gnehil commented on code in PR #36862: URL: https://github.com/apache/doris/pull/36862#discussion_r1714765544
########## fe/fe-core/src/main/java/org/apache/doris/load/loadv2/IngestionLoadJob.java: ########## @@ -0,0 +1,1138 @@ +// 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.CastExpr; +import org.apache.doris.analysis.DescriptorTable; +import org.apache.doris.analysis.Expr; +import org.apache.doris.analysis.LiteralExpr; +import org.apache.doris.analysis.SlotDescriptor; +import org.apache.doris.analysis.SlotRef; +import org.apache.doris.analysis.TupleDescriptor; +import org.apache.doris.analysis.UserIdentity; +import org.apache.doris.catalog.AggregateType; +import org.apache.doris.catalog.Column; +import org.apache.doris.catalog.Database; +import org.apache.doris.catalog.DistributionInfo; +import org.apache.doris.catalog.Env; +import org.apache.doris.catalog.HashDistributionInfo; +import org.apache.doris.catalog.KeysType; +import org.apache.doris.catalog.MaterializedIndex; +import org.apache.doris.catalog.MaterializedIndexMeta; +import org.apache.doris.catalog.OlapTable; +import org.apache.doris.catalog.Partition; +import org.apache.doris.catalog.PartitionItem; +import org.apache.doris.catalog.PartitionKey; +import org.apache.doris.catalog.PartitionType; +import org.apache.doris.catalog.PrimitiveType; +import org.apache.doris.catalog.RangePartitionInfo; +import org.apache.doris.catalog.Replica; +import org.apache.doris.catalog.ScalarType; +import org.apache.doris.catalog.Table; +import org.apache.doris.catalog.TableIf; +import org.apache.doris.catalog.Tablet; +import org.apache.doris.catalog.Type; +import org.apache.doris.common.AnalysisException; +import org.apache.doris.common.DataQualityException; +import org.apache.doris.common.DdlException; +import org.apache.doris.common.DuplicatedRequestException; +import org.apache.doris.common.LabelAlreadyUsedException; +import org.apache.doris.common.LoadException; +import org.apache.doris.common.MetaNotFoundException; +import org.apache.doris.common.Pair; +import org.apache.doris.common.QuotaExceedException; +import org.apache.doris.common.UserException; +import org.apache.doris.common.io.Text; +import org.apache.doris.common.util.LogBuilder; +import org.apache.doris.common.util.LogKey; +import org.apache.doris.common.util.MetaLockUtils; +import org.apache.doris.load.EtlJobType; +import org.apache.doris.load.EtlStatus; +import org.apache.doris.load.FailMsg; +import org.apache.doris.service.ExecuteEnv; +import org.apache.doris.service.FrontendOptions; +import org.apache.doris.sparkdpp.DppResult; +import org.apache.doris.sparkdpp.EtlJobConfig; +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.TColumn; +import org.apache.doris.thrift.TDescriptorTable; +import org.apache.doris.thrift.TEtlState; +import org.apache.doris.thrift.TFileFormatType; +import org.apache.doris.thrift.TFileType; +import org.apache.doris.thrift.TPriority; +import org.apache.doris.thrift.TPushType; +import org.apache.doris.thrift.TUniqueId; +import org.apache.doris.transaction.BeginTransactionException; +import org.apache.doris.transaction.TabletCommitInfo; +import org.apache.doris.transaction.TabletQuorumFailedException; +import org.apache.doris.transaction.TransactionState; + +import cfjd.com.google.gson.annotations.SerializedName; +import com.google.common.base.Preconditions; +import com.google.common.collect.Lists; +import com.google.common.collect.Maps; +import com.google.common.collect.Range; +import com.google.common.collect.Sets; +import com.google.gson.Gson; +import com.google.gson.reflect.TypeToken; +import lombok.Setter; +import org.apache.logging.log4j.LogManager; +import org.apache.logging.log4j.Logger; + +import java.io.DataInput; +import java.io.IOException; +import java.util.ArrayList; +import java.util.Collections; +import java.util.HashMap; +import java.util.HashSet; +import java.util.List; +import java.util.Locale; +import java.util.Map; +import java.util.Set; +import java.util.stream.Collectors; + +/** + * Ingestion Load + * </p> + * Load data file which has been pre-processed + * </p> + * There are 4 steps in IngestionLoadJob: + * Step1: Outside system execute ingestion etl job. + * Step2: LoadEtlChecker will check ingestion etl job status periodically + * and send push tasks to be when ingestion etl job is finished. + * Step3: LoadLoadingChecker will check loading status periodically and commit transaction when push tasks are finished. + * Step4: PublishVersionDaemon will send publish version tasks to be and finish transaction. + */ +public class IngestionLoadJob extends LoadJob { + + public static final Logger LOG = LogManager.getLogger(IngestionLoadJob.class); + + private long etlStartTimestamp = -1; + + private long quorumFinishTimestamp = -1; + + private List<Long> loadTableIds = new ArrayList<>(); + + @Setter + @SerializedName("ests") + private EtlStatus etlStatus; + + private final Map<Long, Set<Long>> tableToLoadPartitions = Maps.newHashMap(); + + private final Map<Long, Map<Long, PushTask>> tabletToSentReplicaPushTask = Maps.newHashMap(); + + // members below updated when job state changed to loading + // { tableId.partitionId.indexId.bucket.schemaHash -> (etlFilePath, etlFileSize) } + @SerializedName(value = "tm2fi") + private final Map<String, Pair<String, Long>> tabletMetaToFileInfo = Maps.newHashMap(); + + private final Map<Long, Integer> indexToSchemaHash = Maps.newHashMap(); + + private final Map<String, Long> filePathToSize = new HashMap<>(); + + private final Set<Long> finishedReplicas = Sets.newHashSet(); + private final Set<Long> quorumTablets = Sets.newHashSet(); + private final Set<Long> fullTablets = Sets.newHashSet(); + + private final List<TabletCommitInfo> commitInfos = Lists.newArrayList(); + + @SerializedName(value = "hp") Review Comment: Is it necessary to persist all fields? Not all fields need to be reloaded from metadata. -- 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. To unsubscribe, e-mail: commits-unsubscr...@doris.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@doris.apache.org For additional commands, e-mail: commits-h...@doris.apache.org
