YARN-5265. Make HBase configuration for the timeline service configurable. Contributed by Joep Rottinghuis.

(cherry picked from commit dc7d9bac79fc303f66e97c10379d680e0c11caa4)

hadoop-yarn-project/hadoop-yarn/hadoop-yarn-api/src/main/java/org/apache/hadoop/yarn/conf/YarnConfiguration.java

@@ -2227,6 +2227,15 @@ public class YarnConfiguration extends Configuration {
       TIMELINE_SERVICE_PREFIX
       + "hbase.coprocessor.app-final-value-retention-milliseconds";
 
+  /**
+   * The name for setting that points to an optional HBase configuration
+   * (hbase-site.xml file) with settings that will override the ones found on
+   * the classpath.
+   */
+  public static final String TIMELINE_SERVICE_HBASE_CONFIGURATION_FILE =
+      TIMELINE_SERVICE_PREFIX
+      + "hbase.configuration.file";
+
   /**
    * The setting that controls how long the final value of a metric of a
    * completed app is retained before merging into the flow sum. Up to this time

hadoop-yarn-project/hadoop-yarn/hadoop-yarn-common/src/main/resources/yarn-default.xml

@@ -2366,6 +2366,18 @@
     <value>prod.</value>
   </property>
 
+  <property>
+    <description> Optional URL to an hbase-site.xml configuration file to be
+    used to connect to the timeline-service hbase cluster. If empty or not
+    specified, then the HBase configuration will be loaded from the classpath.
+    When specified the values in the specified configuration file will override
+    those from the ones that are present on the classpath.
+    </description>
+    <name>yarn.timeline-service.hbase.configuration.file
+    </name>
+    <value></value>
+  </property>
+
   <!--  Shared Cache Configuration -->
 
   <property>

hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-timelineservice/src/main/java/org/apache/hadoop/yarn/server/timelineservice/storage/HBaseTimelineReaderImpl.java

@@ -24,7 +24,6 @@ import java.util.Set;
 import org.apache.commons.logging.Log;
 import org.apache.commons.logging.LogFactory;
 import org.apache.hadoop.conf.Configuration;
-import org.apache.hadoop.hbase.HBaseConfiguration;
 import org.apache.hadoop.hbase.client.Connection;
 import org.apache.hadoop.hbase.client.ConnectionFactory;
 import org.apache.hadoop.service.AbstractService;
@@ -32,6 +31,7 @@ import org.apache.hadoop.yarn.api.records.timelineservice.TimelineEntity;
 import org.apache.hadoop.yarn.server.timelineservice.reader.TimelineDataToRetrieve;
 import org.apache.hadoop.yarn.server.timelineservice.reader.TimelineEntityFilters;
 import org.apache.hadoop.yarn.server.timelineservice.reader.TimelineReaderContext;
+import org.apache.hadoop.yarn.server.timelineservice.storage.common.TimelineStorageUtils;
 import org.apache.hadoop.yarn.server.timelineservice.storage.reader.TimelineEntityReader;
 import org.apache.hadoop.yarn.server.timelineservice.storage.reader.TimelineEntityReaderFactory;
 
@@ -54,7 +54,7 @@ public class HBaseTimelineReaderImpl
   @Override
   public void serviceInit(Configuration conf) throws Exception {
     super.serviceInit(conf);
-    hbaseConf = HBaseConfiguration.create(conf);
+    hbaseConf = TimelineStorageUtils.getTimelineServiceHBaseConf(conf);
     conn = ConnectionFactory.createConnection(hbaseConf);
   }
 

hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-timelineservice/src/main/java/org/apache/hadoop/yarn/server/timelineservice/storage/HBaseTimelineWriterImpl.java

@@ -26,7 +26,6 @@ import org.apache.commons.logging.LogFactory;
 import org.apache.hadoop.classification.InterfaceAudience;
 import org.apache.hadoop.classification.InterfaceStability;
 import org.apache.hadoop.conf.Configuration;
-import org.apache.hadoop.hbase.HBaseConfiguration;
 import org.apache.hadoop.hbase.client.Connection;
 import org.apache.hadoop.hbase.client.ConnectionFactory;
 import org.apache.hadoop.service.AbstractService;
@@ -50,6 +49,7 @@ import org.apache.hadoop.yarn.server.timelineservice.storage.common.KeyConverter
 import org.apache.hadoop.yarn.server.timelineservice.storage.common.LongKeyConverter;
 import org.apache.hadoop.yarn.server.timelineservice.storage.common.Separator;
 import org.apache.hadoop.yarn.server.timelineservice.storage.common.StringKeyConverter;
+import org.apache.hadoop.yarn.server.timelineservice.storage.common.TimelineStorageUtils;
 import org.apache.hadoop.yarn.server.timelineservice.storage.common.TypedBufferedMutator;
 import org.apache.hadoop.yarn.server.timelineservice.storage.entity.EntityColumn;
 import org.apache.hadoop.yarn.server.timelineservice.storage.entity.EntityColumnPrefix;
@@ -112,7 +112,8 @@ public class HBaseTimelineWriterImpl extends AbstractService implements
   @Override
   protected void serviceInit(Configuration conf) throws Exception {
     super.serviceInit(conf);
-    Configuration hbaseConf = HBaseConfiguration.create(conf);
+    Configuration hbaseConf =
+        TimelineStorageUtils.getTimelineServiceHBaseConf(conf);
     conn = ConnectionFactory.createConnection(hbaseConf);
     entityTable = new EntityTable().getTableMutator(hbaseConf, conn);
     appToFlowTable = new AppToFlowTable().getTableMutator(hbaseConf, conn);

hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-timelineservice/src/main/java/org/apache/hadoop/yarn/server/timelineservice/storage/TimelineSchemaCreator.java

@@ -34,13 +34,13 @@ import org.apache.commons.logging.LogFactory;
 import org.apache.hadoop.classification.InterfaceAudience;
 import org.apache.hadoop.classification.InterfaceStability;
 import org.apache.hadoop.conf.Configuration;
-import org.apache.hadoop.hbase.HBaseConfiguration;
 import org.apache.hadoop.hbase.client.Admin;
 import org.apache.hadoop.hbase.client.Connection;
 import org.apache.hadoop.hbase.client.ConnectionFactory;
 import org.apache.hadoop.util.GenericOptionsParser;
 import org.apache.hadoop.yarn.server.timelineservice.storage.application.ApplicationTable;
 import org.apache.hadoop.yarn.server.timelineservice.storage.apptoflow.AppToFlowTable;
+import org.apache.hadoop.yarn.server.timelineservice.storage.common.TimelineStorageUtils;
 import org.apache.hadoop.yarn.server.timelineservice.storage.entity.EntityTable;
 import org.apache.hadoop.yarn.server.timelineservice.storage.flow.FlowActivityTable;
 import org.apache.hadoop.yarn.server.timelineservice.storage.flow.FlowRunTable;
@@ -68,7 +68,8 @@ public final class TimelineSchemaCreator {
 
   public static void main(String[] args) throws Exception {
 
-    Configuration hbaseConf = HBaseConfiguration.create();
+    Configuration hbaseConf =
+        TimelineStorageUtils.getTimelineServiceHBaseConf(null);
     // Grab input args and allow for -Dxyz style arguments
     String[] otherArgs = new GenericOptionsParser(hbaseConf, args)
         .getRemainingArgs();

hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-timelineservice/src/main/java/org/apache/hadoop/yarn/server/timelineservice/storage/common/TimelineStorageUtils.java

@@ -18,6 +18,8 @@
 package org.apache.hadoop.yarn.server.timelineservice.storage.common;
 
 import java.io.IOException;
+import java.net.MalformedURLException;
+import java.net.URL;
 import java.util.HashMap;
 import java.util.HashSet;
 import java.util.List;
@@ -29,14 +31,17 @@ import org.apache.commons.logging.Log;
 import org.apache.commons.logging.LogFactory;
 import org.apache.hadoop.classification.InterfaceAudience.Public;
 import org.apache.hadoop.classification.InterfaceStability.Unstable;
+import org.apache.hadoop.conf.Configuration;
 import org.apache.hadoop.hbase.Cell;
 import org.apache.hadoop.hbase.CellUtil;
+import org.apache.hadoop.hbase.HBaseConfiguration;
 import org.apache.hadoop.hbase.KeyValue;
 import org.apache.hadoop.hbase.Tag;
 import org.apache.hadoop.hbase.util.Bytes;
 import org.apache.hadoop.yarn.api.records.timelineservice.TimelineEntity;
 import org.apache.hadoop.yarn.api.records.timelineservice.TimelineEvent;
 import org.apache.hadoop.yarn.api.records.timelineservice.TimelineMetric;
+import org.apache.hadoop.yarn.conf.YarnConfiguration;
 import org.apache.hadoop.yarn.server.timelineservice.reader.filter.TimelineCompareFilter;
 import org.apache.hadoop.yarn.server.timelineservice.reader.filter.TimelineCompareOp;
 import org.apache.hadoop.yarn.server.timelineservice.reader.filter.TimelineExistsFilter;
@@ -563,4 +568,41 @@ public final class TimelineStorageUtils {
     }
     return appId;
   }
+
+
+  /**
+   * @param conf Yarn configuration. Used to see if there is an explicit config
+   *          pointing to the HBase config file to read. If null then a new
+   *          HBase configuration will be returned.
+   * @return a configuration with the HBase configuration from the classpath,
+   *         optionally overwritten by the timeline service configuration URL if
+   *         specified.
+   * @throws MalformedURLException if a timeline service HBase configuration URL
+   *           is specified but is a malformed URL.
+   */
+  public static Configuration getTimelineServiceHBaseConf(Configuration conf)
+      throws MalformedURLException {
+    Configuration hbaseConf;
+
+    if (conf == null) {
+      return HBaseConfiguration.create();
+    }
+
+    String timelineServiceHBaseConfFileURL =
+        conf.get(YarnConfiguration.TIMELINE_SERVICE_HBASE_CONFIGURATION_FILE);
+    if (timelineServiceHBaseConfFileURL != null
+        && timelineServiceHBaseConfFileURL.length() > 0) {
+      // create a clone so that we don't mess with out input one
+      hbaseConf = new Configuration(conf);
+      Configuration plainHBaseConf = new Configuration(false);
+      URL hbaseSiteXML = new URL(timelineServiceHBaseConfFileURL);
+      plainHBaseConf.addResource(hbaseSiteXML);
+      HBaseConfiguration.merge(hbaseConf, plainHBaseConf);
+    } else {
+      // default to what is on the classpath
+      hbaseConf = HBaseConfiguration.create(conf);
+    }
+    return hbaseConf;
+  }
+
 }

hadoop-yarn-project/hadoop-yarn/hadoop-yarn-site/src/site/markdown/TimelineServiceV2.md

@@ -153,6 +153,7 @@ New configuration parameters that are introduced with v.2 are marked bold.
 | `yarn.timeline-service.address` | Address for the Timeline server to start the RPC server. Defaults to `${yarn.timeline-service.hostname}:10200`. |
 | `yarn.timeline-service.webapp.address` | The http address of the Timeline service web application. Defaults to `${yarn.timeline-service.hostname}:8188`. |
 | `yarn.timeline-service.webapp.https.address` | The https address of the Timeline service web application. Defaults to `${yarn.timeline-service.hostname}:8190`. |
+| **`yarn.timeline-service.hbase.configuration.file`** | Optional URL to an hbase-site.xml configuration file to be used to connect to the timeline-service hbase cluster. If empty or not specified, then the HBase configuration will be loaded from the classpath. When specified the values in the specified configuration file will override those from the ones that are present on the classpath. Defaults to `null`. |
 | **`yarn.timeline-service.writer.flush-interval-seconds`** | The setting that controls how often the timeline collector flushes the timeline writer. Defaults to `60`. |
 | **`yarn.timeline-service.app-collector.linger-period.ms`** | Time period till which the application collector will be alive in NM, after the  application master container finishes. Defaults to `1000` (1 second). |
 | **`yarn.timeline-service.timeline-client.number-of-async-entities-to-merge`** | Time line V2 client tries to merge these many number of async entities (if available) and then call the REST ATS V2 API to submit. Defaults to `10`. |
@@ -249,7 +250,22 @@ are using multiple clusters to store data in the same Apache HBase storage:
 ```
 
 Also, add the `hbase-site.xml` configuration file to the client Hadoop cluster configuration so
-that it can write data to the Apache HBase cluster you are using.
+that it can write data to the Apache HBase cluster you are using, or set
+`yarn.timeline-service.hbase.configuration.file` to the file URL pointing to
+`hbase-site.xml` for the same. For example:
+
+```
+<property>
+  <description> Optional URL to an hbase-site.xml configuration file to be
+  used to connect to the timeline-service hbase cluster. If empty or not
+  specified, then the HBase configuration will be loaded from the classpath.
+  When specified the values in the specified configuration file will override
+  those from the ones that are present on the classpath.
+  </description>
+  <name>yarn.timeline-service.hbase.configuration.file</name>
+  <value>file:/etc/hbase/hbase-ats-dc1/hbase-site.xml</value>
+</property>
+```
 
 #### Running Timeline Service v.2
 Restart the resource manager as well as the node managers to pick up the new configuration. The