relnode.c

PostgreSQL 8.1.4的源码 适用于Linux下的开源数据库系统

 */
RelOptInfo *
build_join_rel(PlannerInfo *root,
			   Relids joinrelids,
			   RelOptInfo *outer_rel,
			   RelOptInfo *inner_rel,
			   JoinType jointype,
			   List **restrictlist_ptr)
{
	RelOptInfo *joinrel;
	List	   *restrictlist;

	/*
	 * See if we already have a joinrel for this set of base rels.
	 */
	joinrel = find_join_rel(root, joinrelids);

	if (joinrel)
	{
		/*
		 * Yes, so we only need to figure the restrictlist for this particular
		 * pair of component relations.
		 */
		if (restrictlist_ptr)
			*restrictlist_ptr = build_joinrel_restrictlist(root,
														   joinrel,
														   outer_rel,
														   inner_rel,
														   jointype);
		return joinrel;
	}

	/*
	 * Nope, so make one.
	 */
	joinrel = makeNode(RelOptInfo);
	joinrel->reloptkind = RELOPT_JOINREL;
	joinrel->relids = bms_copy(joinrelids);
	joinrel->rows = 0;
	joinrel->width = 0;
	joinrel->reltargetlist = NIL;
	joinrel->pathlist = NIL;
	joinrel->cheapest_startup_path = NULL;
	joinrel->cheapest_total_path = NULL;
	joinrel->cheapest_unique_path = NULL;
	joinrel->relid = 0;			/* indicates not a baserel */
	joinrel->rtekind = RTE_JOIN;
	joinrel->min_attr = 0;
	joinrel->max_attr = 0;
	joinrel->attr_needed = NULL;
	joinrel->attr_widths = NULL;
	joinrel->indexlist = NIL;
	joinrel->pages = 0;
	joinrel->tuples = 0;
	joinrel->subplan = NULL;
	joinrel->baserestrictinfo = NIL;
	joinrel->baserestrictcost.startup = 0;
	joinrel->baserestrictcost.per_tuple = 0;
	joinrel->outerjoinset = NULL;
	joinrel->joininfo = NIL;
	joinrel->index_outer_relids = NULL;
	joinrel->index_inner_paths = NIL;

	/*
	 * Create a new tlist containing just the vars that need to be output from
	 * this join (ie, are needed for higher joinclauses or final output).
	 *
	 * NOTE: the tlist order for a join rel will depend on which pair of outer
	 * and inner rels we first try to build it from.  But the contents should
	 * be the same regardless.
	 */
	build_joinrel_tlist(root, joinrel, outer_rel);
	build_joinrel_tlist(root, joinrel, inner_rel);

	/*
	 * Construct restrict and join clause lists for the new joinrel. (The
	 * caller might or might not need the restrictlist, but I need it anyway
	 * for set_joinrel_size_estimates().)
	 */
	restrictlist = build_joinrel_restrictlist(root,
											  joinrel,
											  outer_rel,
											  inner_rel,
											  jointype);
	if (restrictlist_ptr)
		*restrictlist_ptr = restrictlist;
	build_joinrel_joinlist(joinrel, outer_rel, inner_rel);

	/*
	 * Set estimates of the joinrel's size.
	 */
	set_joinrel_size_estimates(root, joinrel, outer_rel, inner_rel,
							   jointype, restrictlist);

	/*
	 * Add the joinrel to the query's joinrel list, and store it into the
	 * auxiliary hashtable if there is one.  NB: GEQO requires us to append
	 * the new joinrel to the end of the list!
	 */
	root->join_rel_list = lappend(root->join_rel_list, joinrel);

	if (root->join_rel_hash)
	{
		JoinHashEntry *hentry;
		bool		found;

		hentry = (JoinHashEntry *) hash_search(root->join_rel_hash,
											   &(joinrel->relids),
											   HASH_ENTER,
											   &found);
		Assert(!found);
		hentry->join_rel = joinrel;
	}

	return joinrel;
}

/*
 * build_joinrel_tlist
 *	  Builds a join relation's target list.
 *
 * The join's targetlist includes all Vars of its member relations that
 * will still be needed above the join.  This subroutine adds all such
 * Vars from the specified input rel's tlist to the join rel's tlist.
 *
 * We also compute the expected width of the join's output, making use
 * of data that was cached at the baserel level by set_rel_width().
 */
static void
build_joinrel_tlist(PlannerInfo *root, RelOptInfo *joinrel,
					RelOptInfo *input_rel)
{
	Relids		relids = joinrel->relids;
	ListCell   *vars;

	foreach(vars, input_rel->reltargetlist)
	{
		Var		   *var = (Var *) lfirst(vars);
		RelOptInfo *baserel;
		int			ndx;

		/* We can't run into any child RowExprs here */
		Assert(IsA(var, Var));

		/* Get the Var's original base rel */
		baserel = find_base_rel(root, var->varno);

		/* Is it still needed above this joinrel? */
		ndx = var->varattno - baserel->min_attr;
		if (bms_nonempty_difference(baserel->attr_needed[ndx], relids))
		{
			/* Yup, add it to the output */
			joinrel->reltargetlist = lappend(joinrel->reltargetlist, var);
			Assert(baserel->attr_widths[ndx] > 0);
			joinrel->width += baserel->attr_widths[ndx];
		}
	}
}

/*
 * build_joinrel_restrictlist
 * build_joinrel_joinlist
 *	  These routines build lists of restriction and join clauses for a
 *	  join relation from the joininfo lists of the relations it joins.
 *
 *	  These routines are separate because the restriction list must be
 *	  built afresh for each pair of input sub-relations we consider, whereas
 *	  the join list need only be computed once for any join RelOptInfo.
 *	  The join list is fully determined by the set of rels making up the
 *	  joinrel, so we should get the same results (up to ordering) from any
 *	  candidate pair of sub-relations.	But the restriction list is whatever
 *	  is not handled in the sub-relations, so it depends on which
 *	  sub-relations are considered.
 *
 *	  If a join clause from an input relation refers to base rels still not
 *	  present in the joinrel, then it is still a join clause for the joinrel;
 *	  we put it into the joininfo list for the joinrel.  Otherwise,
 *	  the clause is now a restrict clause for the joined relation, and we
 *	  return it to the caller of build_joinrel_restrictlist() to be stored in
 *	  join paths made from this pair of sub-relations.	(It will not need to
 *	  be considered further up the join tree.)
 *
 *	  When building a restriction list, we eliminate redundant clauses.
 *	  We don't try to do that for join clause lists, since the join clauses
 *	  aren't really doing anything, just waiting to become part of higher
 *	  levels' restriction lists.
 *
 * 'joinrel' is a join relation node
 * 'outer_rel' and 'inner_rel' are a pair of relations that can be joined
 *		to form joinrel.
 * 'jointype' is the type of join used.
 *
 * build_joinrel_restrictlist() returns a list of relevant restrictinfos,
 * whereas build_joinrel_joinlist() stores its results in the joinrel's
 * joininfo list.  One or the other must accept each given clause!
 *
 * NB: Formerly, we made deep(!) copies of each input RestrictInfo to pass
 * up to the join relation.  I believe this is no longer necessary, because
 * RestrictInfo nodes are no longer context-dependent.	Instead, just include
 * the original nodes in the lists made for the join relation.
 */
static List *
build_joinrel_restrictlist(PlannerInfo *root,
						   RelOptInfo *joinrel,
						   RelOptInfo *outer_rel,
						   RelOptInfo *inner_rel,
						   JoinType jointype)
{
	List	   *result;
	List	   *rlist;

	/*
	 * Collect all the clauses that syntactically belong at this level.
	 */
	rlist = list_concat(subbuild_joinrel_restrictlist(joinrel,
													  outer_rel->joininfo),
						subbuild_joinrel_restrictlist(joinrel,
													  inner_rel->joininfo));

	/*
	 * Eliminate duplicate and redundant clauses.
	 *
	 * We must eliminate duplicates, since we will see many of the same
	 * clauses arriving from both input relations.	Also, if a clause is a
	 * mergejoinable clause, it's possible that it is redundant with previous
	 * clauses (see optimizer/README for discussion).  We detect that case and
	 * omit the redundant clause from the result list.
	 */
	result = remove_redundant_join_clauses(root, rlist,
										   IS_OUTER_JOIN(jointype));

	list_free(rlist);

	return result;
}

static void
build_joinrel_joinlist(RelOptInfo *joinrel,
					   RelOptInfo *outer_rel,
					   RelOptInfo *inner_rel)
{
	subbuild_joinrel_joinlist(joinrel, outer_rel->joininfo);
	subbuild_joinrel_joinlist(joinrel, inner_rel->joininfo);
}

static List *
subbuild_joinrel_restrictlist(RelOptInfo *joinrel,
							  List *joininfo_list)
{
	List	   *restrictlist = NIL;
	ListCell   *l;

	foreach(l, joininfo_list)
	{
		RestrictInfo *rinfo = (RestrictInfo *) lfirst(l);

		if (bms_is_subset(rinfo->required_relids, joinrel->relids))
		{
			/*
			 * This clause becomes a restriction clause for the joinrel, since
			 * it refers to no outside rels.  We don't bother to check for
			 * duplicates here --- build_joinrel_restrictlist will do that.
			 */
			restrictlist = lappend(restrictlist, rinfo);
		}
		else
		{
			/*
			 * This clause is still a join clause at this level, so we ignore
			 * it in this routine.
			 */
		}
	}

	return restrictlist;
}

static void
subbuild_joinrel_joinlist(RelOptInfo *joinrel,
						  List *joininfo_list)
{
	ListCell   *l;

	foreach(l, joininfo_list)
	{
		RestrictInfo *rinfo = (RestrictInfo *) lfirst(l);

		if (bms_is_subset(rinfo->required_relids, joinrel->relids))
		{
			/*
			 * This clause becomes a restriction clause for the joinrel, since
			 * it refers to no outside rels.  So we can ignore it in this
			 * routine.
			 */
		}
		else
		{
			/*
			 * This clause is still a join clause at this level, so add it to
			 * the joininfo list for the joinrel, being careful to eliminate
			 * duplicates.	(Since RestrictInfo nodes are normally
			 * multiply-linked rather than copied, pointer equality should be
			 * a sufficient test.  If two equal() nodes should happen to sneak
			 * in, no great harm is done --- they'll be detected by
			 * redundant-clause testing when they reach a restriction list.)
			 */
			joinrel->joininfo = list_append_unique_ptr(joinrel->joininfo,
													   rinfo);
		}
	}
}