* Definitions for planner's internal data structures.
*
*
- * Portions Copyright (c) 1996-2008, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1996-2010, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
- * $PostgreSQL: pgsql/src/include/nodes/relation.h,v 1.163 2008/10/22 20:17:52 tgl Exp $
+ * src/include/nodes/relation.h
*
*-------------------------------------------------------------------------
*/
List *subrtables; /* Rangetables for SubPlan nodes */
+ List *subrowmarks; /* PlanRowMarks for SubPlan nodes */
+
Bitmapset *rewindPlanIDs; /* indices of subplans that require REWIND */
List *finalrtable; /* "flat" rangetable for executor */
+ List *finalrowmarks; /* "flat" list of PlanRowMarks */
+
List *relationOids; /* OIDs of relations the plan depends on */
List *invalItems; /* other dependencies, as PlanInvalItems */
Index query_level; /* 1 at the outermost Query */
- struct PlannerInfo *parent_root; /* NULL at outermost Query */
+ struct PlannerInfo *parent_root; /* NULL at outermost Query */
/*
* simple_rel_array holds pointers to "base rels" and "other rels" (see
List *join_rel_list; /* list of join-relation RelOptInfos */
struct HTAB *join_rel_hash; /* optional hashtable for join relations */
- List *resultRelations; /* integer list of RT indexes, or NIL */
+ /*
+ * When doing a dynamic-programming-style join search, join_rel_level[k]
+ * is a list of all join-relation RelOptInfos of level k, and
+ * join_cur_level is the current level. New join-relation RelOptInfos are
+ * automatically added to the join_rel_level[join_cur_level] list.
+ * join_rel_level is NULL if not in use.
+ */
+ List **join_rel_level; /* lists of join-relation RelOptInfos */
+ int join_cur_level; /* index of list being extended */
- List *returningLists; /* list of lists of TargetEntry, or NIL */
+ List *resultRelations; /* integer list of RT indexes, or NIL */
List *init_plans; /* init SubPlans for query */
List *full_join_clauses; /* list of RestrictInfos for
* mergejoinable full join clauses */
- List *join_info_list; /* list of SpecialJoinInfos */
+ List *join_info_list; /* list of SpecialJoinInfos */
List *append_rel_list; /* list of AppendRelInfos */
- List *placeholder_list; /* list of PlaceHolderInfos */
+ List *rowMarks; /* list of PlanRowMarks */
+
+ List *placeholder_list; /* list of PlaceHolderInfos */
List *query_pathkeys; /* desired pathkeys for query_planner(), and
* actual pathkeys afterwards */
- List *group_pathkeys; /* groupClause pathkeys, if any */
- List *distinct_pathkeys; /* distinctClause pathkeys, if any */
- List *sort_pathkeys; /* sortClause pathkeys, if any */
+ List *group_pathkeys; /* groupClause pathkeys, if any */
+ List *window_pathkeys; /* pathkeys of bottom window, if any */
+ List *distinct_pathkeys; /* distinctClause pathkeys, if any */
+ List *sort_pathkeys; /* sortClause pathkeys, if any */
+
+ List *minmax_aggs; /* List of MinMaxAggInfos */
List *initial_rels; /* RelOptInfos we are now trying to join */
double total_table_pages; /* # of pages in all tables of query */
double tuple_fraction; /* tuple_fraction passed to query_planner */
+ double limit_tuples; /* limit_tuples passed to query_planner */
+ bool hasInheritedTarget; /* true if parse->resultRelation is an
+ * inheritance child rel */
bool hasJoinRTEs; /* true if any RTEs are RTE_JOIN kind */
bool hasHavingQual; /* true if havingQual was non-null */
bool hasPseudoConstantQuals; /* true if any RestrictInfo has
bool hasRecursion; /* true if planning a recursive WITH item */
/* These fields are used only when hasRecursion is true: */
- int wt_param_id; /* PARAM_EXEC ID for the work table */
+ int wt_param_id; /* PARAM_EXEC ID for the work table */
struct Plan *non_recursive_plan; /* plan for non-recursive term */
+
+ /* These fields are workspace for createplan.c */
+ Relids curOuterRels; /* outer rels above current node */
+ List *curOuterParams; /* not-yet-assigned NestLoopParams */
+
+ /* optional private data for join_search_hook, e.g., GEQO */
+ void *join_search_private;
} PlannerInfo;
*
* We also have "other rels", which are like base rels in that they refer to
* single RT indexes; but they are not part of the join tree, and are given
- * a different RelOptKind to identify them.
+ * a different RelOptKind to identify them. Lastly, there is a RelOptKind
+ * for "dead" relations, which are base rels that we have proven we don't
+ * need to join after all.
*
* Currently the only kind of otherrels are those made for member relations
* of an "append relation", that is an inheritance set or UNION ALL subquery.
* the entire append relation. The member RTEs are otherrels. The parent
* is present in the query join tree but the members are not. The member
* RTEs and otherrels are used to plan the scans of the individual tables or
- * subqueries of the append set; then the parent baserel is given an Append
- * plan comprising the best plans for the individual member rels. (See
- * comments for AppendRelInfo for more information.)
+ * subqueries of the append set; then the parent baserel is given Append
+ * and/or MergeAppend paths comprising the best paths for the individual
+ * member rels. (See comments for AppendRelInfo for more information.)
*
* At one time we also made otherrels to represent join RTEs, for use in
* handling join alias Vars. Currently this is not needed because all join
* tuples - number of tuples in relation (not considering restrictions)
* subplan - plan for subquery (NULL if it's not a subquery)
* subrtable - rangetable for subquery (NIL if it's not a subquery)
+ * subrowmark - rowmarks for subquery (NIL if it's not a subquery)
*
* Note: for a subquery, tuples and subplan are not set immediately
* upon creation of the RelOptInfo object; they are filled in when
{
RELOPT_BASEREL,
RELOPT_JOINREL,
- RELOPT_OTHER_MEMBER_REL
+ RELOPT_OTHER_MEMBER_REL,
+ RELOPT_DEADREL
} RelOptKind;
typedef struct RelOptInfo
/* information about a base rel (not set for join rels!) */
Index relid;
+ Oid reltablespace; /* containing tablespace */
RTEKind rtekind; /* RELATION, SUBQUERY, or FUNCTION */
AttrNumber min_attr; /* smallest attrno of rel (often <0) */
AttrNumber max_attr; /* largest attrno of rel */
double tuples;
struct Plan *subplan; /* if subquery */
List *subrtable; /* if subquery */
+ List *subrowmark; /* if subquery */
/* used by various scans and joins: */
List *baserestrictinfo; /* RestrictInfo structures (if base
*
* opfamily[], indexkeys[], opcintype[], fwdsortop[], revsortop[],
* and nulls_first[] each have ncolumns entries.
- * Note: for historical reasons, the opfamily array has an extra entry
- * that is always zero. Some code scans until it sees a zero entry,
- * rather than looking at ncolumns.
*
* Zeroes in the indexkeys[] array indicate index columns that are
* expressions; there is one element in indexprs for each such column.
NodeTag type;
Oid indexoid; /* OID of the index relation */
+ Oid reltablespace; /* tablespace of index (not table) */
RelOptInfo *rel; /* back-link to index's table */
/* statistics from pg_class */
bool predOK; /* true if predicate matches query */
bool unique; /* true if a unique index */
+ bool amcanorderbyop; /* does AM support order by operator result? */
bool amoptionalkey; /* can query omit key for the first column? */
- bool amsearchnulls; /* can AM search for NULL index entries? */
+ bool amsearchnulls; /* can AM search for NULL/NOT NULL entries? */
+ bool amhasgettuple; /* does AM have amgettuple interface? */
+ bool amhasgetbitmap; /* does AM have amgetbitmap interface? */
} IndexOptInfo;
*
* em_is_child signifies that this element was built by transposing a member
* for an inheritance parent relation to represent the corresponding expression
- * on an inheritance child. The element should be ignored for all purposes
- * except constructing inner-indexscan paths for the child relation. (Other
- * types of join are driven from transposed joininfo-list entries.) Note
- * that the EC's ec_relids field does NOT include the child relation.
+ * on an inheritance child. These elements are used for constructing
+ * inner-indexscan paths for the child relation (other types of join are
+ * driven from transposed joininfo-list entries) and for constructing
+ * MergeAppend paths for the whole inheritance tree. Note that the EC's
+ * ec_relids field does NOT include the child relation.
*
* em_datatype is usually the same as exprType(em_expr), but can be
* different when dealing with a binary-compatible opfamily; in particular
#define IS_DUMMY_PATH(p) \
(IsA((p), AppendPath) && ((AppendPath *) (p))->subpaths == NIL)
+/*
+ * MergeAppendPath represents a MergeAppend plan, ie, the merging of sorted
+ * results from several member plans to produce similarly-sorted output.
+ */
+typedef struct MergeAppendPath
+{
+ Path path;
+ List *subpaths; /* list of component Paths */
+ double limit_tuples; /* hard limit on output tuples, or -1 */
+} MergeAppendPath;
+
/*
* ResultPath represents use of a Result plan node to compute a variable-free
* targetlist with no underlying tables (a "SELECT expressions" query).
/*
* A mergejoin path has these fields.
*
+ * Unlike other path types, a MergePath node doesn't represent just a single
+ * run-time plan node: it can represent up to four. Aside from the MergeJoin
+ * node itself, there can be a Sort node for the outer input, a Sort node
+ * for the inner input, and/or a Material node for the inner input. We could
+ * represent these nodes by separate path nodes, but considering how many
+ * different merge paths are investigated during a complex join problem,
+ * it seems better to avoid unnecessary palloc overhead.
+ *
* path_mergeclauses lists the clauses (in the form of RestrictInfos)
* that will be used in the merge.
*
* outersortkeys (resp. innersortkeys) is NIL if the outer path
* (resp. inner path) is already ordered appropriately for the
* mergejoin. If it is not NIL then it is a PathKeys list describing
- * the ordering that must be created by an explicit sort step.
+ * the ordering that must be created by an explicit Sort node.
+ *
+ * materialize_inner is TRUE if a Material node should be placed atop the
+ * inner input. This may appear with or without an inner Sort step.
*/
typedef struct MergePath
List *path_mergeclauses; /* join clauses to be used for merge */
List *outersortkeys; /* keys for explicit sort, if any */
List *innersortkeys; /* keys for explicit sort, if any */
+ bool materialize_inner; /* add Materialize to inner? */
} MergePath;
/*
{
JoinPath jpath;
List *path_hashclauses; /* join clauses used for hashing */
+ int num_batches; /* number of batches expected */
} HashPath;
/*
* if we decide that it can be pushed down into the nullable side of the join.
* In that case it acts as a plain filter qual for wherever it gets evaluated.
* (In short, is_pushed_down is only false for non-degenerate outer join
- * conditions. Possibly we should rename it to reflect that meaning?)
+ * conditions. Possibly we should rename it to reflect that meaning?)
*
* RestrictInfo nodes also contain an outerjoin_delayed flag, which is true
* if the clause's applicability must be delayed due to any outer joins
- * appearing below its own syntactic level (ie, it references any Vars from
- * the nullable side of any lower outer join).
+ * appearing below it (ie, it has to be postponed to some join level higher
+ * than the set of relations it actually references). There is also a
+ * nullable_relids field, which is the set of rels it references that can be
+ * forced null by some outer join below the clause. outerjoin_delayed = true
+ * is subtly different from nullable_relids != NULL: a clause might reference
+ * some nullable rels and yet not be outerjoin_delayed because it also
+ * references all the other rels of the outer join(s). A clause that is not
+ * outerjoin_delayed can be enforced anywhere it is computable.
*
* In general, the referenced clause might be arbitrarily complex. The
* kinds of clauses we can handle as indexscan quals, mergejoin clauses,
bool is_pushed_down; /* TRUE if clause was pushed down in level */
- bool outerjoin_delayed; /* TRUE if delayed by lower outer join */
+ bool outerjoin_delayed; /* TRUE if delayed by lower outer join */
bool can_join; /* see comment above */
/* The set of relids required to evaluate the clause: */
Relids required_relids;
+ /* The relids used in the clause that are nullable by lower outer joins: */
+ Relids nullable_relids;
+
/* These fields are set for any binary opclause: */
Relids left_relids; /* relids in left side of clause */
Relids right_relids; /* relids in right side of clause */
/* cache space for cost and selectivity */
QualCost eval_cost; /* eval cost of clause; -1 if not yet set */
- Selectivity this_selec; /* selectivity; -1 if not yet set */
+ Selectivity norm_selec; /* selectivity for "normal" (JOIN_INNER)
+ * semantics; -1 if not yet set; >1 means a
+ * redundant clause */
+ Selectivity outer_selec; /* selectivity for outer join semantics; -1 if
+ * not yet set */
/* valid if clause is mergejoinable, else NIL */
List *mergeopfamilies; /* opfamilies containing clause operator */
Path *cheapest_total_innerpath; /* cheapest total cost */
} InnerIndexscanInfo;
-/*
- * "Flattened SubLinks"
- *
- * When we pull an IN or EXISTS SubLink up into the parent query, the
- * join conditions extracted from the IN/EXISTS clause need to be specially
- * treated in distribute_qual_to_rels processing. We handle this by
- * wrapping such expressions in a FlattenedSubLink node that identifies
- * the join they come from. The FlattenedSubLink node is discarded after
- * distribute_qual_to_rels, having served its purpose.
- *
- * Although the planner treats this as an expression node type, it is not
- * recognized by the parser or executor, so we declare it here rather than
- * in primnodes.h.
- */
-
-typedef struct FlattenedSubLink
-{
- Expr xpr;
- JoinType jointype; /* must be JOIN_SEMI or JOIN_ANTI */
- Relids lefthand; /* base relids treated as syntactic LHS */
- Relids righthand; /* base relids syntactically within RHS */
- Expr *quals; /* join quals (in explicit-AND format) */
-} FlattenedSubLink;
-
/*
* Placeholder node for an expression to be evaluated below the top level
- * of a plan tree. This is used during planning to represent the contained
- * expression. At the end of the planning process it is replaced by either
+ * of a plan tree. This is used during planning to represent the contained
+ * expression. At the end of the planning process it is replaced by either
* the contained expression or a Var referring to a lower-level evaluation of
* the contained expression. Typically the evaluation occurs below an outer
* join, and Var references above the outer join might thereby yield NULL
* One-sided outer joins constrain the order of joining partially but not
* completely. We flatten such joins into the planner's top-level list of
* relations to join, but record information about each outer join in a
- * SpecialJoinInfo struct. These structs are kept in the PlannerInfo node's
+ * SpecialJoinInfo struct. These structs are kept in the PlannerInfo node's
* join_info_list.
*
* Similarly, semijoins and antijoins created by flattening IN (subselect)
* For purposes of join selectivity estimation, we create transient
* SpecialJoinInfo structures for regular inner joins; so it is possible
* to have jointype == JOIN_INNER in such a structure, even though this is
- * not allowed within join_info_list. Note that lhs_strict, delay_upper_joins,
- * and join_quals are not set meaningfully for such structs.
+ * not allowed within join_info_list. We also create transient
+ * SpecialJoinInfos with jointype == JOIN_INNER for outer joins, since for
+ * cost estimation purposes it is sometimes useful to know the join size under
+ * plain innerjoin semantics. Note that lhs_strict, delay_upper_joins, and
+ * join_quals are not set meaningfully within such structs.
*/
typedef struct SpecialJoinInfo
Oid parent_reltype; /* OID of parent's composite type */
Oid child_reltype; /* OID of child's composite type */
- /*
- * The N'th element of this list is the integer column number of the child
- * column corresponding to the N'th column of the parent. A list element
- * is zero if it corresponds to a dropped column of the parent (this is
- * only possible for inheritance cases, not UNION ALL).
- */
- List *col_mappings; /* list of child attribute numbers */
-
/*
* The N'th element of this list is a Var or expression representing the
* child column corresponding to the N'th column of the parent. This is
* used to translate Vars referencing the parent rel into references to
* the child. A list element is NULL if it corresponds to a dropped
* column of the parent (this is only possible for inheritance cases, not
- * UNION ALL).
- *
- * This might seem redundant with the col_mappings data, but it is handy
- * because flattening of sub-SELECTs that are members of a UNION ALL will
- * cause changes in the expressions that need to be substituted for a
- * parent Var. Adjusting this data structure lets us track what really
- * needs to be substituted.
+ * UNION ALL). The list elements are always simple Vars for inheritance
+ * cases, but can be arbitrary expressions in UNION ALL cases.
*
* Notice we only store entries for user columns (attno > 0). Whole-row
* Vars are special-cased, and system columns (attno < 0) need no special
* For each distinct placeholder expression generated during planning, we
* store a PlaceHolderInfo node in the PlannerInfo node's placeholder_list.
* This stores info that is needed centrally rather than in each copy of the
- * PlaceHolderVar. The phid fields identify which PlaceHolderInfo goes with
+ * PlaceHolderVar. The phid fields identify which PlaceHolderInfo goes with
* each PlaceHolderVar. Note that phid is unique throughout a planner run,
* not just within a query level --- this is so that we need not reassign ID's
* when pulling a subquery into its parent.
* then allow it to bubble up like a Var until the ph_needed join level.
* ph_needed has the same definition as attr_needed for a regular Var.
*
+ * ph_may_need is an initial estimate of ph_needed, formed using the
+ * syntactic locations of references to the PHV. We need this in order to
+ * determine whether the PHV reference forces a join ordering constraint:
+ * if the PHV has to be evaluated below the nullable side of an outer join,
+ * and then used above that outer join, we must constrain join order to ensure
+ * there's a valid place to evaluate the PHV below the join. The final
+ * actual ph_needed level might be lower than ph_may_need, but we can't
+ * determine that until later on. Fortunately this doesn't matter for what
+ * we need ph_may_need for: if there's a PHV reference syntactically
+ * above the outer join, it's not going to be allowed to drop below the outer
+ * join, so we would come to the same conclusions about join order even if
+ * we had the final ph_needed value to compare to.
+ *
* We create a PlaceHolderInfo only after determining that the PlaceHolderVar
- * is actually referenced in the plan tree.
+ * is actually referenced in the plan tree, so that unreferenced placeholders
+ * don't result in unnecessary constraints on join order.
*/
typedef struct PlaceHolderInfo
PlaceHolderVar *ph_var; /* copy of PlaceHolderVar tree */
Relids ph_eval_at; /* lowest level we can evaluate value at */
Relids ph_needed; /* highest level the value is needed at */
+ Relids ph_may_need; /* highest level it might be needed at */
int32 ph_width; /* estimated attribute width */
} PlaceHolderInfo;
+/*
+ * For each potentially index-optimizable MIN/MAX aggregate function,
+ * root->minmax_aggs stores a MinMaxAggInfo describing it.
+ *
+ * Note: a MIN/MAX agg doesn't really care about the nulls_first property,
+ * so the pathkey's nulls_first flag should be ignored.
+ */
+typedef struct MinMaxAggInfo
+{
+ NodeTag type;
+
+ Oid aggfnoid; /* pg_proc Oid of the aggregate */
+ Oid aggsortop; /* Oid of its sort operator */
+ Expr *target; /* expression we are aggregating on */
+ List *pathkeys; /* pathkeys representing needed sort order */
+} MinMaxAggInfo;
+
/*
* glob->paramlist keeps track of the PARAM_EXEC slots that we have decided
* we need for the query. At runtime these slots are used to pass values
- * either down into subqueries (for outer references in subqueries) or up out
- * of subqueries (for the results of a subplan). The n'th entry in the list
- * (n counts from 0) corresponds to Param->paramid = n.
+ * around from one plan node to another. They can be used to pass values
+ * down into subqueries (for outer references in subqueries), or up out of
+ * subqueries (for the results of a subplan), or from a NestLoop plan node
+ * into its inner relation (when the inner scan is parameterized with values
+ * from the outer relation). The n'th entry in the list (n counts from 0)
+ * corresponds to Param->paramid = n.
*
* Each paramlist item shows the absolute query level it is associated with,
* where the outermost query is level 1 and nested subqueries have higher
* numbers. The item the parameter slot represents can be one of three kinds:
*
* A Var: the slot represents a variable of that level that must be passed
- * down because subqueries have outer references to it. The varlevelsup
+ * down because subqueries have outer references to it, or must be passed
+ * from a NestLoop node of that level to its inner scan. The varlevelsup
* value in the Var will always be zero.
*
* An Aggref (with an expression tree representing its argument): the slot
* to the parent query of the subplan.
*
* Note: we detect duplicate Var parameters and coalesce them into one slot,
- * but we do not do this for Aggref or Param slots.
+ * but we do not bother to do this for Aggrefs, and it would be incorrect
+ * to do so for Param slots. Duplicate detection is actually *necessary*
+ * in the case of NestLoop parameters since it serves to match up the usage
+ * of a Param (in the inner scan) with the assignment of the value (in the
+ * NestLoop node). This might result in the same PARAM_EXEC slot being used
+ * by multiple NestLoop nodes or SubPlan nodes, but no harm is done since
+ * the same value would be assigned anyway.
*/
typedef struct PlannerParamItem
{