planner: don't choose merge join unless there's hint or join key fully matched (pingcap#59936) (pingcap#59946)

close pingcap#20710

Author: ti-chi-bot

pkg/planner/core/exhaust_physical_plans.go

@@ -183,7 +183,8 @@ func (p *LogicalJoin) GetMergeJoin(prop *property.PhysicalProperty, schema *expr
 		offsets := getMaxSortPrefix(lhsChildProperty, leftJoinKeys)
 		// If not all equal conditions hit properties. We ban merge join heuristically. Because in this case, merge join
 		// may get a very low performance. In executor, executes join results before other conditions filter it.
-		if len(offsets) < len(leftJoinKeys) {
+		// And skip the cartesian join case, unless we force to use merge join.
+		if len(offsets) < len(leftJoinKeys) || len(leftJoinKeys) == 0 {
 			continue
 		}
 
@@ -195,7 +196,8 @@ func (p *LogicalJoin) GetMergeJoin(prop *property.PhysicalProperty, schema *expr
 		}
 
 		prefixLen := findMaxPrefixLen(p.rightProperties, rightKeys)
-		if prefixLen == 0 {
+		// right side should also be full match.
+		if prefixLen < len(offsets) || prefixLen == 0 {
 			continue
 		}
 

tests/integrationtest/r/planner/core/issuetest/planner_issue.result

@@ -619,3 +619,26 @@ NULL	NULL	2	2	4	2
 show warnings;
 Level	Code	Message
 drop table if exists t1, t2, t3, t4;
+drop table if exists t1, t2;
+create table t1(a int, b int, index idx(a, b));
+create table t2(a int, b int, index idx(a));
+explain select /*+ merge_join(t1) */ * from t1 join t2 on t1.a=t2.a and t2.b=t1.b;
+id	estRows	task	access object	operator info
+MergeJoin_8	12475.01	root		inner join, left key:test.t1.a, test.t1.b, right key:test.t2.a, test.t2.b
+├─Sort_19(Build)	9980.01	root		test.t2.a, test.t2.b
+│ └─TableReader_14	9980.01	root		data:Selection_13
+│   └─Selection_13	9980.01	cop[tikv]		not(isnull(test.t2.a)), not(isnull(test.t2.b))
+│     └─TableFullScan_12	10000.00	cop[tikv]	table:t2	keep order:false, stats:pseudo
+└─IndexReader_11(Probe)	9980.01	root		index:Selection_10
+  └─Selection_10	9980.01	cop[tikv]		not(isnull(test.t1.b))
+    └─IndexFullScan_9	9990.00	cop[tikv]	table:t1, index:idx(a, b)	keep order:true, stats:pseudo
+explain select /*+ no_hash_join(t1), no_index_join(t1,t2), no_index_hash_join(t1,t2) */ * from t1 join t2 on t1.a=t2.a and t2.b=t1.b;
+id	estRows	task	access object	operator info
+MergeJoin_8	12475.01	root		inner join, left key:test.t1.a, test.t1.b, right key:test.t2.a, test.t2.b
+├─Sort_47(Build)	9980.01	root		test.t2.a, test.t2.b
+│ └─TableReader_42	9980.01	root		data:Selection_41
+│   └─Selection_41	9980.01	cop[tikv]		not(isnull(test.t2.a)), not(isnull(test.t2.b))
+│     └─TableFullScan_40	10000.00	cop[tikv]	table:t2	keep order:false, stats:pseudo
+└─IndexReader_39(Probe)	9980.01	root		index:Selection_38
+  └─Selection_38	9980.01	cop[tikv]		not(isnull(test.t1.b))
+    └─IndexFullScan_37	9990.00	cop[tikv]	table:t1, index:idx(a, b)	keep order:true, stats:pseudo

tests/integrationtest/t/planner/core/issuetest/planner_issue.test

@@ -478,3 +478,10 @@ SELECT t2.a,t2.b,t3.a,t3.b,t4.a,t4.b
        ON t3.a=1 AND t3.b=t2.b AND t2.b=t4.b order by 1, 2, 3, 4, 5;
 show warnings;
 drop table if exists t1, t2, t3, t4;
+
+# TestIssue20710
+drop table if exists t1, t2;
+create table t1(a int, b int, index idx(a, b));
+create table t2(a int, b int, index idx(a));
+explain select /*+ merge_join(t1) */ * from t1 join t2 on t1.a=t2.a and t2.b=t1.b;
+explain select /*+ no_hash_join(t1), no_index_join(t1,t2), no_index_hash_join(t1,t2) */ * from t1 join t2 on t1.a=t2.a and t2.b=t1.b;