[hive] branch master updated: HIVE-23806: Avoid clearing column stat states in all partition in case schema is extended (#1215) (Zoltan Haindrich reviewed by Peter Vary)

[kg...@apache.org]

This is an automated email from the ASF dual-hosted git repository.

kgyrtkirk pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/hive.git


The following commit(s) were added to refs/heads/master by this push:
     new 11cbf17  HIVE-23806: Avoid clearing column stat states in all partition in case schema is extended (#1215) (Zoltan Haindrich reviewed by Peter Vary)
11cbf17 is described below

commit 11cbf17e57dc13b800aa9ef4f987582b9219e3dd
Author: Zoltan Haindrich <ki...@rxd.hu>
AuthorDate: Wed Jul 29 10:02:26 2020 +0200

    HIVE-23806: Avoid clearing column stat states in all partition in case schema is extended (#1215) (Zoltan Haindrich reviewed by Peter Vary)
---
 .../org/apache/hadoop/hive/metastore/HiveAlterHandler.java |  8 ++++++--
 .../hadoop/hive/metastore/utils/MetaStoreServerUtils.java  | 14 ++++++++++++++
 2 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/HiveAlterHandler.java b/standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/HiveAlterHandler.java
index 2beeab4..0cfb329 100644
--- a/standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/HiveAlterHandler.java
+++ b/standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/HiveAlterHandler.java
@@ -59,7 +59,6 @@ import java.io.IOException;
 import java.net.URI;
 import java.util.ArrayList;
 import java.util.Collections;
-import java.util.HashMap;
 import java.util.Iterator;
 import java.util.List;
 import java.util.Map;
@@ -362,7 +361,12 @@ public class HiveAlterHandler implements AlterHandler {
 
         if (isPartitionedTable) {
           //Currently only column related changes can be cascaded in alter table
-          if(!MetaStoreServerUtils.areSameColumns(oldt.getSd().getCols(), newt.getSd().getCols())) {
+          boolean runPartitionMetadataUpdate =
+              (cascade && !MetaStoreServerUtils.areSameColumns(oldt.getSd().getCols(), newt.getSd().getCols()));
+          // we may skip the update entirely if there are only new columns added
+          runPartitionMetadataUpdate |=
+              !cascade && !MetaStoreServerUtils.arePrefixColumns(oldt.getSd().getCols(), newt.getSd().getCols());
+          if (runPartitionMetadataUpdate) {
             parts = msdb.getPartitions(catName, dbname, name, -1);
             for (Partition part : parts) {
               Partition oldPart = new Partition(part);
diff --git a/standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/utils/MetaStoreServerUtils.java b/standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/utils/MetaStoreServerUtils.java
index d6cf43c..1969ddd 100644
--- a/standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/utils/MetaStoreServerUtils.java
+++ b/standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/utils/MetaStoreServerUtils.java
@@ -32,6 +32,7 @@ import java.util.ArrayList;
 import java.util.Collection;
 import java.util.Collections;
 import java.util.HashMap;
+import java.util.Iterator;
 import java.util.List;
 import java.util.Map;
 import java.util.Objects;
@@ -501,6 +502,19 @@ public class MetaStoreServerUtils {
     return ListUtils.isEqualList(oldCols, newCols);
   }
 
+  /**
+   * Returns true if p is a prefix of s.
+   */
+  public static boolean arePrefixColumns(List<FieldSchema> p, List<FieldSchema> s) {
+    if (p == s) {
+      return true;
+    }
+    if (p.size() > s.size()) {
+      return false;
+    }
+    return ListUtils.isEqualList(p, s.subList(0, p.size()));
+  }
+
   public static void updateBasicState(EnvironmentContext environmentContext, Map<String,String>
       params) {
     if (params == null) {