relation.h

PostgreSQL 8.1.4的源码 适用于Linux下的开源数据库系统

 * types.  (Note: in the no-op case, we could eliminate the UniquePath node
 * entirely and just return the subpath; but it's convenient to have a
 * UniquePath in the path tree to signal upper-level routines that the input
 * is known distinct.)
 */
typedef enum
{
	UNIQUE_PATH_NOOP,			/* input is known unique already */
	UNIQUE_PATH_HASH,			/* use hashing */
	UNIQUE_PATH_SORT			/* use sorting */
} UniquePathMethod;

typedef struct UniquePath
{
	Path		path;
	Path	   *subpath;
	UniquePathMethod umethod;
	double		rows;			/* estimated number of result tuples */
} UniquePath;

/*
 * All join-type paths share these fields.
 */

typedef struct JoinPath
{
	Path		path;

	JoinType	jointype;

	Path	   *outerjoinpath;	/* path for the outer side of the join */
	Path	   *innerjoinpath;	/* path for the inner side of the join */

	List	   *joinrestrictinfo;		/* RestrictInfos to apply to join */

	/*
	 * See the notes for RelOptInfo to understand why joinrestrictinfo is
	 * needed in JoinPath, and can't be merged into the parent RelOptInfo.
	 */
} JoinPath;

/*
 * A nested-loop path needs no special fields.
 */

typedef JoinPath NestPath;

/*
 * A mergejoin path has these fields.
 *
 * path_mergeclauses lists the clauses (in the form of RestrictInfos)
 * that will be used in the merge.
 *
 * Note that the mergeclauses are a subset of the parent relation's
 * restriction-clause list.  Any join clauses that are not mergejoinable
 * appear only in the parent's restrict list, and must be checked by a
 * qpqual at execution time.
 *
 * 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.
 */

typedef struct MergePath
{
	JoinPath	jpath;
	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 */
} MergePath;

/*
 * A hashjoin path has these fields.
 *
 * The remarks above for mergeclauses apply for hashclauses as well.
 *
 * Hashjoin does not care what order its inputs appear in, so we have
 * no need for sortkeys.
 */

typedef struct HashPath
{
	JoinPath	jpath;
	List	   *path_hashclauses;		/* join clauses used for hashing */
} HashPath;

/*
 * Restriction clause info.
 *
 * We create one of these for each AND sub-clause of a restriction condition
 * (WHERE or JOIN/ON clause).  Since the restriction clauses are logically
 * ANDed, we can use any one of them or any subset of them to filter out
 * tuples, without having to evaluate the rest.  The RestrictInfo node itself
 * stores data used by the optimizer while choosing the best query plan.
 *
 * If a restriction clause references a single base relation, it will appear
 * in the baserestrictinfo list of the RelOptInfo for that base rel.
 *
 * If a restriction clause references more than one base rel, it will
 * appear in the joininfo list of every RelOptInfo that describes a strict
 * subset of the base rels mentioned in the clause.  The joininfo lists are
 * used to drive join tree building by selecting plausible join candidates.
 * The clause cannot actually be applied until we have built a join rel
 * containing all the base rels it references, however.
 *
 * When we construct a join rel that includes all the base rels referenced
 * in a multi-relation restriction clause, we place that clause into the
 * joinrestrictinfo lists of paths for the join rel, if neither left nor
 * right sub-path includes all base rels referenced in the clause.	The clause
 * will be applied at that join level, and will not propagate any further up
 * the join tree.  (Note: the "predicate migration" code was once intended to
 * push restriction clauses up and down the plan tree based on evaluation
 * costs, but it's dead code and is unlikely to be resurrected in the
 * foreseeable future.)
 *
 * Note that in the presence of more than two rels, a multi-rel restriction
 * might reach different heights in the join tree depending on the join
 * sequence we use.  So, these clauses cannot be associated directly with
 * the join RelOptInfo, but must be kept track of on a per-join-path basis.
 *
 * When dealing with outer joins we have to be very careful about pushing qual
 * clauses up and down the tree.  An outer join's own JOIN/ON conditions must
 * be evaluated exactly at that join node, and any quals appearing in WHERE or
 * in a JOIN above the outer join cannot be pushed down below the outer join.
 * Otherwise the outer join will produce wrong results because it will see the
 * wrong sets of input rows.  All quals are stored as RestrictInfo nodes
 * during planning, but there's a flag to indicate whether a qual has been
 * pushed down to a lower level than its original syntactic placement in the
 * join tree would suggest.  If an outer join prevents us from pushing a qual
 * down to its "natural" semantic level (the level associated with just the
 * base rels used in the qual) then we mark the qual with a "required_relids"
 * value including more than just the base rels it actually uses.  By
 * pretending that the qual references all the rels appearing in the outer
 * join, we prevent it from being evaluated below the outer join's joinrel.
 * When we do form the outer join's joinrel, we still need to distinguish
 * those quals that are actually in that join's JOIN/ON condition from those
 * that appeared higher in the tree and were pushed down to the join rel
 * because they used no other rels.  That's what the is_pushed_down flag is
 * for; it tells us that a qual came from a point above the join of the
 * set of base rels listed in required_relids.	A clause that originally came
 * from WHERE will *always* have its is_pushed_down flag set; a clause that
 * came from an INNER JOIN condition, but doesn't use all the rels being
 * joined, will also have is_pushed_down set because it will get attached to
 * some lower joinrel.
 *
 * When application of a qual must be delayed by outer join, we also mark it
 * with outerjoin_delayed = true.  This isn't redundant with required_relids
 * because that might equal clause_relids whether or not it's an outer-join
 * clause.
 *
 * In general, the referenced clause might be arbitrarily complex.	The
 * kinds of clauses we can handle as indexscan quals, mergejoin clauses,
 * or hashjoin clauses are fairly limited --- the code for each kind of
 * path is responsible for identifying the restrict clauses it can use
 * and ignoring the rest.  Clauses not implemented by an indexscan,
 * mergejoin, or hashjoin will be placed in the plan qual or joinqual field
 * of the finished Plan node, where they will be enforced by general-purpose
 * qual-expression-evaluation code.  (But we are still entitled to count
 * their selectivity when estimating the result tuple count, if we
 * can guess what it is...)
 *
 * When the referenced clause is an OR clause, we generate a modified copy
 * in which additional RestrictInfo nodes are inserted below the top-level
 * OR/AND structure.  This is a convenience for OR indexscan processing:
 * indexquals taken from either the top level or an OR subclause will have
 * associated RestrictInfo nodes.
 */

typedef struct RestrictInfo
{
	NodeTag		type;

	Expr	   *clause;			/* the represented clause of WHERE or JOIN */

	bool		is_pushed_down; /* TRUE if clause was pushed down in level */

	bool		outerjoin_delayed;		/* TRUE if delayed by outer join */

	/*
	 * This flag is set true if the clause looks potentially useful as a merge
	 * or hash join clause, that is if it is a binary opclause with
	 * nonoverlapping sets of relids referenced in the left and right sides.
	 * (Whether the operator is actually merge or hash joinable isn't checked,
	 * however.)
	 */
	bool		can_join;

	/* The set of relids (varnos) actually referenced in the clause: */
	Relids		clause_relids;

	/* The set of relids required to evaluate the clause: */
	Relids		required_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 */

	/* This field is NULL unless clause is an OR clause: */
	Expr	   *orclause;		/* modified clause with RestrictInfos */

	/* 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 */

	/* valid if clause is mergejoinable, else InvalidOid: */
	Oid			mergejoinoperator;		/* copy of clause operator */
	Oid			left_sortop;	/* leftside sortop needed for mergejoin */
	Oid			right_sortop;	/* rightside sortop needed for mergejoin */

	/* cache space for mergeclause processing; NIL if not yet set */
	List	   *left_pathkey;	/* canonical pathkey for left side */
	List	   *right_pathkey;	/* canonical pathkey for right side */

	/* cache space for mergeclause processing; -1 if not yet set */
	Selectivity left_mergescansel;		/* fraction of left side to scan */
	Selectivity right_mergescansel;		/* fraction of right side to scan */

	/* valid if clause is hashjoinable, else InvalidOid: */
	Oid			hashjoinoperator;		/* copy of clause operator */

	/* cache space for hashclause processing; -1 if not yet set */
	Selectivity left_bucketsize;	/* avg bucketsize of left side */
	Selectivity right_bucketsize;		/* avg bucketsize of right side */
} RestrictInfo;

/*
 * Inner indexscan info.
 *
 * An inner indexscan is one that uses one or more joinclauses as index
 * conditions (perhaps in addition to plain restriction clauses).  So it
 * can only be used as the inner path of a nestloop join where the outer
 * relation includes all other relids appearing in those joinclauses.
 * The set of usable joinclauses, and thus the best inner indexscan,
 * thus varies depending on which outer relation we consider; so we have
 * to recompute the best such path for every join.	To avoid lots of
 * redundant computation, we cache the results of such searches.  For
 * each relation we compute the set of possible otherrelids (all relids
 * appearing in joinquals that could become indexquals for this table).
 * Two outer relations whose relids have the same intersection with this
 * set will have the same set of available joinclauses and thus the same
 * best inner indexscan for the inner relation.  By taking the intersection
 * before scanning the cache, we avoid recomputing when considering
 * join rels that differ only by the inclusion of irrelevant other rels.
 *
 * The search key also includes a bool showing whether the join being
 * considered is an outer join.  Since we constrain the join order for
 * outer joins, I believe that this bool can only have one possible value
 * for any particular base relation; but store it anyway to avoid confusion.
 */

typedef struct InnerIndexscanInfo
{
	NodeTag		type;
	/* The lookup key: */
	Relids		other_relids;	/* a set of relevant other relids */
	bool		isouterjoin;	/* true if join is outer */
	/* Best path for this lookup key: */
	Path	   *best_innerpath; /* best inner indexscan, or NULL if none */
} InnerIndexscanInfo;

/*
 * IN clause info.
 *
 * When we convert top-level IN quals into join operations, we must restrict
 * the order of joining and use special join methods at some join points.
 * We record information about each such IN clause in an InClauseInfo struct.
 * These structs are kept in the PlannerInfo node's in_info_list.
 */

typedef struct InClauseInfo
{
	NodeTag		type;
	Relids		lefthand;		/* base relids in lefthand expressions */
	Relids		righthand;		/* base relids coming from the subselect */
	List	   *sub_targetlist; /* targetlist of original RHS subquery */

	/*
	 * Note: sub_targetlist is just a list of Vars or expressions; it does not
	 * contain TargetEntry nodes.
	 */
} InClauseInfo;

#endif   /* RELATION_H */