From c19237253c28a2ee161662306fc36ad3c7eeec5a Mon Sep 17 00:00:00 2001 From: Peter Geoghegan Date: Tue, 16 Apr 2024 13:21:36 -0400 Subject: [PATCH v25 3/6] Add nbtree skip scan optimizations. Teach nbtree composite index scans to opportunistically skip over irrelevant sections of composite indexes given a query with an omitted prefix column. When nbtree is passed input scan keys derived from a query predicate "WHERE b = 5", new nbtree preprocessing steps now output "WHERE a = ANY() AND b = 5" scan keys. That is, preprocessing generates a "skip array" (along with an associated scan key) for the omitted column "a", which makes it safe to mark the scan key on "b" as required to continue the scan. This is far more efficient than a traditional full index scan whenever it allows the scan to skip over many irrelevant leaf pages, by iteratively repositioning itself using the keys on "a" and "b" together. A skip array has "elements" that are generated procedurally and on demand, but otherwise work just like conventional ScalarArrayOp arrays. They advance using the same approach as ScalarArrayOp arrays, which allows nbtree scans to freely add skip arrays either before or after any ScalarArrayOp array. Index scans decide when and where to reposition the scan using the same primitive index scan scheduling logic introduced by commit 5bf748b8 (which enhanced nbtree ScalarArrayOp execution). The core B-Tree operator classes on most discrete types generate their array elements with help from their own custom skip support routine. This infrastructure gives nbtree a way to generate the next required array element by incrementing (or decrementing) the current array value. It can reduce the number of index descents in cases where the very next indexable value frequently turns out to be the next indexed value. In practice, this is likely whenever the scan skips with an input opclass where "dense" indexed values occur naturally, such as btree/date_ops. Opclasses that lack a skip support routine fall back on having nbtree "increment" (or "decrement") a skip array's current element by setting the NEXT (or PRIOR) scan key flag, without directly changing the scan key's sk_argument. These sentinel values behave just like any other value that might appear in an array -- though they can never actually locate matching index tuples. Inequality scan keys can affect how skip arrays generate their values. Their range is constrained by the inequalities. For example, a skip array on "a" will only ever use element values 1 and 2 given a qual "WHERE a BETWEEN 1 AND 2 AND b = 66". A scan using such a skip array has almost identical performance characteristics to a scan with the qual "WHERE a = ANY('{1, 2}') AND b = 66". The scan will be much faster when it can be executed as two selective primitive index scans, rather than a single very large index scan that has to read many more leaf pages. It isn't guaranteed to improve performance, though. B-Tree preprocessing is optimistic about skipping working out: it applies static, generic rules when determining where to generate skip arrays, which assumes that the runtime overhead of maintaining skip arrays will pay for itself -- or lead to only a modest performance loss. As things stand, these assumptions are much too optimistic: skip array maintenance will lead to unacceptable regressions with unsympathetic queries (typically scans with little to no potential for the scan to skip over irrelevant index leaf pages). An upcoming commit will address the problems in this area separately, by adding a new mechanism that greatly lowers the cost of array maintenance in these unfavorable cases. Author: Peter Geoghegan Reviewed-By: Masahiro Ikeda Reviewed-By: Heikki Linnakangas Reviewed-By: Tomas Vondra Reviewed-By: Matthias van de Meent Reviewed-By: Aleksander Alekseev Discussion: https://postgr.es/m/CAH2-Wzmn1YsLzOGgjAQZdn1STSG_y8qP__vggTaPAYXJP+G4bw@mail.gmail.com --- src/include/access/amapi.h | 3 +- src/include/access/nbtree.h | 35 +- src/include/catalog/pg_amproc.dat | 22 + src/include/catalog/pg_proc.dat | 27 + src/include/storage/lwlock.h | 1 + src/include/utils/skipsupport.h | 98 +++ src/backend/access/index/indexam.c | 3 +- src/backend/access/nbtree/nbtcompare.c | 273 +++++++ src/backend/access/nbtree/nbtpreprocesskeys.c | 601 ++++++++++++-- src/backend/access/nbtree/nbtree.c | 211 ++++- src/backend/access/nbtree/nbtsearch.c | 111 ++- src/backend/access/nbtree/nbtutils.c | 748 ++++++++++++++++-- src/backend/access/nbtree/nbtvalidate.c | 4 + src/backend/commands/opclasscmds.c | 25 + src/backend/storage/lmgr/lwlock.c | 1 + .../utils/activity/wait_event_names.txt | 1 + src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/date.c | 46 ++ src/backend/utils/adt/meson.build | 1 + src/backend/utils/adt/selfuncs.c | 405 +++++++--- src/backend/utils/adt/skipsupport.c | 61 ++ src/backend/utils/adt/timestamp.c | 48 ++ src/backend/utils/adt/uuid.c | 70 ++ doc/src/sgml/btree.sgml | 34 +- doc/src/sgml/indexam.sgml | 3 +- doc/src/sgml/indices.sgml | 49 +- doc/src/sgml/monitoring.sgml | 5 +- doc/src/sgml/xindex.sgml | 16 +- src/test/regress/expected/alter_generic.out | 10 +- src/test/regress/expected/btree_index.out | 41 + src/test/regress/expected/create_index.out | 183 ++++- src/test/regress/expected/psql.out | 3 +- src/test/regress/sql/alter_generic.sql | 5 +- src/test/regress/sql/btree_index.sql | 21 + src/test/regress/sql/create_index.sql | 63 +- src/tools/pgindent/typedefs.list | 3 + 36 files changed, 2864 insertions(+), 368 deletions(-) create mode 100644 src/include/utils/skipsupport.h create mode 100644 src/backend/utils/adt/skipsupport.c diff --git a/src/include/access/amapi.h b/src/include/access/amapi.h index fbe6b225e..09aeab3e8 100644 --- a/src/include/access/amapi.h +++ b/src/include/access/amapi.h @@ -214,7 +214,8 @@ typedef void (*amrestrpos_function) (IndexScanDesc scan); */ /* estimate size of parallel scan descriptor */ -typedef Size (*amestimateparallelscan_function) (int nkeys, int norderbys); +typedef Size (*amestimateparallelscan_function) (Relation indexRelation, + int nkeys, int norderbys); /* prepare for parallel index scan */ typedef void (*aminitparallelscan_function) (void *target); diff --git a/src/include/access/nbtree.h b/src/include/access/nbtree.h index 947431954..10d9f8186 100644 --- a/src/include/access/nbtree.h +++ b/src/include/access/nbtree.h @@ -24,6 +24,7 @@ #include "lib/stringinfo.h" #include "storage/bufmgr.h" #include "storage/shm_toc.h" +#include "utils/skipsupport.h" /* There's room for a 16-bit vacuum cycle ID in BTPageOpaqueData */ typedef uint16 BTCycleId; @@ -707,6 +708,10 @@ BTreeTupleGetMaxHeapTID(IndexTuple itup) * (BTOPTIONS_PROC). These procedures define a set of user-visible * parameters that can be used to control operator class behavior. None of * the built-in B-Tree operator classes currently register an "options" proc. + * + * To facilitate more efficient B-Tree skip scans, an operator class may + * choose to offer a sixth amproc procedure (BTSKIPSUPPORT_PROC). For full + * details, see src/include/utils/skipsupport.h. */ #define BTORDER_PROC 1 @@ -714,7 +719,8 @@ BTreeTupleGetMaxHeapTID(IndexTuple itup) #define BTINRANGE_PROC 3 #define BTEQUALIMAGE_PROC 4 #define BTOPTIONS_PROC 5 -#define BTNProcs 5 +#define BTSKIPSUPPORT_PROC 6 +#define BTNProcs 6 /* * We need to be able to tell the difference between read and write @@ -1027,10 +1033,21 @@ typedef BTScanPosData *BTScanPos; /* We need one of these for each equality-type SK_SEARCHARRAY scan key */ typedef struct BTArrayKeyInfo { + /* fields used by both kinds of array (standard arrays and skip arrays) */ int scan_key; /* index of associated key in keyData */ - int cur_elem; /* index of current element in elem_values */ - int num_elems; /* number of elems in current array value */ + int num_elems; /* number of elems (-1 for skip array) */ + + /* fields for standard ScalarArrayOpExpr arrays */ Datum *elem_values; /* array of num_elems Datums */ + int cur_elem; /* index of current element in elem_values */ + + /* fields for skip arrays, which generate element datums procedurally */ + int16 attlen; /* attr len in bytes */ + bool attbyval; /* as FormData_pg_attribute.attbyval */ + bool null_elem; /* lowest/highest element actually NULL? */ + SkipSupport sksup; /* skip support (NULL if opclass lacks it) */ + ScanKey low_compare; /* array's > or >= lower bound */ + ScanKey high_compare; /* array's < or <= upper bound */ } BTArrayKeyInfo; typedef struct BTScanOpaqueData @@ -1042,6 +1059,7 @@ typedef struct BTScanOpaqueData /* workspace for SK_SEARCHARRAY support */ int numArrayKeys; /* number of equality-type array keys */ + bool skipScan; /* At least one skip array in arrayKeys[]? */ bool needPrimScan; /* New prim scan to continue in current dir? */ bool scanBehind; /* arrays might be ahead of scan's key space? */ bool oppositeDirCheck; /* scanBehind opposite-scan-dir check? */ @@ -1119,6 +1137,15 @@ typedef struct BTReadPageState */ #define SK_BT_REQFWD 0x00010000 /* required to continue forward scan */ #define SK_BT_REQBKWD 0x00020000 /* required to continue backward scan */ +#define SK_BT_SKIP 0x00040000 /* skip array on column without input = */ + +/* SK_BT_SKIP-only flags (mutable, set and unset by array advancement) */ +#define SK_BT_MINVAL 0x00080000 /* invalid sk_argument, use low_compare */ +#define SK_BT_MAXVAL 0x00100000 /* invalid sk_argument, use high_compare */ +#define SK_BT_NEXT 0x00200000 /* positions the scan > sk_argument */ +#define SK_BT_PRIOR 0x00400000 /* positions the scan < sk_argument */ + +/* Remaps pg_index flag bits to uppermost SK_BT_* byte */ #define SK_BT_INDOPTION_SHIFT 24 /* must clear the above bits */ #define SK_BT_DESC (INDOPTION_DESC << SK_BT_INDOPTION_SHIFT) #define SK_BT_NULLS_FIRST (INDOPTION_NULLS_FIRST << SK_BT_INDOPTION_SHIFT) @@ -1165,7 +1192,7 @@ extern bool btinsert(Relation rel, Datum *values, bool *isnull, bool indexUnchanged, struct IndexInfo *indexInfo); extern IndexScanDesc btbeginscan(Relation rel, int nkeys, int norderbys); -extern Size btestimateparallelscan(int nkeys, int norderbys); +extern Size btestimateparallelscan(Relation rel, int nkeys, int norderbys); extern void btinitparallelscan(void *target); extern bool btgettuple(IndexScanDesc scan, ScanDirection dir); extern int64 btgetbitmap(IndexScanDesc scan, TIDBitmap *tbm); diff --git a/src/include/catalog/pg_amproc.dat b/src/include/catalog/pg_amproc.dat index 19100482b..37000639f 100644 --- a/src/include/catalog/pg_amproc.dat +++ b/src/include/catalog/pg_amproc.dat @@ -21,6 +21,8 @@ amprocrighttype => 'bit', amprocnum => '4', amproc => 'btequalimage' }, { amprocfamily => 'btree/bool_ops', amproclefttype => 'bool', amprocrighttype => 'bool', amprocnum => '1', amproc => 'btboolcmp' }, +{ amprocfamily => 'btree/bool_ops', amproclefttype => 'bool', + amprocrighttype => 'bool', amprocnum => '6', amproc => 'btboolskipsupport' }, { amprocfamily => 'btree/bool_ops', amproclefttype => 'bool', amprocrighttype => 'bool', amprocnum => '4', amproc => 'btequalimage' }, { amprocfamily => 'btree/bpchar_ops', amproclefttype => 'bpchar', @@ -41,12 +43,16 @@ amprocrighttype => 'char', amprocnum => '1', amproc => 'btcharcmp' }, { amprocfamily => 'btree/char_ops', amproclefttype => 'char', amprocrighttype => 'char', amprocnum => '4', amproc => 'btequalimage' }, +{ amprocfamily => 'btree/char_ops', amproclefttype => 'char', + amprocrighttype => 'char', amprocnum => '6', amproc => 'btcharskipsupport' }, { amprocfamily => 'btree/datetime_ops', amproclefttype => 'date', amprocrighttype => 'date', amprocnum => '1', amproc => 'date_cmp' }, { amprocfamily => 'btree/datetime_ops', amproclefttype => 'date', amprocrighttype => 'date', amprocnum => '2', amproc => 'date_sortsupport' }, { amprocfamily => 'btree/datetime_ops', amproclefttype => 'date', amprocrighttype => 'date', amprocnum => '4', amproc => 'btequalimage' }, +{ amprocfamily => 'btree/datetime_ops', amproclefttype => 'date', + amprocrighttype => 'date', amprocnum => '6', amproc => 'date_skipsupport' }, { amprocfamily => 'btree/datetime_ops', amproclefttype => 'date', amprocrighttype => 'timestamp', amprocnum => '1', amproc => 'date_cmp_timestamp' }, @@ -60,6 +66,9 @@ amproc => 'timestamp_sortsupport' }, { amprocfamily => 'btree/datetime_ops', amproclefttype => 'timestamp', amprocrighttype => 'timestamp', amprocnum => '4', amproc => 'btequalimage' }, +{ amprocfamily => 'btree/datetime_ops', amproclefttype => 'timestamp', + amprocrighttype => 'timestamp', amprocnum => '6', + amproc => 'timestamp_skipsupport' }, { amprocfamily => 'btree/datetime_ops', amproclefttype => 'timestamp', amprocrighttype => 'date', amprocnum => '1', amproc => 'timestamp_cmp_date' }, { amprocfamily => 'btree/datetime_ops', amproclefttype => 'timestamp', @@ -74,6 +83,9 @@ { amprocfamily => 'btree/datetime_ops', amproclefttype => 'timestamptz', amprocrighttype => 'timestamptz', amprocnum => '4', amproc => 'btequalimage' }, +{ amprocfamily => 'btree/datetime_ops', amproclefttype => 'timestamptz', + amprocrighttype => 'timestamptz', amprocnum => '6', + amproc => 'timestamp_skipsupport' }, { amprocfamily => 'btree/datetime_ops', amproclefttype => 'timestamptz', amprocrighttype => 'date', amprocnum => '1', amproc => 'timestamptz_cmp_date' }, @@ -122,6 +134,8 @@ amprocrighttype => 'int2', amprocnum => '2', amproc => 'btint2sortsupport' }, { amprocfamily => 'btree/integer_ops', amproclefttype => 'int2', amprocrighttype => 'int2', amprocnum => '4', amproc => 'btequalimage' }, +{ amprocfamily => 'btree/integer_ops', amproclefttype => 'int2', + amprocrighttype => 'int2', amprocnum => '6', amproc => 'btint2skipsupport' }, { amprocfamily => 'btree/integer_ops', amproclefttype => 'int2', amprocrighttype => 'int4', amprocnum => '1', amproc => 'btint24cmp' }, { amprocfamily => 'btree/integer_ops', amproclefttype => 'int2', @@ -141,6 +155,8 @@ amprocrighttype => 'int4', amprocnum => '2', amproc => 'btint4sortsupport' }, { amprocfamily => 'btree/integer_ops', amproclefttype => 'int4', amprocrighttype => 'int4', amprocnum => '4', amproc => 'btequalimage' }, +{ amprocfamily => 'btree/integer_ops', amproclefttype => 'int4', + amprocrighttype => 'int4', amprocnum => '6', amproc => 'btint4skipsupport' }, { amprocfamily => 'btree/integer_ops', amproclefttype => 'int4', amprocrighttype => 'int8', amprocnum => '1', amproc => 'btint48cmp' }, { amprocfamily => 'btree/integer_ops', amproclefttype => 'int4', @@ -160,6 +176,8 @@ amprocrighttype => 'int8', amprocnum => '2', amproc => 'btint8sortsupport' }, { amprocfamily => 'btree/integer_ops', amproclefttype => 'int8', amprocrighttype => 'int8', amprocnum => '4', amproc => 'btequalimage' }, +{ amprocfamily => 'btree/integer_ops', amproclefttype => 'int8', + amprocrighttype => 'int8', amprocnum => '6', amproc => 'btint8skipsupport' }, { amprocfamily => 'btree/integer_ops', amproclefttype => 'int8', amprocrighttype => 'int4', amprocnum => '1', amproc => 'btint84cmp' }, { amprocfamily => 'btree/integer_ops', amproclefttype => 'int8', @@ -193,6 +211,8 @@ amprocrighttype => 'oid', amprocnum => '2', amproc => 'btoidsortsupport' }, { amprocfamily => 'btree/oid_ops', amproclefttype => 'oid', amprocrighttype => 'oid', amprocnum => '4', amproc => 'btequalimage' }, +{ amprocfamily => 'btree/oid_ops', amproclefttype => 'oid', + amprocrighttype => 'oid', amprocnum => '6', amproc => 'btoidskipsupport' }, { amprocfamily => 'btree/oidvector_ops', amproclefttype => 'oidvector', amprocrighttype => 'oidvector', amprocnum => '1', amproc => 'btoidvectorcmp' }, @@ -261,6 +281,8 @@ amprocrighttype => 'uuid', amprocnum => '2', amproc => 'uuid_sortsupport' }, { amprocfamily => 'btree/uuid_ops', amproclefttype => 'uuid', amprocrighttype => 'uuid', amprocnum => '4', amproc => 'btequalimage' }, +{ amprocfamily => 'btree/uuid_ops', amproclefttype => 'uuid', + amprocrighttype => 'uuid', amprocnum => '6', amproc => 'uuid_skipsupport' }, { amprocfamily => 'btree/record_ops', amproclefttype => 'record', amprocrighttype => 'record', amprocnum => '1', amproc => 'btrecordcmp' }, { amprocfamily => 'btree/record_image_ops', amproclefttype => 'record', diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index e2d5c0d08..783c67eaf 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -1004,18 +1004,27 @@ { oid => '3129', descr => 'sort support', proname => 'btint2sortsupport', prorettype => 'void', proargtypes => 'internal', prosrc => 'btint2sortsupport' }, +{ oid => '9290', descr => 'skip support', + proname => 'btint2skipsupport', prorettype => 'void', + proargtypes => 'internal', prosrc => 'btint2skipsupport' }, { oid => '351', descr => 'less-equal-greater', proname => 'btint4cmp', proleakproof => 't', prorettype => 'int4', proargtypes => 'int4 int4', prosrc => 'btint4cmp' }, { oid => '3130', descr => 'sort support', proname => 'btint4sortsupport', prorettype => 'void', proargtypes => 'internal', prosrc => 'btint4sortsupport' }, +{ oid => '9291', descr => 'skip support', + proname => 'btint4skipsupport', prorettype => 'void', + proargtypes => 'internal', prosrc => 'btint4skipsupport' }, { oid => '842', descr => 'less-equal-greater', proname => 'btint8cmp', proleakproof => 't', prorettype => 'int4', proargtypes => 'int8 int8', prosrc => 'btint8cmp' }, { oid => '3131', descr => 'sort support', proname => 'btint8sortsupport', prorettype => 'void', proargtypes => 'internal', prosrc => 'btint8sortsupport' }, +{ oid => '9292', descr => 'skip support', + proname => 'btint8skipsupport', prorettype => 'void', + proargtypes => 'internal', prosrc => 'btint8skipsupport' }, { oid => '354', descr => 'less-equal-greater', proname => 'btfloat4cmp', proleakproof => 't', prorettype => 'int4', proargtypes => 'float4 float4', prosrc => 'btfloat4cmp' }, @@ -1034,12 +1043,18 @@ { oid => '3134', descr => 'sort support', proname => 'btoidsortsupport', prorettype => 'void', proargtypes => 'internal', prosrc => 'btoidsortsupport' }, +{ oid => '9293', descr => 'skip support', + proname => 'btoidskipsupport', prorettype => 'void', + proargtypes => 'internal', prosrc => 'btoidskipsupport' }, { oid => '404', descr => 'less-equal-greater', proname => 'btoidvectorcmp', proleakproof => 't', prorettype => 'int4', proargtypes => 'oidvector oidvector', prosrc => 'btoidvectorcmp' }, { oid => '358', descr => 'less-equal-greater', proname => 'btcharcmp', proleakproof => 't', prorettype => 'int4', proargtypes => 'char char', prosrc => 'btcharcmp' }, +{ oid => '9294', descr => 'skip support', + proname => 'btcharskipsupport', prorettype => 'void', + proargtypes => 'internal', prosrc => 'btcharskipsupport' }, { oid => '359', descr => 'less-equal-greater', proname => 'btnamecmp', proleakproof => 't', prorettype => 'int4', proargtypes => 'name name', prosrc => 'btnamecmp' }, @@ -2266,6 +2281,9 @@ { oid => '3136', descr => 'sort support', proname => 'date_sortsupport', prorettype => 'void', proargtypes => 'internal', prosrc => 'date_sortsupport' }, +{ oid => '9295', descr => 'skip support', + proname => 'date_skipsupport', prorettype => 'void', + proargtypes => 'internal', prosrc => 'date_skipsupport' }, { oid => '4133', descr => 'window RANGE support', proname => 'in_range', prorettype => 'bool', proargtypes => 'date date interval bool bool', @@ -4456,6 +4474,9 @@ { oid => '1693', descr => 'less-equal-greater', proname => 'btboolcmp', proleakproof => 't', prorettype => 'int4', proargtypes => 'bool bool', prosrc => 'btboolcmp' }, +{ oid => '9296', descr => 'skip support', + proname => 'btboolskipsupport', prorettype => 'void', + proargtypes => 'internal', prosrc => 'btboolskipsupport' }, { oid => '1688', descr => 'hash', proname => 'time_hash', prorettype => 'int4', proargtypes => 'time', @@ -6328,6 +6349,9 @@ { oid => '3137', descr => 'sort support', proname => 'timestamp_sortsupport', prorettype => 'void', proargtypes => 'internal', prosrc => 'timestamp_sortsupport' }, +{ oid => '9297', descr => 'skip support', + proname => 'timestamp_skipsupport', prorettype => 'void', + proargtypes => 'internal', prosrc => 'timestamp_skipsupport' }, { oid => '4134', descr => 'window RANGE support', proname => 'in_range', prorettype => 'bool', @@ -9376,6 +9400,9 @@ { oid => '3300', descr => 'sort support', proname => 'uuid_sortsupport', prorettype => 'void', proargtypes => 'internal', prosrc => 'uuid_sortsupport' }, +{ oid => '9298', descr => 'skip support', + proname => 'uuid_skipsupport', prorettype => 'void', + proargtypes => 'internal', prosrc => 'uuid_skipsupport' }, { oid => '2961', descr => 'I/O', proname => 'uuid_recv', prorettype => 'uuid', proargtypes => 'internal', prosrc => 'uuid_recv' }, diff --git a/src/include/storage/lwlock.h b/src/include/storage/lwlock.h index 13a7dc899..ffa03189e 100644 --- a/src/include/storage/lwlock.h +++ b/src/include/storage/lwlock.h @@ -194,6 +194,7 @@ typedef enum BuiltinTrancheIds LWTRANCHE_LOCK_MANAGER, LWTRANCHE_PREDICATE_LOCK_MANAGER, LWTRANCHE_PARALLEL_HASH_JOIN, + LWTRANCHE_PARALLEL_BTREE_SCAN, LWTRANCHE_PARALLEL_QUERY_DSA, LWTRANCHE_PER_SESSION_DSA, LWTRANCHE_PER_SESSION_RECORD_TYPE, diff --git a/src/include/utils/skipsupport.h b/src/include/utils/skipsupport.h new file mode 100644 index 000000000..bc51847cf --- /dev/null +++ b/src/include/utils/skipsupport.h @@ -0,0 +1,98 @@ +/*------------------------------------------------------------------------- + * + * skipsupport.h + * Support routines for B-Tree skip scan. + * + * B-Tree operator classes for discrete types can optionally provide a support + * function for skipping. This is used during skip scans. + * + * A B-tree operator class that implements skip support provides B-tree index + * scans with a way of enumerating and iterating through every possible value + * from the domain of indexable values. This gives scans a way to determine + * the next value in line for a given skip array/scan key/skipped attribute. + * Scans request the next (or previous) value whenever they run out of tuples + * matching the skip array's current element value. The next (or previous) + * value can be used to relocate the scan; it is applied in combination with + * at least one additional lower-order non-skip key, taken from the query. + * + * Skip support is used by discrete type (e.g., integer and date) opclasses. + * Indexes with an attribute whose input opclass is of one of these types tend + * to store adjacent values in adjoining groups of index tuples. Each time a + * skip scan with skip support successfully guesses that the next value in the + * index (for a given skipped column) is indeed the value that skip support + * just incremented its skip array to, it will have saved the scan some work. + * The scan will have avoided an index probe that directly finds the next + * value that appears in the index. (When skip support guesses wrong, then it + * won't have saved any work, but it also won't have added any useless work. + * The failed attempt to locate exactly-matching index tuples acts just like + * an explicit probe would; it'll still find the index's true next value.) + * + * It usually isn't feasible to implement skip support for an opclass whose + * input type is continuous. The B-Tree code falls back on next-key sentinel + * values for any opclass that doesn't provide its own skip support function. + * This isn't really an implementation restriction; there is no benefit to + * providing skip support for an opclass where guessing that the next indexed + * value is the next possible indexable value never (or hardly ever) works out. + * + * + * Portions Copyright (c) 1996-2025, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/utils/skipsupport.h + * + *------------------------------------------------------------------------- + */ +#ifndef SKIPSUPPORT_H +#define SKIPSUPPORT_H + +#include "utils/relcache.h" + +typedef struct SkipSupportData *SkipSupport; +typedef Datum (*SkipSupportIncDec) (Relation rel, + Datum existing, + bool *overflow); + +/* + * State/callbacks used by skip arrays to procedurally generate elements. + * + * A BTSKIPSUPPORT_PROC function must set each and every field when called + * (there are no optional fields). + */ +typedef struct SkipSupportData +{ + /* + * low_elem and high_elem must be set with the lowest and highest possible + * values from the domain of indexable values (assuming ascending order) + */ + Datum low_elem; /* lowest sorting/leftmost non-NULL value */ + Datum high_elem; /* highest sorting/rightmost non-NULL value */ + + /* + * Decrement/increment functions. + * + * Returns a decremented/incremented copy of caller's existing datum, + * allocated in caller's memory context (for pass-by-reference types). + * It's not okay for these functions to leak any memory. + * + * When the decrement function (or increment function) is called with a + * value that already matches low_elem (or high_elem), function must set + * the *overflow argument. The return value is treated as undefined by + * the B-Tree code; it shouldn't need to be (and won't be) pfree'd. + * + * The B-Tree code's "existing" datum argument is often just a straight + * copy of a value from an index tuple. Operator classes must accept + * every possible representational variation within the underlying type. + * On the other hand, opclasses are _not_ required to preserve information + * that doesn't affect how datums are sorted (e.g., skip support for a + * fixed precision numeric type needn't preserve datum display scale). + * Operator class decrement/increment functions will never be called with + * a NULL "existing" argument, either. + */ + SkipSupportIncDec decrement; + SkipSupportIncDec increment; +} SkipSupportData; + +extern SkipSupport PrepareSkipSupportFromOpclass(Oid opfamily, Oid opcintype, + bool reverse); + +#endif /* SKIPSUPPORT_H */ diff --git a/src/backend/access/index/indexam.c b/src/backend/access/index/indexam.c index 8b1f55543..0e62d7a7a 100644 --- a/src/backend/access/index/indexam.c +++ b/src/backend/access/index/indexam.c @@ -470,7 +470,8 @@ index_parallelscan_estimate(Relation indexRelation, int nkeys, int norderbys, */ if (indexRelation->rd_indam->amestimateparallelscan != NULL) nbytes = add_size(nbytes, - indexRelation->rd_indam->amestimateparallelscan(nkeys, + indexRelation->rd_indam->amestimateparallelscan(indexRelation, + nkeys, norderbys)); return nbytes; diff --git a/src/backend/access/nbtree/nbtcompare.c b/src/backend/access/nbtree/nbtcompare.c index 291cb8fc1..4da5a3c1d 100644 --- a/src/backend/access/nbtree/nbtcompare.c +++ b/src/backend/access/nbtree/nbtcompare.c @@ -58,6 +58,7 @@ #include #include "utils/fmgrprotos.h" +#include "utils/skipsupport.h" #include "utils/sortsupport.h" #ifdef STRESS_SORT_INT_MIN @@ -78,6 +79,51 @@ btboolcmp(PG_FUNCTION_ARGS) PG_RETURN_INT32((int32) a - (int32) b); } +static Datum +bool_decrement(Relation rel, Datum existing, bool *underflow) +{ + bool bexisting = DatumGetBool(existing); + + if (bexisting == false) + { + /* return value is undefined */ + *underflow = true; + return (Datum) 0; + } + + *underflow = false; + return BoolGetDatum(bexisting - 1); +} + +static Datum +bool_increment(Relation rel, Datum existing, bool *overflow) +{ + bool bexisting = DatumGetBool(existing); + + if (bexisting == true) + { + /* return value is undefined */ + *overflow = true; + return (Datum) 0; + } + + *overflow = false; + return BoolGetDatum(bexisting + 1); +} + +Datum +btboolskipsupport(PG_FUNCTION_ARGS) +{ + SkipSupport sksup = (SkipSupport) PG_GETARG_POINTER(0); + + sksup->decrement = bool_decrement; + sksup->increment = bool_increment; + sksup->low_elem = BoolGetDatum(false); + sksup->high_elem = BoolGetDatum(true); + + PG_RETURN_VOID(); +} + Datum btint2cmp(PG_FUNCTION_ARGS) { @@ -105,6 +151,51 @@ btint2sortsupport(PG_FUNCTION_ARGS) PG_RETURN_VOID(); } +static Datum +int2_decrement(Relation rel, Datum existing, bool *underflow) +{ + int16 iexisting = DatumGetInt16(existing); + + if (iexisting == PG_INT16_MIN) + { + /* return value is undefined */ + *underflow = true; + return (Datum) 0; + } + + *underflow = false; + return Int16GetDatum(iexisting - 1); +} + +static Datum +int2_increment(Relation rel, Datum existing, bool *overflow) +{ + int16 iexisting = DatumGetInt16(existing); + + if (iexisting == PG_INT16_MAX) + { + /* return value is undefined */ + *overflow = true; + return (Datum) 0; + } + + *overflow = false; + return Int16GetDatum(iexisting + 1); +} + +Datum +btint2skipsupport(PG_FUNCTION_ARGS) +{ + SkipSupport sksup = (SkipSupport) PG_GETARG_POINTER(0); + + sksup->decrement = int2_decrement; + sksup->increment = int2_increment; + sksup->low_elem = Int16GetDatum(PG_INT16_MIN); + sksup->high_elem = Int16GetDatum(PG_INT16_MAX); + + PG_RETURN_VOID(); +} + Datum btint4cmp(PG_FUNCTION_ARGS) { @@ -128,6 +219,51 @@ btint4sortsupport(PG_FUNCTION_ARGS) PG_RETURN_VOID(); } +static Datum +int4_decrement(Relation rel, Datum existing, bool *underflow) +{ + int32 iexisting = DatumGetInt32(existing); + + if (iexisting == PG_INT32_MIN) + { + /* return value is undefined */ + *underflow = true; + return (Datum) 0; + } + + *underflow = false; + return Int32GetDatum(iexisting - 1); +} + +static Datum +int4_increment(Relation rel, Datum existing, bool *overflow) +{ + int32 iexisting = DatumGetInt32(existing); + + if (iexisting == PG_INT32_MAX) + { + /* return value is undefined */ + *overflow = true; + return (Datum) 0; + } + + *overflow = false; + return Int32GetDatum(iexisting + 1); +} + +Datum +btint4skipsupport(PG_FUNCTION_ARGS) +{ + SkipSupport sksup = (SkipSupport) PG_GETARG_POINTER(0); + + sksup->decrement = int4_decrement; + sksup->increment = int4_increment; + sksup->low_elem = Int32GetDatum(PG_INT32_MIN); + sksup->high_elem = Int32GetDatum(PG_INT32_MAX); + + PG_RETURN_VOID(); +} + Datum btint8cmp(PG_FUNCTION_ARGS) { @@ -171,6 +307,51 @@ btint8sortsupport(PG_FUNCTION_ARGS) PG_RETURN_VOID(); } +static Datum +int8_decrement(Relation rel, Datum existing, bool *underflow) +{ + int64 iexisting = DatumGetInt64(existing); + + if (iexisting == PG_INT64_MIN) + { + /* return value is undefined */ + *underflow = true; + return (Datum) 0; + } + + *underflow = false; + return Int64GetDatum(iexisting - 1); +} + +static Datum +int8_increment(Relation rel, Datum existing, bool *overflow) +{ + int64 iexisting = DatumGetInt64(existing); + + if (iexisting == PG_INT64_MAX) + { + /* return value is undefined */ + *overflow = true; + return (Datum) 0; + } + + *overflow = false; + return Int64GetDatum(iexisting + 1); +} + +Datum +btint8skipsupport(PG_FUNCTION_ARGS) +{ + SkipSupport sksup = (SkipSupport) PG_GETARG_POINTER(0); + + sksup->decrement = int8_decrement; + sksup->increment = int8_increment; + sksup->low_elem = Int64GetDatum(PG_INT64_MIN); + sksup->high_elem = Int64GetDatum(PG_INT64_MAX); + + PG_RETURN_VOID(); +} + Datum btint48cmp(PG_FUNCTION_ARGS) { @@ -292,6 +473,51 @@ btoidsortsupport(PG_FUNCTION_ARGS) PG_RETURN_VOID(); } +static Datum +oid_decrement(Relation rel, Datum existing, bool *underflow) +{ + Oid oexisting = DatumGetObjectId(existing); + + if (oexisting == InvalidOid) + { + /* return value is undefined */ + *underflow = true; + return (Datum) 0; + } + + *underflow = false; + return ObjectIdGetDatum(oexisting - 1); +} + +static Datum +oid_increment(Relation rel, Datum existing, bool *overflow) +{ + Oid oexisting = DatumGetObjectId(existing); + + if (oexisting == OID_MAX) + { + /* return value is undefined */ + *overflow = true; + return (Datum) 0; + } + + *overflow = false; + return ObjectIdGetDatum(oexisting + 1); +} + +Datum +btoidskipsupport(PG_FUNCTION_ARGS) +{ + SkipSupport sksup = (SkipSupport) PG_GETARG_POINTER(0); + + sksup->decrement = oid_decrement; + sksup->increment = oid_increment; + sksup->low_elem = ObjectIdGetDatum(InvalidOid); + sksup->high_elem = ObjectIdGetDatum(OID_MAX); + + PG_RETURN_VOID(); +} + Datum btoidvectorcmp(PG_FUNCTION_ARGS) { @@ -325,3 +551,50 @@ btcharcmp(PG_FUNCTION_ARGS) /* Be careful to compare chars as unsigned */ PG_RETURN_INT32((int32) ((uint8) a) - (int32) ((uint8) b)); } + +static Datum +char_decrement(Relation rel, Datum existing, bool *underflow) +{ + uint8 cexisting = UInt8GetDatum(existing); + + if (cexisting == 0) + { + /* return value is undefined */ + *underflow = true; + return (Datum) 0; + } + + *underflow = false; + return CharGetDatum((uint8) cexisting - 1); +} + +static Datum +char_increment(Relation rel, Datum existing, bool *overflow) +{ + uint8 cexisting = UInt8GetDatum(existing); + + if (cexisting == UCHAR_MAX) + { + /* return value is undefined */ + *overflow = true; + return (Datum) 0; + } + + *overflow = false; + return CharGetDatum((uint8) cexisting + 1); +} + +Datum +btcharskipsupport(PG_FUNCTION_ARGS) +{ + SkipSupport sksup = (SkipSupport) PG_GETARG_POINTER(0); + + sksup->decrement = char_decrement; + sksup->increment = char_increment; + + /* btcharcmp compares chars as unsigned */ + sksup->low_elem = UInt8GetDatum(0); + sksup->high_elem = UInt8GetDatum(UCHAR_MAX); + + PG_RETURN_VOID(); +} diff --git a/src/backend/access/nbtree/nbtpreprocesskeys.c b/src/backend/access/nbtree/nbtpreprocesskeys.c index 1fd1da5f1..3d8ff701f 100644 --- a/src/backend/access/nbtree/nbtpreprocesskeys.c +++ b/src/backend/access/nbtree/nbtpreprocesskeys.c @@ -45,8 +45,15 @@ static bool _bt_compare_array_scankey_args(IndexScanDesc scan, ScanKey arraysk, ScanKey skey, FmgrInfo *orderproc, BTArrayKeyInfo *array, bool *qual_ok); +static bool _bt_saoparray_shrink(IndexScanDesc scan, ScanKey arraysk, + ScanKey skey, FmgrInfo *orderproc, + BTArrayKeyInfo *array, bool *qual_ok); +static bool _bt_skiparray_shrink(IndexScanDesc scan, ScanKey skey, + BTArrayKeyInfo *array, bool *qual_ok); static ScanKey _bt_preprocess_array_keys(IndexScanDesc scan, int *new_numberOfKeys); static void _bt_preprocess_array_keys_final(IndexScanDesc scan, int *keyDataMap); +static int _bt_num_array_keys(IndexScanDesc scan, Oid *skip_eq_ops, + int *numSkipArrayKeys); static Datum _bt_find_extreme_element(IndexScanDesc scan, ScanKey skey, Oid elemtype, StrategyNumber strat, Datum *elems, int nelems); @@ -89,6 +96,8 @@ static int _bt_compare_array_elements(const void *a, const void *b, void *arg); * within each attribute may be done as a byproduct of the processing here. * That process must leave array scan keys (within an attribute) in the same * order as corresponding entries from the scan's BTArrayKeyInfo array info. + * We might also construct skip array scan keys that weren't present in the + * original input keys; these are also output in standard attribute order. * * The output keys are marked with flags SK_BT_REQFWD and/or SK_BT_REQBKWD * if they must be satisfied in order to continue the scan forward or backward @@ -101,10 +110,16 @@ static int _bt_compare_array_elements(const void *a, const void *b, void *arg); * attributes with "=" keys are marked both SK_BT_REQFWD and SK_BT_REQBKWD. * For the first attribute without an "=" key, any "<" and "<=" keys are * marked SK_BT_REQFWD while any ">" and ">=" keys are marked SK_BT_REQBKWD. - * This can be seen to be correct by considering the above example. Note - * in particular that if there are no keys for a given attribute, the keys for - * subsequent attributes can never be required; for instance "WHERE y = 4" - * requires a full-index scan. + * This can be seen to be correct by considering the above example. + * + * If we never generated skip array scan keys, it would be possible for "gaps" + * to appear that make it unsafe to mark any subsequent input scan keys + * (copied from scan->keyData[]) as required to continue the scan. Prior to + * Postgres 18, a qual like "WHERE y = 4" always required a full index scan. + * It'll now become "WHERE x = ANY('{every possible x value}') and y = 4" on + * output, due to the addition of a skip array on "x". This has the potential + * to be much more efficient than a full index scan (though it'll behave like + * a full index scan when there are many distinct values for "x"). * * If possible, redundant keys are eliminated: we keep only the tightest * >/>= bound and the tightest orderProcs[] later */ keyDataMap = MemoryContextAlloc(so->arrayContext, numberOfKeys * sizeof(int)); + + /* + * Also enlarge output array when it might otherwise not have room for + * a skip array's scan key + */ + if (numberOfKeys > scan->numberOfKeys) + so->keyData = repalloc(so->keyData, + numberOfKeys * sizeof(ScanKeyData)); } else inkeys = scan->keyData; @@ -231,6 +259,7 @@ _bt_preprocess_keys(IndexScanDesc scan) (so->arrayKeys[0].scan_key == 0 && OidIsValid(so->orderProcs[0].fn_oid))); } + Assert(!so->skipScan); return; } @@ -288,7 +317,8 @@ _bt_preprocess_keys(IndexScanDesc scan) * redundant. Note that this is no less true if the = key is * SEARCHARRAY; the only real difference is that the inequality * key _becomes_ redundant by making _bt_compare_scankey_args - * eliminate the subset of elements that won't need to be matched. + * eliminate the subset of elements that won't need to be matched + * (with regular SAOP arrays and skip arrays alike). * * If we have a case like "key = 1 AND key > 2", we set qual_ok to * false and abandon further processing. We'll do the same thing @@ -345,7 +375,6 @@ _bt_preprocess_keys(IndexScanDesc scan) return; } /* else discard the redundant non-equality key */ - Assert(!array || array->num_elems > 0); xform[j].inkey = NULL; xform[j].inkeyi = -1; } @@ -393,6 +422,11 @@ _bt_preprocess_keys(IndexScanDesc scan) * Emit the cleaned-up keys into the so->keyData[] array, and then * mark them if they are required. They are required (possibly * only in one direction) if all attrs before this one had "=". + * + * In practice we'll rarely output non-required scan keys here; + * typically, _bt_preprocess_array_keys has already added "=" keys + * sufficient to form an unbroken series of "=" constraints on all + * attrs prior to the attr from the final scan->keyData[] key. */ for (j = BTMaxStrategyNumber; --j >= 0;) { @@ -481,6 +515,7 @@ _bt_preprocess_keys(IndexScanDesc scan) Assert(array->scan_key == i); Assert(OidIsValid(orderproc->fn_oid)); + Assert(!(inkey->sk_flags & SK_BT_SKIP)); } else if (xform[j].inkey->sk_flags & SK_SEARCHARRAY) { @@ -489,6 +524,7 @@ _bt_preprocess_keys(IndexScanDesc scan) Assert(array->scan_key == xform[j].inkeyi); Assert(OidIsValid(orderproc->fn_oid)); + Assert(!(xform[j].inkey->sk_flags & SK_BT_SKIP)); } /* @@ -508,8 +544,6 @@ _bt_preprocess_keys(IndexScanDesc scan) /* Have all we need to determine redundancy */ if (test_result) { - Assert(!array || array->num_elems > 0); - /* * New key is more restrictive, and so replaces old key... */ @@ -803,6 +837,9 @@ _bt_compare_scankey_args(IndexScanDesc scan, ScanKey op, cmp_op; StrategyNumber strat; + Assert(!((leftarg->sk_flags | rightarg->sk_flags) & + (SK_ROW_HEADER | SK_ROW_MEMBER))); + /* * First, deal with cases where one or both args are NULL. This should * only happen when the scankeys represent IS NULL/NOT NULL conditions. @@ -812,6 +849,22 @@ _bt_compare_scankey_args(IndexScanDesc scan, ScanKey op, bool leftnull, rightnull; + /* Handle skip array comparison with IS NOT NULL scan key */ + if ((leftarg->sk_flags | rightarg->sk_flags) & SK_BT_SKIP) + { + /* Shouldn't generate skip array in presence of IS NULL key */ + Assert(!((leftarg->sk_flags | rightarg->sk_flags) & SK_SEARCHNULL)); + Assert((leftarg->sk_flags | rightarg->sk_flags) & SK_SEARCHNOTNULL); + + /* Skip array will have no NULL element/IS NULL scan key */ + Assert(array->num_elems == -1); + array->null_elem = false; + + /* IS NOT NULL key (could be leftarg or rightarg) now redundant */ + *result = true; + return true; + } + if (leftarg->sk_flags & SK_ISNULL) { Assert(leftarg->sk_flags & (SK_SEARCHNULL | SK_SEARCHNOTNULL)); @@ -885,6 +938,7 @@ _bt_compare_scankey_args(IndexScanDesc scan, ScanKey op, { /* Can't make the comparison */ *result = false; /* suppress compiler warnings */ + Assert(!((leftarg->sk_flags | rightarg->sk_flags) & SK_BT_SKIP)); return false; } @@ -978,24 +1032,55 @@ _bt_compare_scankey_args(IndexScanDesc scan, ScanKey op, * Compare an array scan key to a scalar scan key, eliminating contradictory * array elements such that the scalar scan key becomes redundant. * + * If the opfamily is incomplete we may not be able to determine which + * elements are contradictory. When we return true we'll have validly set + * *qual_ok, guaranteeing that at least the scalar scan key can be considered + * redundant. We return false if the comparison could not be made (caller + * must keep both scan keys when this happens). + * + * Note: it's up to caller to deal with IS [NOT] NULL scan keys, as well as + * row comparison scan keys. We only deal with scalar scan keys. + */ +static bool +_bt_compare_array_scankey_args(IndexScanDesc scan, ScanKey arraysk, ScanKey skey, + FmgrInfo *orderproc, BTArrayKeyInfo *array, + bool *qual_ok) +{ + Assert(arraysk->sk_attno == skey->sk_attno); + Assert(!(arraysk->sk_flags & (SK_ISNULL | SK_ROW_HEADER | SK_ROW_MEMBER))); + Assert((arraysk->sk_flags & SK_SEARCHARRAY) && + arraysk->sk_strategy == BTEqualStrategyNumber); + /* don't expect to have to deal with NULLs/row comparison scan keys */ + Assert(!(skey->sk_flags & (SK_ISNULL | SK_ROW_HEADER | SK_ROW_MEMBER))); + Assert(!(skey->sk_flags & SK_SEARCHARRAY) || + skey->sk_strategy != BTEqualStrategyNumber); + + /* + * Just call the appropriate helper function based on whether it's a SAOP + * array or a skip array. Both helpers will set *qual_ok in passing. + */ + if (array->num_elems != -1) + return _bt_saoparray_shrink(scan, arraysk, skey, orderproc, array, + qual_ok); + else + return _bt_skiparray_shrink(scan, skey, array, qual_ok); +} + +/* + * Preprocessing of SAOP (non-skip) array scan key, used to determine which + * array elements are eliminated as contradictory by a non-array scalar key. + * _bt_compare_array_scankey_args helper function. + * * Array elements can be eliminated as contradictory when excluded by some * other operator on the same attribute. For example, with an index scan qual * "WHERE a IN (1, 2, 3) AND a < 2", all array elements except the value "1" * are eliminated, and the < scan key is eliminated as redundant. Cases where * every array element is eliminated by a redundant scalar scan key have an * unsatisfiable qual, which we handle by setting *qual_ok=false for caller. - * - * If the opfamily doesn't supply a complete set of cross-type ORDER procs we - * may not be able to determine which elements are contradictory. If we have - * the required ORDER proc then we return true (and validly set *qual_ok), - * guaranteeing that at least the scalar scan key can be considered redundant. - * We return false if the comparison could not be made (caller must keep both - * scan keys when this happens). */ static bool -_bt_compare_array_scankey_args(IndexScanDesc scan, ScanKey arraysk, ScanKey skey, - FmgrInfo *orderproc, BTArrayKeyInfo *array, - bool *qual_ok) +_bt_saoparray_shrink(IndexScanDesc scan, ScanKey arraysk, ScanKey skey, + FmgrInfo *orderproc, BTArrayKeyInfo *array, bool *qual_ok) { Relation rel = scan->indexRelation; Oid opcintype = rel->rd_opcintype[arraysk->sk_attno - 1]; @@ -1006,14 +1091,8 @@ _bt_compare_array_scankey_args(IndexScanDesc scan, ScanKey arraysk, ScanKey skey FmgrInfo crosstypeproc; FmgrInfo *orderprocp = orderproc; - Assert(arraysk->sk_attno == skey->sk_attno); Assert(array->num_elems > 0); - Assert(!(arraysk->sk_flags & (SK_ISNULL | SK_ROW_HEADER | SK_ROW_MEMBER))); - Assert((arraysk->sk_flags & SK_SEARCHARRAY) && - arraysk->sk_strategy == BTEqualStrategyNumber); - Assert(!(skey->sk_flags & (SK_ISNULL | SK_ROW_HEADER | SK_ROW_MEMBER))); - Assert(!(skey->sk_flags & SK_SEARCHARRAY) || - skey->sk_strategy != BTEqualStrategyNumber); + Assert(!(arraysk->sk_flags & SK_BT_SKIP)); /* * _bt_binsrch_array_skey searches an array for the entry best matching a @@ -1112,6 +1191,103 @@ _bt_compare_array_scankey_args(IndexScanDesc scan, ScanKey arraysk, ScanKey skey return true; } +/* + * Preprocessing of skip (non-SAOP) array scan key, used to determine + * redundancy against a non-array scalar scan key (must be an inequality). + * _bt_compare_array_scankey_args helper function. + * + * Unlike _bt_saoparray_shrink, we don't modify caller's array in-place. Skip + * arrays work by procedurally generating their elements as needed, so we just + * store the inequality as the skip array's low_compare or high_compare. The + * array's elements will be generated from the range of values that satisfies + * both low_compare and high_compare. + */ +static bool +_bt_skiparray_shrink(IndexScanDesc scan, ScanKey skey, BTArrayKeyInfo *array, + bool *qual_ok) +{ + bool test_result; + + Assert(array->num_elems == -1); + + /* + * Array's index attribute will be constrained by a strict operator/key. + * Array must not "contain a NULL element" (i.e. the scan must not apply + * "IS NULL" qual when it reaches the end of the index that stores NULLs). + */ + array->null_elem = false; + *qual_ok = true; + + /* + * Consider if we should treat caller's scalar scan key as the skip + * array's high_compare or low_compare. + * + * In general the current array element must either be a copy of a value + * taken from an index tuple, or a derivative value generated by opclass's + * skip support function. That way the scan can always safely assume that + * it's okay to use the input-opclass-only-type proc from so->orderProcs[] + * (they can be cross-type with SAOP arrays, but never with skip arrays). + * + * This approach is enabled by MINVAL/MAXVAL sentinel key markings, which + * can be thought of as representing either the lowest or highest matching + * array element (excluding the NULL element, where applicable, though as + * just discussed it isn't applicable to this range skip array anyway). + * Array keys marked MINVAL/MAXVAL never has a valid datum stored in its + * sk_argument. The scan must directly apply the array's low_compare when + * it encounters MINVAL (or its high_compare when it encounters MAXVAL), + * and must never use the array's so->orderProcs[] proc against + * low_compare's/high_compare's sk_argument. + */ + switch (skey->sk_strategy) + { + case BTLessStrategyNumber: + case BTLessEqualStrategyNumber: + if (array->high_compare) + { + /* replace existing high_compare with caller's key? */ + if (!_bt_compare_scankey_args(scan, array->high_compare, skey, + array->high_compare, NULL, NULL, + &test_result)) + return false; /* can't determine more restrictive key */ + + if (!test_result) + return true; /* no, just discard caller's key */ + + /* yes, replace existing high_compare with caller's key */ + } + + /* caller's key becomes skip array's high_compare */ + array->high_compare = skey; + break; + case BTGreaterEqualStrategyNumber: + case BTGreaterStrategyNumber: + if (array->low_compare) + { + /* replace existing low_compare with caller's key? */ + if (!_bt_compare_scankey_args(scan, array->low_compare, skey, + array->low_compare, NULL, NULL, + &test_result)) + return false; /* can't determine more restrictive key */ + + if (!test_result) + return true; /* no, just discard caller's key */ + + /* yes, replace existing low_compare with caller's key */ + } + + /* caller's key becomes skip array's low_compare */ + array->low_compare = skey; + break; + case BTEqualStrategyNumber: + default: + elog(ERROR, "unrecognized StrategyNumber: %d", + (int) skey->sk_strategy); + break; + } + + return true; +} + /* * _bt_preprocess_array_keys() -- Preprocess SK_SEARCHARRAY scan keys * @@ -1137,6 +1313,12 @@ _bt_compare_array_scankey_args(IndexScanDesc scan, ScanKey arraysk, ScanKey skey * one equality strategy array scan key per index attribute. We'll always be * able to set things up that way when complete opfamilies are used. * + * We're also responsible for generating skip arrays (and their associated + * scan keys) here. This enables skip scan. We do this for index attributes + * that initially lacked an equality condition within scan->keyData[], iff + * doing so allows a later scan key (that was passed to us in scan->keyData[]) + * to be marked required by our _bt_preprocess_keys caller. + * * We set the scan key references from the scan's BTArrayKeyInfo info array to * offsets into the temp modified input array returned to caller. Scans that * have array keys should call _bt_preprocess_array_keys_final when standard @@ -1152,41 +1334,36 @@ _bt_preprocess_array_keys(IndexScanDesc scan, int *new_numberOfKeys) { BTScanOpaque so = (BTScanOpaque) scan->opaque; Relation rel = scan->indexRelation; - int numberOfKeys = scan->numberOfKeys; int16 *indoption = rel->rd_indoption; + Oid skip_eq_ops[INDEX_MAX_KEYS]; int numArrayKeys, - output_ikey = 0; + numSkipArrayKeys, + numArrayKeyData; + AttrNumber attno_skip = 1; int origarrayatt = InvalidAttrNumber, origarraykey = -1; Oid origelemtype = InvalidOid; - ScanKey cur; MemoryContext oldContext; ScanKey arrayKeyData; /* modified copy of scan->keyData */ - Assert(numberOfKeys); - - /* Quick check to see if there are any array keys */ - numArrayKeys = 0; - for (int i = 0; i < numberOfKeys; i++) - { - cur = &scan->keyData[i]; - if (cur->sk_flags & SK_SEARCHARRAY) - { - numArrayKeys++; - Assert(!(cur->sk_flags & (SK_ROW_HEADER | SK_SEARCHNULL | SK_SEARCHNOTNULL))); - /* If any arrays are null as a whole, we can quit right now. */ - if (cur->sk_flags & SK_ISNULL) - { - so->qual_ok = false; - return NULL; - } - } - } + /* + * Check the number of input array keys within scan->keyData[] input keys + * (also checks if we should add extra skip arrays based on input keys) + */ + numArrayKeys = _bt_num_array_keys(scan, skip_eq_ops, &numSkipArrayKeys); + so->skipScan = (numSkipArrayKeys > 0); /* Quit if nothing to do. */ if (numArrayKeys == 0) return NULL; + /* + * Estimated final size of arrayKeyData[] array we'll return to our caller + * is the size of the original scan->keyData[] input array, plus space for + * any additional skip array scan keys we'll need to generate below + */ + numArrayKeyData = scan->numberOfKeys + numSkipArrayKeys; + /* * Make a scan-lifespan context to hold array-associated data, or reset it * if we already have one from a previous rescan cycle. @@ -1201,18 +1378,20 @@ _bt_preprocess_array_keys(IndexScanDesc scan, int *new_numberOfKeys) oldContext = MemoryContextSwitchTo(so->arrayContext); /* Create output scan keys in the workspace context */ - arrayKeyData = (ScanKey) palloc(numberOfKeys * sizeof(ScanKeyData)); + arrayKeyData = (ScanKey) palloc(numArrayKeyData * sizeof(ScanKeyData)); /* Allocate space for per-array data in the workspace context */ so->arrayKeys = (BTArrayKeyInfo *) palloc(numArrayKeys * sizeof(BTArrayKeyInfo)); /* Allocate space for ORDER procs used to help _bt_checkkeys */ - so->orderProcs = (FmgrInfo *) palloc(numberOfKeys * sizeof(FmgrInfo)); + so->orderProcs = (FmgrInfo *) palloc(numArrayKeyData * sizeof(FmgrInfo)); - /* Now process each array key */ numArrayKeys = 0; - for (int input_ikey = 0; input_ikey < numberOfKeys; input_ikey++) + numArrayKeyData = 0; + for (int input_ikey = 0; input_ikey < scan->numberOfKeys; input_ikey++) { + ScanKey inkey = scan->keyData + input_ikey, + cur; FmgrInfo sortproc; FmgrInfo *sortprocp = &sortproc; Oid elemtype; @@ -1225,21 +1404,114 @@ _bt_preprocess_array_keys(IndexScanDesc scan, int *new_numberOfKeys) Datum *elem_values; bool *elem_nulls; int num_nonnulls; - int j; + + /* set up next output scan key */ + cur = &arrayKeyData[numArrayKeyData]; + + /* Backfill skip arrays for attrs < or <= input key's attr? */ + while (numSkipArrayKeys && attno_skip <= inkey->sk_attno) + { + Oid opfamily = rel->rd_opfamily[attno_skip - 1]; + Oid opcintype = rel->rd_opcintype[attno_skip - 1]; + Oid collation = rel->rd_indcollation[attno_skip - 1]; + Oid eq_op = skip_eq_ops[attno_skip - 1]; + CompactAttribute *attr; + RegProcedure cmp_proc; + + if (!OidIsValid(eq_op)) + { + /* + * Attribute already has an = input key, so don't output a + * skip array for attno_skip. Just copy attribute's = input + * key into arrayKeyData[] once outside this inner loop. + * + * Note: When we get here there must be a later attribute that + * lacks an equality input key, and still needs a skip array + * (if there wasn't then numSkipArrayKeys would be 0 by now). + */ + Assert(attno_skip == inkey->sk_attno); + /* inkey can't be last input key to be marked required: */ + Assert(input_ikey < scan->numberOfKeys - 1); +#if 0 + /* Could be a redundant input scan key, so can't do this: */ + Assert(inkey->sk_strategy == BTEqualStrategyNumber || + (inkey->sk_flags & SK_SEARCHNULL)); +#endif + + attno_skip++; + break; + } + + cmp_proc = get_opcode(eq_op); + if (!RegProcedureIsValid(cmp_proc)) + elog(ERROR, "missing oprcode for skipping equals operator %u", eq_op); + + ScanKeyEntryInitialize(cur, + SK_SEARCHARRAY | SK_BT_SKIP, /* flags */ + attno_skip, /* skipped att number */ + BTEqualStrategyNumber, /* equality strategy */ + InvalidOid, /* opclass input subtype */ + collation, /* index column's collation */ + cmp_proc, /* equality operator's proc */ + (Datum) 0); /* constant */ + + /* Initialize generic BTArrayKeyInfo fields */ + so->arrayKeys[numArrayKeys].scan_key = numArrayKeyData; + so->arrayKeys[numArrayKeys].num_elems = -1; + + /* Initialize skip array specific BTArrayKeyInfo fields */ + attr = TupleDescCompactAttr(RelationGetDescr(rel), attno_skip - 1); + reverse = (indoption[attno_skip - 1] & INDOPTION_DESC) != 0; + so->arrayKeys[numArrayKeys].attlen = attr->attlen; + so->arrayKeys[numArrayKeys].attbyval = attr->attbyval; + so->arrayKeys[numArrayKeys].null_elem = true; /* for now */ + so->arrayKeys[numArrayKeys].sksup = + PrepareSkipSupportFromOpclass(opfamily, opcintype, reverse); + so->arrayKeys[numArrayKeys].low_compare = NULL; /* for now */ + so->arrayKeys[numArrayKeys].high_compare = NULL; /* for now */ + + /* + * We'll need a 3-way ORDER proc to perform "binary searches" for + * the next matching array element. Set that up now. + */ + _bt_setup_array_cmp(scan, cur, opcintype, + &so->orderProcs[numArrayKeyData], NULL); + + numArrayKeys++; + numArrayKeyData++; /* keep this scan key/array */ + + /* set up next output scan key */ + cur = &arrayKeyData[numArrayKeyData]; + + /* remember having output this skip array and scan key */ + numSkipArrayKeys--; + attno_skip++; + } /* * Provisionally copy scan key into arrayKeyData[] array we'll return * to _bt_preprocess_keys caller */ - cur = &arrayKeyData[output_ikey]; - *cur = scan->keyData[input_ikey]; + *cur = *inkey; if (!(cur->sk_flags & SK_SEARCHARRAY)) { - output_ikey++; /* keep this non-array scan key */ + numArrayKeyData++; /* keep this non-array scan key */ continue; } + /* + * Process conventional/SAOP array scan key + */ + Assert(!(cur->sk_flags & (SK_ROW_HEADER | SK_SEARCHNULL | SK_SEARCHNOTNULL))); + + /* If array is null as a whole, the scan qual is unsatisfiable */ + if (cur->sk_flags & SK_ISNULL) + { + so->qual_ok = false; + break; + } + /* * Deconstruct the array into elements */ @@ -1257,7 +1529,7 @@ _bt_preprocess_array_keys(IndexScanDesc scan, int *new_numberOfKeys) * all btree operators are strict. */ num_nonnulls = 0; - for (j = 0; j < num_elems; j++) + for (int j = 0; j < num_elems; j++) { if (!elem_nulls[j]) elem_values[num_nonnulls++] = elem_values[j]; @@ -1295,7 +1567,7 @@ _bt_preprocess_array_keys(IndexScanDesc scan, int *new_numberOfKeys) _bt_find_extreme_element(scan, cur, elemtype, BTGreaterStrategyNumber, elem_values, num_nonnulls); - output_ikey++; /* keep this transformed scan key */ + numArrayKeyData++; /* keep this transformed scan key */ continue; case BTEqualStrategyNumber: /* proceed with rest of loop */ @@ -1306,7 +1578,7 @@ _bt_preprocess_array_keys(IndexScanDesc scan, int *new_numberOfKeys) _bt_find_extreme_element(scan, cur, elemtype, BTLessStrategyNumber, elem_values, num_nonnulls); - output_ikey++; /* keep this transformed scan key */ + numArrayKeyData++; /* keep this transformed scan key */ continue; default: elog(ERROR, "unrecognized StrategyNumber: %d", @@ -1323,7 +1595,7 @@ _bt_preprocess_array_keys(IndexScanDesc scan, int *new_numberOfKeys) * sortproc just points to the same proc used during binary searches. */ _bt_setup_array_cmp(scan, cur, elemtype, - &so->orderProcs[output_ikey], &sortprocp); + &so->orderProcs[numArrayKeyData], &sortprocp); /* * Sort the non-null elements and eliminate any duplicates. We must @@ -1392,23 +1664,24 @@ _bt_preprocess_array_keys(IndexScanDesc scan, int *new_numberOfKeys) origelemtype = elemtype; } - /* - * And set up the BTArrayKeyInfo data. - * - * Note: _bt_preprocess_array_keys_final will fix-up each array's - * scan_key field later on, after so->keyData[] has been finalized. - */ - so->arrayKeys[numArrayKeys].scan_key = output_ikey; + /* Initialize generic BTArrayKeyInfo fields */ + so->arrayKeys[numArrayKeys].scan_key = numArrayKeyData; so->arrayKeys[numArrayKeys].num_elems = num_elems; + + /* Initialize SAOP array specific BTArrayKeyInfo fields */ so->arrayKeys[numArrayKeys].elem_values = elem_values; + so->arrayKeys[numArrayKeys].cur_elem = -1; /* i.e. invalid */ + numArrayKeys++; - output_ikey++; /* keep this scan key/array */ + numArrayKeyData++; /* keep this scan key/array */ } + Assert(numSkipArrayKeys == 0); + /* Set final number of equality-type array keys */ so->numArrayKeys = numArrayKeys; - /* Set number of scan keys remaining in arrayKeyData[] */ - *new_numberOfKeys = output_ikey; + /* Set final number of scan keys in arrayKeyData[] */ + *new_numberOfKeys = numArrayKeyData; MemoryContextSwitchTo(oldContext); @@ -1514,7 +1787,8 @@ _bt_preprocess_array_keys_final(IndexScanDesc scan, int *keyDataMap) { BTArrayKeyInfo *array = &so->arrayKeys[arrayidx]; - Assert(array->num_elems > 0); + Assert(array->num_elems > 0 || array->num_elems == -1); + Assert(array->num_elems != -1 || outkey->sk_flags & SK_BT_REQFWD); if (array->scan_key == input_ikey) { @@ -1565,7 +1839,7 @@ _bt_preprocess_array_keys_final(IndexScanDesc scan, int *keyDataMap) * Parallel index scans require space in shared memory to store the * current array elements (for arrays kept by preprocessing) to schedule * the next primitive index scan. The underlying structure is protected - * using a spinlock, so defensively limit its size. In practice this can + * using an LWLock, so defensively limit its size. In practice this can * only affect parallel scans that use an incomplete opfamily. */ if (scan->parallel_scan && so->numArrayKeys > INDEX_MAX_KEYS) @@ -1575,6 +1849,189 @@ _bt_preprocess_array_keys_final(IndexScanDesc scan, int *keyDataMap) so->numArrayKeys, INDEX_MAX_KEYS))); } +/* + * _bt_num_array_keys() -- determine # of BTArrayKeyInfo entries + * + * _bt_preprocess_array_keys helper function. Returns the estimated size of + * the scan's BTArrayKeyInfo array, which is guaranteed to be large enough to + * fit every so->arrayKeys[] entry. + * + * Also sets *numSkipArrayKeys to # of skip arrays _bt_preprocess_array_keys + * caller must add to the scan keys it'll output. Caller must add this many + * skip arrays to each of the most significant attributes lacking any keys + * that use the = strategy (IS NULL keys count as = keys here). The specific + * attributes that need skip arrays are indicated by initializing caller's + * skip_eq_ops[] 0-based attribute offset to a valid = op strategy Oid. We'll + * only ever set skip_eq_ops[] entries to InvalidOid for attributes that + * already have an equality key in scan->keyData[] input keys -- and only when + * there's some later "attribute gap" for us to "fill-in" with a skip array. + * + * We're optimistic about skipping working out: we always add exactly the skip + * arrays needed to maximize the number of input scan keys that can ultimately + * be marked as required to continue the scan (but no more). For a composite + * index on (a, b, c, d), we'll instruct caller to add skip arrays as follows: + * + * Input keys Output keys (after all preprocessing) + * ---------- ------------------------------------- + * a = 1 a = 1 (no skip arrays) + * a = ANY('{0, 1}') a = ANY('{0, 1}') (no skip arrays) + * b = 42 skip a AND b = 42 + * b = ANY('{40, 42}') skip a AND b = ANY('{40, 42}') + * a = 1 AND b = 42 a = 1 AND b = 42 (no skip arrays) + * a >= 1 AND b = 42 range skip a AND b = 42 + * a = 1 AND b > 42 a = 1 AND b > 42 (no skip arrays) + * a >= 1 AND a <= 3 AND b = 42 range skip a AND b = 42 + * a = 1 AND c <= 27 a = 1 AND skip b AND c <= 27 + * a = 1 AND d >= 1 a = 1 AND skip b AND skip c AND d >= 1 + * a = 1 AND b >= 42 AND d > 1 a = 1 AND range skip b AND skip c AND d > 1 + */ +static int +_bt_num_array_keys(IndexScanDesc scan, Oid *skip_eq_ops, int *numSkipArrayKeys) +{ + Relation rel = scan->indexRelation; + AttrNumber attno_skip = 1, + attno_inkey = 1; + bool attno_has_equal = false, + attno_has_rowcompare = false; + int numArrayKeys; + int prev_numSkipArrayKeys = 0; + + Assert(scan->numberOfKeys); + + /* + * Initial pass over input scan keys counts the number of conventional + * (non-skip) arrays + */ + numArrayKeys = 0; + *numSkipArrayKeys = 0; + for (int i = 0; i < scan->numberOfKeys; i++) + { + ScanKey inkey = scan->keyData + i; + + if (inkey->sk_flags & SK_SEARCHARRAY) + numArrayKeys++; + } + +#ifdef DEBUG_DISABLE_SKIP_SCAN + /* don't attempt to add skip arrays */ + return numArrayKeys; +#endif + + for (int i = 0;; i++) + { + ScanKey inkey = scan->keyData + i; + + /* + * Backfill skip arrays for any wholly omitted attributes prior to + * attno_inkey + */ + while (attno_skip < attno_inkey) + { + Oid opfamily = rel->rd_opfamily[attno_skip - 1]; + Oid opcintype = rel->rd_opcintype[attno_skip - 1]; + + /* Look up input opclass's equality operator (might fail) */ + skip_eq_ops[attno_skip - 1] = + get_opfamily_member(opfamily, opcintype, opcintype, + BTEqualStrategyNumber); + if (!OidIsValid(skip_eq_ops[attno_skip - 1])) + { + /* + * Cannot generate a skip array for this or later attributes + * (input opclass lacks an equality strategy operator) + */ + *numSkipArrayKeys = prev_numSkipArrayKeys; + return numArrayKeys + prev_numSkipArrayKeys; + } + + /* plan on adding a backfill skip array for this attribute */ + (*numSkipArrayKeys)++; + attno_skip++; + } + + prev_numSkipArrayKeys = *numSkipArrayKeys; + + /* + * Stop once past the final input scan key. We deliberately never add + * a skip attribute for the attribute of the last input scan key + * (doesn't matter whether that attribute has an equality key, or just + * uses inequality keys). + */ + if (i == scan->numberOfKeys) + break; + + /* + * Cannot keep adding skip arrays after a RowCompare + */ + if (attno_has_rowcompare) + break; + + /* + * Now consider next attno_inkey (or keep going if this is an + * additional scan key against the same attribute) + */ + if (attno_inkey < inkey->sk_attno) + { + /* + * Now add skip array for previous scan key's attribute, though + * only if the attribute has no equality strategy scan keys + */ + if (attno_has_equal) + { + /* Attributes with an = key must have InvalidOid eq_op set */ + skip_eq_ops[attno_skip - 1] = InvalidOid; + } + else + { + Oid opfamily = rel->rd_opfamily[attno_skip - 1]; + Oid opcintype = rel->rd_opcintype[attno_skip - 1]; + + /* Look up input opclass's equality operator (might fail) */ + skip_eq_ops[attno_skip - 1] = + get_opfamily_member(opfamily, opcintype, opcintype, + BTEqualStrategyNumber); + + if (!OidIsValid(skip_eq_ops[attno_skip - 1])) + { + /* + * Input opclass lacks an equality strategy operator, so + * don't generate a skip array that definitely won't work + */ + break; + } + + /* plan on adding a backfill skip array for this attribute */ + (*numSkipArrayKeys)++; + } + + /* Set things up for this new attribute */ + attno_skip++; + attno_inkey = inkey->sk_attno; + attno_has_equal = false; + } + + /* + * Track if this attribute's scan keys have any equality strategy scan + * keys (while counting IS NULL scan keys as equality scan keys) + */ + if (inkey->sk_strategy == BTEqualStrategyNumber || + (inkey->sk_flags & SK_SEARCHNULL)) + attno_has_equal = true; + + /* + * We don't support RowCompare transformation. Remember that we saw a + * RowCompare, so that we don't keep adding skip attributes. (We may + * still backfill skip attributes before the RowCompare, so that it + * will be marked required later on.) + */ + if (inkey->sk_flags & SK_ROW_HEADER) + attno_has_rowcompare = true; + } + + /* numArrayKeys returned to caller includes any skip arrays */ + return numArrayKeys + *numSkipArrayKeys; +} + /* * _bt_find_extreme_element() -- get least or greatest array element * diff --git a/src/backend/access/nbtree/nbtree.c b/src/backend/access/nbtree/nbtree.c index fe8578eed..aae2a46c8 100644 --- a/src/backend/access/nbtree/nbtree.c +++ b/src/backend/access/nbtree/nbtree.c @@ -30,6 +30,7 @@ #include "storage/indexfsm.h" #include "storage/ipc.h" #include "storage/lmgr.h" +#include "utils/datum.h" #include "utils/fmgrprotos.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" @@ -71,7 +72,7 @@ typedef struct BTParallelScanDescData * available for scan. see above for * possible states of parallel scan. */ uint64 btps_nsearches; /* counts index searches for EXPLAIN ANALYZE */ - slock_t btps_mutex; /* protects above variables, btps_arrElems */ + LWLock btps_lock; /* protects above variables, btps_arrElems */ ConditionVariable btps_cv; /* used to synchronize parallel scan */ /* @@ -79,11 +80,24 @@ typedef struct BTParallelScanDescData * index scan. Holds BTArrayKeyInfo.cur_elem offsets for scan keys. */ int btps_arrElems[FLEXIBLE_ARRAY_MEMBER]; + + /* + * The remainder of the space allocated in shared memory is used by scans + * that need to schedule another primitive index scan with skip arrays. + * + * Space holds a flattened representation of each skip array's current + * array element, in datum format. We don't store BTArrayKeyInfo.cur_elem + * offsets for skip arrays; their elements are determined dynamically. + */ } BTParallelScanDescData; typedef struct BTParallelScanDescData *BTParallelScanDesc; +static void _bt_parallel_serialize_arrays(Relation rel, BTParallelScanDesc btscan, + BTScanOpaque so); +static void _bt_parallel_restore_arrays(Relation rel, BTParallelScanDesc btscan, + BTScanOpaque so); static void btvacuumscan(IndexVacuumInfo *info, IndexBulkDeleteResult *stats, IndexBulkDeleteCallback callback, void *callback_state, BTCycleId cycleid); @@ -333,6 +347,7 @@ btbeginscan(Relation rel, int nkeys, int norderbys) else so->keyData = NULL; + so->skipScan = false; so->needPrimScan = false; so->scanBehind = false; so->oppositeDirCheck = false; @@ -538,10 +553,155 @@ btrestrpos(IndexScanDesc scan) * btestimateparallelscan -- estimate storage for BTParallelScanDescData */ Size -btestimateparallelscan(int nkeys, int norderbys) +btestimateparallelscan(Relation rel, int nkeys, int norderbys) { - /* Pessimistically assume all input scankeys will be output with arrays */ - return offsetof(BTParallelScanDescData, btps_arrElems) + sizeof(int) * nkeys; + int16 nkeyatts = IndexRelationGetNumberOfKeyAttributes(rel); + Size estnbtreeshared, + genericattrspace; + + /* + * Pessimistically assume all input scankeys will be output with its own + * SAOP array + */ + estnbtreeshared = offsetof(BTParallelScanDescData, btps_arrElems) + + sizeof(int) * nkeys; + + /* + * Pessimistically assume that every index attribute will require a skip + * scan array (and associated scan key) + */ + genericattrspace = datumEstimateSpace((Datum) 0, false, true, + sizeof(Datum)); + for (int attnum = 1; attnum <= nkeyatts; attnum++) + { + CompactAttribute *attr; + + /* Every skip array needs a space for storing sk_flags */ + estnbtreeshared = add_size(estnbtreeshared, sizeof(int)); + + attr = TupleDescCompactAttr(rel->rd_att, attnum - 1); + if (attr->attlen > 0) + { + /* Fixed length datum */ + Size estfixed = datumEstimateSpace((Datum) 0, false, + attr->attbyval, + attr->attlen); + + estnbtreeshared = add_size(estnbtreeshared, estfixed); + continue; + } + + /* + * Varlena (or other variable-length) datum. + * + * Assume that serializing the arrays will use just as much space as a + * pass-by-value datum, in addition to a full third of a page of + * space. + */ + estnbtreeshared = add_size(estnbtreeshared, genericattrspace); + estnbtreeshared = add_size(estnbtreeshared, BLCKSZ / 3); + } + + return estnbtreeshared; +} + +/* + * _bt_parallel_serialize_arrays() -- Serialize parallel array state. + * + * Caller must have exclusively locked btscan->btps_lock when called. + */ +static void +_bt_parallel_serialize_arrays(Relation rel, BTParallelScanDesc btscan, + BTScanOpaque so) +{ + char *datumshared; + + /* Space for serialized datums begins immediately after btps_arrElems[] */ + datumshared = ((char *) &btscan->btps_arrElems[so->numArrayKeys]); + for (int i = 0; i < so->numArrayKeys; i++) + { + BTArrayKeyInfo *array = &so->arrayKeys[i]; + ScanKey skey = &so->keyData[array->scan_key]; + + if (array->num_elems != -1) + { + /* Serialize regular (non-skip) array using cur_elem */ + Assert(!(skey->sk_flags & SK_BT_SKIP)); + btscan->btps_arrElems[i] = array->cur_elem; + continue; + } + + /* Serialize skip array key */ + Assert(skey->sk_flags & SK_BT_SKIP); + memcpy(datumshared, &skey->sk_flags, sizeof(int)); + datumshared += sizeof(int); + + if (skey->sk_flags & (SK_BT_MINVAL | SK_BT_MAXVAL)) + { + /* No sk_argument datum to serialize */ + Assert(skey->sk_argument == 0); + continue; + } + + datumSerialize(skey->sk_argument, (skey->sk_flags & SK_ISNULL) != 0, + array->attbyval, array->attlen, &datumshared); + } +} + +/* + * _bt_parallel_restore_arrays() -- Restore serialized parallel array state. + * + * Caller must have exclusively locked btscan->btps_lock when called. + */ +static void +_bt_parallel_restore_arrays(Relation rel, BTParallelScanDesc btscan, + BTScanOpaque so) +{ + char *datumshared; + + /* Space for serialized datums begins immediately after btps_arrElems[] */ + datumshared = ((char *) &btscan->btps_arrElems[so->numArrayKeys]); + for (int i = 0; i < so->numArrayKeys; i++) + { + BTArrayKeyInfo *array = &so->arrayKeys[i]; + ScanKey skey = &so->keyData[array->scan_key]; + bool isnull; + + if (array->num_elems != -1) + { + /* Restore regular (non-skip) array's cur_elem */ + Assert(!(skey->sk_flags & SK_BT_SKIP)); + array->cur_elem = btscan->btps_arrElems[i]; + skey->sk_argument = array->elem_values[array->cur_elem]; + continue; + } + + /* + * Restore skip array key, while freeing memory allocated for old + * sk_argument where required + */ + if (!array->attbyval && skey->sk_argument) + pfree(DatumGetPointer(skey->sk_argument)); + skey->sk_argument = (Datum) 0; + memcpy(&skey->sk_flags, datumshared, sizeof(int)); + datumshared += sizeof(int); + + Assert(skey->sk_flags & SK_BT_SKIP); + + if (skey->sk_flags & (SK_BT_MINVAL | SK_BT_MAXVAL)) + { + /* No sk_argument datum to restore */ + continue; + } + + skey->sk_argument = datumRestore(&datumshared, &isnull); + if (isnull) + { + Assert(skey->sk_argument == 0); + Assert(skey->sk_flags & SK_SEARCHNULL); + Assert(skey->sk_flags & SK_ISNULL); + } + } } /* @@ -552,7 +712,8 @@ btinitparallelscan(void *target) { BTParallelScanDesc bt_target = (BTParallelScanDesc) target; - SpinLockInit(&bt_target->btps_mutex); + LWLockInitialize(&bt_target->btps_lock, + LWTRANCHE_PARALLEL_BTREE_SCAN); bt_target->btps_nextScanPage = InvalidBlockNumber; bt_target->btps_lastCurrPage = InvalidBlockNumber; bt_target->btps_pageStatus = BTPARALLEL_NOT_INITIALIZED; @@ -575,16 +736,16 @@ btparallelrescan(IndexScanDesc scan) parallel_scan->ps_offset); /* - * In theory, we don't need to acquire the spinlock here, because there + * In theory, we don't need to acquire the LWLock here, because there * shouldn't be any other workers running at this point, but we do so for * consistency. */ - SpinLockAcquire(&btscan->btps_mutex); + LWLockAcquire(&btscan->btps_lock, LW_EXCLUSIVE); btscan->btps_nextScanPage = InvalidBlockNumber; btscan->btps_lastCurrPage = InvalidBlockNumber; btscan->btps_pageStatus = BTPARALLEL_NOT_INITIALIZED; /* deliberately don't reset btps_nsearches (matches index_rescan) */ - SpinLockRelease(&btscan->btps_mutex); + LWLockRelease(&btscan->btps_lock); } /* @@ -611,6 +772,7 @@ bool _bt_parallel_seize(IndexScanDesc scan, BlockNumber *next_scan_page, BlockNumber *last_curr_page, bool first) { + Relation rel = scan->indexRelation; BTScanOpaque so = (BTScanOpaque) scan->opaque; bool exit_loop = false, status = true, @@ -655,7 +817,7 @@ _bt_parallel_seize(IndexScanDesc scan, BlockNumber *next_scan_page, while (1) { - SpinLockAcquire(&btscan->btps_mutex); + LWLockAcquire(&btscan->btps_lock, LW_EXCLUSIVE); if (btscan->btps_pageStatus == BTPARALLEL_DONE) { @@ -677,14 +839,9 @@ _bt_parallel_seize(IndexScanDesc scan, BlockNumber *next_scan_page, { /* Can start scheduled primitive scan right away, so do so */ btscan->btps_pageStatus = BTPARALLEL_ADVANCING; - for (int i = 0; i < so->numArrayKeys; i++) - { - BTArrayKeyInfo *array = &so->arrayKeys[i]; - ScanKey skey = &so->keyData[array->scan_key]; - array->cur_elem = btscan->btps_arrElems[i]; - skey->sk_argument = array->elem_values[array->cur_elem]; - } + /* Restore scan's array keys from serialized values */ + _bt_parallel_restore_arrays(rel, btscan, so); exit_loop = true; } else @@ -722,7 +879,7 @@ _bt_parallel_seize(IndexScanDesc scan, BlockNumber *next_scan_page, *last_curr_page = btscan->btps_lastCurrPage; exit_loop = true; } - SpinLockRelease(&btscan->btps_mutex); + LWLockRelease(&btscan->btps_lock); if (exit_loop || !status) break; ConditionVariableSleep(&btscan->btps_cv, WAIT_EVENT_BTREE_PAGE); @@ -766,11 +923,11 @@ _bt_parallel_release(IndexScanDesc scan, BlockNumber next_scan_page, btscan = (BTParallelScanDesc) OffsetToPointer(parallel_scan, parallel_scan->ps_offset); - SpinLockAcquire(&btscan->btps_mutex); + LWLockAcquire(&btscan->btps_lock, LW_EXCLUSIVE); btscan->btps_nextScanPage = next_scan_page; btscan->btps_lastCurrPage = curr_page; btscan->btps_pageStatus = BTPARALLEL_IDLE; - SpinLockRelease(&btscan->btps_mutex); + LWLockRelease(&btscan->btps_lock); ConditionVariableSignal(&btscan->btps_cv); } @@ -809,7 +966,7 @@ _bt_parallel_done(IndexScanDesc scan) * Mark the parallel scan as done, unless some other process did so * already */ - SpinLockAcquire(&btscan->btps_mutex); + LWLockAcquire(&btscan->btps_lock, LW_EXCLUSIVE); Assert(btscan->btps_pageStatus != BTPARALLEL_NEED_PRIMSCAN); if (btscan->btps_pageStatus != BTPARALLEL_DONE) { @@ -822,7 +979,7 @@ _bt_parallel_done(IndexScanDesc scan) * primscan counter, which we maintain in shared memory */ scan->nsearches = btscan->btps_nsearches; - SpinLockRelease(&btscan->btps_mutex); + LWLockRelease(&btscan->btps_lock); /* wake up all the workers associated with this parallel scan */ if (status_changed) @@ -840,6 +997,7 @@ _bt_parallel_done(IndexScanDesc scan) void _bt_parallel_primscan_schedule(IndexScanDesc scan, BlockNumber curr_page) { + Relation rel = scan->indexRelation; BTScanOpaque so = (BTScanOpaque) scan->opaque; ParallelIndexScanDesc parallel_scan = scan->parallel_scan; BTParallelScanDesc btscan; @@ -849,7 +1007,7 @@ _bt_parallel_primscan_schedule(IndexScanDesc scan, BlockNumber curr_page) btscan = (BTParallelScanDesc) OffsetToPointer(parallel_scan, parallel_scan->ps_offset); - SpinLockAcquire(&btscan->btps_mutex); + LWLockAcquire(&btscan->btps_lock, LW_EXCLUSIVE); if (btscan->btps_lastCurrPage == curr_page && btscan->btps_pageStatus == BTPARALLEL_IDLE) { @@ -859,14 +1017,9 @@ _bt_parallel_primscan_schedule(IndexScanDesc scan, BlockNumber curr_page) btscan->btps_nsearches++; /* Serialize scan's current array keys */ - for (int i = 0; i < so->numArrayKeys; i++) - { - BTArrayKeyInfo *array = &so->arrayKeys[i]; - - btscan->btps_arrElems[i] = array->cur_elem; - } + _bt_parallel_serialize_arrays(rel, btscan, so); } - SpinLockRelease(&btscan->btps_mutex); + LWLockRelease(&btscan->btps_lock); } /* diff --git a/src/backend/access/nbtree/nbtsearch.c b/src/backend/access/nbtree/nbtsearch.c index babb530ed..3e06a260e 100644 --- a/src/backend/access/nbtree/nbtsearch.c +++ b/src/backend/access/nbtree/nbtsearch.c @@ -964,6 +964,15 @@ _bt_first(IndexScanDesc scan, ScanDirection dir) * attributes to its right, because it would break our simplistic notion * of what initial positioning strategy to use. * + * In practice we rarely see any attributes with no boundary key here. + * Preprocessing can usually backfill skip array keys for any attributes + * that were omitted from the original scan->keyData[] input keys. All + * array keys are always considered = keys, but we'll sometimes need to + * treat the current key value as if we were using an inequality strategy. + * This happens whenever a skip array's scan key is found to have been set + * to one of the special sentinel values representing an imaginary point + * before/after some (or all) of the index's real indexable values. + * * When the scan keys include cross-type operators, _bt_preprocess_keys * may not be able to eliminate redundant keys; in such cases we will * arbitrarily pick a usable one for each attribute. This is correct @@ -1039,8 +1048,56 @@ _bt_first(IndexScanDesc scan, ScanDirection dir) if (i >= so->numberOfKeys || cur->sk_attno != curattr) { /* - * Done looking at keys for curattr. If we didn't find a - * usable boundary key, see if we can deduce a NOT NULL key. + * Done looking at keys for curattr. + * + * If this is a scan key for a skip array whose current + * element is MINVAL, choose low_compare (when scanning + * backwards it'll be MAXVAL, and we'll choose high_compare). + * + * Note: if the array's low_compare key makes 'chosen' NULL, + * then we behave as if the array's first element is -inf, + * except when !array->null_elem implies a usable NOT NULL + * constraint. + */ + if (chosen != NULL && + (chosen->sk_flags & (SK_BT_MINVAL | SK_BT_MAXVAL))) + { + int ikey = chosen - so->keyData; + ScanKey skipequalitykey = chosen; + BTArrayKeyInfo *array = NULL; + + Assert(so->skipScan); + + for (int arridx = 0; arridx < so->numArrayKeys; arridx++) + { + array = &so->arrayKeys[arridx]; + if (array->scan_key == ikey) + break; + } + + if (ScanDirectionIsForward(dir)) + { + Assert(!(skipequalitykey->sk_flags & SK_BT_MAXVAL)); + chosen = array->low_compare; + } + else + { + Assert(!(skipequalitykey->sk_flags & SK_BT_MINVAL)); + chosen = array->high_compare; + } + + Assert(chosen == NULL || + chosen->sk_attno == skipequalitykey->sk_attno); + + if (!array->null_elem) + impliesNN = skipequalitykey; + else + Assert(chosen == NULL && impliesNN == NULL); + } + + /* + * If we didn't find a usable boundary key, see if we can + * deduce a NOT NULL key */ if (chosen == NULL && impliesNN != NULL && ((impliesNN->sk_flags & SK_BT_NULLS_FIRST) ? @@ -1083,9 +1140,41 @@ _bt_first(IndexScanDesc scan, ScanDirection dir) break; /* - * Done if that was the last attribute, or if next key is not - * in sequence (implying no boundary key is available for the - * next attribute). + * If the key that we just added to startKeys[] is a skip + * array = key whose current element is marked NEXT or PRIOR, + * make strat_total > or < (and stop adding boundary keys). + * This can only happen with opclasses that lack skip support. + */ + if (chosen->sk_flags & (SK_BT_NEXT | SK_BT_PRIOR)) + { + Assert(so->skipScan); + Assert(chosen->sk_flags & SK_BT_SKIP); + Assert(strat_total == BTEqualStrategyNumber); + + if (ScanDirectionIsForward(dir)) + { + Assert(!(chosen->sk_flags & SK_BT_PRIOR)); + strat_total = BTGreaterStrategyNumber; + } + else + { + Assert(!(chosen->sk_flags & SK_BT_NEXT)); + strat_total = BTLessStrategyNumber; + } + + /* + * We're done. We'll never find an exact = match for a + * NEXT or PRIOR sentinel sk_argument value. There's no + * sense in trying to add more keys to startKeys[]. + */ + break; + } + + /* + * Done if that was the last scan key output by preprocessing. + * Also done if there is a gap index attribute that lacks a + * usable key (only possible when preprocessing was unable to + * generate a skip array key to "fill in the gap"). */ if (i >= so->numberOfKeys || cur->sk_attno != curattr + 1) @@ -1577,10 +1666,12 @@ _bt_readpage(IndexScanDesc scan, ScanDirection dir, OffsetNumber offnum, * corresponding value from the last item on the page. So checking with * the last item on the page would give a more precise answer. * - * We skip this for the first page read by each (primitive) scan, to avoid - * slowing down point queries. They typically don't stand to gain much - * when the optimization can be applied, and are more likely to notice the - * overhead of the precheck. + * We don't do this for the first page read by each (primitive) scan, to + * avoid slowing down point queries. They typically don't stand to gain + * much when the optimization can be applied, and are more likely to + * notice the overhead of the precheck. Also avoid it during skip scans, + * where individual primitive scans that don't just read one leaf page are + * likely to advance their skip array(s) several times per leaf page read. * * The optimization is unsafe and must be avoided whenever _bt_checkkeys * just set a low-order required array's key to the best available match @@ -1604,7 +1695,7 @@ _bt_readpage(IndexScanDesc scan, ScanDirection dir, OffsetNumber offnum, * required < or <= strategy scan keys) during the precheck, we can safely * assume that this must also be true of all earlier tuples from the page. */ - if (!pstate.firstpage && !so->scanBehind && minoff < maxoff) + if (!pstate.firstpage && !so->skipScan && !so->scanBehind && minoff < maxoff) { ItemId iid; IndexTuple itup; diff --git a/src/backend/access/nbtree/nbtutils.c b/src/backend/access/nbtree/nbtutils.c index 6a44d293f..b45e3d32a 100644 --- a/src/backend/access/nbtree/nbtutils.c +++ b/src/backend/access/nbtree/nbtutils.c @@ -30,6 +30,17 @@ static inline int32 _bt_compare_array_skey(FmgrInfo *orderproc, Datum tupdatum, bool tupnull, Datum arrdatum, ScanKey cur); +static void _bt_binsrch_skiparray_skey(bool cur_elem_trig, ScanDirection dir, + Datum tupdatum, bool tupnull, + BTArrayKeyInfo *array, ScanKey cur, + int32 *set_elem_result); +static void _bt_skiparray_set_element(Relation rel, ScanKey skey, BTArrayKeyInfo *array, + int32 set_elem_result, Datum tupdatum, bool tupnull); +static void _bt_skiparray_set_isnull(Relation rel, ScanKey skey, BTArrayKeyInfo *array); +static void _bt_array_set_low_or_high(Relation rel, ScanKey skey, + BTArrayKeyInfo *array, bool low_not_high); +static bool _bt_array_decrement(Relation rel, ScanKey skey, BTArrayKeyInfo *array); +static bool _bt_array_increment(Relation rel, ScanKey skey, BTArrayKeyInfo *array); static bool _bt_advance_array_keys_increment(IndexScanDesc scan, ScanDirection dir); static void _bt_rewind_nonrequired_arrays(IndexScanDesc scan, ScanDirection dir); static bool _bt_tuple_before_array_skeys(IndexScanDesc scan, ScanDirection dir, @@ -207,6 +218,7 @@ _bt_compare_array_skey(FmgrInfo *orderproc, int32 result = 0; Assert(cur->sk_strategy == BTEqualStrategyNumber); + Assert(!(cur->sk_flags & (SK_BT_MINVAL | SK_BT_MAXVAL))); if (tupnull) /* NULL tupdatum */ { @@ -283,6 +295,8 @@ _bt_binsrch_array_skey(FmgrInfo *orderproc, Datum arrdatum; Assert(cur->sk_flags & SK_SEARCHARRAY); + Assert(!(cur->sk_flags & SK_BT_SKIP)); + Assert(!(cur->sk_flags & SK_ISNULL)); /* plain arrays can't do this */ Assert(cur->sk_strategy == BTEqualStrategyNumber); if (cur_elem_trig) @@ -405,6 +419,185 @@ _bt_binsrch_array_skey(FmgrInfo *orderproc, return low_elem; } +/* + * _bt_binsrch_skiparray_skey() -- "Binary search" within a skip array + * + * Does not return an index into the array, since skip arrays don't really + * contain elements (they generate their array elements procedurally instead). + * Our interface matches that of _bt_binsrch_array_skey in every other way. + * + * Sets *set_elem_result just like _bt_binsrch_array_skey would with a true + * array. The value 0 indicates that tupdatum/tupnull is within the range of + * the skip array. We return -1 when tupdatum/tupnull is lower that any value + * within the range of the array, and 1 when it is higher than every value. + * Caller should pass *set_elem_result to _bt_skiparray_set_element to advance + * the array. + * + * cur_elem_trig indicates if array advancement was triggered by this array's + * scan key. We use this to optimize-away comparisons that are known by our + * caller to be unnecessary from context, just like _bt_binsrch_array_skey. + */ +static void +_bt_binsrch_skiparray_skey(bool cur_elem_trig, ScanDirection dir, + Datum tupdatum, bool tupnull, + BTArrayKeyInfo *array, ScanKey cur, + int32 *set_elem_result) +{ + Assert(cur->sk_flags & SK_BT_SKIP); + Assert(cur->sk_flags & SK_SEARCHARRAY); + Assert(cur->sk_flags & SK_BT_REQFWD); + Assert(array->num_elems == -1); + Assert(!ScanDirectionIsNoMovement(dir)); + + if (array->null_elem) + { + Assert(!array->low_compare && !array->high_compare); + + *set_elem_result = 0; + return; + } + + if (tupnull) /* NULL tupdatum */ + { + if (cur->sk_flags & SK_BT_NULLS_FIRST) + *set_elem_result = -1; /* NULL "<" NOT_NULL */ + else + *set_elem_result = 1; /* NULL ">" NOT_NULL */ + return; + } + + /* + * Array inequalities determine whether tupdatum is within the range of + * caller's skip array + */ + *set_elem_result = 0; + if (ScanDirectionIsForward(dir)) + { + /* + * Evaluate low_compare first (unless cur_elem_trig tells us that it + * cannot possibly fail to be satisfied), then evaluate high_compare + */ + if (!cur_elem_trig && array->low_compare && + !DatumGetBool(FunctionCall2Coll(&array->low_compare->sk_func, + array->low_compare->sk_collation, + tupdatum, + array->low_compare->sk_argument))) + *set_elem_result = -1; + else if (array->high_compare && + !DatumGetBool(FunctionCall2Coll(&array->high_compare->sk_func, + array->high_compare->sk_collation, + tupdatum, + array->high_compare->sk_argument))) + *set_elem_result = 1; + } + else + { + /* + * Evaluate high_compare first (unless cur_elem_trig tells us that it + * cannot possibly fail to be satisfied), then evaluate low_compare + */ + if (!cur_elem_trig && array->high_compare && + !DatumGetBool(FunctionCall2Coll(&array->high_compare->sk_func, + array->high_compare->sk_collation, + tupdatum, + array->high_compare->sk_argument))) + *set_elem_result = 1; + else if (array->low_compare && + !DatumGetBool(FunctionCall2Coll(&array->low_compare->sk_func, + array->low_compare->sk_collation, + tupdatum, + array->low_compare->sk_argument))) + *set_elem_result = -1; + } + + /* + * Assert that any keys that were assumed to be satisfied already (due to + * caller passing cur_elem_trig=true) really are satisfied as expected + */ +#ifdef USE_ASSERT_CHECKING + if (cur_elem_trig) + { + if (ScanDirectionIsForward(dir) && array->low_compare) + Assert(DatumGetBool(FunctionCall2Coll(&array->low_compare->sk_func, + array->low_compare->sk_collation, + tupdatum, + array->low_compare->sk_argument))); + + if (ScanDirectionIsBackward(dir) && array->high_compare) + Assert(DatumGetBool(FunctionCall2Coll(&array->high_compare->sk_func, + array->high_compare->sk_collation, + tupdatum, + array->high_compare->sk_argument))); + } +#endif +} + +/* + * _bt_skiparray_set_element() -- Set skip array scan key's sk_argument + * + * Caller passes set_elem_result returned by _bt_binsrch_skiparray_skey for + * caller's tupdatum/tupnull. + * + * We copy tupdatum/tupnull into skey's sk_argument iff set_elem_result == 0. + * Otherwise, we set skey to either the lowest or highest value that's within + * the range of caller's skip array (whichever is the best available match to + * tupdatum/tupnull that is still within the range of the skip array according + * to _bt_binsrch_skiparray_skey/set_elem_result). + */ +static void +_bt_skiparray_set_element(Relation rel, ScanKey skey, BTArrayKeyInfo *array, + int32 set_elem_result, Datum tupdatum, bool tupnull) +{ + Assert(skey->sk_flags & SK_BT_SKIP); + Assert(skey->sk_flags & SK_SEARCHARRAY); + + if (set_elem_result) + { + /* tupdatum/tupnull is out of the range of the skip array */ + Assert(!array->null_elem); + + _bt_array_set_low_or_high(rel, skey, array, set_elem_result < 0); + return; + } + + /* Advance skip array to tupdatum (or tupnull) value */ + if (unlikely(tupnull)) + { + _bt_skiparray_set_isnull(rel, skey, array); + return; + } + + /* Free memory previously allocated for sk_argument if needed */ + if (!array->attbyval && skey->sk_argument) + pfree(DatumGetPointer(skey->sk_argument)); + skey->sk_argument = (Datum) 0; + skey->sk_flags &= ~(SK_SEARCHNULL | SK_ISNULL | + SK_BT_MINVAL | SK_BT_MAXVAL | + SK_BT_NEXT | SK_BT_PRIOR); + skey->sk_argument = datumCopy(tupdatum, array->attbyval, array->attlen); +} + +/* + * _bt_skiparray_set_isnull() -- set skip array scan key to NULL + */ +static void +_bt_skiparray_set_isnull(Relation rel, ScanKey skey, BTArrayKeyInfo *array) +{ + Assert(skey->sk_flags & SK_BT_SKIP); + Assert(skey->sk_flags & SK_SEARCHARRAY); + Assert(array->null_elem && !array->low_compare && !array->high_compare); + + /* Free memory previously allocated for sk_argument if needed */ + if (!array->attbyval && skey->sk_argument) + pfree(DatumGetPointer(skey->sk_argument)); + + /* Set sk_argument to NULL */ + skey->sk_argument = (Datum) 0; + skey->sk_flags &= ~(SK_BT_MINVAL | SK_BT_MAXVAL | + SK_BT_NEXT | SK_BT_PRIOR); + skey->sk_flags |= (SK_SEARCHNULL | SK_ISNULL); +} + /* * _bt_start_array_keys() -- Initialize array keys at start of a scan * @@ -414,29 +607,349 @@ _bt_binsrch_array_skey(FmgrInfo *orderproc, void _bt_start_array_keys(IndexScanDesc scan, ScanDirection dir) { + Relation rel = scan->indexRelation; BTScanOpaque so = (BTScanOpaque) scan->opaque; - int i; Assert(so->numArrayKeys); Assert(so->qual_ok); - for (i = 0; i < so->numArrayKeys; i++) + for (int i = 0; i < so->numArrayKeys; i++) { - BTArrayKeyInfo *curArrayKey = &so->arrayKeys[i]; - ScanKey skey = &so->keyData[curArrayKey->scan_key]; + BTArrayKeyInfo *array = &so->arrayKeys[i]; + ScanKey skey = &so->keyData[array->scan_key]; - Assert(curArrayKey->num_elems > 0); Assert(skey->sk_flags & SK_SEARCHARRAY); - if (ScanDirectionIsBackward(dir)) - curArrayKey->cur_elem = curArrayKey->num_elems - 1; - else - curArrayKey->cur_elem = 0; - skey->sk_argument = curArrayKey->elem_values[curArrayKey->cur_elem]; + _bt_array_set_low_or_high(rel, skey, array, + ScanDirectionIsForward(dir)); } so->scanBehind = so->oppositeDirCheck = false; /* reset */ } +/* + * _bt_array_set_low_or_high() -- Set array scan key to lowest/highest element + * + * Caller also passes associated scan key, which will have its argument set to + * the lowest/highest array value in passing. + */ +static void +_bt_array_set_low_or_high(Relation rel, ScanKey skey, BTArrayKeyInfo *array, + bool low_not_high) +{ + Assert(skey->sk_flags & SK_SEARCHARRAY); + + if (array->num_elems != -1) + { + /* set low or high element for conventional array */ + int set_elem = 0; + + Assert(!(skey->sk_flags & SK_BT_SKIP)); + + if (!low_not_high) + set_elem = array->num_elems - 1; + + /* + * Just copy over array datum (only skip arrays require freeing and + * allocating memory for sk_argument) + */ + array->cur_elem = set_elem; + skey->sk_argument = array->elem_values[set_elem]; + + return; + } + + /* set low or high element for skip array */ + Assert(skey->sk_flags & SK_BT_SKIP); + Assert(array->num_elems == -1); + + /* Free memory previously allocated for sk_argument if needed */ + if (!array->attbyval && skey->sk_argument) + pfree(DatumGetPointer(skey->sk_argument)); + + /* Reset flags */ + skey->sk_argument = (Datum) 0; + skey->sk_flags &= ~(SK_SEARCHNULL | SK_ISNULL | + SK_BT_MINVAL | SK_BT_MAXVAL | + SK_BT_NEXT | SK_BT_PRIOR); + + if (array->null_elem && + (low_not_high == ((skey->sk_flags & SK_BT_NULLS_FIRST) != 0))) + { + /* Requested element (either lowest or highest) has the value NULL */ + skey->sk_flags |= (SK_SEARCHNULL | SK_ISNULL); + } + else if (low_not_high) + { + /* Setting array to lowest element (according to low_compare) */ + skey->sk_flags |= SK_BT_MINVAL; + } + else + { + /* Setting array to highest element (according to high_compare) */ + skey->sk_flags |= SK_BT_MAXVAL; + } +} + +/* + * _bt_array_decrement() -- decrement array scan key's sk_argument + * + * Return value indicates whether caller's array was successfully decremented. + * Cannot decrement an array whose current element is already the first one. + */ +static bool +_bt_array_decrement(Relation rel, ScanKey skey, BTArrayKeyInfo *array) +{ + bool uflow = false; + Datum dec_sk_argument; + + Assert(skey->sk_flags & SK_SEARCHARRAY); + Assert(!(skey->sk_flags & (SK_BT_MAXVAL | SK_BT_NEXT | SK_BT_PRIOR))); + + /* Regular (non-skip) array? */ + if (array->num_elems != -1) + { + Assert(!(skey->sk_flags & (SK_BT_SKIP | SK_BT_MINVAL | SK_BT_MAXVAL))); + if (array->cur_elem > 0) + { + /* + * Just decrement current element, and assign its datum to skey + * (only skip arrays need us to free existing sk_argument memory) + */ + array->cur_elem--; + skey->sk_argument = array->elem_values[array->cur_elem]; + + /* Successfully decremented array */ + return true; + } + + /* Cannot decrement to before first array element */ + return false; + } + + /* Nope, this is a skip array */ + Assert(skey->sk_flags & SK_BT_SKIP); + + /* + * The sentinel value that represents the minimum value within the range + * of a skip array (often just -inf) is never decrementable + */ + if (skey->sk_flags & SK_BT_MINVAL) + return false; + + /* + * When the current array element is NULL, and the lowest sorting value in + * the index is also NULL, we cannot decrement before first array element + */ + if ((skey->sk_flags & SK_ISNULL) && (skey->sk_flags & SK_BT_NULLS_FIRST)) + return false; + + /* + * Opclasses without skip support "decrement" the scan key's current + * element by setting the PRIOR flag. The true prior value is determined + * by repositioning to the last index tuple < existing sk_argument/current + * array element. Note that this works in the usual way when the scan key + * is already marked ISNULL (i.e. when the current element is NULL). + */ + if (!array->sksup) + { + skey->sk_flags |= SK_BT_PRIOR; + return true; + } + + /* + * Opclasses with skip support directly decrement sk_argument + */ + if (skey->sk_flags & SK_ISNULL) + { + Assert(!(skey->sk_flags & SK_BT_NULLS_FIRST)); + + /* + * Existing sk_argument/array element is NULL (for an IS NULL qual). + * + * "Decrement" from NULL to the high_elem value provided by opclass + * skip support routine. + */ + skey->sk_flags &= ~(SK_SEARCHNULL | SK_ISNULL); + skey->sk_argument = datumCopy(array->sksup->high_elem, + array->attbyval, array->attlen); + return true; + } + + /* + * Ask opclass support routine to provide decremented copy of existing + * non-NULL sk_argument + */ + dec_sk_argument = array->sksup->decrement(rel, skey->sk_argument, &uflow); + if (unlikely(uflow)) + { + /* dec_sk_argument has undefined value (so no pfree) */ + if (array->null_elem && (skey->sk_flags & SK_BT_NULLS_FIRST)) + { + /* "Decrement" sk_argument to NULL */ + _bt_skiparray_set_isnull(rel, skey, array); + return true; + } + + /* Cannot decrement before first array element */ + return false; + } + + /* + * Successfully decremented sk_argument to a non-NULL value. Make sure + * that the decremented value is still within the range of the array. + */ + if (array->low_compare && + !DatumGetBool(FunctionCall2Coll(&array->low_compare->sk_func, + array->low_compare->sk_collation, + dec_sk_argument, + array->low_compare->sk_argument))) + { + /* Keep existing sk_argument after all */ + if (!array->attbyval) + pfree(DatumGetPointer(dec_sk_argument)); + + /* Cannot decrement before first array element */ + return false; + } + + /* Accept non-NULL datum value from opclass decrement callback */ + if (!array->attbyval && skey->sk_argument) + pfree(DatumGetPointer(skey->sk_argument)); + skey->sk_argument = dec_sk_argument; + + return true; +} + +/* + * _bt_array_increment() -- increment array scan key's sk_argument + * + * Return value indicates whether caller's array was successfully incremented. + * Cannot increment an array whose current element is already the final one. + */ +static bool +_bt_array_increment(Relation rel, ScanKey skey, BTArrayKeyInfo *array) +{ + bool oflow = false; + Datum inc_sk_argument; + + Assert(skey->sk_flags & SK_SEARCHARRAY); + Assert(!(skey->sk_flags & (SK_BT_MINVAL | SK_BT_NEXT | SK_BT_PRIOR))); + + /* Regular (non-skip) array? */ + if (array->num_elems != -1) + { + Assert(!(skey->sk_flags & (SK_BT_SKIP | SK_BT_MINVAL | SK_BT_MAXVAL))); + if (array->cur_elem < array->num_elems - 1) + { + /* + * Just increment current element, and assign its datum to skey + * (only skip arrays need us to free existing sk_argument memory) + */ + array->cur_elem++; + skey->sk_argument = array->elem_values[array->cur_elem]; + + /* Successfully incremented array */ + return true; + } + + /* Cannot increment past final array element */ + return false; + } + + /* Nope, this is a skip array */ + Assert(skey->sk_flags & SK_BT_SKIP); + + /* + * The sentinel value that represents the maximum value within the range + * of a skip array (often just +inf) is never incrementable + */ + if (skey->sk_flags & SK_BT_MAXVAL) + return false; + + /* + * When the current array element is NULL, and the highest sorting value + * in the index is also NULL, we cannot increment past the final element + */ + if ((skey->sk_flags & SK_ISNULL) && !(skey->sk_flags & SK_BT_NULLS_FIRST)) + return false; + + /* + * Opclasses without skip support "increment" the scan key's current + * element by setting the NEXT flag. The true next value is determined by + * repositioning to the first index tuple > existing sk_argument/current + * array element. Note that this works in the usual way when the scan key + * is already marked ISNULL (i.e. when the current element is NULL). + */ + if (!array->sksup) + { + skey->sk_flags |= SK_BT_NEXT; + return true; + } + + /* + * Opclasses with skip support directly increment sk_argument + */ + if (skey->sk_flags & SK_ISNULL) + { + Assert(skey->sk_flags & SK_BT_NULLS_FIRST); + + /* + * Existing sk_argument/array element is NULL (for an IS NULL qual). + * + * "Increment" from NULL to the low_elem value provided by opclass + * skip support routine. + */ + skey->sk_flags &= ~(SK_SEARCHNULL | SK_ISNULL); + skey->sk_argument = datumCopy(array->sksup->low_elem, + array->attbyval, array->attlen); + return true; + } + + /* + * Ask opclass support routine to provide incremented copy of existing + * non-NULL sk_argument + */ + inc_sk_argument = array->sksup->increment(rel, skey->sk_argument, &oflow); + if (unlikely(oflow)) + { + /* inc_sk_argument has undefined value (so no pfree) */ + if (array->null_elem && !(skey->sk_flags & SK_BT_NULLS_FIRST)) + { + /* "Increment" sk_argument to NULL */ + _bt_skiparray_set_isnull(rel, skey, array); + return true; + } + + /* Cannot increment past final array element */ + return false; + } + + /* + * Successfully incremented sk_argument to a non-NULL value. Make sure + * that the incremented value is still within the range of the array. + */ + if (array->high_compare && + !DatumGetBool(FunctionCall2Coll(&array->high_compare->sk_func, + array->high_compare->sk_collation, + inc_sk_argument, + array->high_compare->sk_argument))) + { + /* Keep existing sk_argument after all */ + if (!array->attbyval) + pfree(DatumGetPointer(inc_sk_argument)); + + /* Cannot increment past final array element */ + return false; + } + + /* Accept non-NULL datum value from opclass increment callback */ + if (!array->attbyval && skey->sk_argument) + pfree(DatumGetPointer(skey->sk_argument)); + skey->sk_argument = inc_sk_argument; + + return true; +} + /* * _bt_advance_array_keys_increment() -- Advance to next set of array elements * @@ -452,6 +965,7 @@ _bt_start_array_keys(IndexScanDesc scan, ScanDirection dir) static bool _bt_advance_array_keys_increment(IndexScanDesc scan, ScanDirection dir) { + Relation rel = scan->indexRelation; BTScanOpaque so = (BTScanOpaque) scan->opaque; /* @@ -461,29 +975,30 @@ _bt_advance_array_keys_increment(IndexScanDesc scan, ScanDirection dir) */ for (int i = so->numArrayKeys - 1; i >= 0; i--) { - BTArrayKeyInfo *curArrayKey = &so->arrayKeys[i]; - ScanKey skey = &so->keyData[curArrayKey->scan_key]; - int cur_elem = curArrayKey->cur_elem; - int num_elems = curArrayKey->num_elems; - bool rolled = false; + BTArrayKeyInfo *array = &so->arrayKeys[i]; + ScanKey skey = &so->keyData[array->scan_key]; - if (ScanDirectionIsForward(dir) && ++cur_elem >= num_elems) + if (ScanDirectionIsForward(dir)) { - cur_elem = 0; - rolled = true; + if (_bt_array_increment(rel, skey, array)) + return true; } - else if (ScanDirectionIsBackward(dir) && --cur_elem < 0) + else { - cur_elem = num_elems - 1; - rolled = true; + if (_bt_array_decrement(rel, skey, array)) + return true; } - curArrayKey->cur_elem = cur_elem; - skey->sk_argument = curArrayKey->elem_values[cur_elem]; - if (!rolled) - return true; + /* + * Couldn't increment (or decrement) array. Handle array roll over. + * + * Start over at the array's lowest sorting value (or its highest + * value, for backward scans)... + */ + _bt_array_set_low_or_high(rel, skey, array, + ScanDirectionIsForward(dir)); - /* Need to advance next array key, if any */ + /* ...then increment (or decrement) next most significant array */ } /* @@ -507,7 +1022,7 @@ _bt_advance_array_keys_increment(IndexScanDesc scan, ScanDirection dir) } /* - * _bt_rewind_nonrequired_arrays() -- Rewind non-required arrays + * _bt_rewind_nonrequired_arrays() -- Rewind SAOP arrays not marked required * * Called when _bt_advance_array_keys decides to start a new primitive index * scan on the basis of the current scan position being before the position @@ -539,10 +1054,15 @@ _bt_advance_array_keys_increment(IndexScanDesc scan, ScanDirection dir) * * Note: _bt_verify_arrays_bt_first is called by an assertion to enforce that * everybody got this right. + * + * Note: In practice almost all SAOP arrays are marked required during + * preprocessing (if necessary by generating skip arrays). It is hardly ever + * truly necessary to call here, but consistently doing so is simpler. */ static void _bt_rewind_nonrequired_arrays(IndexScanDesc scan, ScanDirection dir) { + Relation rel = scan->indexRelation; BTScanOpaque so = (BTScanOpaque) scan->opaque; int arrayidx = 0; @@ -550,7 +1070,6 @@ _bt_rewind_nonrequired_arrays(IndexScanDesc scan, ScanDirection dir) { ScanKey cur = so->keyData + ikey; BTArrayKeyInfo *array = NULL; - int first_elem_dir; if (!(cur->sk_flags & SK_SEARCHARRAY) || cur->sk_strategy != BTEqualStrategyNumber) @@ -562,16 +1081,10 @@ _bt_rewind_nonrequired_arrays(IndexScanDesc scan, ScanDirection dir) if ((cur->sk_flags & (SK_BT_REQFWD | SK_BT_REQBKWD))) continue; - if (ScanDirectionIsForward(dir)) - first_elem_dir = 0; - else - first_elem_dir = array->num_elems - 1; + Assert(array->num_elems != -1); /* No non-required skip arrays */ - if (array->cur_elem != first_elem_dir) - { - array->cur_elem = first_elem_dir; - cur->sk_argument = array->elem_values[first_elem_dir]; - } + _bt_array_set_low_or_high(rel, cur, array, + ScanDirectionIsForward(dir)); } } @@ -696,9 +1209,77 @@ _bt_tuple_before_array_skeys(IndexScanDesc scan, ScanDirection dir, tupdatum = index_getattr(tuple, cur->sk_attno, tupdesc, &tupnull); - result = _bt_compare_array_skey(&so->orderProcs[ikey], - tupdatum, tupnull, - cur->sk_argument, cur); + if (likely(!(cur->sk_flags & (SK_BT_MINVAL | SK_BT_MAXVAL)))) + { + /* Scankey has a valid/comparable sk_argument value */ + result = _bt_compare_array_skey(&so->orderProcs[ikey], + tupdatum, tupnull, + cur->sk_argument, cur); + + if (result == 0) + { + /* + * Interpret result in a way that takes NEXT/PRIOR into + * account + */ + if (cur->sk_flags & SK_BT_NEXT) + result = -1; + else if (cur->sk_flags & SK_BT_PRIOR) + result = 1; + + Assert(result == 0 || (cur->sk_flags & SK_BT_SKIP)); + } + } + else + { + BTArrayKeyInfo *array = NULL; + + /* + * Current array element/array = scan key value is a sentinel + * value that represents the lowest (or highest) possible value + * that's still within the range of the array. + * + * Like _bt_first, we only see MINVAL keys during forwards scans + * (and similarly only see MAXVAL keys during backwards scans). + * Even if the scan's direction changes, we'll stop at some higher + * order key before we can ever reach any MAXVAL (or MINVAL) keys. + * (However, unlike _bt_first we _can_ get to keys marked either + * NEXT or PRIOR, regardless of the scan's current direction.) + */ + Assert(ScanDirectionIsForward(dir) ? + !(cur->sk_flags & SK_BT_MAXVAL) : + !(cur->sk_flags & SK_BT_MINVAL)); + + /* + * There are no valid sk_argument values in MINVAL/MAXVAL keys. + * Check if tupdatum is within the range of skip array instead. + */ + for (int arrayidx = 0; arrayidx < so->numArrayKeys; arrayidx++) + { + array = &so->arrayKeys[arrayidx]; + if (array->scan_key == ikey) + break; + } + + _bt_binsrch_skiparray_skey(false, dir, tupdatum, tupnull, + array, cur, &result); + + if (result == 0) + { + /* + * tupdatum satisfies both low_compare and high_compare, so + * it's time to advance the array keys. + * + * Note: It's possible that the skip array will "advance" from + * its MINVAL (or MAXVAL) representation to an alternative, + * logically equivalent representation of the same value: a + * representation where the = key gets a valid datum in its + * sk_argument. This is only possible when low_compare uses + * the >= strategy (or high_compare uses the <= strategy). + */ + return false; + } + } /* * Does this comparison indicate that caller must _not_ advance the @@ -1017,18 +1598,9 @@ _bt_advance_array_keys(IndexScanDesc scan, BTReadPageState *pstate, */ if (beyond_end_advance) { - int final_elem_dir; - - if (ScanDirectionIsBackward(dir) || !array) - final_elem_dir = 0; - else - final_elem_dir = array->num_elems - 1; - - if (array && array->cur_elem != final_elem_dir) - { - array->cur_elem = final_elem_dir; - cur->sk_argument = array->elem_values[final_elem_dir]; - } + if (array) + _bt_array_set_low_or_high(rel, cur, array, + ScanDirectionIsBackward(dir)); continue; } @@ -1053,18 +1625,9 @@ _bt_advance_array_keys(IndexScanDesc scan, BTReadPageState *pstate, */ if (!all_required_satisfied || cur->sk_attno > tupnatts) { - int first_elem_dir; - - if (ScanDirectionIsForward(dir) || !array) - first_elem_dir = 0; - else - first_elem_dir = array->num_elems - 1; - - if (array && array->cur_elem != first_elem_dir) - { - array->cur_elem = first_elem_dir; - cur->sk_argument = array->elem_values[first_elem_dir]; - } + if (array) + _bt_array_set_low_or_high(rel, cur, array, + ScanDirectionIsForward(dir)); continue; } @@ -1080,14 +1643,22 @@ _bt_advance_array_keys(IndexScanDesc scan, BTReadPageState *pstate, bool cur_elem_trig = (sktrig_required && ikey == sktrig); /* - * Binary search for closest match that's available from the array + * "Binary search" by checking if tupdatum/tupnull are within the + * range of the skip array */ - set_elem = _bt_binsrch_array_skey(&so->orderProcs[ikey], - cur_elem_trig, dir, - tupdatum, tupnull, array, cur, - &result); + if (array->num_elems == -1) + _bt_binsrch_skiparray_skey(cur_elem_trig, dir, + tupdatum, tupnull, array, cur, + &result); - Assert(set_elem >= 0 && set_elem < array->num_elems); + /* + * Binary search for the closest match from the SAOP array + */ + else + set_elem = _bt_binsrch_array_skey(&so->orderProcs[ikey], + cur_elem_trig, dir, + tupdatum, tupnull, array, cur, + &result); } else { @@ -1163,11 +1734,21 @@ _bt_advance_array_keys(IndexScanDesc scan, BTReadPageState *pstate, } } - /* Advance array keys, even when set_elem isn't an exact match */ - if (array && array->cur_elem != set_elem) + /* Advance array keys, even when we don't have an exact match */ + if (array) { - array->cur_elem = set_elem; - cur->sk_argument = array->elem_values[set_elem]; + if (array->num_elems == -1) + { + /* Skip array's "binary search" determines its new element */ + _bt_skiparray_set_element(rel, cur, array, result, + tupdatum, tupnull); + } + else if (array->cur_elem != set_elem) + { + /* SAOP array has new set_elem (returned by binary search) */ + array->cur_elem = set_elem; + cur->sk_argument = array->elem_values[set_elem]; + } } } @@ -1580,10 +2161,11 @@ _bt_verify_keys_with_arraykeys(IndexScanDesc scan) if (array->scan_key != ikey) return false; - if (array->num_elems <= 0) + if (array->num_elems == 0 || array->num_elems < -1) return false; - if (cur->sk_argument != array->elem_values[array->cur_elem]) + if (array->num_elems != -1 && + cur->sk_argument != array->elem_values[array->cur_elem]) return false; if (last_sk_attno > cur->sk_attno) return false; @@ -1914,6 +2496,20 @@ _bt_check_compare(IndexScanDesc scan, ScanDirection dir, continue; } + /* + * A skip array scan key uses one of several sentinel values. We just + * fall back on _bt_tuple_before_array_skeys when we see such a value. + */ + if (key->sk_flags & (SK_BT_MINVAL | SK_BT_MAXVAL | + SK_BT_NEXT | SK_BT_PRIOR)) + { + Assert(key->sk_flags & SK_SEARCHARRAY); + Assert(key->sk_flags & SK_BT_SKIP); + + *continuescan = false; + return false; + } + /* row-comparison keys need special processing */ if (key->sk_flags & SK_ROW_HEADER) { diff --git a/src/backend/access/nbtree/nbtvalidate.c b/src/backend/access/nbtree/nbtvalidate.c index dd6f5a15c..817ad358f 100644 --- a/src/backend/access/nbtree/nbtvalidate.c +++ b/src/backend/access/nbtree/nbtvalidate.c @@ -106,6 +106,10 @@ btvalidate(Oid opclassoid) case BTOPTIONS_PROC: ok = check_amoptsproc_signature(procform->amproc); break; + case BTSKIPSUPPORT_PROC: + ok = check_amproc_signature(procform->amproc, VOIDOID, true, + 1, 1, INTERNALOID); + break; default: ereport(INFO, (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), diff --git a/src/backend/commands/opclasscmds.c b/src/backend/commands/opclasscmds.c index 2c325badf..303622f9d 100644 --- a/src/backend/commands/opclasscmds.c +++ b/src/backend/commands/opclasscmds.c @@ -1331,6 +1331,31 @@ assignProcTypes(OpFamilyMember *member, Oid amoid, Oid typeoid, (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), errmsg("btree equal image functions must not be cross-type"))); } + else if (member->number == BTSKIPSUPPORT_PROC) + { + if (procform->pronargs != 1 || + procform->proargtypes.values[0] != INTERNALOID) + ereport(ERROR, + (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), + errmsg("btree skip support functions must accept type \"internal\""))); + if (procform->prorettype != VOIDOID) + ereport(ERROR, + (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), + errmsg("btree skip support functions must return void"))); + + /* + * pg_amproc functions are indexed by (lefttype, righttype), but a + * skip support function doesn't make sense in cross-type + * scenarios. The same opclass opcintype OID is always used for + * lefttype and righttype. Providing a cross-type routine isn't + * sensible. Reject cross-type ALTER OPERATOR FAMILY ... ADD + * FUNCTION 6 statements here. + */ + if (member->lefttype != member->righttype) + ereport(ERROR, + (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), + errmsg("btree skip support functions must not be cross-type"))); + } } else if (amoid == HASH_AM_OID) { diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 8a7fb6a22..4e7a67b16 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -143,6 +143,7 @@ static const char *const BuiltinTrancheNames[] = { [LWTRANCHE_LOCK_MANAGER] = "LockManager", [LWTRANCHE_PREDICATE_LOCK_MANAGER] = "PredicateLockManager", [LWTRANCHE_PARALLEL_HASH_JOIN] = "ParallelHashJoin", + [LWTRANCHE_PARALLEL_BTREE_SCAN] = "ParallelBtreeScan", [LWTRANCHE_PARALLEL_QUERY_DSA] = "ParallelQueryDSA", [LWTRANCHE_PER_SESSION_DSA] = "PerSessionDSA", [LWTRANCHE_PER_SESSION_RECORD_TYPE] = "PerSessionRecordType", diff --git a/src/backend/utils/activity/wait_event_names.txt b/src/backend/utils/activity/wait_event_names.txt index e199f0716..1d3d901dc 100644 --- a/src/backend/utils/activity/wait_event_names.txt +++ b/src/backend/utils/activity/wait_event_names.txt @@ -371,6 +371,7 @@ BufferMapping "Waiting to associate a data block with a buffer in the buffer poo LockManager "Waiting to read or update information about heavyweight locks." PredicateLockManager "Waiting to access predicate lock information used by serializable transactions." ParallelHashJoin "Waiting to synchronize workers during Parallel Hash Join plan execution." +ParallelBtreeScan "Waiting to synchronize workers during a parallel B-tree scan." ParallelQueryDSA "Waiting for parallel query dynamic shared memory allocation." PerSessionDSA "Waiting for parallel query dynamic shared memory allocation." PerSessionRecordType "Waiting to access a parallel query's information about composite types." diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 35e8c01aa..4a233b63c 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -99,6 +99,7 @@ OBJS = \ rowtypes.o \ ruleutils.o \ selfuncs.o \ + skipsupport.o \ tid.o \ timestamp.o \ trigfuncs.o \ diff --git a/src/backend/utils/adt/date.c b/src/backend/utils/adt/date.c index f279853de..4227ab1a7 100644 --- a/src/backend/utils/adt/date.c +++ b/src/backend/utils/adt/date.c @@ -34,6 +34,7 @@ #include "utils/date.h" #include "utils/datetime.h" #include "utils/numeric.h" +#include "utils/skipsupport.h" #include "utils/sortsupport.h" /* @@ -462,6 +463,51 @@ date_sortsupport(PG_FUNCTION_ARGS) PG_RETURN_VOID(); } +static Datum +date_decrement(Relation rel, Datum existing, bool *underflow) +{ + DateADT dexisting = DatumGetDateADT(existing); + + if (dexisting == DATEVAL_NOBEGIN) + { + /* return value is undefined */ + *underflow = true; + return (Datum) 0; + } + + *underflow = false; + return DateADTGetDatum(dexisting - 1); +} + +static Datum +date_increment(Relation rel, Datum existing, bool *overflow) +{ + DateADT dexisting = DatumGetDateADT(existing); + + if (dexisting == DATEVAL_NOEND) + { + /* return value is undefined */ + *overflow = true; + return (Datum) 0; + } + + *overflow = false; + return DateADTGetDatum(dexisting + 1); +} + +Datum +date_skipsupport(PG_FUNCTION_ARGS) +{ + SkipSupport sksup = (SkipSupport) PG_GETARG_POINTER(0); + + sksup->decrement = date_decrement; + sksup->increment = date_increment; + sksup->low_elem = DateADTGetDatum(DATEVAL_NOBEGIN); + sksup->high_elem = DateADTGetDatum(DATEVAL_NOEND); + + PG_RETURN_VOID(); +} + Datum hashdate(PG_FUNCTION_ARGS) { diff --git a/src/backend/utils/adt/meson.build b/src/backend/utils/adt/meson.build index f23cfad71..244f48f4f 100644 --- a/src/backend/utils/adt/meson.build +++ b/src/backend/utils/adt/meson.build @@ -86,6 +86,7 @@ backend_sources += files( 'rowtypes.c', 'ruleutils.c', 'selfuncs.c', + 'skipsupport.c', 'tid.c', 'timestamp.c', 'trigfuncs.c', diff --git a/src/backend/utils/adt/selfuncs.c b/src/backend/utils/adt/selfuncs.c index c2918c9c8..7315a288f 100644 --- a/src/backend/utils/adt/selfuncs.c +++ b/src/backend/utils/adt/selfuncs.c @@ -94,7 +94,6 @@ #include "postgres.h" -#include #include #include "access/brin.h" @@ -193,6 +192,8 @@ static double convert_timevalue_to_scalar(Datum value, Oid typid, bool *failure); static void examine_simple_variable(PlannerInfo *root, Var *var, VariableStatData *vardata); +static void examine_indexcol_variable(PlannerInfo *root, IndexOptInfo *index, + int indexcol, VariableStatData *vardata); static bool get_variable_range(PlannerInfo *root, VariableStatData *vardata, Oid sortop, Oid collation, Datum *min, Datum *max); @@ -214,6 +215,8 @@ static bool get_actual_variable_endpoint(Relation heapRel, MemoryContext outercontext, Datum *endpointDatum); static RelOptInfo *find_join_input_rel(PlannerInfo *root, Relids relids); +static double btcost_correlation(IndexOptInfo *index, + VariableStatData *vardata); /* @@ -5768,6 +5771,92 @@ examine_simple_variable(PlannerInfo *root, Var *var, } } +/* + * examine_indexcol_variable + * Try to look up statistical data about an index column/expression. + * Fill in a VariableStatData struct to describe the column. + * + * Inputs: + * root: the planner info + * index: the index whose column we're interested in + * indexcol: 0-based index column number (subscripts index->indexkeys[]) + * + * Outputs: *vardata is filled as follows: + * var: the input expression (with any binary relabeling stripped, if + * it is or contains a variable; but otherwise the type is preserved) + * rel: RelOptInfo for table relation containing variable. + * statsTuple: the pg_statistic entry for the variable, if one exists; + * otherwise NULL. + * freefunc: pointer to a function to release statsTuple with. + * + * Caller is responsible for doing ReleaseVariableStats() before exiting. + */ +static void +examine_indexcol_variable(PlannerInfo *root, IndexOptInfo *index, + int indexcol, VariableStatData *vardata) +{ + AttrNumber colnum; + Oid relid; + + if (index->indexkeys[indexcol] != 0) + { + /* Simple variable --- look to stats for the underlying table */ + RangeTblEntry *rte = planner_rt_fetch(index->rel->relid, root); + + Assert(rte->rtekind == RTE_RELATION); + relid = rte->relid; + Assert(relid != InvalidOid); + colnum = index->indexkeys[indexcol]; + vardata->rel = index->rel; + + if (get_relation_stats_hook && + (*get_relation_stats_hook) (root, rte, colnum, vardata)) + { + /* + * The hook took control of acquiring a stats tuple. If it did + * supply a tuple, it'd better have supplied a freefunc. + */ + if (HeapTupleIsValid(vardata->statsTuple) && + !vardata->freefunc) + elog(ERROR, "no function provided to release variable stats with"); + } + else + { + vardata->statsTuple = SearchSysCache3(STATRELATTINH, + ObjectIdGetDatum(relid), + Int16GetDatum(colnum), + BoolGetDatum(rte->inh)); + vardata->freefunc = ReleaseSysCache; + } + } + else + { + /* Expression --- maybe there are stats for the index itself */ + relid = index->indexoid; + colnum = indexcol + 1; + + if (get_index_stats_hook && + (*get_index_stats_hook) (root, relid, colnum, vardata)) + { + /* + * The hook took control of acquiring a stats tuple. If it did + * supply a tuple, it'd better have supplied a freefunc. + */ + if (HeapTupleIsValid(vardata->statsTuple) && + !vardata->freefunc) + elog(ERROR, "no function provided to release variable stats with"); + } + else + { + vardata->statsTuple = SearchSysCache3(STATRELATTINH, + ObjectIdGetDatum(relid), + Int16GetDatum(colnum), + BoolGetDatum(false)); + vardata->freefunc = ReleaseSysCache; + } + } +} + /* * Check whether it is permitted to call func_oid passing some of the * pg_statistic data in vardata. We allow this either if the user has SELECT @@ -6826,6 +6915,53 @@ add_predicate_to_index_quals(IndexOptInfo *index, List *indexQuals) return list_concat(predExtraQuals, indexQuals); } +/* + * Estimate correlation of btree index's first column. + * + * If we can get an estimate of the first column's ordering correlation C + * from pg_statistic, estimate the index correlation as C for a single-column + * index, or C * 0.75 for multiple columns. The idea here is that multiple + * columns dilute the importance of the first column's ordering, but don't + * negate it entirely. + * + * We already filled in the stats tuple for *vardata when called. + */ +static double +btcost_correlation(IndexOptInfo *index, VariableStatData *vardata) +{ + Oid sortop; + AttStatsSlot sslot; + double indexCorrelation = 0; + + Assert(HeapTupleIsValid(vardata->statsTuple)); + + sortop = get_opfamily_member(index->opfamily[0], + index->opcintype[0], + index->opcintype[0], + BTLessStrategyNumber); + if (OidIsValid(sortop) && + get_attstatsslot(&sslot, vardata->statsTuple, + STATISTIC_KIND_CORRELATION, sortop, + ATTSTATSSLOT_NUMBERS)) + { + double varCorrelation; + + Assert(sslot.nnumbers == 1); + varCorrelation = sslot.numbers[0]; + + if (index->reverse_sort[0]) + varCorrelation = -varCorrelation; + + if (index->nkeycolumns > 1) + indexCorrelation = varCorrelation * 0.75; + else + indexCorrelation = varCorrelation; + + free_attstatsslot(&sslot); + } + + return indexCorrelation; +} void btcostestimate(PlannerInfo *root, IndexPath *path, double loop_count, @@ -6835,17 +6971,21 @@ btcostestimate(PlannerInfo *root, IndexPath *path, double loop_count, { IndexOptInfo *index = path->indexinfo; GenericCosts costs = {0}; - Oid relid; - AttrNumber colnum; VariableStatData vardata = {0}; double numIndexTuples; + double correlation = 0; Cost descentCost; List *indexBoundQuals; int indexcol; + bool set_correlation = false; bool eqQualHere; - bool found_saop; + bool found_array; + bool found_rowcompare; bool found_is_null_op; + bool upper_inequal_col; + bool lower_inequal_col; double num_sa_scans; + double inequalselectivity; ListCell *lc; /* @@ -6861,16 +7001,21 @@ btcostestimate(PlannerInfo *root, IndexPath *path, double loop_count, * For a RowCompareExpr, we consider only the first column, just as * rowcomparesel() does. * - * If there's a ScalarArrayOpExpr in the quals, we'll actually perform up - * to N index descents (not just one), but the ScalarArrayOpExpr's - * operator can be considered to act the same as it normally does. + * If there's a ScalarArrayOpExpr in the quals, or if we expect to + * generate a skip scan array, then we'll actually perform up to N index + * descents (not just one), but the underlying operator can be considered + * to act the same as it normally does. */ indexBoundQuals = NIL; indexcol = 0; eqQualHere = false; - found_saop = false; + found_array = false; + found_rowcompare = false; found_is_null_op = false; + upper_inequal_col = false; + lower_inequal_col = false; num_sa_scans = 1; + inequalselectivity = 1; foreach(lc, path->indexclauses) { IndexClause *iclause = lfirst_node(IndexClause, lc); @@ -6878,13 +7023,103 @@ btcostestimate(PlannerInfo *root, IndexPath *path, double loop_count, if (indexcol != iclause->indexcol) { + bool past_first_skipped = false; + /* Beginning of a new column's quals */ - if (!eqQualHere) - break; /* done if no '=' qual for indexcol */ - eqQualHere = false; - indexcol++; + if (eqQualHere) + indexcol++; /* don't skip the previous '=' qual's column */ + else if (found_rowcompare) + break; /* Skip arrays can't come after a RowCompare */ + + /* + * Now estimate number of "array elements" using ndistinct. + * + * Internally, nbtree treats skip scans as scans with SAOP style + * arrays that generate elements procedurally. We effectively + * assume a "col = ANY('{every possible col value}')" qual. + */ + while (indexcol < iclause->indexcol) + { + double ndistinct = DEFAULT_NUM_DISTINCT, + new_num_sa_scans; + bool isdefault = true; + + /* Attain ndistinct for index column/indexed expression */ + examine_indexcol_variable(root, index, indexcol, &vardata); + if (HeapTupleIsValid(vardata.statsTuple)) + { + ndistinct = get_variable_numdistinct(&vardata, &isdefault); + + if (indexcol == 0) + { + /* + * Get an estimate of the leading column's correlation + * in passing (avoids rereading variable stats below) + */ + Assert(!set_correlation); + correlation = btcost_correlation(index, &vardata); + set_correlation = true; + } + } + + ReleaseVariableStats(vardata); + + if (!past_first_skipped) + { + /* + * Apply the selectivities of any inequalities to + * ndistinct (unless ndistinct is only a default estimate) + */ + if (!isdefault) + ndistinct *= inequalselectivity; + + /* + * Skip scan will likely require an initial index descent + * to find out what the real first element is... + */ + if (!upper_inequal_col) + ndistinct += 1; + + /* + * ...and another extra descent to confirm no further + * groupings/matches + */ + if (!lower_inequal_col) + ndistinct += 1; + + past_first_skipped = true; + } + + /* + * Multiply our running estimate by ndistinct to update it. + * Here we make the pessimistic assumption that there is no + * naturally occurring cross-column correlation. This is + * often wrong, but it seems best to err on the side of not + * relying on skipping. + */ + found_array = true; + new_num_sa_scans = num_sa_scans * ndistinct; + + /* + * Stop adding new skip arrays when the would-be new + * num_sa_scans exceeds a third of the number of index pages + */ + if (ceil(index->pages * 0.3333333) < new_num_sa_scans) + break; + + /* Done costing skipping for this index column */ + num_sa_scans = new_num_sa_scans; + indexcol++; + } + if (indexcol != iclause->indexcol) - break; /* no quals at all for indexcol */ + break; /* no quals for indexcol (can't skip scan) */ + + /* reset for next indexcol */ + eqQualHere = false; + upper_inequal_col = false; + lower_inequal_col = false; + inequalselectivity = 1.0; } /* Examine each indexqual associated with this index clause */ @@ -6906,6 +7141,7 @@ btcostestimate(PlannerInfo *root, IndexPath *path, double loop_count, RowCompareExpr *rc = (RowCompareExpr *) clause; clause_op = linitial_oid(rc->opnos); + found_rowcompare = true; } else if (IsA(clause, ScalarArrayOpExpr)) { @@ -6914,7 +7150,7 @@ btcostestimate(PlannerInfo *root, IndexPath *path, double loop_count, double alength = estimate_array_length(root, other_operand); clause_op = saop->opno; - found_saop = true; + found_array = true; /* estimate SA descents by indexBoundQuals only */ if (alength > 1) num_sa_scans *= alength; @@ -6926,7 +7162,7 @@ btcostestimate(PlannerInfo *root, IndexPath *path, double loop_count, if (nt->nulltesttype == IS_NULL) { found_is_null_op = true; - /* IS NULL is like = for selectivity purposes */ + /* IS NULL is like = for selectivity/skip scan purposes */ eqQualHere = true; } } @@ -6942,6 +7178,34 @@ btcostestimate(PlannerInfo *root, IndexPath *path, double loop_count, Assert(op_strategy != 0); /* not a member of opfamily?? */ if (op_strategy == BTEqualStrategyNumber) eqQualHere = true; + else if (rinfo->norm_selec >= 0) + { + /* + * Skip scan requires tracking inequality selectivities to + * compute an adjusted whole-column ndistinct. + * + * Assume inequality selectivities are _not_ independent, + * but only track up to one upper bound inequality and up + * to one lower bound inequality. This avoids wildly + * wrong estimates given redundant operators. + */ + if (op_strategy < BTEqualStrategyNumber) + { + if (!upper_inequal_col) + inequalselectivity = + Max(inequalselectivity - (1.0 - rinfo->norm_selec), + DEFAULT_RANGE_INEQ_SEL); + upper_inequal_col = true; + } + else + { + if (!lower_inequal_col) + inequalselectivity = + Max(inequalselectivity - (1.0 - rinfo->norm_selec), + DEFAULT_RANGE_INEQ_SEL); + lower_inequal_col = true; + } + } } indexBoundQuals = lappend(indexBoundQuals, rinfo); @@ -6957,7 +7221,7 @@ btcostestimate(PlannerInfo *root, IndexPath *path, double loop_count, if (index->unique && indexcol == index->nkeycolumns - 1 && eqQualHere && - !found_saop && + !found_array && !found_is_null_op) numIndexTuples = 1.0; else @@ -6997,14 +7261,18 @@ btcostestimate(PlannerInfo *root, IndexPath *path, double loop_count, * of leaf pages (we make it 1/3 the total number of pages instead) to * give the btree code credit for its ability to continue on the leaf * level with low selectivity scans. + * + * Note: num_sa_scans is derived in a way that treats any skip scan + * quals as if they were ScalarArrayOpExpr quals whose array has as + * many distinct elements as possibly-matching values in the index. */ num_sa_scans = Min(num_sa_scans, ceil(index->pages * 0.3333333)); num_sa_scans = Max(num_sa_scans, 1); /* * As in genericcostestimate(), we have to adjust for any - * ScalarArrayOpExpr quals included in indexBoundQuals, and then round - * to integer. + * ScalarArrayOpExpr quals (as well as any skip scan quals) included + * in indexBoundQuals, and then round to integer. * * It is tempting to make genericcostestimate behave as if SAOP * clauses work in almost the same way as scalar operators during @@ -7059,110 +7327,25 @@ btcostestimate(PlannerInfo *root, IndexPath *path, double loop_count, * cost is somewhat arbitrarily set at 50x cpu_operator_cost per page * touched. The number of such pages is btree tree height plus one (ie, * we charge for the leaf page too). As above, charge once per estimated - * SA index descent. + * index descent. */ descentCost = (index->tree_height + 1) * DEFAULT_PAGE_CPU_MULTIPLIER * cpu_operator_cost; costs.indexStartupCost += descentCost; costs.indexTotalCost += costs.num_sa_scans * descentCost; - /* - * If we can get an estimate of the first column's ordering correlation C - * from pg_statistic, estimate the index correlation as C for a - * single-column index, or C * 0.75 for multiple columns. (The idea here - * is that multiple columns dilute the importance of the first column's - * ordering, but don't negate it entirely. Before 8.0 we divided the - * correlation by the number of columns, but that seems too strong.) - */ - if (index->indexkeys[0] != 0) + if (!set_correlation) { - /* Simple variable --- look to stats for the underlying table */ - RangeTblEntry *rte = planner_rt_fetch(index->rel->relid, root); - - Assert(rte->rtekind == RTE_RELATION); - relid = rte->relid; - Assert(relid != InvalidOid); - colnum = index->indexkeys[0]; - - if (get_relation_stats_hook && - (*get_relation_stats_hook) (root, rte, colnum, &vardata)) - { - /* - * The hook took control of acquiring a stats tuple. If it did - * supply a tuple, it'd better have supplied a freefunc. - */ - if (HeapTupleIsValid(vardata.statsTuple) && - !vardata.freefunc) - elog(ERROR, "no function provided to release variable stats with"); - } - else - { - vardata.statsTuple = SearchSysCache3(STATRELATTINH, - ObjectIdGetDatum(relid), - Int16GetDatum(colnum), - BoolGetDatum(rte->inh)); - vardata.freefunc = ReleaseSysCache; - } + examine_indexcol_variable(root, index, 0, &vardata); + if (HeapTupleIsValid(vardata.statsTuple)) + costs.indexCorrelation = btcost_correlation(index, &vardata); + ReleaseVariableStats(vardata); } else { - /* Expression --- maybe there are stats for the index itself */ - relid = index->indexoid; - colnum = 1; - - if (get_index_stats_hook && - (*get_index_stats_hook) (root, relid, colnum, &vardata)) - { - /* - * The hook took control of acquiring a stats tuple. If it did - * supply a tuple, it'd better have supplied a freefunc. - */ - if (HeapTupleIsValid(vardata.statsTuple) && - !vardata.freefunc) - elog(ERROR, "no function provided to release variable stats with"); - } - else - { - vardata.statsTuple = SearchSysCache3(STATRELATTINH, - ObjectIdGetDatum(relid), - Int16GetDatum(colnum), - BoolGetDatum(false)); - vardata.freefunc = ReleaseSysCache; - } + /* get_variable_index_correlation called earlier */ + costs.indexCorrelation = correlation; } - if (HeapTupleIsValid(vardata.statsTuple)) - { - Oid sortop; - AttStatsSlot sslot; - - sortop = get_opfamily_member(index->opfamily[0], - index->opcintype[0], - index->opcintype[0], - BTLessStrategyNumber); - if (OidIsValid(sortop) && - get_attstatsslot(&sslot, vardata.statsTuple, - STATISTIC_KIND_CORRELATION, sortop, - ATTSTATSSLOT_NUMBERS)) - { - double varCorrelation; - - Assert(sslot.nnumbers == 1); - varCorrelation = sslot.numbers[0]; - - if (index->reverse_sort[0]) - varCorrelation = -varCorrelation; - - if (index->nkeycolumns > 1) - costs.indexCorrelation = varCorrelation * 0.75; - else - costs.indexCorrelation = varCorrelation; - - free_attstatsslot(&sslot); - } - } - - ReleaseVariableStats(vardata); - *indexStartupCost = costs.indexStartupCost; *indexTotalCost = costs.indexTotalCost; *indexSelectivity = costs.indexSelectivity; diff --git a/src/backend/utils/adt/skipsupport.c b/src/backend/utils/adt/skipsupport.c new file mode 100644 index 000000000..2bd35d2d2 --- /dev/null +++ b/src/backend/utils/adt/skipsupport.c @@ -0,0 +1,61 @@ +/*------------------------------------------------------------------------- + * + * skipsupport.c + * Support routines for B-Tree skip scan. + * + * + * Portions Copyright (c) 1996-2025, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * IDENTIFICATION + * src/backend/utils/adt/skipsupport.c + * + *------------------------------------------------------------------------- + */ + +#include "postgres.h" + +#include "access/nbtree.h" +#include "utils/lsyscache.h" +#include "utils/skipsupport.h" + +/* + * Fill in SkipSupport given an operator class (opfamily + opcintype). + * + * On success, returns skip support struct, allocating in caller's memory + * context. Otherwise returns NULL, indicating that operator class has no + * skip support function. + */ +SkipSupport +PrepareSkipSupportFromOpclass(Oid opfamily, Oid opcintype, bool reverse) +{ + Oid skipSupportFunction; + SkipSupport sksup; + + /* Look for a skip support function */ + skipSupportFunction = get_opfamily_proc(opfamily, opcintype, opcintype, + BTSKIPSUPPORT_PROC); + if (!OidIsValid(skipSupportFunction)) + return NULL; + + sksup = palloc(sizeof(SkipSupportData)); + OidFunctionCall1(skipSupportFunction, PointerGetDatum(sksup)); + + if (reverse) + { + /* + * DESC/reverse case: swap low_elem with high_elem, and swap decrement + * with increment + */ + Datum low_elem = sksup->low_elem; + SkipSupportIncDec decrement = sksup->decrement; + + sksup->low_elem = sksup->high_elem; + sksup->decrement = sksup->increment; + + sksup->high_elem = low_elem; + sksup->increment = decrement; + } + + return sksup; +} diff --git a/src/backend/utils/adt/timestamp.c b/src/backend/utils/adt/timestamp.c index 9682f9dbd..347089b76 100644 --- a/src/backend/utils/adt/timestamp.c +++ b/src/backend/utils/adt/timestamp.c @@ -37,6 +37,7 @@ #include "utils/datetime.h" #include "utils/float.h" #include "utils/numeric.h" +#include "utils/skipsupport.h" #include "utils/sortsupport.h" /* @@ -2304,6 +2305,53 @@ timestamp_sortsupport(PG_FUNCTION_ARGS) PG_RETURN_VOID(); } +/* note: this is used for timestamptz also */ +static Datum +timestamp_decrement(Relation rel, Datum existing, bool *underflow) +{ + Timestamp texisting = DatumGetTimestamp(existing); + + if (texisting == PG_INT64_MIN) + { + /* return value is undefined */ + *underflow = true; + return (Datum) 0; + } + + *underflow = false; + return TimestampGetDatum(texisting - 1); +} + +/* note: this is used for timestamptz also */ +static Datum +timestamp_increment(Relation rel, Datum existing, bool *overflow) +{ + Timestamp texisting = DatumGetTimestamp(existing); + + if (texisting == PG_INT64_MAX) + { + /* return value is undefined */ + *overflow = true; + return (Datum) 0; + } + + *overflow = false; + return TimestampGetDatum(texisting + 1); +} + +Datum +timestamp_skipsupport(PG_FUNCTION_ARGS) +{ + SkipSupport sksup = (SkipSupport) PG_GETARG_POINTER(0); + + sksup->decrement = timestamp_decrement; + sksup->increment = timestamp_increment; + sksup->low_elem = TimestampGetDatum(PG_INT64_MIN); + sksup->high_elem = TimestampGetDatum(PG_INT64_MAX); + + PG_RETURN_VOID(); +} + Datum timestamp_hash(PG_FUNCTION_ARGS) { diff --git a/src/backend/utils/adt/uuid.c b/src/backend/utils/adt/uuid.c index 4f8402ef9..1b72059d2 100644 --- a/src/backend/utils/adt/uuid.c +++ b/src/backend/utils/adt/uuid.c @@ -13,6 +13,7 @@ #include "postgres.h" +#include #include /* for clock_gettime() */ #include "common/hashfn.h" @@ -21,6 +22,7 @@ #include "port/pg_bswap.h" #include "utils/fmgrprotos.h" #include "utils/guc.h" +#include "utils/skipsupport.h" #include "utils/sortsupport.h" #include "utils/timestamp.h" #include "utils/uuid.h" @@ -416,6 +418,74 @@ uuid_abbrev_convert(Datum original, SortSupport ssup) return res; } +static Datum +uuid_decrement(Relation rel, Datum existing, bool *underflow) +{ + pg_uuid_t *uuid; + + uuid = (pg_uuid_t *) palloc(UUID_LEN); + memcpy(uuid, DatumGetUUIDP(existing), UUID_LEN); + for (int i = UUID_LEN - 1; i >= 0; i--) + { + if (uuid->data[i] > 0) + { + uuid->data[i]--; + *underflow = false; + return UUIDPGetDatum(uuid); + } + uuid->data[i] = UCHAR_MAX; + } + + pfree(uuid); /* cannot leak memory */ + + /* return value is undefined */ + *underflow = true; + return (Datum) 0; +} + +static Datum +uuid_increment(Relation rel, Datum existing, bool *overflow) +{ + pg_uuid_t *uuid; + + uuid = (pg_uuid_t *) palloc(UUID_LEN); + memcpy(uuid, DatumGetUUIDP(existing), UUID_LEN); + for (int i = UUID_LEN - 1; i >= 0; i--) + { + if (uuid->data[i] < UCHAR_MAX) + { + uuid->data[i]++; + *overflow = false; + return UUIDPGetDatum(uuid); + } + uuid->data[i] = 0; + } + + pfree(uuid); /* cannot leak memory */ + + /* return value is undefined */ + *overflow = true; + return (Datum) 0; +} + +Datum +uuid_skipsupport(PG_FUNCTION_ARGS) +{ + SkipSupport sksup = (SkipSupport) PG_GETARG_POINTER(0); + pg_uuid_t *uuid_min = palloc(UUID_LEN); + pg_uuid_t *uuid_max = palloc(UUID_LEN); + + memset(uuid_min->data, 0x00, UUID_LEN); + memset(uuid_max->data, 0xFF, UUID_LEN); + + sksup->decrement = uuid_decrement; + sksup->increment = uuid_increment; + sksup->low_elem = UUIDPGetDatum(uuid_min); + sksup->high_elem = UUIDPGetDatum(uuid_max); + + PG_RETURN_VOID(); +} + /* hash index support */ Datum uuid_hash(PG_FUNCTION_ARGS) diff --git a/doc/src/sgml/btree.sgml b/doc/src/sgml/btree.sgml index 2b3997988..0a6a48749 100644 --- a/doc/src/sgml/btree.sgml +++ b/doc/src/sgml/btree.sgml @@ -207,7 +207,7 @@ As shown in , btree defines - one required and four optional support functions. The five + one required and five optional support functions. The six user-defined methods are: @@ -583,6 +583,38 @@ options(relopts local_relopts *) returns + + skipsupport + + + Optionally, a btree operator family may provide a skip + support function, registered under support function + number 6. These functions allow the B-tree code to more efficiently + navigate the index structure during an index skip scan. Operator classes + that implement skip support provide the core B-Tree code with a way of + enumerating and iterating through every possible value from the domain of + indexable values. The APIs involved in this are defined in + src/include/utils/skipsupport.h. + + + Operator classes that do not provide a skip support function are still + eligible to use skip scan. The core code can still use a fallback + strategy, though it might be somewhat less efficient with discrete types. + It usually doesn't make sense (and may not even be feasible) for operator + classes on continuous types to provide a skip support function. + + + It is not sensible for an operator family to register a cross-type + skipsupport function, and attempting to do so will + result in an error. This is because determining the next indexable value + from some earlier value does not just depend on sorting/equality + semantics, which are more or less defined at the operator family level. + Skip scan works by exhaustively considering every possible value stored + in an index, so the domain of the particular data type stored within the + index must also be considered. + + + diff --git a/doc/src/sgml/indexam.sgml b/doc/src/sgml/indexam.sgml index d17fcbd5c..1f1aafb36 100644 --- a/doc/src/sgml/indexam.sgml +++ b/doc/src/sgml/indexam.sgml @@ -829,7 +829,8 @@ amrestrpos (IndexScanDesc scan); Size -amestimateparallelscan (int nkeys, +amestimateparallelscan (Relation indexRelation, + int nkeys, int norderbys); Estimate and return the number of bytes of dynamic shared memory which diff --git a/doc/src/sgml/indices.sgml b/doc/src/sgml/indices.sgml index 6d731e070..b0cb09eb7 100644 --- a/doc/src/sgml/indices.sgml +++ b/doc/src/sgml/indices.sgml @@ -457,23 +457,26 @@ CREATE INDEX test2_mm_idx ON test2 (major, minor); A multicolumn B-tree index can be used with query conditions that involve any subset of the index's columns, but the index is most - efficient when there are constraints on the leading (leftmost) columns. - The exact rule is that equality constraints on leading columns, plus - any inequality constraints on the first column that does not have an - equality constraint, will be used to limit the portion of the index - that is scanned. Constraints on columns to the right of these columns - are checked in the index, so they save visits to the table proper, but - they do not reduce the portion of the index that has to be scanned. + efficient when there are equality constraints on the leading (leftmost) columns. + B-Tree index scans can use the index skip scan strategy to generate + equality constraints on prefix columns that were wholly omitted from the + query predicate, as well as prefix columns whose values were constrained by + inequality conditions. For example, given an index on (a, b, c) and a query condition WHERE a = 5 AND b >= 42 AND c < 77, the index would have to be scanned from the first entry with a = 5 and b = 42 up through the last entry with - a = 5. Index entries with c >= 77 would be - skipped, but they'd still have to be scanned through. + a = 5. Intervening groups of index entries with + c >= 77 would not need to be returned by the scan, + and can be skipped over entirely by applying the skip scan strategy. This index could in principle be used for queries that have constraints on b and/or c with no constraint on a - — but the entire index would have to be scanned, so in most cases - the planner would prefer a sequential table scan over using the index. + — but that approach is generally only taken when there are so few + distinct a values that the planner expects the skip scan + strategy to allow the scan to skip over most individual index leaf pages. + If there are many distinct a values, then the entire + index will have to be scanned, so in most cases the planner will prefer a + sequential table scan over using the index. @@ -508,11 +511,15 @@ CREATE INDEX test2_mm_idx ON test2 (major, minor); - Multicolumn indexes should be used sparingly. In most situations, - an index on a single column is sufficient and saves space and time. - Indexes with more than three columns are unlikely to be helpful - unless the usage of the table is extremely stylized. See also - and + Multicolumn indexes should only be used when testing shows that they'll + offer a clear advantage over simply using multiple single column indexes. + Indexes with more than three columns can make sense, but only when most + queries that make use of later columns also make use of earlier prefix + columns. It's possible for B-Tree index scans to make use of skip + scan optimizations with queries that omit a low cardinality + leading prefix column, but this is usually much less efficient than a scan + of an index without the extra prefix column. See and for some discussion of the merits of different index configurations. @@ -669,9 +676,13 @@ CREATE INDEX test3_desc_index ON test3 (id DESC NULLS LAST); multicolumn index on (x, y). This index would typically be more efficient than index combination for queries involving both columns, but as discussed in , it - would be almost useless for queries involving only y, so it - should not be the only index. A combination of the multicolumn index - and a separate index on y would serve reasonably well. For + would be less useful for queries involving only y. Just + how useful might depend on how effective the B-Tree index skip scan + optimization is; if x has no more than several hundred + distinct values, skip scan will make searches for specific + y values execute reasonably efficiently. A combination + of a multicolumn index on (x, y) and a separate index on + y might also serve reasonably well. For queries involving only x, the multicolumn index could be used, though it would be larger and hence slower than an index on x alone. The last alternative is to create all three diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 11cdfac0d..0bf3e39f3 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -4283,7 +4283,10 @@ description | Waiting for a newly initialized WAL file to reach durable storage value1 OR expression = value2 ... constructs when the query planner transforms the constructs - into an equivalent multi-valued array representation. + into an equivalent multi-valued array representation. Similarly, when + B-Tree index scans use the skip scan strategy, an index search is + performed each time the scan is repositioned to the next index leaf page + that might have matching tuples. diff --git a/doc/src/sgml/xindex.sgml b/doc/src/sgml/xindex.sgml index 053619624..7e23a7b6e 100644 --- a/doc/src/sgml/xindex.sgml +++ b/doc/src/sgml/xindex.sgml @@ -461,6 +461,13 @@ 5 + + + Return the addresses of C-callable skip support function(s) + (optional) + + 6 + @@ -1062,7 +1069,8 @@ DEFAULT FOR TYPE int8 USING btree FAMILY integer_ops AS FUNCTION 1 btint8cmp(int8, int8) , FUNCTION 2 btint8sortsupport(internal) , FUNCTION 3 in_range(int8, int8, int8, boolean, boolean) , - FUNCTION 4 btequalimage(oid) ; + FUNCTION 4 btequalimage(oid) , + FUNCTION 6 btint8skipsupport(internal) ; CREATE OPERATOR CLASS int4_ops DEFAULT FOR TYPE int4 USING btree FAMILY integer_ops AS @@ -1075,7 +1083,8 @@ DEFAULT FOR TYPE int4 USING btree FAMILY integer_ops AS FUNCTION 1 btint4cmp(int4, int4) , FUNCTION 2 btint4sortsupport(internal) , FUNCTION 3 in_range(int4, int4, int4, boolean, boolean) , - FUNCTION 4 btequalimage(oid) ; + FUNCTION 4 btequalimage(oid) , + FUNCTION 6 btint4skipsupport(internal) ; CREATE OPERATOR CLASS int2_ops DEFAULT FOR TYPE int2 USING btree FAMILY integer_ops AS @@ -1088,7 +1097,8 @@ DEFAULT FOR TYPE int2 USING btree FAMILY integer_ops AS FUNCTION 1 btint2cmp(int2, int2) , FUNCTION 2 btint2sortsupport(internal) , FUNCTION 3 in_range(int2, int2, int2, boolean, boolean) , - FUNCTION 4 btequalimage(oid) ; + FUNCTION 4 btequalimage(oid) , + FUNCTION 6 btint2skipsupport(internal) ; ALTER OPERATOR FAMILY integer_ops USING btree ADD -- cross-type comparisons int8 vs int2 diff --git a/src/test/regress/expected/alter_generic.out b/src/test/regress/expected/alter_generic.out index ae54cb254..f5aa73ac7 100644 --- a/src/test/regress/expected/alter_generic.out +++ b/src/test/regress/expected/alter_generic.out @@ -362,9 +362,9 @@ ERROR: invalid operator number 0, must be between 1 and 5 ALTER OPERATOR FAMILY alt_opf4 USING btree ADD OPERATOR 1 < ; -- operator without argument types ERROR: operator argument types must be specified in ALTER OPERATOR FAMILY ALTER OPERATOR FAMILY alt_opf4 USING btree ADD FUNCTION 0 btint42cmp(int4, int2); -- invalid options parsing function -ERROR: invalid function number 0, must be between 1 and 5 -ALTER OPERATOR FAMILY alt_opf4 USING btree ADD FUNCTION 6 btint42cmp(int4, int2); -- function number should be between 1 and 5 -ERROR: invalid function number 6, must be between 1 and 5 +ERROR: invalid function number 0, must be between 1 and 6 +ALTER OPERATOR FAMILY alt_opf4 USING btree ADD FUNCTION 7 btint42cmp(int4, int2); -- function number should be between 1 and 6 +ERROR: invalid function number 7, must be between 1 and 6 ALTER OPERATOR FAMILY alt_opf4 USING btree ADD STORAGE invalid_storage; -- Ensure STORAGE is not a part of ALTER OPERATOR FAMILY ERROR: STORAGE cannot be specified in ALTER OPERATOR FAMILY DROP OPERATOR FAMILY alt_opf4 USING btree; @@ -505,6 +505,10 @@ ALTER OPERATOR FAMILY alt_opf18 USING btree ADD ALTER OPERATOR FAMILY alt_opf18 USING btree ADD FUNCTION 4 (int4, int2) btequalimage(oid); ERROR: btree equal image functions must not be cross-type +-- Should fail. Not allowed to have cross-type skip support function. +ALTER OPERATOR FAMILY alt_opf18 USING btree + ADD FUNCTION 6 (int4, int2) btint4skipsupport(internal); +ERROR: btree skip support functions must not be cross-type ALTER OPERATOR FAMILY alt_opf18 USING btree DROP FUNCTION 2 (int4, int4); ERROR: function 2(integer,integer) does not exist in operator family "alt_opf18" DROP OPERATOR FAMILY alt_opf18 USING btree; diff --git a/src/test/regress/expected/btree_index.out b/src/test/regress/expected/btree_index.out index 8879554c3..bfb1a286e 100644 --- a/src/test/regress/expected/btree_index.out +++ b/src/test/regress/expected/btree_index.out @@ -581,6 +581,47 @@ alter table btree_tall_tbl alter COLUMN t set storage plain; create index btree_tall_idx on btree_tall_tbl (t, id) with (fillfactor = 10); insert into btree_tall_tbl select g, repeat('x', 250) from generate_series(1, 130) g; +insert into btree_tall_tbl select g, NULL +from generate_series(50, 60) g; +-- +-- Test for skip scan with type that lacks skip support (text) +-- +set enable_seqscan to false; +set enable_bitmapscan to false; +-- Forwards scan +SELECT id FROM btree_tall_tbl WHERE id = 55 ORDER BY t, id; + id +---- + 55 + 55 +(2 rows) + +explain (costs off) +SELECT id FROM btree_tall_tbl WHERE id = 55 ORDER BY t, id; + QUERY PLAN +-------------------------------------------------------- + Index Only Scan using btree_tall_idx on btree_tall_tbl + Index Cond: (id = 55) +(2 rows) + +-- Backwards scan +SELECT id FROM btree_tall_tbl WHERE id = 55 ORDER BY t DESC, id DESC; + id +---- + 55 + 55 +(2 rows) + +explain (costs off) +SELECT id FROM btree_tall_tbl WHERE id = 55 ORDER BY t DESC, id DESC; + QUERY PLAN +----------------------------------------------------------------- + Index Only Scan Backward using btree_tall_idx on btree_tall_tbl + Index Cond: (id = 55) +(2 rows) + +reset enable_seqscan; +reset enable_bitmapscan; -- -- Test for multilevel page deletion -- diff --git a/src/test/regress/expected/create_index.out b/src/test/regress/expected/create_index.out index bd5f002cf..15dde752f 100644 --- a/src/test/regress/expected/create_index.out +++ b/src/test/regress/expected/create_index.out @@ -1637,7 +1637,9 @@ DROP TABLE syscol_table; -- Tests for IS NULL/IS NOT NULL with b-tree indexes -- CREATE TABLE onek_with_null AS SELECT unique1, unique2 FROM onek; -INSERT INTO onek_with_null (unique1,unique2) VALUES (NULL, -1), (NULL, NULL); +INSERT INTO onek_with_null(unique1, unique2) +VALUES (NULL, -1), (NULL, 2_147_483_647), (NULL, NULL), + (100, NULL), (500, NULL); CREATE UNIQUE INDEX onek_nulltest ON onek_with_null (unique2,unique1); SET enable_seqscan = OFF; SET enable_indexscan = ON; @@ -1645,7 +1647,7 @@ SET enable_bitmapscan = ON; SELECT count(*) FROM onek_with_null WHERE unique1 IS NULL; count ------- - 2 + 3 (1 row) SELECT count(*) FROM onek_with_null WHERE unique1 IS NULL AND unique2 IS NULL; @@ -1657,13 +1659,13 @@ SELECT count(*) FROM onek_with_null WHERE unique1 IS NULL AND unique2 IS NULL; SELECT count(*) FROM onek_with_null WHERE unique1 IS NOT NULL; count ------- - 1000 + 1002 (1 row) SELECT count(*) FROM onek_with_null WHERE unique1 IS NULL AND unique2 IS NOT NULL; count ------- - 1 + 2 (1 row) SELECT count(*) FROM onek_with_null WHERE unique1 IS NOT NULL AND unique1 > 500; @@ -1678,12 +1680,18 @@ SELECT count(*) FROM onek_with_null WHERE unique1 IS NULL AND unique1 > 500; 0 (1 row) +SELECT unique1, unique2 FROM onek_with_null WHERE unique1 = 500 ORDER BY unique2 DESC, unique1 DESC LIMIT 1; + unique1 | unique2 +---------+--------- + 500 | +(1 row) + DROP INDEX onek_nulltest; CREATE UNIQUE INDEX onek_nulltest ON onek_with_null (unique2 desc,unique1); SELECT count(*) FROM onek_with_null WHERE unique1 IS NULL; count ------- - 2 + 3 (1 row) SELECT count(*) FROM onek_with_null WHERE unique1 IS NULL AND unique2 IS NULL; @@ -1695,13 +1703,13 @@ SELECT count(*) FROM onek_with_null WHERE unique1 IS NULL AND unique2 IS NULL; SELECT count(*) FROM onek_with_null WHERE unique1 IS NOT NULL; count ------- - 1000 + 1002 (1 row) SELECT count(*) FROM onek_with_null WHERE unique1 IS NULL AND unique2 IS NOT NULL; count ------- - 1 + 2 (1 row) SELECT count(*) FROM onek_with_null WHERE unique1 IS NOT NULL AND unique1 > 500; @@ -1722,12 +1730,18 @@ SELECT count(*) FROM onek_with_null WHERE unique1 IS NULL AND unique2 IN (-1, 0, 1 (1 row) +SELECT unique1, unique2 FROM onek_with_null WHERE unique1 = 500 ORDER BY unique2 DESC, unique1 DESC LIMIT 1; + unique1 | unique2 +---------+--------- + 500 | +(1 row) + DROP INDEX onek_nulltest; CREATE UNIQUE INDEX onek_nulltest ON onek_with_null (unique2 desc nulls last,unique1); SELECT count(*) FROM onek_with_null WHERE unique1 IS NULL; count ------- - 2 + 3 (1 row) SELECT count(*) FROM onek_with_null WHERE unique1 IS NULL AND unique2 IS NULL; @@ -1739,13 +1753,13 @@ SELECT count(*) FROM onek_with_null WHERE unique1 IS NULL AND unique2 IS NULL; SELECT count(*) FROM onek_with_null WHERE unique1 IS NOT NULL; count ------- - 1000 + 1002 (1 row) SELECT count(*) FROM onek_with_null WHERE unique1 IS NULL AND unique2 IS NOT NULL; count ------- - 1 + 2 (1 row) SELECT count(*) FROM onek_with_null WHERE unique1 IS NOT NULL AND unique1 > 500; @@ -1760,12 +1774,18 @@ SELECT count(*) FROM onek_with_null WHERE unique1 IS NULL AND unique1 > 500; 0 (1 row) +SELECT unique1, unique2 FROM onek_with_null WHERE unique1 = 500 ORDER BY unique2 DESC, unique1 DESC LIMIT 1; + unique1 | unique2 +---------+--------- + 500 | +(1 row) + DROP INDEX onek_nulltest; CREATE UNIQUE INDEX onek_nulltest ON onek_with_null (unique2 nulls first,unique1); SELECT count(*) FROM onek_with_null WHERE unique1 IS NULL; count ------- - 2 + 3 (1 row) SELECT count(*) FROM onek_with_null WHERE unique1 IS NULL AND unique2 IS NULL; @@ -1777,13 +1797,13 @@ SELECT count(*) FROM onek_with_null WHERE unique1 IS NULL AND unique2 IS NULL; SELECT count(*) FROM onek_with_null WHERE unique1 IS NOT NULL; count ------- - 1000 + 1002 (1 row) SELECT count(*) FROM onek_with_null WHERE unique1 IS NULL AND unique2 IS NOT NULL; count ------- - 1 + 2 (1 row) SELECT count(*) FROM onek_with_null WHERE unique1 IS NOT NULL AND unique1 > 500; @@ -1798,6 +1818,12 @@ SELECT count(*) FROM onek_with_null WHERE unique1 IS NULL AND unique1 > 500; 0 (1 row) +SELECT unique1, unique2 FROM onek_with_null WHERE unique1 = 500 ORDER BY unique2 DESC, unique1 DESC LIMIT 1; + unique1 | unique2 +---------+--------- + 500 | +(1 row) + DROP INDEX onek_nulltest; -- Check initial-positioning logic too CREATE UNIQUE INDEX onek_nulltest ON onek_with_null (unique2); @@ -1829,20 +1855,24 @@ SELECT unique1, unique2 FROM onek_with_null WHERE unique2 >= 0 (2 rows) SELECT unique1, unique2 FROM onek_with_null - ORDER BY unique2 DESC LIMIT 2; - unique1 | unique2 ----------+--------- - | - 278 | 999 -(2 rows) + ORDER BY unique2 DESC LIMIT 5; + unique1 | unique2 +---------+------------ + 500 | + 100 | + | + | 2147483647 + 278 | 999 +(5 rows) SELECT unique1, unique2 FROM onek_with_null WHERE unique2 >= -1 - ORDER BY unique2 DESC LIMIT 2; - unique1 | unique2 ----------+--------- - 278 | 999 - 0 | 998 -(2 rows) + ORDER BY unique2 DESC LIMIT 3; + unique1 | unique2 +---------+------------ + | 2147483647 + 278 | 999 + 0 | 998 +(3 rows) SELECT unique1, unique2 FROM onek_with_null WHERE unique2 < 999 ORDER BY unique2 DESC LIMIT 2; @@ -2247,7 +2277,8 @@ SELECT count(*) FROM dupindexcols (1 row) -- --- Check that index scans with =ANY indexquals return rows in index order +-- Check that index scans with SAOP array and/or skip array indexquals +-- return rows in index order -- explain (costs off) SELECT unique1 FROM tenk1 @@ -2269,7 +2300,7 @@ ORDER BY unique1; 42 (3 rows) --- Non-required array scan key on "tenthous": +-- Skip array on "thousand", SAOP array on "tenthous": explain (costs off) SELECT thousand, tenthous FROM tenk1 WHERE thousand < 2 AND tenthous IN (1001,3000) @@ -2289,7 +2320,7 @@ ORDER BY thousand; 1 | 1001 (2 rows) --- Non-required array scan key on "tenthous", backward scan: +-- Skip array on "thousand", SAOP array on "tenthous", backward scan: explain (costs off) SELECT thousand, tenthous FROM tenk1 WHERE thousand < 2 AND tenthous IN (1001,3000) @@ -2309,6 +2340,25 @@ ORDER BY thousand DESC, tenthous DESC; 0 | 3000 (2 rows) +explain (costs off) +SELECT thousand, tenthous FROM tenk1 +WHERE thousand > 995 and tenthous in (998, 999) +ORDER BY thousand desc; + QUERY PLAN +-------------------------------------------------------------------------------- + Index Only Scan Backward using tenk1_thous_tenthous on tenk1 + Index Cond: ((thousand > 995) AND (tenthous = ANY ('{998,999}'::integer[]))) +(2 rows) + +SELECT thousand, tenthous FROM tenk1 +WHERE thousand > 995 and tenthous in (998, 999) +ORDER BY thousand desc; + thousand | tenthous +----------+---------- + 999 | 999 + 998 | 998 +(2 rows) + -- -- Check elimination of redundant and contradictory index quals -- @@ -2339,6 +2389,45 @@ SELECT unique1 FROM tenk1 WHERE unique1 = ANY('{7, 14, 22}') and unique1 = ANY(' --------- (0 rows) +explain (costs off) +SELECT unique1 FROM tenk1 WHERE unique1 = ANY(NULL); + QUERY PLAN +------------------------------------------------- + Index Only Scan using tenk1_unique1 on tenk1 + Index Cond: (unique1 = ANY (NULL::integer[])) +(2 rows) + +SELECT unique1 FROM tenk1 WHERE unique1 = ANY(NULL); + unique1 +--------- +(0 rows) + +explain (costs off) +SELECT unique1 FROM tenk1 WHERE unique1 = ANY('{NULL,NULL,NULL}'); + QUERY PLAN +--------------------------------------------------------------- + Index Only Scan using tenk1_unique1 on tenk1 + Index Cond: (unique1 = ANY ('{NULL,NULL,NULL}'::integer[])) +(2 rows) + +SELECT unique1 FROM tenk1 WHERE unique1 = ANY('{NULL,NULL,NULL}'); + unique1 +--------- +(0 rows) + +explain (costs off) +SELECT unique1 FROM tenk1 WHERE unique1 IS NULL AND unique1 IS NULL; + QUERY PLAN +--------------------------------------------------------- + Index Only Scan using tenk1_unique1 on tenk1 + Index Cond: ((unique1 IS NULL) AND (unique1 IS NULL)) +(2 rows) + +SELECT unique1 FROM tenk1 WHERE unique1 IS NULL AND unique1 IS NULL; + unique1 +--------- +(0 rows) + explain (costs off) SELECT unique1 FROM tenk1 WHERE unique1 IN (1, 42, 7) and unique1 = 1; QUERY PLAN @@ -2462,6 +2551,44 @@ SELECT unique1 FROM tenk1 WHERE (thousand, tenthous) > (NULL, 5); --------- (0 rows) +-- Skip array redundancy (pair of redundant low_compare inequalities) +explain (costs off) +SELECT thousand, tenthous FROM tenk1 +WHERE thousand > -1 and thousand >= 0 AND tenthous = 3000 +ORDER BY thousand; + QUERY PLAN +-------------------------------------------------------------------------------------- + Index Only Scan using tenk1_thous_tenthous on tenk1 + Index Cond: ((thousand > '-1'::integer) AND (thousand >= 0) AND (tenthous = 3000)) +(2 rows) + +SELECT thousand, tenthous FROM tenk1 +WHERE thousand > -1 and thousand >= 0 AND tenthous = 3000 +ORDER BY thousand; + thousand | tenthous +----------+---------- + 0 | 3000 +(1 row) + +-- Skip array redundancy (pair of redundant high_compare inequalities) +explain (costs off) +SELECT thousand, tenthous FROM tenk1 +WHERE thousand < 3 and thousand <= 2 AND tenthous = 1001 +ORDER BY thousand; + QUERY PLAN +-------------------------------------------------------------------------- + Index Only Scan using tenk1_thous_tenthous on tenk1 + Index Cond: ((thousand < 3) AND (thousand <= 2) AND (tenthous = 1001)) +(2 rows) + +SELECT thousand, tenthous FROM tenk1 +WHERE thousand < 3 and thousand <= 2 AND tenthous = 1001 +ORDER BY thousand; + thousand | tenthous +----------+---------- + 1 | 1001 +(1 row) + -- -- Check elimination of constant-NULL subexpressions -- diff --git a/src/test/regress/expected/psql.out b/src/test/regress/expected/psql.out index 6543e90de..6ebd6265f 100644 --- a/src/test/regress/expected/psql.out +++ b/src/test/regress/expected/psql.out @@ -5331,9 +5331,10 @@ Function | in_range(time without time zone,time without time zone,i btree | uuid_ops | uuid | uuid | 1 | uuid_cmp btree | uuid_ops | uuid | uuid | 2 | uuid_sortsupport btree | uuid_ops | uuid | uuid | 4 | btequalimage + btree | uuid_ops | uuid | uuid | 6 | uuid_skipsupport hash | uuid_ops | uuid | uuid | 1 | uuid_hash hash | uuid_ops | uuid | uuid | 2 | uuid_hash_extended -(5 rows) +(6 rows) -- check \dconfig set work_mem = 10240; diff --git a/src/test/regress/sql/alter_generic.sql b/src/test/regress/sql/alter_generic.sql index de58d268d..5e20dc633 100644 --- a/src/test/regress/sql/alter_generic.sql +++ b/src/test/regress/sql/alter_generic.sql @@ -310,7 +310,7 @@ ALTER OPERATOR FAMILY alt_opf4 USING btree ADD OPERATOR 6 < (int4, int2); -- ope ALTER OPERATOR FAMILY alt_opf4 USING btree ADD OPERATOR 0 < (int4, int2); -- operator number should be between 1 and 5 ALTER OPERATOR FAMILY alt_opf4 USING btree ADD OPERATOR 1 < ; -- operator without argument types ALTER OPERATOR FAMILY alt_opf4 USING btree ADD FUNCTION 0 btint42cmp(int4, int2); -- invalid options parsing function -ALTER OPERATOR FAMILY alt_opf4 USING btree ADD FUNCTION 6 btint42cmp(int4, int2); -- function number should be between 1 and 5 +ALTER OPERATOR FAMILY alt_opf4 USING btree ADD FUNCTION 7 btint42cmp(int4, int2); -- function number should be between 1 and 6 ALTER OPERATOR FAMILY alt_opf4 USING btree ADD STORAGE invalid_storage; -- Ensure STORAGE is not a part of ALTER OPERATOR FAMILY DROP OPERATOR FAMILY alt_opf4 USING btree; @@ -444,6 +444,9 @@ ALTER OPERATOR FAMILY alt_opf18 USING btree ADD -- Should fail. Not allowed to have cross-type equalimage function. ALTER OPERATOR FAMILY alt_opf18 USING btree ADD FUNCTION 4 (int4, int2) btequalimage(oid); +-- Should fail. Not allowed to have cross-type skip support function. +ALTER OPERATOR FAMILY alt_opf18 USING btree + ADD FUNCTION 6 (int4, int2) btint4skipsupport(internal); ALTER OPERATOR FAMILY alt_opf18 USING btree DROP FUNCTION 2 (int4, int4); DROP OPERATOR FAMILY alt_opf18 USING btree; diff --git a/src/test/regress/sql/btree_index.sql b/src/test/regress/sql/btree_index.sql index 670ad5c6e..68c61dbc7 100644 --- a/src/test/regress/sql/btree_index.sql +++ b/src/test/regress/sql/btree_index.sql @@ -327,6 +327,27 @@ alter table btree_tall_tbl alter COLUMN t set storage plain; create index btree_tall_idx on btree_tall_tbl (t, id) with (fillfactor = 10); insert into btree_tall_tbl select g, repeat('x', 250) from generate_series(1, 130) g; +insert into btree_tall_tbl select g, NULL +from generate_series(50, 60) g; + +-- +-- Test for skip scan with type that lacks skip support (text) +-- +set enable_seqscan to false; +set enable_bitmapscan to false; + +-- Forwards scan +SELECT id FROM btree_tall_tbl WHERE id = 55 ORDER BY t, id; +explain (costs off) +SELECT id FROM btree_tall_tbl WHERE id = 55 ORDER BY t, id; + +-- Backwards scan +SELECT id FROM btree_tall_tbl WHERE id = 55 ORDER BY t DESC, id DESC; +explain (costs off) +SELECT id FROM btree_tall_tbl WHERE id = 55 ORDER BY t DESC, id DESC; + +reset enable_seqscan; +reset enable_bitmapscan; -- -- Test for multilevel page deletion diff --git a/src/test/regress/sql/create_index.sql b/src/test/regress/sql/create_index.sql index be570da08..40ba3d65b 100644 --- a/src/test/regress/sql/create_index.sql +++ b/src/test/regress/sql/create_index.sql @@ -650,7 +650,9 @@ DROP TABLE syscol_table; -- CREATE TABLE onek_with_null AS SELECT unique1, unique2 FROM onek; -INSERT INTO onek_with_null (unique1,unique2) VALUES (NULL, -1), (NULL, NULL); +INSERT INTO onek_with_null(unique1, unique2) +VALUES (NULL, -1), (NULL, 2_147_483_647), (NULL, NULL), + (100, NULL), (500, NULL); CREATE UNIQUE INDEX onek_nulltest ON onek_with_null (unique2,unique1); SET enable_seqscan = OFF; @@ -663,6 +665,7 @@ SELECT count(*) FROM onek_with_null WHERE unique1 IS NOT NULL; SELECT count(*) FROM onek_with_null WHERE unique1 IS NULL AND unique2 IS NOT NULL; SELECT count(*) FROM onek_with_null WHERE unique1 IS NOT NULL AND unique1 > 500; SELECT count(*) FROM onek_with_null WHERE unique1 IS NULL AND unique1 > 500; +SELECT unique1, unique2 FROM onek_with_null WHERE unique1 = 500 ORDER BY unique2 DESC, unique1 DESC LIMIT 1; DROP INDEX onek_nulltest; @@ -675,6 +678,7 @@ SELECT count(*) FROM onek_with_null WHERE unique1 IS NULL AND unique2 IS NOT NUL SELECT count(*) FROM onek_with_null WHERE unique1 IS NOT NULL AND unique1 > 500; SELECT count(*) FROM onek_with_null WHERE unique1 IS NULL AND unique1 > 500; SELECT count(*) FROM onek_with_null WHERE unique1 IS NULL AND unique2 IN (-1, 0, 1); +SELECT unique1, unique2 FROM onek_with_null WHERE unique1 = 500 ORDER BY unique2 DESC, unique1 DESC LIMIT 1; DROP INDEX onek_nulltest; @@ -686,6 +690,7 @@ SELECT count(*) FROM onek_with_null WHERE unique1 IS NOT NULL; SELECT count(*) FROM onek_with_null WHERE unique1 IS NULL AND unique2 IS NOT NULL; SELECT count(*) FROM onek_with_null WHERE unique1 IS NOT NULL AND unique1 > 500; SELECT count(*) FROM onek_with_null WHERE unique1 IS NULL AND unique1 > 500; +SELECT unique1, unique2 FROM onek_with_null WHERE unique1 = 500 ORDER BY unique2 DESC, unique1 DESC LIMIT 1; DROP INDEX onek_nulltest; @@ -697,6 +702,7 @@ SELECT count(*) FROM onek_with_null WHERE unique1 IS NOT NULL; SELECT count(*) FROM onek_with_null WHERE unique1 IS NULL AND unique2 IS NOT NULL; SELECT count(*) FROM onek_with_null WHERE unique1 IS NOT NULL AND unique1 > 500; SELECT count(*) FROM onek_with_null WHERE unique1 IS NULL AND unique1 > 500; +SELECT unique1, unique2 FROM onek_with_null WHERE unique1 = 500 ORDER BY unique2 DESC, unique1 DESC LIMIT 1; DROP INDEX onek_nulltest; @@ -716,9 +722,9 @@ SELECT unique1, unique2 FROM onek_with_null WHERE unique2 >= 0 ORDER BY unique2 LIMIT 2; SELECT unique1, unique2 FROM onek_with_null - ORDER BY unique2 DESC LIMIT 2; + ORDER BY unique2 DESC LIMIT 5; SELECT unique1, unique2 FROM onek_with_null WHERE unique2 >= -1 - ORDER BY unique2 DESC LIMIT 2; + ORDER BY unique2 DESC LIMIT 3; SELECT unique1, unique2 FROM onek_with_null WHERE unique2 < 999 ORDER BY unique2 DESC LIMIT 2; @@ -852,7 +858,8 @@ SELECT count(*) FROM dupindexcols WHERE f1 BETWEEN 'WA' AND 'ZZZ' and id < 1000 and f1 ~<~ 'YX'; -- --- Check that index scans with =ANY indexquals return rows in index order +-- Check that index scans with SAOP array and/or skip array indexquals +-- return rows in index order -- explain (costs off) @@ -864,7 +871,7 @@ SELECT unique1 FROM tenk1 WHERE unique1 IN (1,42,7) ORDER BY unique1; --- Non-required array scan key on "tenthous": +-- Skip array on "thousand", SAOP array on "tenthous": explain (costs off) SELECT thousand, tenthous FROM tenk1 WHERE thousand < 2 AND tenthous IN (1001,3000) @@ -874,7 +881,7 @@ SELECT thousand, tenthous FROM tenk1 WHERE thousand < 2 AND tenthous IN (1001,3000) ORDER BY thousand; --- Non-required array scan key on "tenthous", backward scan: +-- Skip array on "thousand", SAOP array on "tenthous", backward scan: explain (costs off) SELECT thousand, tenthous FROM tenk1 WHERE thousand < 2 AND tenthous IN (1001,3000) @@ -884,6 +891,15 @@ SELECT thousand, tenthous FROM tenk1 WHERE thousand < 2 AND tenthous IN (1001,3000) ORDER BY thousand DESC, tenthous DESC; +explain (costs off) +SELECT thousand, tenthous FROM tenk1 +WHERE thousand > 995 and tenthous in (998, 999) +ORDER BY thousand desc; + +SELECT thousand, tenthous FROM tenk1 +WHERE thousand > 995 and tenthous in (998, 999) +ORDER BY thousand desc; + -- -- Check elimination of redundant and contradictory index quals -- @@ -897,6 +913,21 @@ SELECT unique1 FROM tenk1 WHERE unique1 = ANY('{7, 14, 22}') and unique1 = ANY(' SELECT unique1 FROM tenk1 WHERE unique1 = ANY('{7, 14, 22}') and unique1 = ANY('{33, 44}'::bigint[]); +explain (costs off) +SELECT unique1 FROM tenk1 WHERE unique1 = ANY(NULL); + +SELECT unique1 FROM tenk1 WHERE unique1 = ANY(NULL); + +explain (costs off) +SELECT unique1 FROM tenk1 WHERE unique1 = ANY('{NULL,NULL,NULL}'); + +SELECT unique1 FROM tenk1 WHERE unique1 = ANY('{NULL,NULL,NULL}'); + +explain (costs off) +SELECT unique1 FROM tenk1 WHERE unique1 IS NULL AND unique1 IS NULL; + +SELECT unique1 FROM tenk1 WHERE unique1 IS NULL AND unique1 IS NULL; + explain (costs off) SELECT unique1 FROM tenk1 WHERE unique1 IN (1, 42, 7) and unique1 = 1; @@ -942,6 +973,26 @@ SELECT unique1 FROM tenk1 WHERE (thousand, tenthous) > (NULL, 5); SELECT unique1 FROM tenk1 WHERE (thousand, tenthous) > (NULL, 5); +-- Skip array redundancy (pair of redundant low_compare inequalities) +explain (costs off) +SELECT thousand, tenthous FROM tenk1 +WHERE thousand > -1 and thousand >= 0 AND tenthous = 3000 +ORDER BY thousand; + +SELECT thousand, tenthous FROM tenk1 +WHERE thousand > -1 and thousand >= 0 AND tenthous = 3000 +ORDER BY thousand; + +-- Skip array redundancy (pair of redundant high_compare inequalities) +explain (costs off) +SELECT thousand, tenthous FROM tenk1 +WHERE thousand < 3 and thousand <= 2 AND tenthous = 1001 +ORDER BY thousand; + +SELECT thousand, tenthous FROM tenk1 +WHERE thousand < 3 and thousand <= 2 AND tenthous = 1001 +ORDER BY thousand; + -- -- Check elimination of constant-NULL subexpressions -- diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index b09d8af71..1ab169b14 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -220,6 +220,7 @@ BTScanPos BTScanPosData BTScanPosItem BTShared +BTSkipPreproc BTSortArrayContext BTSpool BTStack @@ -2697,6 +2698,8 @@ SimpleStringListCell SingleBoundSortItem Size SkipPages +SkipSupport +SkipSupportData SlabBlock SlabContext SlabSlot -- 2.47.2