relation.h

PostgreSQL 8.2中增加了很多企业用户所需要的功能和性能上的提高,其开发团队说,该版本将加速更多企业向该数据库移植.核心开发成员之一Bruce Momjian表示,在新版PostgreSQL

/*-------------------------------------------------------------------------
 *
 * relation.h
 *	  Definitions for planner's internal data structures.
 *
 *
 * Portions Copyright (c) 1996-2006, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 * $PostgreSQL: pgsql/src/include/nodes/relation.h,v 1.128.2.4 2007/08/31 01:44:14 tgl Exp $
 *
 *-------------------------------------------------------------------------
 */
#ifndef RELATION_H
#define RELATION_H

#include "access/sdir.h"
#include "nodes/bitmapset.h"
#include "nodes/parsenodes.h"
#include "storage/block.h"


/*
 * Relids
 *		Set of relation identifiers (indexes into the rangetable).
 */
typedef Bitmapset *Relids;

/*
 * When looking for a "cheapest path", this enum specifies whether we want
 * cheapest startup cost or cheapest total cost.
 */
typedef enum CostSelector
{
	STARTUP_COST, TOTAL_COST
} CostSelector;

/*
 * The cost estimate produced by cost_qual_eval() includes both a one-time
 * (startup) cost, and a per-tuple cost.
 */
typedef struct QualCost
{
	Cost		startup;		/* one-time cost */
	Cost		per_tuple;		/* per-evaluation cost */
} QualCost;


/*----------
 * PlannerInfo
 *		Per-query information for planning/optimization
 *
 * This struct is conventionally called "root" in all the planner routines.
 * It holds links to all of the planner's working state, in addition to the
 * original Query.	Note that at present the planner extensively modifies
 * the passed-in Query data structure; someday that should stop.
 *----------
 */
typedef struct PlannerInfo
{
	NodeTag		type;

	Query	   *parse;			/* the Query being planned */

	/*
	 * simple_rel_array holds pointers to "base rels" and "other rels" (see
	 * comments for RelOptInfo for more info).	It is indexed by rangetable
	 * index (so entry 0 is always wasted).  Entries can be NULL when an RTE
	 * does not correspond to a base relation, such as a join RTE or an
	 * unreferenced view RTE; or if the RelOptInfo hasn't been made yet.
	 */
	struct RelOptInfo **simple_rel_array;		/* All 1-relation RelOptInfos */
	int			simple_rel_array_size;	/* allocated size of array */

	/*
	 * join_rel_list is a list of all join-relation RelOptInfos we have
	 * considered in this planning run.  For small problems we just scan the
	 * list to do lookups, but when there are many join relations we build a
	 * hash table for faster lookups.  The hash table is present and valid
	 * when join_rel_hash is not NULL.	Note that we still maintain the list
	 * even when using the hash table for lookups; this simplifies life for
	 * GEQO.
	 */
	List	   *join_rel_list;	/* list of join-relation RelOptInfos */
	struct HTAB *join_rel_hash; /* optional hashtable for join relations */

	List	   *equi_key_list;	/* list of lists of equijoined PathKeyItems */

	List	   *left_join_clauses;		/* list of RestrictInfos for outer
										 * join clauses w/nonnullable var on
										 * left */

	List	   *right_join_clauses;		/* list of RestrictInfos for outer
										 * join clauses w/nonnullable var on
										 * right */

	List	   *full_join_clauses;		/* list of RestrictInfos for full
										 * outer join clauses */

	List	   *oj_info_list;	/* list of OuterJoinInfos */

	List	   *in_info_list;	/* list of InClauseInfos */

	List	   *append_rel_list;	/* list of AppendRelInfos */

	List	   *query_pathkeys; /* desired pathkeys for query_planner(), and
								 * actual pathkeys afterwards */

	List	   *group_pathkeys; /* groupClause pathkeys, if any */
	List	   *sort_pathkeys;	/* sortClause pathkeys, if any */

	double		total_table_pages;		/* # of pages in all tables of query */

	double		tuple_fraction; /* tuple_fraction passed to query_planner */

	bool		hasJoinRTEs;	/* true if any RTEs are RTE_JOIN kind */
	bool		hasOuterJoins;	/* true if any RTEs are outer joins */
	bool		hasHavingQual;	/* true if havingQual was non-null */
	bool		hasPseudoConstantQuals; /* true if any RestrictInfo has
										 * pseudoconstant = true */
} PlannerInfo;


/*----------
 * RelOptInfo
 *		Per-relation information for planning/optimization
 *
 * For planning purposes, a "base rel" is either a plain relation (a table)
 * or the output of a sub-SELECT or function that appears in the range table.
 * In either case it is uniquely identified by an RT index.  A "joinrel"
 * is the joining of two or more base rels.  A joinrel is identified by
 * the set of RT indexes for its component baserels.  We create RelOptInfo
 * nodes for each baserel and joinrel, and store them in the PlannerInfo's
 * simple_rel_array and join_rel_list respectively.
 *
 * Note that there is only one joinrel for any given set of component
 * baserels, no matter what order we assemble them in; so an unordered
 * set is the right datatype to identify it with.
 *
 * 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.
 *
 * 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.
 * An append relation has a parent RTE that is a base rel, which represents
 * 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.)
 *
 * 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
 * alias Vars are expanded to non-aliased form during preprocess_expression.
 *
 * Parts of this data structure are specific to various scan and join
 * mechanisms.	It didn't seem worth creating new node types for them.
 *
 *		relids - Set of base-relation identifiers; it is a base relation
 *				if there is just one, a join relation if more than one
 *		rows - estimated number of tuples in the relation after restriction
 *			   clauses have been applied (ie, output rows of a plan for it)
 *		width - avg. number of bytes per tuple in the relation after the
 *				appropriate projections have been done (ie, output width)
 *		reltargetlist - List of Var nodes for the attributes we need to
 *						output from this relation (in no particular order)
 *						NOTE: in a child relation, may contain RowExprs
 *		pathlist - List of Path nodes, one for each potentially useful
 *				   method of generating the relation
 *		cheapest_startup_path - the pathlist member with lowest startup cost
 *								(regardless of its ordering)
 *		cheapest_total_path - the pathlist member with lowest total cost
 *							  (regardless of its ordering)
 *		cheapest_unique_path - for caching cheapest path to produce unique
 *							   (no duplicates) output from relation
 *
 * If the relation is a base relation it will have these fields set:
 *
 *		relid - RTE index (this is redundant with the relids field, but
 *				is provided for convenience of access)
 *		rtekind - distinguishes plain relation, subquery, or function RTE
 *		min_attr, max_attr - range of valid AttrNumbers for rel
 *		attr_needed - array of bitmapsets indicating the highest joinrel
 *				in which each attribute is needed; if bit 0 is set then
 *				the attribute is needed as part of final targetlist
 *		attr_widths - cache space for per-attribute width estimates;
 *					  zero means not computed yet
 *		indexlist - list of IndexOptInfo nodes for relation's indexes
 *					(always NIL if it's not a table)
 *		pages - number of disk pages in relation (zero if not a table)
 *		tuples - number of tuples in relation (not considering restrictions)
 *		subplan - plan for subquery (NULL 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
 *		set_base_rel_pathlist processes the object.
 *
 *		For otherrels that are appendrel members, these fields are filled
 *		in just as for a baserel.
 *
 * The presence of the remaining fields depends on the restrictions
 * and joins that the relation participates in:
 *
 *		baserestrictinfo - List of RestrictInfo nodes, containing info about
 *					each non-join qualification clause in which this relation
 *					participates (only used for base rels)
 *		baserestrictcost - Estimated cost of evaluating the baserestrictinfo
 *					clauses at a single tuple (only used for base rels)
 *		joininfo  - List of RestrictInfo nodes, containing info about each
 *					join clause in which this relation participates
 *		index_outer_relids - only used for base rels; set of outer relids
 *					that participate in indexable joinclauses for this rel
 *		index_inner_paths - only used for base rels; list of InnerIndexscanInfo
 *					nodes showing best indexpaths for various subsets of
 *					index_outer_relids.
 *
 * Note: Keeping a restrictinfo list in the RelOptInfo is useful only for
 * base rels, because for a join rel the set of clauses that are treated as
 * restrict clauses varies depending on which sub-relations we choose to join.
 * (For example, in a 3-base-rel join, a clause relating rels 1 and 2 must be
 * treated as a restrictclause if we join {1} and {2 3} to make {1 2 3}; but
 * if we join {1 2} and {3} then that clause will be a restrictclause in {1 2}
 * and should not be processed again at the level of {1 2 3}.)	Therefore,
 * the restrictinfo list in the join case appears in individual JoinPaths
 * (field joinrestrictinfo), not in the parent relation.  But it's OK for
 * the RelOptInfo to store the joininfo list, because that is the same
 * for a given rel no matter how we form it.
 *
 * We store baserestrictcost in the RelOptInfo (for base relations) because
 * we know we will need it at least once (to price the sequential scan)
 * and may need it multiple times to price index scans.
 *----------
 */
typedef enum RelOptKind
{
	RELOPT_BASEREL,
	RELOPT_JOINREL,
	RELOPT_OTHER_MEMBER_REL
} RelOptKind;

typedef struct RelOptInfo
{
	NodeTag		type;

	RelOptKind	reloptkind;

	/* all relations included in this RelOptInfo */
	Relids		relids;			/* set of base relids (rangetable indexes) */

	/* size estimates generated by planner */
	double		rows;			/* estimated number of result tuples */
	int			width;			/* estimated avg width of result tuples */

	/* materialization information */
	List	   *reltargetlist;	/* needed Vars */
	List	   *pathlist;		/* Path structures */
	struct Path *cheapest_startup_path;
	struct Path *cheapest_total_path;
	struct Path *cheapest_unique_path;

	/* information about a base rel (not set for join rels!) */
	Index		relid;
	RTEKind		rtekind;		/* RELATION, SUBQUERY, or FUNCTION */
	AttrNumber	min_attr;		/* smallest attrno of rel (often <0) */
	AttrNumber	max_attr;		/* largest attrno of rel */
	Relids	   *attr_needed;	/* array indexed [min_attr .. max_attr] */
	int32	   *attr_widths;	/* array indexed [min_attr .. max_attr] */
	List	   *indexlist;
	BlockNumber pages;
	double		tuples;
	struct Plan *subplan;		/* if subquery */

	/* used by various scans and joins: */
	List	   *baserestrictinfo;		/* RestrictInfo structures (if base
										 * rel) */
	QualCost	baserestrictcost;		/* cost of evaluating the above */
	List	   *joininfo;		/* RestrictInfo structures for join clauses
								 * involving this rel */

	/* cached info about inner indexscan paths for relation: */
	Relids		index_outer_relids;		/* other relids in indexable join
										 * clauses */
	List	   *index_inner_paths;		/* InnerIndexscanInfo nodes */

	/*
	 * Inner indexscans are not in the main pathlist because they are not
	 * usable except in specific join contexts.  We use the index_inner_paths
	 * list just to avoid recomputing the best inner indexscan repeatedly for
	 * similar outer relations.  See comments for InnerIndexscanInfo.
	 */
} RelOptInfo;

/*
 * IndexOptInfo
 *		Per-index information for planning/optimization
 *
 *		Prior to Postgres 7.0, RelOptInfo was used to describe both relations
 *		and indexes, but that created confusion without actually doing anything
 *		useful.  So now we have a separate IndexOptInfo struct for indexes.
 *
 *		classlist[], indexkeys[], and ordering[] have ncolumns entries.
 *		Zeroes in the indexkeys[] array indicate index columns that are
 *		expressions; there is one element in indexprs for each such column.
 *
 *		Note: for historical reasons, the classlist and ordering arrays have
 *		an extra entry that is always zero.  Some code scans until it sees a
 *		zero entry, rather than looking at ncolumns.
 *
 *		The indexprs and indpred expressions have been run through
 *		prepqual.c and eval_const_expressions() for ease of matching to
 *		WHERE clauses.	indpred is in implicit-AND form.
 */

typedef struct IndexOptInfo
{
	NodeTag		type;

	Oid			indexoid;		/* OID of the index relation */
	RelOptInfo *rel;			/* back-link to index's table */

	/* statistics from pg_class */
	BlockNumber pages;			/* number of disk pages in index */
	double		tuples;			/* number of index tuples in index */

	/* index descriptor information */
	int			ncolumns;		/* number of columns in index */
	Oid		   *classlist;		/* OIDs of operator classes for columns */
	int		   *indexkeys;		/* column numbers of index's keys, or 0 */
	Oid		   *ordering;		/* OIDs of sort operators for each column */
	Oid			relam;			/* OID of the access method (in pg_am) */

	RegProcedure amcostestimate;	/* OID of the access method's cost fcn */