereport(ERROR, + errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("ANALYZE option must be specified when a column list is provide= d")); + + /* + * For partitioned tables, let caller handle this. Otherwise, process it + * here and we're done. + */ + if (rel->rd_rel->relkind =3D=3D RELKIND_PARTITIONED_TABLE) + return rel; + else + { + Oid indexOid; + + indexOid =3D determine_clustered_index(rel, stmt->usingindex, + stmt->indexname); + if (OidIsValid(indexOid)) + check_index_is_clusterable(rel, indexOid, AccessExclusiveLock); + cluster_rel(stmt->command, rel, indexOid, params); + + /* Do an analyze, if requested */ + if (params->options & CLUOPT_ANALYZE) + { + VacuumParams vac_params =3D {0}; + + vac_params.options |=3D VACOPT_ANALYZE; + if (params->options & CLUOPT_VERBOSE) + vac_params.options |=3D VACOPT_VERBOSE; + analyze_rel(tableOid, NULL, vac_params, + stmt->relation->va_cols, true, NULL); + } + + return NULL; + } +} + +/* + * Given a relation and the usingindex/indexname options in a + * REPACK USING INDEX or CLUSTER command, return the OID of the + * index to use for clustering the table. + * + * Caller must hold lock on the relation so that the set of indexes + * doesn't change, and must call check_index_is_clusterable. + */ +static Oid +determine_clustered_index(Relation rel, bool usingindex, const char *index= name) +{ + Oid indexOid; + + if (indexname =3D=3D NULL && usingindex) + { + /* + * If USING INDEX with no name is given, find a clustered index, or + * error out if none. + */ + indexOid =3D InvalidOid; + foreach_oid(idxoid, RelationGetIndexList(rel)) + { + if (get_index_isclustered(idxoid)) + { + indexOid =3D idxoid; + break; + } + } + + if (!OidIsValid(indexOid)) + ereport(ERROR, + errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("there is no previously clustered index for table \"%s\"", + RelationGetRelationName(rel))); + } + else if (indexname !=3D NULL) + { + /* An index was specified; obtain its OID. */ + indexOid =3D get_relname_relid(indexname, rel->rd_rel->relnamespace); + if (!OidIsValid(indexOid)) + ereport(ERROR, + errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("index \"%s\" for table \"%s\" does not exist", + indexname, RelationGetRelationName(rel))); + } + else + indexOid =3D InvalidOid; + + return indexOid; +} + +static const char * +RepackCommandAsString(RepackCommand cmd) +{ + switch (cmd) + { + case REPACK_COMMAND_REPACK: + return "REPACK"; + case REPACK_COMMAND_VACUUMFULL: + return "VACUUM"; + case REPACK_COMMAND_CLUSTER: + return "CLUSTER"; + } + return "???"; /* keep compiler quiet */ +} diff --git a/src/backend/commands/vacuum.c b/src/backend/commands/vacuum.c index aa4fbec143f..c363467a9cc 100644 --- a/src/backend/commands/vacuum.c +++ b/src/backend/commands/vacuum.c @@ -351,7 +351,6 @@ ExecVacuum(ParseState *pstate, VacuumStmt *vacstmt, boo= l isTopLevel) } } =20 - /* * Sanity check DISABLE_PAGE_SKIPPING option. */ @@ -2289,8 +2288,9 @@ vacuum_rel(Oid relid, RangeVar *relation, VacuumParam= s params, if ((params.options & VACOPT_VERBOSE) !=3D 0) cluster_params.options |=3D CLUOPT_VERBOSE; =20 - /* VACUUM FULL is now a variant of CLUSTER; see cluster.c */ - cluster_rel(rel, InvalidOid, &cluster_params); + /* VACUUM FULL is a variant of REPACK; see cluster.c */ + cluster_rel(REPACK_COMMAND_VACUUMFULL, rel, InvalidOid, + &cluster_params); /* cluster_rel closes the relation, but keeps lock */ =20 rel =3D NULL; diff --git a/src/backend/parser/gram.y b/src/backend/parser/gram.y index 713ee5c10a2..54d37c10447 100644 --- a/src/backend/parser/gram.y +++ b/src/backend/parser/gram.y @@ -287,7 +287,7 @@ static Node *makeRecursiveViewSelect(char *relname, Lis= t *aliases, Node *query); AlterCompositeTypeStmt AlterUserMappingStmt AlterRoleStmt AlterRoleSetStmt AlterPolicyStmt AlterStatsStmt AlterDefaultPrivilegesStmt DefACLAction - AnalyzeStmt CallStmt ClosePortalStmt ClusterStmt CommentStmt + AnalyzeStmt CallStmt ClosePortalStmt CommentStmt ConstraintsSetStmt CopyStmt CreateAsStmt CreateCastStmt CreateDomainStmt CreateExtensionStmt CreateGroupStmt CreateOpClassStmt CreateOpFamilyStmt AlterOpFamilyStmt CreatePLangStmt @@ -304,7 +304,7 @@ static Node *makeRecursiveViewSelect(char *relname, Lis= t *aliases, Node *query); GrantStmt GrantRoleStmt ImportForeignSchemaStmt IndexStmt InsertStmt ListenStmt LoadStmt LockStmt MergeStmt NotifyStmt ExplainableStmt Prepar= ableStmt CreateFunctionStmt AlterFunctionStmt ReindexStmt RemoveAggrStmt - RemoveFuncStmt RemoveOperStmt RenameStmt ReturnStmt RevokeStmt RevokeRol= eStmt + RemoveFuncStmt RemoveOperStmt RenameStmt RepackStmt ReturnStmt RevokeStm= t RevokeRoleStmt RuleActionStmt RuleActionStmtOrEmpty RuleStmt SecLabelStmt SelectStmt TransactionStmt TransactionStmtLegacy TruncateSt= mt UnlistenStmt UpdateStmt VacuumStmt @@ -323,7 +323,7 @@ static Node *makeRecursiveViewSelect(char *relname, Lis= t *aliases, Node *query); =20 %type <str> opt_single_name %type <list> opt_qualified_name -%type <boolean> opt_concurrently +%type <boolean> opt_concurrently opt_usingindex %type <dbehavior> opt_drop_behavior %type <list> opt_utility_option_list %type <list> opt_wait_with_clause @@ -773,7 +773,7 @@ static Node *makeRecursiveViewSelect(char *relname, Lis= t *aliases, Node *query); QUOTE QUOTES =20 RANGE READ REAL REASSIGN RECURSIVE REF_P REFERENCES REFERENCING - REFRESH REINDEX RELATIVE_P RELEASE RENAME REPEATABLE REPLACE REPLICA + REFRESH REINDEX RELATIVE_P RELEASE RENAME REPACK REPEATABLE REPLACE REPLI= CA RESET RESPECT_P RESTART RESTRICT RETURN RETURNING RETURNS REVOKE RIGHT RO= LE ROLLBACK ROLLUP ROUTINE ROUTINES ROW ROWS RULE =20 @@ -1035,7 +1035,6 @@ stmt: | CallStmt | CheckPointStmt | ClosePortalStmt - | ClusterStmt | CommentStmt | ConstraintsSetStmt | CopyStmt @@ -1109,6 +1108,7 @@ stmt: | RemoveFuncStmt | RemoveOperStmt | RenameStmt + | RepackStmt | RevokeStmt | RevokeRoleStmt | RuleStmt @@ -1146,6 +1146,11 @@ opt_concurrently: | /*EMPTY*/ { $$ =3D false; } ; =20 +opt_usingindex: + USING INDEX { $$ =3D true; } + | /* EMPTY */ { $$ =3D false; } + ; + opt_drop_behavior: CASCADE { $$ =3D DROP_CASCADE; } | RESTRICT { $$ =3D DROP_RESTRICT; } @@ -12036,38 +12041,82 @@ CreateConversionStmt: /*************************************************************************= **** * * QUERY: + * REPACK [ (options) ] [ <qualified_name> [ <name_list> ] [ USING INDE= X <index_name> ] ] + * + * obsolete variants: * CLUSTER (options) [ <qualified_name> [ USING <index_name> ] ] * CLUSTER [VERBOSE] [ <qualified_name> [ USING <index_name> ] ] * CLUSTER [VERBOSE] <index_name> ON <qualified_name> (for pre-8.3) * *************************************************************************= ****/ =20 -ClusterStmt: - CLUSTER '(' utility_option_list ')' qualified_name cluster_index_specif= ication +RepackStmt: + REPACK opt_utility_option_list vacuum_relation USING INDEX name { - ClusterStmt *n =3D makeNode(ClusterStmt); + RepackStmt *n =3D makeNode(RepackStmt); =20 - n->relation =3D $5; + n->command =3D REPACK_COMMAND_REPACK; + n->relation =3D (VacuumRelation *) $3; n->indexname =3D $6; + n->usingindex =3D true; + n->params =3D $2; + $$ =3D (Node *) n; + } + | REPACK opt_utility_option_list vacuum_relation opt_usingindex + { + RepackStmt *n =3D makeNode(RepackStmt); + + n->command =3D REPACK_COMMAND_REPACK; + n->relation =3D (VacuumRelation *) $3; + n->indexname =3D NULL; + n->usingindex =3D $4; + n->params =3D $2; + $$ =3D (Node *) n; + } + | REPACK opt_utility_option_list opt_usingindex + { + RepackStmt *n =3D makeNode(RepackStmt); + + n->command =3D REPACK_COMMAND_REPACK; + n->relation =3D NULL; + n->indexname =3D NULL; + n->usingindex =3D $3; + n->params =3D $2; + $$ =3D (Node *) n; + } + | CLUSTER '(' utility_option_list ')' qualified_name cluster_index_spec= ification + { + RepackStmt *n =3D makeNode(RepackStmt); + + n->command =3D REPACK_COMMAND_CLUSTER; + n->relation =3D makeNode(VacuumRelation); + n->relation->relation =3D $5; + n->indexname =3D $6; + n->usingindex =3D true; n->params =3D $3; $$ =3D (Node *) n; } | CLUSTER opt_utility_option_list { - ClusterStmt *n =3D makeNode(ClusterStmt); + RepackStmt *n =3D makeNode(RepackStmt); =20 + n->command =3D REPACK_COMMAND_CLUSTER; n->relation =3D NULL; n->indexname =3D NULL; + n->usingindex =3D true; n->params =3D $2; $$ =3D (Node *) n; } /* unparenthesized VERBOSE kept for pre-14 compatibility */ | CLUSTER opt_verbose qualified_name cluster_index_specification { - ClusterStmt *n =3D makeNode(ClusterStmt); + RepackStmt *n =3D makeNode(RepackStmt); =20 - n->relation =3D $3; + n->command =3D REPACK_COMMAND_CLUSTER; + n->relation =3D makeNode(VacuumRelation); + n->relation->relation =3D $3; n->indexname =3D $4; + n->usingindex =3D true; if ($2) n->params =3D list_make1(makeDefElem("verbose", NULL, @2)); $$ =3D (Node *) n; @@ -12075,20 +12124,25 @@ ClusterStmt: /* unparenthesized VERBOSE kept for pre-17 compatibility */ | CLUSTER VERBOSE { - ClusterStmt *n =3D makeNode(ClusterStmt); + RepackStmt *n =3D makeNode(RepackStmt); =20 + n->command =3D REPACK_COMMAND_CLUSTER; n->relation =3D NULL; n->indexname =3D NULL; + n->usingindex =3D true; n->params =3D list_make1(makeDefElem("verbose", NULL, @2)); $$ =3D (Node *) n; } /* kept for pre-8.3 compatibility */ | CLUSTER opt_verbose name ON qualified_name { - ClusterStmt *n =3D makeNode(ClusterStmt); + RepackStmt *n =3D makeNode(RepackStmt); =20 - n->relation =3D $5; + n->command =3D REPACK_COMMAND_CLUSTER; + n->relation =3D makeNode(VacuumRelation); + n->relation->relation =3D $5; n->indexname =3D $3; + n->usingindex =3D true; if ($2) n->params =3D list_make1(makeDefElem("verbose", NULL, @2)); $$ =3D (Node *) n; @@ -18127,6 +18181,7 @@ unreserved_keyword: | RELATIVE_P | RELEASE | RENAME + | REPACK | REPEATABLE | REPLACE | REPLICA @@ -18764,6 +18819,7 @@ bare_label_keyword: | RELATIVE_P | RELEASE | RENAME + | REPACK | REPEATABLE | REPLACE | REPLICA diff --git a/src/backend/tcop/utility.c b/src/backend/tcop/utility.c index 34dd6e18df5..ca737b05115 100644 --- a/src/backend/tcop/utility.c +++ b/src/backend/tcop/utility.c @@ -279,9 +279,9 @@ ClassifyUtilityCommandAsReadOnly(Node *parsetree) return COMMAND_OK_IN_RECOVERY | COMMAND_OK_IN_READ_ONLY_TXN; } =20 - case T_ClusterStmt: case T_ReindexStmt: case T_VacuumStmt: + case T_RepackStmt: { /* * These commands write WAL, so they're not strictly @@ -856,14 +856,14 @@ standard_ProcessUtility(PlannedStmt *pstmt, ExecuteCallStmt(castNode(CallStmt, parsetree), params, isAtomicContext,= dest); break; =20 - case T_ClusterStmt: - cluster(pstate, (ClusterStmt *) parsetree, isTopLevel); - break; - case T_VacuumStmt: ExecVacuum(pstate, (VacuumStmt *) parsetree, isTopLevel); break; =20 + case T_RepackStmt: + ExecRepack(pstate, (RepackStmt *) parsetree, isTopLevel); + break; + case T_ExplainStmt: ExplainQuery(pstate, (ExplainStmt *) parsetree, params, dest); break; @@ -2865,10 +2865,6 @@ CreateCommandTag(Node *parsetree) tag =3D CMDTAG_CALL; break; =20 - case T_ClusterStmt: - tag =3D CMDTAG_CLUSTER; - break; - case T_VacuumStmt: if (((VacuumStmt *) parsetree)->is_vacuumcmd) tag =3D CMDTAG_VACUUM; @@ -2876,6 +2872,13 @@ CreateCommandTag(Node *parsetree) tag =3D CMDTAG_ANALYZE; break; =20 + case T_RepackStmt: + if (((RepackStmt *) parsetree)->command =3D=3D REPACK_COMMAND_CLUSTER) + tag =3D CMDTAG_CLUSTER; + else + tag =3D CMDTAG_REPACK; + break; + case T_ExplainStmt: tag =3D CMDTAG_EXPLAIN; break; @@ -3517,7 +3520,7 @@ GetCommandLogLevel(Node *parsetree) lev =3D LOGSTMT_ALL; break; =20 - case T_ClusterStmt: + case T_RepackStmt: lev =3D LOGSTMT_DDL; break; =20 diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pg= statfuncs.c index 73ca0bb0b7f..55a69bf681d 100644 --- a/src/backend/utils/adt/pgstatfuncs.c +++ b/src/backend/utils/adt/pgstatfuncs.c @@ -287,8 +287,8 @@ pg_stat_get_progress_info(PG_FUNCTION_ARGS) cmdtype =3D PROGRESS_COMMAND_VACUUM; else if (pg_strcasecmp(cmd, "ANALYZE") =3D=3D 0) cmdtype =3D PROGRESS_COMMAND_ANALYZE; - else if (pg_strcasecmp(cmd, "CLUSTER") =3D=3D 0) - cmdtype =3D PROGRESS_COMMAND_CLUSTER; + else if (pg_strcasecmp(cmd, "REPACK") =3D=3D 0) + cmdtype =3D PROGRESS_COMMAND_REPACK; else if (pg_strcasecmp(cmd, "CREATE INDEX") =3D=3D 0) cmdtype =3D PROGRESS_COMMAND_CREATE_INDEX; else if (pg_strcasecmp(cmd, "BASEBACKUP") =3D=3D 0) diff --git a/src/bin/psql/tab-complete.in.c b/src/bin/psql/tab-complete.in.c index 8b91bc00062..2a1bb47ff03 100644 --- a/src/bin/psql/tab-complete.in.c +++ b/src/bin/psql/tab-complete.in.c @@ -1267,7 +1267,7 @@ static const char *const sql_commands[] =3D { "DELETE FROM", "DISCARD", "DO", "DROP", "END", "EXECUTE", "EXPLAIN", "FETCH", "GRANT", "IMPORT FOREIGN SCHEMA", "INSERT INTO", "LISTEN", "LOAD= ", "LOCK", "MERGE INTO", "MOVE", "NOTIFY", "PREPARE", - "REASSIGN", "REFRESH MATERIALIZED VIEW", "REINDEX", "RELEASE", + "REASSIGN", "REFRESH MATERIALIZED VIEW", "REINDEX", "RELEASE", "REPACK", "RESET", "REVOKE", "ROLLBACK", "SAVEPOINT", "SECURITY LABEL", "SELECT", "SET", "SHOW", "START", "TABLE", "TRUNCATE", "UNLISTEN", "UPDATE", "VACUUM", "VALUES", @@ -5086,6 +5086,46 @@ match_previous_words(int pattern_id, COMPLETE_WITH_QUERY(Query_for_list_of_tablespaces); } =20 +/* REPACK */ + else if (Matches("REPACK")) + COMPLETE_WITH_SCHEMA_QUERY_PLUS(Query_for_list_of_clusterables, + "(", "USING INDEX"); + else if (Matches("REPACK", "(*)")) + COMPLETE_WITH_SCHEMA_QUERY_PLUS(Query_for_list_of_clusterables, + "USING INDEX"); + else if (Matches("REPACK", MatchAnyExcept("("))) + COMPLETE_WITH("USING INDEX"); + else if (Matches("REPACK", "(*)", MatchAnyExcept("("))) + COMPLETE_WITH("USING INDEX"); + else if (Matches("REPACK", MatchAny, "USING", "INDEX") || + Matches("REPACK", "(*)", MatchAny, "USING", "INDEX")) + { + set_completion_reference(prev3_wd); + COMPLETE_WITH_SCHEMA_QUERY(Query_for_index_of_table); + } + /* + * Complete ... [ (*) ] <sth> USING INDEX, with a list of indexes for + * <sth>. + */ + else if (TailMatches(MatchAny, "USING", "INDEX")) + { + set_completion_reference(prev3_wd); + COMPLETE_WITH_SCHEMA_QUERY(Query_for_index_of_table); + } + else if (HeadMatches("REPACK", "(*") && + !HeadMatches("REPACK", "(*)")) + { + /* + * This fires if we're in an unfinished parenthesized option list. + * get_previous_words treats a completed parenthesized option list as + * one word, so the above test is correct. + */ + if (ends_with(prev_wd, '(') || ends_with(prev_wd, ',')) + COMPLETE_WITH("ANALYZE", "VERBOSE"); + else if (TailMatches("ANALYZE", "VERBOSE")) + COMPLETE_WITH("ON", "OFF"); + } + /* SECURITY LABEL */ else if (Matches("SECURITY")) COMPLETE_WITH("LABEL"); diff --git a/src/bin/scripts/Makefile b/src/bin/scripts/Makefile index e6cd9ef4af5..f964a5803ca 100644 --- a/src/bin/scripts/Makefile +++ b/src/bin/scripts/Makefile @@ -23,6 +23,7 @@ PROGRAMS =3D \ dropdb \ dropuser \ pg_isready \ + pg_repackdb \ reindexdb \ vacuumdb =20 @@ -39,6 +40,7 @@ clusterdb: clusterdb.o common.o $(WIN32RES) | submake-lib= pq submake-libpgport su vacuumdb: vacuumdb.o vacuuming.o common.o $(WIN32RES) | submake-libpq subm= ake-libpgport submake-libpgfeutils reindexdb: reindexdb.o common.o $(WIN32RES) | submake-libpq submake-libpgp= ort submake-libpgfeutils pg_isready: pg_isready.o common.o $(WIN32RES) | submake-libpq submake-libp= gport submake-libpgfeutils +pg_repackdb: pg_repackdb.o vacuuming.o common.o $(WIN32RES) | submake-libp= q submake-libpgport submake-libpgfeutils =20 install: all installdirs $(INSTALL_PROGRAM) createdb$(X) '$(DESTDIR)$(bindir)'/createdb$(X) @@ -49,6 +51,7 @@ install: all installdirs $(INSTALL_PROGRAM) vacuumdb$(X) '$(DESTDIR)$(bindir)'/vacuumdb$(X) $(INSTALL_PROGRAM) reindexdb$(X) '$(DESTDIR)$(bindir)'/reindexdb$(X) $(INSTALL_PROGRAM) pg_isready$(X) '$(DESTDIR)$(bindir)'/pg_isready$(X) + $(INSTALL_PROGRAM) pg_repackdb$(X) '$(DESTDIR)$(bindir)'/pg_repackdb$(X) =20 installdirs: $(MKDIR_P) '$(DESTDIR)$(bindir)' diff --git a/src/bin/scripts/meson.build b/src/bin/scripts/meson.build index c083ec38099..1e88bacebba 100644 --- a/src/bin/scripts/meson.build +++ b/src/bin/scripts/meson.build @@ -42,6 +42,7 @@ vacuuming_common =3D static_library('libvacuuming_common', =20 binaries =3D [ 'vacuumdb', + 'pg_repackdb', ] foreach binary : binaries binary_sources =3D files('@[email protected]'.format(binary)) @@ -80,6 +81,7 @@ tests +=3D { 't/100_vacuumdb.pl', 't/101_vacuumdb_all.pl', 't/102_vacuumdb_stages.pl', + 't/103_repackdb.pl', 't/200_connstr.pl', ], }, diff --git a/src/bin/scripts/pg_repackdb.c b/src/bin/scripts/pg_repackdb.c new file mode 100644 index 00000000000..2765d1e97b8 --- /dev/null +++ b/src/bin/scripts/pg_repackdb.c @@ -0,0 +1,240 @@ +/*------------------------------------------------------------------------- + * + * pg_repackdb + * An utility to run REPACK + * + * Portions Copyright (c) 1996-2025, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * FIXME: this is missing a way to specify the index to use to repack one + * table, or whether to pass a WITH INDEX clause when multiple tables are + * used. Something like --index[=3Dindexname]. Adding that bleeds into + * vacuuming.c as well. + * + * src/bin/scripts/pg_repackdb.c + * + *------------------------------------------------------------------------- + */ + +#include "postgres_fe.h" + +#include <limits.h> + +#include "common.h" +#include "common/logging.h" +#include "fe_utils/option_utils.h" +#include "vacuuming.h" + +static void help(const char *progname); +static void check_objfilter(bits32 objfilter); + +int +main(int argc, char *argv[]) +{ + static struct option long_options[] =3D { + {"host", required_argument, NULL, 'h'}, + {"port", required_argument, NULL, 'p'}, + {"username", required_argument, NULL, 'U'}, + {"no-password", no_argument, NULL, 'w'}, + {"password", no_argument, NULL, 'W'}, + {"echo", no_argument, NULL, 'e'}, + {"quiet", no_argument, NULL, 'q'}, + {"dbname", required_argument, NULL, 'd'}, + {"analyze", no_argument, NULL, 'z'}, + {"all", no_argument, NULL, 'a'}, + /* XXX this could be 'i', but optional_arg is messy */ + {"index", optional_argument, NULL, 1}, + {"table", required_argument, NULL, 't'}, + {"verbose", no_argument, NULL, 'v'}, + {"jobs", required_argument, NULL, 'j'}, + {"schema", required_argument, NULL, 'n'}, + {"exclude-schema", required_argument, NULL, 'N'}, + {"maintenance-db", required_argument, NULL, 2}, + {NULL, 0, NULL, 0} + }; + + const char *progname; + int optindex; + int c; + const char *dbname =3D NULL; + const char *maintenance_db =3D NULL; + ConnParams cparams; + vacuumingOptions vacopts; + SimpleStringList objects =3D {NULL, NULL}; + int concurrentCons =3D 1; + int tbl_count =3D 0; + int ret; + + /* initialize options */ + memset(&vacopts, 0, sizeof(vacopts)); + vacopts.mode =3D MODE_REPACK; + + /* the same for connection parameters */ + memset(&cparams, 0, sizeof(cparams)); + cparams.prompt_password =3D TRI_DEFAULT; + + pg_logging_init(argv[0]); + progname =3D get_progname(argv[0]); + set_pglocale_pgservice(argv[0], PG_TEXTDOMAIN("pgscripts")); + + handle_help_version_opts(argc, argv, progname, help); + + while ((c =3D getopt_long(argc, argv, "ad:eh:j:n:N:p:qt:U:vwWz", + long_options, &optindex)) !=3D -1) + { + switch (c) + { + case 'a': + vacopts.objfilter |=3D OBJFILTER_ALL_DBS; + break; + case 'd': + vacopts.objfilter |=3D OBJFILTER_DATABASE; + dbname =3D pg_strdup(optarg); + break; + case 'e': + vacopts.echo =3D true; + break; + case 'h': + cparams.pghost =3D pg_strdup(optarg); + break; + case 'j': + if (!option_parse_int(optarg, "-j/--jobs", 1, INT_MAX, + &concurrentCons)) + exit(1); + break; + case 'n': + vacopts.objfilter |=3D OBJFILTER_SCHEMA; + simple_string_list_append(&objects, optarg); + break; + case 'N': + vacopts.objfilter |=3D OBJFILTER_SCHEMA_EXCLUDE; + simple_string_list_append(&objects, optarg); + break; + case 'p': + cparams.pgport =3D pg_strdup(optarg); + break; + case 'q': + vacopts.quiet =3D true; + break; + case 't': + vacopts.objfilter |=3D OBJFILTER_TABLE; + simple_string_list_append(&objects, optarg); + tbl_count++; + break; + case 'U': + cparams.pguser =3D pg_strdup(optarg); + break; + case 'v': + vacopts.verbose =3D true; + break; + case 'w': + cparams.prompt_password =3D TRI_NO; + break; + case 'W': + cparams.prompt_password =3D TRI_YES; + break; + case 'z': + vacopts.and_analyze =3D true; + break; + case 1: + vacopts.using_index =3D true; + if (optarg) + vacopts.indexname =3D pg_strdup(optarg); + else + vacopts.indexname =3D NULL; + break; + case 2: + maintenance_db =3D pg_strdup(optarg); + break; + default: + /* getopt_long already emitted a complaint */ + pg_log_error_hint("Try \"%s --help\" for more information.", progname); + exit(1); + } + } + + /* + * Non-option argument specifies database name as long as it wasn't + * already specified with -d / --dbname + */ + if (optind < argc && dbname =3D=3D NULL) + { + vacopts.objfilter |=3D OBJFILTER_DATABASE; + dbname =3D argv[optind]; + optind++; + } + + if (optind < argc) + { + pg_log_error("too many command-line arguments (first is \"%s\")", + argv[optind]); + pg_log_error_hint("Try \"%s --help\" for more information.", progname); + exit(1); + } + + /* + * Validate the combination of filters specified in the command-line + * options. + */ + check_objfilter(vacopts.objfilter); + + ret =3D vacuuming_main(&cparams, dbname, maintenance_db, &vacopts, + &objects, tbl_count, concurrentCons, + progname); + exit(ret); +} + +/* + * Verify that the filters used at command line are compatible. + */ +void +check_objfilter(bits32 objfilter) +{ + if ((objfilter & OBJFILTER_ALL_DBS) && + (objfilter & OBJFILTER_DATABASE)) + pg_fatal("cannot repack all databases and a specific one at the same tim= e"); + + if ((objfilter & OBJFILTER_TABLE) && + (objfilter & OBJFILTER_SCHEMA)) + pg_fatal("cannot repack all tables in schema(s) and specific table(s) at= the same time"); + + if ((objfilter & OBJFILTER_TABLE) && + (objfilter & OBJFILTER_SCHEMA_EXCLUDE)) + pg_fatal("cannot repack specific table(s) and exclude schema(s) at the s= ame time"); + + if ((objfilter & OBJFILTER_SCHEMA) && + (objfilter & OBJFILTER_SCHEMA_EXCLUDE)) + pg_fatal("cannot repack all tables in schema(s) and exclude schema(s) at= the same time"); +} + +static void +help(const char *progname) +{ + printf(_("%s repacks a PostgreSQL database.\n\n"), progname); + printf(_("Usage:\n")); + printf(_(" %s [OPTION]... [DBNAME]\n"), progname); + printf(_("\nOptions:\n")); + printf(_(" -a, --all repack all databases\n")); + printf(_(" -d, --dbname=3DDBNAME database to repack\n")); + printf(_(" -e, --echo show the commands being sent = to the server\n")); + printf(_(" --index[=3DINDEX] repack following an index\n= ")); + printf(_(" -j, --jobs=3DNUM use this many concurrent co= nnections to repack\n")); + printf(_(" -n, --schema=3DSCHEMA repack tables in the specif= ied schema(s) only\n")); + printf(_(" -N, --exclude-schema=3DSCHEMA do not repack tables in the= specified schema(s)\n")); + printf(_(" -q, --quiet don't write any messages\n")); + printf(_(" -t, --table=3D'TABLE[(COLUMNS)]' repack specific table(s) on= ly\n")); + printf(_(" -v, --verbose write a lot of output\n")); + printf(_(" -V, --version output version information, t= hen exit\n")); + printf(_(" -z, --analyze update optimizer statistics\n= ")); + printf(_(" -?, --help show this help, then exit\n")= ); + printf(_("\nConnection options:\n")); + printf(_(" -h, --host=3DHOSTNAME database server host or socket di= rectory\n")); + printf(_(" -p, --port=3DPORT database server port\n")); + printf(_(" -U, --username=3DUSERNAME user name to connect as\n")); + printf(_(" -w, --no-password never prompt for password\n")); + printf(_(" -W, --password force password prompt\n")); + printf(_(" --maintenance-db=3DDBNAME alternate maintenance database\n"= )); + printf(_("\nRead the description of the SQL command REPACK for details.\n= ")); + printf(_("\nReport bugs to <%s>.\n"), PACKAGE_BUGREPORT); + printf(_("%s home page: <%s>\n"), PACKAGE_NAME, PACKAGE_URL); +} diff --git a/src/bin/scripts/t/103_repackdb.pl b/src/bin/scripts/t/103_repa= ckdb.pl new file mode 100644 index 00000000000..44113367a61 --- /dev/null +++ b/src/bin/scripts/t/103_repackdb.pl @@ -0,0 +1,47 @@ +# Copyright (c) 2021-2026, PostgreSQL Global Development Group + +use strict; +use warnings FATAL =3D> 'all'; + +use PostgreSQL::Test::Cluster; +use PostgreSQL::Test::Utils; +use Test::More; + +program_help_ok('pg_repackdb'); +program_version_ok('pg_repackdb'); +program_options_handling_ok('pg_repackdb'); + +my $node =3D PostgreSQL::Test::Cluster->new('main'); +$node->init; +$node->start; + +$node->issues_sql_like( + [ 'pg_repackdb', 'postgres', '-t', 'pg_class'], + qr/statement: REPACK.*pg_class;/, + 'pg_repackdb processes a single table'); + +$node->safe_psql('postgres', 'CREATE USER testusr; + GRANT CREATE ON SCHEMA public TO testusr'); +$node->safe_psql('postgres', + 'CREATE TABLE cluster_1 (a int primary key); + ALTER TABLE cluster_1 CLUSTER ON cluster_1_pkey; + CREATE TABLE cluster_2 (a int unique); + ALTER TABLE cluster_2 CLUSTER ON cluster_2_a_key;', + extra_params =3D> ['-U' =3D> 'testusr']); + +$node->issues_sql_like( + [ 'pg_repackdb', 'postgres', '-U', 'testusr' ], + qr/statement: REPACK.*;/, + 'SQL REPACK run'); + +$node->issues_sql_like( + [ 'pg_repackdb', 'postgres', '--index'], + qr/statement: REPACK.*cluster_1 USING INDEX.*statement: REPACK.*cluster_2= USING INDEX/ms, + 'pg_repackdb --index chooses multiple tables'); + +$node->issues_sql_like( + [ 'pg_repackdb', 'postgres', '--analyze', '-t', 'cluster_1'], + qr/statement: REPACK \(ANALYZE\) public.cluster_1/, + 'pg_repackdb --analyze works'); + +done_testing(); diff --git a/src/bin/scripts/vacuuming.c b/src/bin/scripts/vacuuming.c index faac9089a01..0fa7be3c0c3 100644 --- a/src/bin/scripts/vacuuming.c +++ b/src/bin/scripts/vacuuming.c @@ -1,6 +1,6 @@ /*------------------------------------------------------------------------- * vacuuming.c - * Helper routines for vacuumdb + * Helper routines for vacuumdb and pg_repackdb * * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group * Portions Copyright (c) 1994, Regents of the University of California @@ -194,6 +194,14 @@ vacuum_one_database(ConnParams *cparams, =20 conn =3D connectDatabase(cparams, progname, vacopts->echo, false, true); =20 + if (vacopts->mode =3D=3D MODE_REPACK && PQserverVersion(conn) < 190000) + { + /* XXX arguably, here we should use VACUUM FULL instead of failing */ + PQfinish(conn); + pg_fatal("cannot use the \"%s\" command on server versions older than Po= stgreSQL %s", + "REPACK", "19"); + } + if (vacopts->disable_page_skipping && PQserverVersion(conn) < 90600) { PQfinish(conn); @@ -286,9 +294,18 @@ vacuum_one_database(ConnParams *cparams, if (vacopts->mode =3D=3D MODE_ANALYZE_IN_STAGES) printf(_("%s: processing database \"%s\": %s\n"), progname, PQdb(conn), _(stage_messages[stage])); - else + else if (vacopts->mode =3D=3D MODE_ANALYZE) + printf(_("%s: analyzing database \"%s\"\n"), + progname, PQdb(conn)); + else if (vacopts->mode =3D=3D MODE_VACUUM) printf(_("%s: vacuuming database \"%s\"\n"), progname, PQdb(conn)); + else + { + Assert(vacopts->mode =3D=3D MODE_REPACK); + printf(_("%s: repacking database \"%s\"\n"), + progname, PQdb(conn)); + } fflush(stdout); } =20 @@ -640,6 +657,35 @@ retrieve_objects(PGconn *conn, vacuumingOptions *vacop= ts, " AND listed_objects.object_oid IS NOT NULL\n"); } =20 + /* + * In REPACK mode, if the 'using_index' option was given but no index + * name, filter only tables that have an index with indisclustered set. + * (If an index name is given, we trust the user to pass a reasonable list + * of tables.) + * + * XXX it may be worth printing an error if an index name is given with no + * list of tables. + */ + if (vacopts->mode =3D=3D MODE_REPACK && + vacopts->using_index && !vacopts->indexname) + { + appendPQExpBufferStr(&catalog_query, + " AND EXISTS (SELECT 1 FROM pg_catalog.pg_index\n" + " WHERE indrelid =3D c.oid AND indisclustered)\n"); + } + + /* + * In REPACK mode, only consider the tables that the current user has + * MAINTAIN privileges on. XXX maybe we should do this in all cases, not + * just REPACK. The vacuumdb output is too noisy for no reason. + */ + if (vacopts->mode =3D=3D MODE_REPACK) + { + appendPQExpBufferStr(&catalog_query, + " AND pg_catalog.has_table_privilege(current_user, " + "c.oid, 'MAINTAIN')\n"); + } + /* * If no tables were listed, filter for the relevant relation types. If * tables were given via --table, don't bother filtering by relation type. @@ -878,8 +924,10 @@ prepare_vacuum_command(PGconn *conn, PQExpBuffer sql, if (vacopts->verbose) appendPQExpBufferStr(sql, " VERBOSE"); } + + appendPQExpBuffer(sql, " %s", table); } - else + else if (vacopts->mode =3D=3D MODE_VACUUM) { appendPQExpBufferStr(sql, "VACUUM"); =20 @@ -993,9 +1041,39 @@ prepare_vacuum_command(PGconn *conn, PQExpBuffer sql, if (vacopts->and_analyze) appendPQExpBufferStr(sql, " ANALYZE"); } + + appendPQExpBuffer(sql, " %s", table); } + else if (vacopts->mode =3D=3D MODE_REPACK) + { + appendPQExpBufferStr(sql, "REPACK"); =20 - appendPQExpBuffer(sql, " %s;", table); + if (vacopts->verbose) + { + appendPQExpBuffer(sql, "%sVERBOSE", sep); + sep =3D comma; + } + if (vacopts->and_analyze) + { + appendPQExpBuffer(sql, "%sANALYZE", sep); + sep =3D comma; + } + + if (sep !=3D paren) + appendPQExpBufferChar(sql, ')'); + + appendPQExpBuffer(sql, " %s", table); + + if (vacopts->using_index) + { + appendPQExpBuffer(sql, " USING INDEX"); + if (vacopts->indexname) + appendPQExpBuffer(sql, " %s", fmtIdEnc(vacopts->indexname, + PQclientEncoding(conn))); + } + } + + appendPQExpBufferChar(sql, ';'); } =20 /* @@ -1024,13 +1102,21 @@ run_vacuum_command(ParallelSlot *free_slot, vacuumi= ngOptions *vacopts, { if (table) { - pg_log_error("vacuuming of table \"%s\" in database \"%s\" failed: %s", - table, PQdb(conn), PQerrorMessage(conn)); + if (vacopts->mode =3D=3D MODE_VACUUM) + pg_log_error("vacuuming of table \"%s\" in database \"%s\" failed: %s", + table, PQdb(conn), PQerrorMessage(conn)); + else + pg_log_error("repacking of table \"%s\" in database \"%s\" failed: %s", + table, PQdb(conn), PQerrorMessage(conn)); } else { - pg_log_error("vacuuming of database \"%s\" failed: %s", - PQdb(conn), PQerrorMessage(conn)); + if (vacopts->mode =3D=3D MODE_VACUUM) + pg_log_error("vacuuming of database \"%s\" failed: %s", + PQdb(conn), PQerrorMessage(conn)); + else + pg_log_error("repacking of database \"%s\" failed: %s", + PQdb(conn), PQerrorMessage(conn)); } } } diff --git a/src/bin/scripts/vacuuming.h b/src/bin/scripts/vacuuming.h index be4a75ef2f4..6e8abe00a4f 100644 --- a/src/bin/scripts/vacuuming.h +++ b/src/bin/scripts/vacuuming.h @@ -20,6 +20,7 @@ typedef enum { MODE_VACUUM, + MODE_REPACK, MODE_ANALYZE, MODE_ANALYZE_IN_STAGES } RunMode; @@ -37,6 +38,8 @@ typedef struct vacuumingOptions bool and_analyze; bool full; bool freeze; + bool using_index; + char *indexname; bool disable_page_skipping; bool skip_locked; int min_xid_age; diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 8ea81622f9d..28741988478 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -24,6 +24,7 @@ #define CLUOPT_RECHECK 0x02 /* recheck relation state */ #define CLUOPT_RECHECK_ISCLUSTERED 0x04 /* recheck relation state for * indisclustered */ +#define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ =20 /* options for CLUSTER */ typedef struct ClusterParams @@ -31,8 +32,11 @@ typedef struct ClusterParams bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; =20 -extern void cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel= ); -extern void cluster_rel(Relation OldHeap, Oid indexOid, ClusterParams *par= ams); + +extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLev= el); + +extern void cluster_rel(RepackCommand command, Relation OldHeap, Oid index= Oid, + ClusterParams *params); extern void check_index_is_clusterable(Relation OldHeap, Oid indexOid, LOCKMODE lockmode); extern void mark_index_clustered(Relation rel, Oid indexOid, bool is_inter= nal); diff --git a/src/include/commands/progress.h b/src/include/commands/progres= s.h index 359221dc296..f00e39b937d 100644 --- a/src/include/commands/progress.h +++ b/src/include/commands/progress.h @@ -73,28 +73,34 @@ #define PROGRESS_ANALYZE_STARTED_BY_MANUAL 1 #define PROGRESS_ANALYZE_STARTED_BY_AUTOVACUUM 2 =20 -/* Progress parameters for cluster */ -#define PROGRESS_CLUSTER_COMMAND 0 -#define PROGRESS_CLUSTER_PHASE 1 -#define PROGRESS_CLUSTER_INDEX_RELID 2 -#define PROGRESS_CLUSTER_HEAP_TUPLES_SCANNED 3 -#define PROGRESS_CLUSTER_HEAP_TUPLES_WRITTEN 4 -#define PROGRESS_CLUSTER_TOTAL_HEAP_BLKS 5 -#define PROGRESS_CLUSTER_HEAP_BLKS_SCANNED 6 -#define PROGRESS_CLUSTER_INDEX_REBUILD_COUNT 7 - -/* Phases of cluster (as advertised via PROGRESS_CLUSTER_PHASE) */ -#define PROGRESS_CLUSTER_PHASE_SEQ_SCAN_HEAP 1 -#define PROGRESS_CLUSTER_PHASE_INDEX_SCAN_HEAP 2 -#define PROGRESS_CLUSTER_PHASE_SORT_TUPLES 3 -#define PROGRESS_CLUSTER_PHASE_WRITE_NEW_HEAP 4 -#define PROGRESS_CLUSTER_PHASE_SWAP_REL_FILES 5 -#define PROGRESS_CLUSTER_PHASE_REBUILD_INDEX 6 -#define PROGRESS_CLUSTER_PHASE_FINAL_CLEANUP 7 - -/* Commands of PROGRESS_CLUSTER */ -#define PROGRESS_CLUSTER_COMMAND_CLUSTER 1 -#define PROGRESS_CLUSTER_COMMAND_VACUUM_FULL 2 +/* + * Progress parameters for REPACK. + * + * Values for PROGRESS_REPACK_COMMAND are defined as in RepackCommand. + * + * Note: Since REPACK shares code with CLUSTER, these values are also + * used by CLUSTER. (CLUSTER is now deprecated, so it makes little sense to + * introduce a separate set of constants.) + */ +#define PROGRESS_REPACK_COMMAND 0 +#define PROGRESS_REPACK_PHASE 1 +#define PROGRESS_REPACK_INDEX_RELID 2 +#define PROGRESS_REPACK_HEAP_TUPLES_SCANNED 3 +#define PROGRESS_REPACK_HEAP_TUPLES_WRITTEN 4 +#define PROGRESS_REPACK_TOTAL_HEAP_BLKS 5 +#define PROGRESS_REPACK_HEAP_BLKS_SCANNED 6 +#define PROGRESS_REPACK_INDEX_REBUILD_COUNT 7 + +/* + * Phases of repack (as advertised via PROGRESS_REPACK_PHASE). + */ +#define PROGRESS_REPACK_PHASE_SEQ_SCAN_HEAP 1 +#define PROGRESS_REPACK_PHASE_INDEX_SCAN_HEAP 2 +#define PROGRESS_REPACK_PHASE_SORT_TUPLES 3 +#define PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP 4 +#define PROGRESS_REPACK_PHASE_SWAP_REL_FILES 5 +#define PROGRESS_REPACK_PHASE_REBUILD_INDEX 6 +#define PROGRESS_REPACK_PHASE_FINAL_CLEANUP 7 =20 /* Progress parameters for CREATE INDEX */ /* 3, 4 and 5 reserved for "waitfor" metrics */ diff --git a/src/include/nodes/parsenodes.h b/src/include/nodes/parsenodes.h index aac4bfc70d9..e651ed3a1ff 100644 --- a/src/include/nodes/parsenodes.h +++ b/src/include/nodes/parsenodes.h @@ -3980,18 +3980,6 @@ typedef struct AlterSystemStmt VariableSetStmt *setstmt; /* SET subcommand */ } AlterSystemStmt; =20 -/* ---------------------- - * Cluster Statement (support pbrown's cluster index implementation) - * ---------------------- - */ -typedef struct ClusterStmt -{ - NodeTag type; - RangeVar *relation; /* relation being indexed, or NULL if all */ - char *indexname; /* original index defined */ - List *params; /* list of DefElem nodes */ -} ClusterStmt; - /* ---------------------- * Vacuum and Analyze Statements * @@ -4004,7 +3992,7 @@ typedef struct VacuumStmt NodeTag type; List *options; /* list of DefElem nodes */ List *rels; /* list of VacuumRelation, or NIL for all */ - bool is_vacuumcmd; /* true for VACUUM, false for ANALYZE */ + bool is_vacuumcmd; /* true for VACUUM, false otherwise */ } VacuumStmt; =20 /* @@ -4022,6 +4010,27 @@ typedef struct VacuumRelation List *va_cols; /* list of column names, or NIL for all */ } VacuumRelation; =20 +/* ---------------------- + * Repack Statement + * ---------------------- + */ +typedef enum RepackCommand +{ + REPACK_COMMAND_CLUSTER =3D 1, + REPACK_COMMAND_REPACK, + REPACK_COMMAND_VACUUMFULL, +} RepackCommand; + +typedef struct RepackStmt +{ + NodeTag type; + RepackCommand command; /* type of command being run */ + VacuumRelation *relation; /* relation being repacked */ + char *indexname; /* order tuples by this index */ + bool usingindex; /* whether USING INDEX is specified */ + List *params; /* list of DefElem nodes */ +} RepackStmt; + /* ---------------------- * Explain Statement * diff --git a/src/include/parser/kwlist.h b/src/include/parser/kwlist.h index f7753c5c8a8..6f74a8c05c7 100644 --- a/src/include/parser/kwlist.h +++ b/src/include/parser/kwlist.h @@ -377,6 +377,7 @@ PG_KEYWORD("reindex", REINDEX, UNRESERVED_KEYWORD, BARE= _LABEL) PG_KEYWORD("relative", RELATIVE_P, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("release", RELEASE, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("rename", RENAME, UNRESERVED_KEYWORD, BARE_LABEL) +PG_KEYWORD("repack", REPACK, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("repeatable", REPEATABLE, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("replace", REPLACE, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("replica", REPLICA, UNRESERVED_KEYWORD, BARE_LABEL) diff --git a/src/include/tcop/cmdtaglist.h b/src/include/tcop/cmdtaglist.h index 1290c9bab68..652dc61b834 100644 --- a/src/include/tcop/cmdtaglist.h +++ b/src/include/tcop/cmdtaglist.h @@ -196,6 +196,7 @@ PG_CMDTAG(CMDTAG_REASSIGN_OWNED, "REASSIGN OWNED", fals= e, false, false) PG_CMDTAG(CMDTAG_REFRESH_MATERIALIZED_VIEW, "REFRESH MATERIALIZED VIEW", t= rue, false, false) PG_CMDTAG(CMDTAG_REINDEX, "REINDEX", true, false, false) PG_CMDTAG(CMDTAG_RELEASE, "RELEASE", false, false, false) +PG_CMDTAG(CMDTAG_REPACK, "REPACK", false, false, false) PG_CMDTAG(CMDTAG_RESET, "RESET", false, false, false) PG_CMDTAG(CMDTAG_REVOKE, "REVOKE", true, false, false) PG_CMDTAG(CMDTAG_REVOKE_ROLE, "REVOKE ROLE", false, false, false) diff --git a/src/include/utils/backend_progress.h b/src/include/utils/backe= nd_progress.h index 19f63b41431..6300dbd15d5 100644 --- a/src/include/utils/backend_progress.h +++ b/src/include/utils/backend_progress.h @@ -24,10 +24,10 @@ typedef enum ProgressCommandType PROGRESS_COMMAND_INVALID, PROGRESS_COMMAND_VACUUM, PROGRESS_COMMAND_ANALYZE, - PROGRESS_COMMAND_CLUSTER, PROGRESS_COMMAND_CREATE_INDEX, PROGRESS_COMMAND_BASEBACKUP, PROGRESS_COMMAND_COPY, + PROGRESS_COMMAND_REPACK, } ProgressCommandType; =20 #define PGSTAT_NUM_PROGRESS_PARAM 20 diff --git a/src/test/regress/expected/cluster.out b/src/test/regress/expec= ted/cluster.out index 4d40a6809ab..277854418fa 100644 --- a/src/test/regress/expected/cluster.out +++ b/src/test/regress/expected/cluster.out @@ -495,6 +495,43 @@ ALTER TABLE clstrpart SET WITHOUT CLUSTER; ERROR: cannot mark index clustered in partitioned table ALTER TABLE clstrpart CLUSTER ON clstrpart_idx; ERROR: cannot mark index clustered in partitioned table +-- Check that REPACK sets new relfilenodes: it should process exactly the = same +-- tables as CLUSTER did. +DROP TABLE old_cluster_info; +DROP TABLE new_cluster_info; +CREATE TEMP TABLE old_cluster_info AS SELECT relname, level, relfilenode, = relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class= c ON c.oid=3Dtree.relid ; +REPACK clstrpart USING INDEX clstrpart_idx; +CREATE TEMP TABLE new_cluster_info AS SELECT relname, level, relfilenode, = relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class= c ON c.oid=3Dtree.relid ; +SELECT relname, old.level, old.relkind, old.relfilenode =3D new.relfilenod= e FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname)= ORDER BY relname COLLATE "C"; + relname | level | relkind | ?column?=20 +-------------+-------+---------+---------- + clstrpart | 0 | p | t + clstrpart1 | 1 | p | t + clstrpart11 | 2 | r | f + clstrpart12 | 2 | p | t + clstrpart2 | 1 | r | f + clstrpart3 | 1 | p | t + clstrpart33 | 2 | r | f +(7 rows) + +-- And finally the same for REPACK w/o index. +DROP TABLE old_cluster_info; +DROP TABLE new_cluster_info; +CREATE TEMP TABLE old_cluster_info AS SELECT relname, level, relfilenode, = relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class= c ON c.oid=3Dtree.relid ; +REPACK clstrpart; +CREATE TEMP TABLE new_cluster_info AS SELECT relname, level, relfilenode, = relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class= c ON c.oid=3Dtree.relid ; +SELECT relname, old.level, old.relkind, old.relfilenode =3D new.relfilenod= e FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname)= ORDER BY relname COLLATE "C"; + relname | level | relkind | ?column?=20 +-------------+-------+---------+---------- + clstrpart | 0 | p | t + clstrpart1 | 1 | p | t + clstrpart11 | 2 | r | f + clstrpart12 | 2 | p | t + clstrpart2 | 1 | r | f + clstrpart3 | 1 | p | t + clstrpart33 | 2 | r | f +(7 rows) + DROP TABLE clstrpart; -- Ownership of partitions is checked CREATE TABLE ptnowner(i int unique) PARTITION BY LIST (i); @@ -513,7 +550,7 @@ CREATE TEMP TABLE ptnowner_oldnodes AS JOIN pg_class AS c ON c.oid=3Dtree.relid; SET SESSION AUTHORIZATION regress_ptnowner; CLUSTER ptnowner USING ptnowner_i_idx; -WARNING: permission denied to cluster "ptnowner2", skipping it +WARNING: permission denied to execute CLUSTER on "ptnowner2", skipping it RESET SESSION AUTHORIZATION; SELECT a.relname, a.relfilenode=3Db.relfilenode FROM pg_class a JOIN ptnowner_oldnodes b USING (oid) ORDER BY a.relname COLLATE "C"; @@ -665,6 +702,101 @@ SELECT * FROM clstr_expression WHERE -a =3D -3 ORDER = BY -a, b; (4 rows) =20 COMMIT; +---------------------------------------------------------------------- +-- +-- REPACK +-- +---------------------------------------------------------------------- +-- REPACK handles individual tables identically to CLUSTER, but it's worth +-- checking if it handles table hierarchies identically as well. +REPACK clstr_tst USING INDEX clstr_tst_c; +-- Verify that inheritance link still works +INSERT INTO clstr_tst_inh VALUES (0, 100, 'in child table 2'); +SELECT a,b,c,substring(d for 30), length(d) from clstr_tst; + a | b | c | substring | length=20 +----+-----+------------------+--------------------------------+-------- + 10 | 14 | catorce | |=20=20=20= =20=20=20=20 + 18 | 5 | cinco | |=20=20=20= =20=20=20=20 + 9 | 4 | cuatro | |=20=20=20= =20=20=20=20 + 26 | 19 | diecinueve | |=20=20=20= =20=20=20=20 + 12 | 18 | dieciocho | |=20=20=20= =20=20=20=20 + 30 | 16 | dieciseis | |=20=20=20= =20=20=20=20 + 24 | 17 | diecisiete | |=20=20=20= =20=20=20=20 + 2 | 10 | diez | |=20=20=20= =20=20=20=20 + 23 | 12 | doce | |=20=20=20= =20=20=20=20 + 11 | 2 | dos | |=20=20=20= =20=20=20=20 + 25 | 9 | nueve | |=20=20=20= =20=20=20=20 + 31 | 8 | ocho | |=20=20=20= =20=20=20=20 + 1 | 11 | once | |=20=20=20= =20=20=20=20 + 28 | 15 | quince | |=20=20=20= =20=20=20=20 + 32 | 6 | seis | xyzzyxyzzyxyzzyxyzzyxyzzyxyzzy | 500000 + 29 | 7 | siete | |=20=20=20= =20=20=20=20 + 15 | 13 | trece | |=20=20=20= =20=20=20=20 + 22 | 30 | treinta | |=20=20=20= =20=20=20=20 + 17 | 32 | treinta y dos | |=20=20=20= =20=20=20=20 + 3 | 31 | treinta y uno | |=20=20=20= =20=20=20=20 + 5 | 3 | tres | |=20=20=20= =20=20=20=20 + 20 | 1 | uno | |=20=20=20= =20=20=20=20 + 6 | 20 | veinte | |=20=20=20= =20=20=20=20 + 14 | 25 | veinticinco | |=20=20=20= =20=20=20=20 + 21 | 24 | veinticuatro | |=20=20=20= =20=20=20=20 + 4 | 22 | veintidos | |=20=20=20= =20=20=20=20 + 19 | 29 | veintinueve | |=20=20=20= =20=20=20=20 + 16 | 28 | veintiocho | |=20=20=20= =20=20=20=20 + 27 | 26 | veintiseis | |=20=20=20= =20=20=20=20 + 13 | 27 | veintisiete | |=20=20=20= =20=20=20=20 + 7 | 23 | veintitres | |=20=20=20= =20=20=20=20 + 8 | 21 | veintiuno | |=20=20=20= =20=20=20=20 + 0 | 100 | in child table | |=20=20=20= =20=20=20=20 + 0 | 100 | in child table 2 | |=20=20=20= =20=20=20=20 +(34 rows) + +-- Verify that foreign key link still works +INSERT INTO clstr_tst (b, c) VALUES (1111, 'this should fail'); +ERROR: insert or update on table "clstr_tst" violates foreign key constra= int "clstr_tst_con" +DETAIL: Key (b)=3D(1111) is not present in table "clstr_tst_s". +SELECT conname FROM pg_constraint WHERE conrelid =3D 'clstr_tst'::regclass +ORDER BY 1; + conname=20=20=20=20=20=20=20=20 +---------------------- + clstr_tst_a_not_null + clstr_tst_con + clstr_tst_pkey +(3 rows) + +-- Verify partial analyze works +REPACK (ANALYZE) clstr_tst (a); +REPACK (ANALYZE) clstr_tst; +REPACK (VERBOSE) clstr_tst (a); +ERROR: ANALYZE option must be specified when a column list is provided +-- REPACK w/o argument performs no ordering, so we can only check which ta= bles +-- have the relfilenode changed. +RESET SESSION AUTHORIZATION; +CREATE TEMP TABLE relnodes_old AS +(SELECT relname, relfilenode +FROM pg_class +WHERE relname IN ('clstr_1', 'clstr_2', 'clstr_3')); +SET SESSION AUTHORIZATION regress_clstr_user; +SET client_min_messages =3D ERROR; -- order of "skipping" warnings may va= ry +REPACK; +RESET client_min_messages; +RESET SESSION AUTHORIZATION; +CREATE TEMP TABLE relnodes_new AS +(SELECT relname, relfilenode +FROM pg_class +WHERE relname IN ('clstr_1', 'clstr_2', 'clstr_3')); +-- Do the actual comparison. Unlike CLUSTER, clstr_3 should have been +-- processed because there is nothing like clustering index here. +SELECT o.relname FROM relnodes_old o +JOIN relnodes_new n ON o.relname =3D n.relname +WHERE o.relfilenode <> n.relfilenode +ORDER BY o.relname; + relname=20 +--------- + clstr_1 + clstr_3 +(2 rows) + -- clean up DROP TABLE clustertest; DROP TABLE clstr_1; diff --git a/src/test/regress/expected/rules.out b/src/test/regress/expecte= d/rules.out index f4ee2bd7459..48461550636 100644 --- a/src/test/regress/expected/rules.out +++ b/src/test/regress/expected/rules.out @@ -2002,34 +2002,23 @@ pg_stat_progress_basebackup| SELECT pid, ELSE NULL::text END AS backup_type FROM pg_stat_get_progress_info('BASEBACKUP'::text) s(pid, datid, relid,= param1, param2, param3, param4, param5, param6, param7, param8, param9, pa= ram10, param11, param12, param13, param14, param15, param16, param17, param= 18, param19, param20); -pg_stat_progress_cluster| SELECT s.pid, - s.datid, - d.datname, - s.relid, - CASE s.param1 - WHEN 1 THEN 'CLUSTER'::text - WHEN 2 THEN 'VACUUM FULL'::text - ELSE NULL::text +pg_stat_progress_cluster| SELECT pid, + datid, + datname, + relid, + CASE + WHEN (command =3D ANY (ARRAY['CLUSTER'::text, 'VACUUM FULL'::t= ext])) THEN command + WHEN (repack_index_relid =3D (0)::oid) THEN 'VACUUM FULL'::text + ELSE 'CLUSTER'::text END AS command, - CASE s.param2 - WHEN 0 THEN 'initializing'::text - WHEN 1 THEN 'seq scanning heap'::text - WHEN 2 THEN 'index scanning heap'::text - WHEN 3 THEN 'sorting tuples'::text - WHEN 4 THEN 'writing new heap'::text - WHEN 5 THEN 'swapping relation files'::text - WHEN 6 THEN 'rebuilding index'::text - WHEN 7 THEN 'performing final cleanup'::text - ELSE NULL::text - END AS phase, - (s.param3)::oid AS cluster_index_relid, - s.param4 AS heap_tuples_scanned, - s.param5 AS heap_tuples_written, - s.param6 AS heap_blks_total, - s.param7 AS heap_blks_scanned, - s.param8 AS index_rebuild_count - FROM (pg_stat_get_progress_info('CLUSTER'::text) s(pid, datid, relid, p= aram1, param2, param3, param4, param5, param6, param7, param8, param9, para= m10, param11, param12, param13, param14, param15, param16, param17, param18= , param19, param20) - LEFT JOIN pg_database d ON ((s.datid =3D d.oid))); + phase, + repack_index_relid AS cluster_index_relid, + heap_tuples_scanned, + heap_tuples_written, + heap_blks_total, + heap_blks_scanned, + index_rebuild_count + FROM pg_stat_progress_repack; pg_stat_progress_copy| SELECT s.pid, s.datid, d.datname, @@ -2089,6 +2078,35 @@ pg_stat_progress_create_index| SELECT s.pid, s.param15 AS partitions_done FROM (pg_stat_get_progress_info('CREATE INDEX'::text) s(pid, datid, rel= id, param1, param2, param3, param4, param5, param6, param7, param8, param9,= param10, param11, param12, param13, param14, param15, param16, param17, pa= ram18, param19, param20) LEFT JOIN pg_database d ON ((s.datid =3D d.oid))); +pg_stat_progress_repack| SELECT s.pid, + s.datid, + d.datname, + s.relid, + CASE s.param1 + WHEN 1 THEN 'CLUSTER'::text + WHEN 2 THEN 'REPACK'::text + WHEN 3 THEN 'VACUUM FULL'::text + ELSE NULL::text + END AS command, + CASE s.param2 + WHEN 0 THEN 'initializing'::text + WHEN 1 THEN 'seq scanning heap'::text + WHEN 2 THEN 'index scanning heap'::text + WHEN 3 THEN 'sorting tuples'::text + WHEN 4 THEN 'writing new heap'::text + WHEN 5 THEN 'swapping relation files'::text + WHEN 6 THEN 'rebuilding index'::text + WHEN 7 THEN 'performing final cleanup'::text + ELSE NULL::text + END AS phase, + (s.param3)::oid AS repack_index_relid, + s.param4 AS heap_tuples_scanned, + s.param5 AS heap_tuples_written, + s.param6 AS heap_blks_total, + s.param7 AS heap_blks_scanned, + s.param8 AS index_rebuild_count + FROM (pg_stat_get_progress_info('REPACK'::text) s(pid, datid, relid, pa= ram1, param2, param3, param4, param5, param6, param7, param8, param9, param= 10, param11, param12, param13, param14, param15, param16, param17, param18,= param19, param20) + LEFT JOIN pg_database d ON ((s.datid =3D d.oid))); pg_stat_progress_vacuum| SELECT s.pid, s.datid, d.datname, diff --git a/src/test/regress/sql/cluster.sql b/src/test/regress/sql/cluste= r.sql index b7115f86104..c976823a3cb 100644 --- a/src/test/regress/sql/cluster.sql +++ b/src/test/regress/sql/cluster.sql @@ -76,7 +76,6 @@ INSERT INTO clstr_tst (b, c) VALUES (1111, 'this should f= ail'); SELECT conname FROM pg_constraint WHERE conrelid =3D 'clstr_tst'::regclass ORDER BY 1; =20 - SELECT relname, relkind, EXISTS(SELECT 1 FROM pg_class WHERE oid =3D c.reltoastrelid) AS hastoa= st FROM pg_class c WHERE relname LIKE 'clstr_tst%' ORDER BY relname; @@ -229,6 +228,24 @@ SELECT relname, old.level, old.relkind, old.relfilenod= e =3D new.relfilenode FROM o CLUSTER clstrpart; ALTER TABLE clstrpart SET WITHOUT CLUSTER; ALTER TABLE clstrpart CLUSTER ON clstrpart_idx; + +-- Check that REPACK sets new relfilenodes: it should process exactly the = same +-- tables as CLUSTER did. +DROP TABLE old_cluster_info; +DROP TABLE new_cluster_info; +CREATE TEMP TABLE old_cluster_info AS SELECT relname, level, relfilenode, = relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class= c ON c.oid=3Dtree.relid ; +REPACK clstrpart USING INDEX clstrpart_idx; +CREATE TEMP TABLE new_cluster_info AS SELECT relname, level, relfilenode, = relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class= c ON c.oid=3Dtree.relid ; +SELECT relname, old.level, old.relkind, old.relfilenode =3D new.relfilenod= e FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname)= ORDER BY relname COLLATE "C"; + +-- And finally the same for REPACK w/o index. +DROP TABLE old_cluster_info; +DROP TABLE new_cluster_info; +CREATE TEMP TABLE old_cluster_info AS SELECT relname, level, relfilenode, = relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class= c ON c.oid=3Dtree.relid ; +REPACK clstrpart; +CREATE TEMP TABLE new_cluster_info AS SELECT relname, level, relfilenode, = relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class= c ON c.oid=3Dtree.relid ; +SELECT relname, old.level, old.relkind, old.relfilenode =3D new.relfilenod= e FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname)= ORDER BY relname COLLATE "C"; + DROP TABLE clstrpart; =20 -- Ownership of partitions is checked @@ -313,6 +330,57 @@ EXPLAIN (COSTS OFF) SELECT * FROM clstr_expression WHE= RE -a =3D -3 ORDER BY -a, b; SELECT * FROM clstr_expression WHERE -a =3D -3 ORDER BY -a, b; COMMIT; =20 +---------------------------------------------------------------------- +-- +-- REPACK +-- +---------------------------------------------------------------------- + +-- REPACK handles individual tables identically to CLUSTER, but it's worth +-- checking if it handles table hierarchies identically as well. +REPACK clstr_tst USING INDEX clstr_tst_c; + +-- Verify that inheritance link still works +INSERT INTO clstr_tst_inh VALUES (0, 100, 'in child table 2'); +SELECT a,b,c,substring(d for 30), length(d) from clstr_tst; + +-- Verify that foreign key link still works +INSERT INTO clstr_tst (b, c) VALUES (1111, 'this should fail'); + +SELECT conname FROM pg_constraint WHERE conrelid =3D 'clstr_tst'::regclass +ORDER BY 1; + +-- Verify partial analyze works +REPACK (ANALYZE) clstr_tst (a); +REPACK (ANALYZE) clstr_tst; +REPACK (VERBOSE) clstr_tst (a); + +-- REPACK w/o argument performs no ordering, so we can only check which ta= bles +-- have the relfilenode changed. +RESET SESSION AUTHORIZATION; +CREATE TEMP TABLE relnodes_old AS +(SELECT relname, relfilenode +FROM pg_class +WHERE relname IN ('clstr_1', 'clstr_2', 'clstr_3')); + +SET SESSION AUTHORIZATION regress_clstr_user; +SET client_min_messages =3D ERROR; -- order of "skipping" warnings may va= ry +REPACK; +RESET client_min_messages; + +RESET SESSION AUTHORIZATION; +CREATE TEMP TABLE relnodes_new AS +(SELECT relname, relfilenode +FROM pg_class +WHERE relname IN ('clstr_1', 'clstr_2', 'clstr_3')); + +-- Do the actual comparison. Unlike CLUSTER, clstr_3 should have been +-- processed because there is nothing like clustering index here. +SELECT o.relname FROM relnodes_old o +JOIN relnodes_new n ON o.relname =3D n.relname +WHERE o.relfilenode <> n.relfilenode +ORDER BY o.relname; + -- clean up DROP TABLE clustertest; DROP TABLE clstr_1; diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs= .list index 09e7f1d420e..c81d93d0e5a 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2569,6 +2569,8 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepOriginId +RepackCommand +RepackStmt ReparameterizeForeignPathByChild_function ReplaceVarsFromTargetList_context ReplaceVarsNoMatchOption --=20 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v30-0002-Refactor-index_concurrently_create_copy-for-use-with.patch ^ permalink raw reply [nested|flat] 2+ messages in thread
end of thread, other threads:[~2026-01-12 16:30 UTC | newest] Thread overview: 2+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2021-03-05 04:03 [PATCH 1/5] Built-in compression method Dilip Kumar <[email protected]> 2026-01-12 16:30 [PATCH 1/6] Add REPACK command Antonin Houska <[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