Function create_unique_path

src/backend/optimizer/util/pathnode.c:2334–2632

* create_unique_path * Creates a path representing elimination of distinct rows from the * input data. Distinct-ness is defined according to the needs of the * semijoin represented by sjinfo. If it is not possible to identify * how to make the data unique, NULL is returned. * * If used at all, this is likely to be called repeatedly on the same rel; * and the input subpath should a

 * for the rel).  So we cache the result.
 */
UniquePath *
create_unique_path(PlannerInfo *root, RelOptInfo *rel, Path *subpath,
				   SpecialJoinInfo *sjinfo)
{
	UniquePath *pathnode;
	Path		sort_path;		/* dummy for result of cost_sort */
	Path		agg_path;		/* dummy for result of cost_agg */
	MemoryContext oldcontext;
	int			numCols;
	CdbPathLocus locus;
	bool		add_motion = false;
	double		numsegments;

	/* Caller made a mistake if subpath isn't cheapest_total ... */
	Assert(subpath == rel->cheapest_total_path);
	Assert(subpath->parent == rel);
	/* ... or if SpecialJoinInfo is the wrong one */
	Assert(sjinfo->jointype == JOIN_SEMI);
	Assert(bms_equal(rel->relids, sjinfo->syn_righthand));

	/* If result already cached, return it */
	if (rel->cheapest_unique_path)
		return (UniquePath *) rel->cheapest_unique_path;

	/* If it's not possible to unique-ify, return NULL */
	if (!(sjinfo->semi_can_btree || sjinfo->semi_can_hash))
		return NULL;

	/*
	 * When called during GEQO join planning, we are in a short-lived memory
	 * context.  We must make sure that the path and any subsidiary data
	 * structures created for a baserel survive the GEQO cycle, else the
	 * baserel is trashed for future GEQO cycles.  On the other hand, when we
	 * are creating those for a joinrel during GEQO, we don't want them to
	 * clutter the main planning context.  Upshot is that the best solution is
	 * to explicitly allocate memory in the same context the given RelOptInfo
	 * is in.
	 */
	oldcontext = MemoryContextSwitchTo(GetMemoryChunkContext(rel));

	/* Repartition first if duplicates might be on different QEs. */
	if (!CdbPathLocus_IsBottleneck(subpath->locus) &&
		!cdbpathlocus_is_hashed_on_exprs(subpath->locus, sjinfo->semi_rhs_exprs, false))
	{
		int			numsegments = CdbPathLocus_NumSegments(subpath->locus);

		List	   *opfamilies = NIL;
		List	   *sortrefs = NIL;
		ListCell   *lc;

		foreach(lc, sjinfo->semi_rhs_exprs)
		{
			Node	   *expr = lfirst(lc);
			Oid			opfamily;

			opfamily = cdb_default_distribution_opfamily_for_type(exprType(expr));
			opfamilies = lappend_oid(opfamilies, opfamily);
			sortrefs = lappend_int(sortrefs, 0);