[GitHub] [incubator-doris] wyb commented on a change in pull request #3717: [Spark load][Fe 5/5] Fe process etl and loading state job

[GitBox <gi...@apache.org>]

wyb commented on a change in pull request #3717:
URL: https://github.com/apache/incubator-doris/pull/3717#discussion_r433986019



##########
File path: fe/src/main/java/org/apache/doris/load/loadv2/SparkLoadJob.java
##########
@@ -0,0 +1,700 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements.  See the NOTICE file
+// distributed with this work for additional information
+// regarding copyright ownership.  The ASF licenses this file
+// to you under the Apache License, Version 2.0 (the
+// "License"); you may not use this file except in compliance
+// with the License.  You may obtain a copy of the License at
+//
+//   http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing,
+// software distributed under the License is distributed on an
+// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+// KIND, either express or implied.  See the License for the
+// specific language governing permissions and limitations
+// under the License.
+
+package org.apache.doris.load.loadv2;
+
+import org.apache.doris.analysis.Analyzer;
+import org.apache.doris.analysis.BrokerDesc;
+import org.apache.doris.analysis.CastExpr;
+import org.apache.doris.analysis.DescriptorTable;
+import org.apache.doris.analysis.ResourceDesc;
+import org.apache.doris.analysis.Expr;
+import org.apache.doris.analysis.SlotDescriptor;
+import org.apache.doris.analysis.SlotRef;
+import org.apache.doris.analysis.TupleDescriptor;
+import org.apache.doris.catalog.Catalog;
+import org.apache.doris.catalog.Column;
+import org.apache.doris.catalog.Database;
+import org.apache.doris.catalog.FsBroker;
+import org.apache.doris.catalog.MaterializedIndex;
+import org.apache.doris.catalog.MaterializedIndex.IndexExtState;
+import org.apache.doris.catalog.OlapTable;
+import org.apache.doris.catalog.Partition;
+import org.apache.doris.catalog.PrimitiveType;
+import org.apache.doris.catalog.Replica;
+import org.apache.doris.catalog.ScalarType;
+import org.apache.doris.catalog.SparkResource;
+import org.apache.doris.catalog.Tablet;
+import org.apache.doris.catalog.Type;
+import org.apache.doris.common.Config;
+import org.apache.doris.common.LoadException;
+import org.apache.doris.common.MetaNotFoundException;
+import org.apache.doris.common.Pair;
+import org.apache.doris.common.UserException;
+import org.apache.doris.common.util.LogBuilder;
+import org.apache.doris.common.util.LogKey;
+import org.apache.doris.load.EtlJobType;
+import org.apache.doris.load.EtlStatus;
+import org.apache.doris.load.FailMsg;
+import org.apache.doris.load.loadv2.etl.EtlJobConfig;
+import org.apache.doris.planner.PlanNodeId;
+import org.apache.doris.planner.ScanNode;
+import org.apache.doris.qe.OriginStatement;
+import org.apache.doris.system.Backend;
+import org.apache.doris.task.AgentBatchTask;
+import org.apache.doris.task.AgentTaskExecutor;
+import org.apache.doris.task.AgentTaskQueue;
+import org.apache.doris.task.PushTask;
+import org.apache.doris.thrift.TBrokerRangeDesc;
+import org.apache.doris.thrift.TBrokerScanRange;
+import org.apache.doris.thrift.TBrokerScanRangeParams;
+import org.apache.doris.thrift.TDescriptorTable;
+import org.apache.doris.thrift.TFileFormatType;
+import org.apache.doris.thrift.TFileType;
+import org.apache.doris.thrift.TNetworkAddress;
+import org.apache.doris.thrift.TPlanNode;
+import org.apache.doris.thrift.TPriority;
+import org.apache.doris.thrift.TPushType;
+import org.apache.doris.thrift.TScanRangeLocations;
+import org.apache.doris.transaction.TabletCommitInfo;
+import org.apache.doris.transaction.TabletQuorumFailedException;
+
+import org.apache.logging.log4j.LogManager;
+import org.apache.logging.log4j.Logger;
+import org.apache.spark.launcher.SparkAppHandle;
+
+import com.google.common.base.Preconditions;
+import com.google.common.collect.Lists;
+import com.google.common.collect.Maps;
+import com.google.common.collect.Sets;
+import com.google.gson.annotations.SerializedName;
+
+import java.util.List;
+import java.util.Map;
+import java.util.Set;
+
+/**
+ * There are 4 steps in SparkLoadJob:
+ * Step1: SparkLoadPendingTask will be created by unprotectedExecuteJob method and submit spark etl job.
+ * Step2: LoadEtlChecker will check spark etl job status periodly and send push tasks to be when spark etl job is finished.
+ * Step3: LoadLoadingChecker will check loading status periodly and commit transaction when push tasks are finished.
+ * Step4: PublishVersionDaemon will send publish version tasks to be and finish transaction.
+ */
+public class SparkLoadJob extends BulkLoadJob {
+    private static final Logger LOG = LogManager.getLogger(SparkLoadJob.class);
+
+    // for global dict
+    public static final String BITMAP_DATA_PROPERTY = "bitmap_data";
+
+    // --- members below need persist ---
+    // create from resourceDesc when job created
+    private SparkResource sparkResource;
+    // members below updated when job state changed to etl
+    private long etlStartTimestamp = -1;
+    // for spark yarn
+    private String appId = "";
+    // spark job outputPath
+    private String etlOutputPath = "";
+    // members below updated when job state changed to loading
+    // { tableId.partitionId.indexId.bucket.schemaHash -> (etlFilePath, etlFileSize) }
+    private Map<String, Pair<String, Long>> tabletMetaToFileInfo = Maps.newHashMap();
+
+    // --- members below not persist ---
+    // temporary use
+    // one SparkLoadJob has only one table to load
+    // hivedb.table for global dict
+    private String hiveTableName = "";
+    private ResourceDesc resourceDesc;
+    // for spark standalone
+    private SparkAppHandle sparkAppHandle;

Review comment:
       setJobProperties in SparkLoadJob.
   This is for temporary use. I am investigating load from hive table, and i will update it recently.




----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org



---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@doris.apache.org
For additional commands, e-mail: commits-help@doris.apache.org