diff options
author | Robert Haas <rhaas@postgresql.org> | 2016-12-07 13:17:43 -0500 |
---|---|---|
committer | Robert Haas <rhaas@postgresql.org> | 2016-12-07 13:17:55 -0500 |
commit | f0e44751d7175fa3394da2c8f85e3ceb3cdbfe63 (patch) | |
tree | d869b1c4ae0416d1e7a36adb72e3683eb8ce0266 /src/backend/utils/adt/ruleutils.c | |
parent | b7e1ae2328f7d5a88d8916d78b4561d8ef16f99b (diff) | |
download | postgresql-f0e44751d7175fa3394da2c8f85e3ceb3cdbfe63.tar.gz postgresql-f0e44751d7175fa3394da2c8f85e3ceb3cdbfe63.zip |
Implement table partitioning.
Table partitioning is like table inheritance and reuses much of the
existing infrastructure, but there are some important differences.
The parent is called a partitioned table and is always empty; it may
not have indexes or non-inherited constraints, since those make no
sense for a relation with no data of its own. The children are called
partitions and contain all of the actual data. Each partition has an
implicit partitioning constraint. Multiple inheritance is not
allowed, and partitioning and inheritance can't be mixed. Partitions
can't have extra columns and may not allow nulls unless the parent
does. Tuples inserted into the parent are automatically routed to the
correct partition, so tuple-routing ON INSERT triggers are not needed.
Tuple routing isn't yet supported for partitions which are foreign
tables, and it doesn't handle updates that cross partition boundaries.
Currently, tables can be range-partitioned or list-partitioned. List
partitioning is limited to a single column, but range partitioning can
involve multiple columns. A partitioning "column" can be an
expression.
Because table partitioning is less general than table inheritance, it
is hoped that it will be easier to reason about properties of
partitions, and therefore that this will serve as a better foundation
for a variety of possible optimizations, including query planner
optimizations. The tuple routing based which this patch does based on
the implicit partitioning constraints is an example of this, but it
seems likely that many other useful optimizations are also possible.
Amit Langote, reviewed and tested by Robert Haas, Ashutosh Bapat,
Amit Kapila, Rajkumar Raghuwanshi, Corey Huinker, Jaime Casanova,
Rushabh Lathia, Erik Rijkers, among others. Minor revisions by me.
Diffstat (limited to 'src/backend/utils/adt/ruleutils.c')
-rw-r--r-- | src/backend/utils/adt/ruleutils.c | 241 |
1 files changed, 241 insertions, 0 deletions
diff --git a/src/backend/utils/adt/ruleutils.c b/src/backend/utils/adt/ruleutils.c index fecee85e5ba..4e2ba19d1b7 100644 --- a/src/backend/utils/adt/ruleutils.c +++ b/src/backend/utils/adt/ruleutils.c @@ -33,6 +33,7 @@ #include "catalog/pg_language.h" #include "catalog/pg_opclass.h" #include "catalog/pg_operator.h" +#include "catalog/pg_partitioned_table.h" #include "catalog/pg_proc.h" #include "catalog/pg_trigger.h" #include "catalog/pg_type.h" @@ -315,6 +316,7 @@ static char *pg_get_indexdef_worker(Oid indexrelid, int colno, const Oid *excludeOps, bool attrsOnly, bool showTblSpc, int prettyFlags, bool missing_ok); +static char *pg_get_partkeydef_worker(Oid relid, int prettyFlags); static char *pg_get_constraintdef_worker(Oid constraintId, bool fullCommand, int prettyFlags, bool missing_ok); static text *pg_get_expr_worker(text *expr, Oid relid, const char *relname, @@ -1415,6 +1417,163 @@ pg_get_indexdef_worker(Oid indexrelid, int colno, return buf.data; } +/* + * pg_get_partkeydef + * + * Returns the partition key specification, ie, the following: + * + * PARTITION BY { RANGE | LIST } (column opt_collation opt_opclass [, ...]) + */ +Datum +pg_get_partkeydef(PG_FUNCTION_ARGS) +{ + Oid relid = PG_GETARG_OID(0); + + PG_RETURN_TEXT_P(string_to_text(pg_get_partkeydef_worker(relid, + PRETTYFLAG_INDENT))); +} + +/* + * Internal workhorse to decompile a partition key definition. + */ +static char * +pg_get_partkeydef_worker(Oid relid, int prettyFlags) +{ + Form_pg_partitioned_table form; + HeapTuple tuple; + oidvector *partclass; + oidvector *partcollation; + List *partexprs; + ListCell *partexpr_item; + List *context; + Datum datum; + bool isnull; + StringInfoData buf; + int keyno; + char *str; + char *sep; + + tuple = SearchSysCache1(PARTRELID, ObjectIdGetDatum(relid)); + if (!HeapTupleIsValid(tuple)) + elog(ERROR, "cache lookup failed for partition key of %u", relid); + + form = (Form_pg_partitioned_table) GETSTRUCT(tuple); + + Assert(form->partrelid == relid); + + /* Must get partclass and partcollation the hard way */ + datum = SysCacheGetAttr(PARTRELID, tuple, + Anum_pg_partitioned_table_partclass, &isnull); + Assert(!isnull); + partclass = (oidvector *) DatumGetPointer(datum); + + datum = SysCacheGetAttr(PARTRELID, tuple, + Anum_pg_partitioned_table_partcollation, &isnull); + Assert(!isnull); + partcollation = (oidvector *) DatumGetPointer(datum); + + + /* + * Get the expressions, if any. (NOTE: we do not use the relcache + * versions of the expressions, because we want to display non-const-folded + * expressions.) + */ + if (!heap_attisnull(tuple, Anum_pg_partitioned_table_partexprs)) + { + Datum exprsDatum; + bool isnull; + char *exprsString; + + exprsDatum = SysCacheGetAttr(PARTRELID, tuple, + Anum_pg_partitioned_table_partexprs, &isnull); + Assert(!isnull); + exprsString = TextDatumGetCString(exprsDatum); + partexprs = (List *) stringToNode(exprsString); + + if (!IsA(partexprs, List)) + elog(ERROR, "unexpected node type found in partexprs: %d", + (int) nodeTag(partexprs)); + + pfree(exprsString); + } + else + partexprs = NIL; + + partexpr_item = list_head(partexprs); + context = deparse_context_for(get_relation_name(relid), relid); + + initStringInfo(&buf); + + switch (form->partstrat) + { + case PARTITION_STRATEGY_LIST: + appendStringInfo(&buf, "LIST"); + break; + case PARTITION_STRATEGY_RANGE: + appendStringInfo(&buf, "RANGE"); + break; + default: + elog(ERROR, "unexpected partition strategy: %d", + (int) form->partstrat); + } + + appendStringInfo(&buf, " ("); + sep = ""; + for (keyno = 0; keyno < form->partnatts; keyno++) + { + AttrNumber attnum = form->partattrs.values[keyno]; + Oid keycoltype; + Oid keycolcollation; + Oid partcoll; + + appendStringInfoString(&buf, sep); + sep = ", "; + if (attnum != 0) + { + /* Simple attribute reference */ + char *attname; + int32 keycoltypmod; + + attname = get_relid_attribute_name(relid, attnum); + appendStringInfoString(&buf, quote_identifier(attname)); + get_atttypetypmodcoll(relid, attnum, + &keycoltype, &keycoltypmod, + &keycolcollation); + } + else + { + /* Expression */ + Node *partkey; + + if (partexpr_item == NULL) + elog(ERROR, "too few entries in partexprs list"); + partkey = (Node *) lfirst(partexpr_item); + partexpr_item = lnext(partexpr_item); + /* Deparse */ + str = deparse_expression_pretty(partkey, context, false, false, + 0, 0); + + appendStringInfoString(&buf, str); + keycoltype = exprType(partkey); + keycolcollation = exprCollation(partkey); + } + + /* Add collation, if not default for column */ + partcoll = partcollation->values[keyno]; + if (OidIsValid(partcoll) && partcoll != keycolcollation) + appendStringInfo(&buf, " COLLATE %s", + generate_collation_name((partcoll))); + + /* Add the operator class name, if not default */ + get_opclass_name(partclass->values[keyno], keycoltype, &buf); + } + appendStringInfoChar(&buf, ')'); + + /* Clean up */ + ReleaseSysCache(tuple); + + return buf.data; +} /* * pg_get_constraintdef @@ -8291,6 +8450,88 @@ get_rule_expr(Node *node, deparse_context *context, } break; + case T_PartitionBoundSpec: + { + PartitionBoundSpec *spec = (PartitionBoundSpec *) node; + ListCell *cell; + char *sep; + + switch (spec->strategy) + { + case PARTITION_STRATEGY_LIST: + Assert(spec->listdatums != NIL); + + appendStringInfoString(buf, "FOR VALUES"); + appendStringInfoString(buf, " IN ("); + sep = ""; + foreach (cell, spec->listdatums) + { + Const *val = lfirst(cell); + + appendStringInfoString(buf, sep); + get_const_expr(val, context, -1); + sep = ", "; + } + + appendStringInfoString(buf, ")"); + break; + + case PARTITION_STRATEGY_RANGE: + Assert(spec->lowerdatums != NIL && + spec->upperdatums != NIL && + list_length(spec->lowerdatums) == + list_length(spec->upperdatums)); + + appendStringInfoString(buf, "FOR VALUES"); + appendStringInfoString(buf, " FROM"); + appendStringInfoString(buf, " ("); + sep = ""; + foreach (cell, spec->lowerdatums) + { + PartitionRangeDatum *datum = lfirst(cell); + Const *val; + + appendStringInfoString(buf, sep); + if (datum->infinite) + appendStringInfoString(buf, "UNBOUNDED"); + else + { + val = (Const *) datum->value; + get_const_expr(val, context, -1); + } + sep = ", "; + } + appendStringInfoString(buf, ")"); + + appendStringInfoString(buf, " TO"); + appendStringInfoString(buf, " ("); + sep = ""; + foreach (cell, spec->upperdatums) + { + PartitionRangeDatum *datum = lfirst(cell); + Const *val; + + appendStringInfoString(buf, sep); + if (datum->infinite) + appendStringInfoString(buf, "UNBOUNDED"); + else + { + val = (Const *) datum->value; + get_const_expr(val, context, -1); + } + sep = ", "; + } + appendStringInfoString(buf, ")"); + break; + + default: + elog(ERROR, "unrecognized partition strategy: %d", + (int) spec->strategy); + break; + } + } + break; + case T_List: { char *sep; |