From 4ed733e26ff49da985bd3453ba1211044e2ac1a0 Mon Sep 17 00:00:00 2001
From: Yiming Liu <liuyiming.vip@gmail.com>
Date: Sun, 4 Sep 2016 17:22:20 +0800
Subject: [PATCH] KYLIN-1984: Disable compress in default configuration

---
 build/conf/kylin.properties                               |  4 ++--
 build/conf/kylin_hive_conf.xml                            | 13 ++++++++++++-
 build/conf/kylin_job_conf.xml                             | 15 ++++++++++++---
 build/conf/kylin_job_conf_inmem.xml                       | 15 ++++++++++++---
 .../java/org/apache/kylin/common/KylinConfigBase.java     |  2 +-
 .../apache/kylin/storage/hbase/steps/CubeHTableUtil.java  |  5 +++--
 6 files changed, 42 insertions(+), 12 deletions(-)

diff --git a/build/conf/kylin.properties b/build/conf/kylin.properties
index 5607336..c20488a 100644
--- a/build/conf/kylin.properties
+++ b/build/conf/kylin.properties
@@ -54,8 +54,8 @@ kylin.storage.cleanup.time.threshold=172800000
 # Working folder in HDFS, make sure user has the right access to the hdfs directory
 kylin.hdfs.working.dir=/kylin
 
-# Compression codec for htable, valid value [snappy, lzo, gzip, lz4]
-kylin.hbase.default.compression.codec=snappy
+# Compression codec for htable, valid value [none, snappy, lzo, gzip, lz4]
+kylin.hbase.default.compression.codec=none
 
 # HBase Cluster FileSystem, which serving hbase, format as hdfs://hbase-cluster:8020
 # Leave empty if hbase running on same cluster with hive and mapreduce
diff --git a/build/conf/kylin_hive_conf.xml b/build/conf/kylin_hive_conf.xml
index 3d6109b..30c4feb 100644
--- a/build/conf/kylin_hive_conf.xml
+++ b/build/conf/kylin_hive_conf.xml
@@ -39,17 +39,28 @@
         <description>enable map-side join</description>
     </property>
 
+    <!--
+    The default map outputs compress codec is org.apache.hadoop.io.compress.DefaultCodec,
+    if SnappyCodec is supported, org.apache.hadoop.io.compress.SnappyCodec could be used.
+    -->
+    <!--
     <property>
         <name>mapreduce.map.output.compress.codec</name>
         <value>org.apache.hadoop.io.compress.SnappyCodec</value>
         <description></description>
     </property>
+    -->
+    <!--
+    The default job outputs compress codec is org.apache.hadoop.io.compress.DefaultCodec,
+    if SnappyCodec is supported, org.apache.hadoop.io.compress.SnappyCodec could be used.
+    -->
+    <!--
     <property>
         <name>mapreduce.output.fileoutputformat.compress.codec</name>
         <value>org.apache.hadoop.io.compress.SnappyCodec</value>
         <description></description>
     </property>
-
+    -->
     <property>
         <name>mapred.output.compression.type</name>
         <value>BLOCK</value>
diff --git a/build/conf/kylin_job_conf.xml b/build/conf/kylin_job_conf.xml
index 877e82f..96b806c 100644
--- a/build/conf/kylin_job_conf.xml
+++ b/build/conf/kylin_job_conf.xml
@@ -31,26 +31,35 @@
         <description>Compress map outputs</description>
     </property>
 
+    <!--
+    The default map outputs compress codec is org.apache.hadoop.io.compress.DefaultCodec,
+    if SnappyCodec is supported, org.apache.hadoop.io.compress.SnappyCodec could be used.
+    -->
+    <!--
     <property>
         <name>mapred.map.output.compression.codec</name>
         <value>org.apache.hadoop.io.compress.SnappyCodec</value>
         <description>The compression codec to use for map outputs
         </description>
     </property>
-
+    -->
     <property>
         <name>mapred.output.compress</name>
         <value>true</value>
         <description>Compress the output of a MapReduce job</description>
     </property>
-
+    <!--
+    The default job outputs compress codec is org.apache.hadoop.io.compress.DefaultCodec,
+    if SnappyCodec is supported, org.apache.hadoop.io.compress.SnappyCodec could be used.
+    -->
+    <!--
     <property>
         <name>mapred.output.compression.codec</name>
         <value>org.apache.hadoop.io.compress.SnappyCodec</value>
         <description>The compression codec to use for job outputs
         </description>
     </property>
-
+    -->
     <property>
         <name>mapred.output.compression.type</name>
         <value>BLOCK</value>
diff --git a/build/conf/kylin_job_conf_inmem.xml b/build/conf/kylin_job_conf_inmem.xml
index 1cd809d..fea2f68 100644
--- a/build/conf/kylin_job_conf_inmem.xml
+++ b/build/conf/kylin_job_conf_inmem.xml
@@ -31,26 +31,35 @@
         <description>Compress map outputs</description>
     </property>
 
+    <!--
+    The default map outputs compress codec is org.apache.hadoop.io.compress.DefaultCodec,
+    if SnappyCodec is supported, org.apache.hadoop.io.compress.SnappyCodec could be used.
+    -->
+    <!--
     <property>
         <name>mapred.map.output.compression.codec</name>
         <value>org.apache.hadoop.io.compress.SnappyCodec</value>
         <description>The compression codec to use for map outputs
         </description>
     </property>
-
+    -->
     <property>
         <name>mapred.output.compress</name>
         <value>true</value>
         <description>Compress the output of a MapReduce job</description>
     </property>
-
+    <!--
+    The default job outputs compress codec is org.apache.hadoop.io.compress.DefaultCodec,
+    if SnappyCodec is supported, org.apache.hadoop.io.compress.SnappyCodec could be used.
+    -->
+    <!--
     <property>
         <name>mapred.output.compression.codec</name>
         <value>org.apache.hadoop.io.compress.SnappyCodec</value>
         <description>The compression codec to use for job outputs
         </description>
     </property>
-
+    -->
     <property>
         <name>mapred.output.compression.type</name>
         <value>BLOCK</value>
diff --git a/core-common/src/main/java/org/apache/kylin/common/KylinConfigBase.java b/core-common/src/main/java/org/apache/kylin/common/KylinConfigBase.java
index 1390e24..f0c91da 100644
--- a/core-common/src/main/java/org/apache/kylin/common/KylinConfigBase.java
+++ b/core-common/src/main/java/org/apache/kylin/common/KylinConfigBase.java
@@ -615,7 +615,7 @@ abstract public class KylinConfigBase implements Serializable {
     }
 
     public String getHbaseDefaultCompressionCodec() {
-        return getOptional("kylin.hbase.default.compression.codec", "");
+        return getOptional("kylin.hbase.default.compression.codec", "none");
     }
 
     public String getHbaseDefaultEncoding() {
diff --git a/storage-hbase/src/main/java/org/apache/kylin/storage/hbase/steps/CubeHTableUtil.java b/storage-hbase/src/main/java/org/apache/kylin/storage/hbase/steps/CubeHTableUtil.java
index fe65598..9b487a7 100644
--- a/storage-hbase/src/main/java/org/apache/kylin/storage/hbase/steps/CubeHTableUtil.java
+++ b/storage-hbase/src/main/java/org/apache/kylin/storage/hbase/steps/CubeHTableUtil.java
@@ -183,8 +183,9 @@ public class CubeHTableUtil {
             cf.setCompressionType(Algorithm.LZ4);
             break;
         }
+        case "none":
         default: {
-            logger.info("hbase will not user any compression algorithm to compress data");
+            logger.info("hbase will not use any compression algorithm to compress data");
             cf.setCompressionType(Algorithm.NONE);
         }
         }
@@ -194,7 +195,7 @@ public class CubeHTableUtil {
             DataBlockEncoding encoding = DataBlockEncoding.valueOf(encodingStr);
             cf.setDataBlockEncoding(encoding);
         } catch (Exception e) {
-            logger.info("hbase will not use any encoding");
+            logger.info("hbase will not use any encoding", e);
             cf.setDataBlockEncoding(DataBlockEncoding.NONE);
         }
 
-- 
2.7.4 (Apple Git-66)