From 27cdb17454507604f87c8362c4d4e48f5d879f35 Mon Sep 17 00:00:00 2001
From: Richard Guo <guofenglinux@gmail.com>
Date: Wed, 30 Jun 2021 10:39:36 +0800
Subject: [PATCH] Using each rel as both outer and inner for anti joins

---
 src/backend/commands/explain.c        | 3 +++
 src/backend/executor/nodeHashjoin.c   | 9 +++++++++
 src/backend/optimizer/path/joinpath.c | 7 +++++++
 src/backend/optimizer/path/joinrels.c | 3 +++
 src/backend/optimizer/plan/setrefs.c  | 1 +
 src/include/nodes/nodes.h             | 4 +++-
 6 files changed, 26 insertions(+), 1 deletion(-)

diff --git a/src/backend/commands/explain.c b/src/backend/commands/explain.c
index e81b990092..a9f6ebf1f3 100644
--- a/src/backend/commands/explain.c
+++ b/src/backend/commands/explain.c
@@ -1517,6 +1517,9 @@ ExplainNode(PlanState *planstate, List *ancestors,
 					case JOIN_ANTI:
 						jointype = "Anti";
 						break;
+					case JOIN_RIGHT_ANTI:
+						jointype = "Right Anti";
+						break;
 					default:
 						jointype = "???";
 						break;
diff --git a/src/backend/executor/nodeHashjoin.c b/src/backend/executor/nodeHashjoin.c
index 510bdd39ad..6592a81de3 100644
--- a/src/backend/executor/nodeHashjoin.c
+++ b/src/backend/executor/nodeHashjoin.c
@@ -482,6 +482,14 @@ ExecHashJoinImpl(PlanState *pstate, bool parallel)
 						continue;
 					}
 
+					/*
+					 * In a right-antijoin, we never return a matched tuple.
+					 * And we need to use current outer tuple to scan the
+					 * bucket for matches
+					 */
+					if (node->js.jointype == JOIN_RIGHT_ANTI)
+						continue;
+
 					/*
 					 * If we only need to join to the first matching inner
 					 * tuple, then consider returning this one, but after that
@@ -694,6 +702,7 @@ ExecInitHashJoin(HashJoin *node, EState *estate, int eflags)
 				ExecInitNullTupleSlot(estate, innerDesc, &TTSOpsVirtual);
 			break;
 		case JOIN_RIGHT:
+		case JOIN_RIGHT_ANTI:
 			hjstate->hj_NullOuterTupleSlot =
 				ExecInitNullTupleSlot(estate, outerDesc, &TTSOpsVirtual);
 			break;
diff --git a/src/backend/optimizer/path/joinpath.c b/src/backend/optimizer/path/joinpath.c
index b67b517770..e91293ff54 100644
--- a/src/backend/optimizer/path/joinpath.c
+++ b/src/backend/optimizer/path/joinpath.c
@@ -1110,6 +1110,9 @@ sort_inner_and_outer(PlannerInfo *root,
 	List	   *all_pathkeys;
 	ListCell   *l;
 
+	if (jointype == JOIN_RIGHT_ANTI)
+		return;
+
 	/*
 	 * We only consider the cheapest-total-cost input paths, since we are
 	 * assuming here that a sort is required.  We will consider
@@ -1559,6 +1562,9 @@ match_unsorted_outer(PlannerInfo *root,
 	Path	   *matpath = NULL;
 	ListCell   *lc1;
 
+	if (jointype == JOIN_RIGHT_ANTI)
+		return;
+
 	/*
 	 * Nestloop only supports inner, left, semi, and anti joins.  Also, if we
 	 * are doing a right or full mergejoin, we must use *all* the mergeclauses
@@ -2100,6 +2106,7 @@ hash_inner_and_outer(PlannerInfo *root,
 			save_jointype != JOIN_UNIQUE_OUTER &&
 			save_jointype != JOIN_FULL &&
 			save_jointype != JOIN_RIGHT &&
+			save_jointype != JOIN_RIGHT_ANTI &&
 			outerrel->partial_pathlist != NIL &&
 			bms_is_empty(joinrel->lateral_relids))
 		{
diff --git a/src/backend/optimizer/path/joinrels.c b/src/backend/optimizer/path/joinrels.c
index 0dbe2ac726..194f820c2f 100644
--- a/src/backend/optimizer/path/joinrels.c
+++ b/src/backend/optimizer/path/joinrels.c
@@ -915,6 +915,9 @@ populate_joinrel_with_paths(PlannerInfo *root, RelOptInfo *rel1,
 			add_paths_to_joinrel(root, joinrel, rel1, rel2,
 								 JOIN_ANTI, sjinfo,
 								 restrictlist);
+			add_paths_to_joinrel(root, joinrel, rel2, rel1,
+								 JOIN_RIGHT_ANTI, sjinfo,
+								 restrictlist);
 			break;
 		default:
 			/* other values not expected here */
diff --git a/src/backend/optimizer/plan/setrefs.c b/src/backend/optimizer/plan/setrefs.c
index 61ccfd300b..56fc238b0e 100644
--- a/src/backend/optimizer/plan/setrefs.c
+++ b/src/backend/optimizer/plan/setrefs.c
@@ -2069,6 +2069,7 @@ set_join_references(PlannerInfo *root, Join *join, int rtoffset)
 			inner_itlist->has_non_vars = false;
 			break;
 		case JOIN_RIGHT:
+		case JOIN_RIGHT_ANTI:
 			outer_itlist->has_non_vars = false;
 			break;
 		case JOIN_FULL:
diff --git a/src/include/nodes/nodes.h b/src/include/nodes/nodes.h
index d9e417bcd7..7c07792e56 100644
--- a/src/include/nodes/nodes.h
+++ b/src/include/nodes/nodes.h
@@ -725,6 +725,7 @@ typedef enum JoinType
 	 */
 	JOIN_SEMI,					/* 1 copy of each LHS row that has match(es) */
 	JOIN_ANTI,					/* 1 copy of each LHS row that has no match */
+	JOIN_RIGHT_ANTI,			/* 1 copy of each RHS row that has no match */
 
 	/*
 	 * These codes are used internally in the planner, but are not supported
@@ -757,7 +758,8 @@ typedef enum JoinType
 	  ((1 << JOIN_LEFT) | \
 	   (1 << JOIN_FULL) | \
 	   (1 << JOIN_RIGHT) | \
-	   (1 << JOIN_ANTI))) != 0)
+	   (1 << JOIN_ANTI) | \
+	   (1 << JOIN_RIGHT_ANTI))) != 0)
 
 /*
  * AggStrategy -
-- 
2.31.0