Retry simplify until a RexNode is simplified completely, upto a max of 5

tries. This can be removed after upgrading to Calcite 1.38 https://issues.apache.org/jira/browse/CALCITE-6453
apache · Jul 23, 2024 · 298d298 · 298d298
1 parent da97bce
commit 298d298
Show file tree

Hide file tree

Showing 3 changed files with 15 additions and 4 deletions.
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/HiveCalciteUtil.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/HiveCalciteUtil.java
@@ -660,7 +660,7 @@ public static ImmutableList<RexNode> getPredsNotPushedAlready(Set<String> predic
     Map<String,RexNode> stringToRexNode = Maps.newLinkedHashMap();
     RexSimplify simplify = new RexSimplify(inp.getCluster().getRexBuilder(), RelOptPredicateList.EMPTY, RexUtil.EXECUTOR);
     for (RexNode r : predsToPushDown) {
-      r = simplify.simplify(r);
+      r = simplify(simplify, r);
       String rexNodeString = r.toString();
       if (predicatesToExclude.add(rexNodeString)) {
         stringToRexNode.put(rexNodeString, r);
@@ -687,6 +687,20 @@ public static ImmutableList<RexNode> getPredsNotPushedAlready(Set<String> predic
     predicatesToExclude.addAll(predicatesInSubtree);
     return newConjuncts.build();
   }
+
+  private static RexNode simplify(RexSimplify simplifier, RexNode node) {
+    RexNode result = node;
+    int maxTries = 5;
+    for (int i = 0; i < maxTries; i++) {
+      RexNode simplified = simplifier.simplify(result);
+      if (simplified.equals(result)) {
+        break;
+      }
+      result = simplified;
+    }
+
+    return result;
+  }
 
   public static RexNode getTypeSafePred(RelOptCluster cluster, RexNode rex, RelDataType rType) {
     RexNode typeSafeRex = rex;

diff --git a/ql/src/test/queries/clientpositive/cardinality_preserving_join_opt2.q b/ql/src/test/queries/clientpositive/cardinality_preserving_join_opt2.q
@@ -2,7 +2,6 @@ set hive.support.concurrency=true;
 set hive.txn.manager=org.apache.hadoop.hive.ql.lockmgr.DbTxnManager;
 set hive.strict.checks.cartesian.product=false;
 set hive.stats.fetch.column.stats=true;
-set hive.cbo.rule.exclusion.regex=HivePreFilteringRule;
 
 create database if not exists mydb_e10;
 

diff --git a/ql/src/test/results/clientpositive/llap/cardinality_preserving_join_opt2.q.out b/ql/src/test/results/clientpositive/llap/cardinality_preserving_join_opt2.q.out
@@ -217,8 +217,6 @@ POSTHOOK: Input: mydb_e10@d4_tab_e10
 POSTHOOK: Input: mydb_e10@f2_tab_e10
 POSTHOOK: Input: mydb_e10@f_tab_e10
 #### A masked pattern was here ####
-Excluded rules: HivePreFilteringRule
-
 CBO PLAN:
 HiveProject(c1=[$11], c5=[$13], c6=[$14], c3=[$1], c4=[$2], c51=[$3], c61=[$4], c7=[$5], c8=[$6], c9=[$7], c10=[$8], c11=[$9], c12=[$19], c41=[$21], c52=[$22], c2=[$18])
   HiveJoin(condition=[=($11, $20)], joinType=[inner], algorithm=[none], cost=[not available])