[GitHub] [kafka] satishd commented on a diff in pull request #13206: [KAFKA-14685] Refactor logic to handle OFFSET_MOVED_TO_TIERED_STORAGE error

["satishd (via GitHub)" <gi...@apache.org>]

satishd commented on code in PR #13206:
URL: https://github.com/apache/kafka/pull/13206#discussion_r1098319549


##########
core/src/main/java/kafka/server/ReplicaFetcherTierStateMachine.java:
##########
@@ -0,0 +1,246 @@
+/*
+ * 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 kafka.server;
+
+import kafka.cluster.Partition;
+import kafka.log.LeaderOffsetIncremented$;
+import kafka.log.UnifiedLog;
+import kafka.log.remote.RemoteLogManager;
+import kafka.server.checkpoints.LeaderEpochCheckpointFile;
+import kafka.server.epoch.EpochEntry;
+import org.apache.kafka.common.KafkaException;
+import org.apache.kafka.common.TopicPartition;
+import org.apache.kafka.common.message.OffsetForLeaderEpochResponseData.EpochEndOffset;
+import org.apache.kafka.common.message.OffsetForLeaderEpochRequestData.OffsetForLeaderPartition;
+import org.apache.kafka.common.protocol.Errors;
+
+import java.io.BufferedReader;
+import java.io.File;
+import java.io.IOException;
+import java.io.InputStream;
+import java.io.InputStreamReader;
+import java.nio.charset.StandardCharsets;
+import java.nio.file.Files;
+import java.nio.file.StandardCopyOption;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Optional;
+
+import org.apache.kafka.common.requests.FetchRequest.PartitionData;
+import org.apache.kafka.common.utils.Utils;
+import org.apache.kafka.server.common.CheckpointFile;
+import org.apache.kafka.server.log.remote.storage.RemoteLogSegmentMetadata;
+import org.apache.kafka.server.log.remote.storage.RemoteStorageException;
+import org.apache.kafka.server.log.remote.storage.RemoteStorageManager;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+import scala.Option;
+import scala.Tuple2;
+import scala.collection.JavaConverters;
+import scala.collection.immutable.Seq;
+
+/**
+ The replica fetcher tier state machine follows a state machine progression.
+
+ Currently, the tier state machine follows a synchronous execution and only the start is needed.
+ There is no need to advance the state.
+
+ When started, the tier state machine will fetch the local log start offset of the
+ leader and then build the follower's remote log aux state until the leader's
+ local log start offset.
+ */
+public class ReplicaFetcherTierStateMachine implements TierStateMachine {
+    private static final Logger LOGGER = LoggerFactory.getLogger(ReplicaFetcherTierStateMachine.class);

Review Comment:
   nit: convention is to name it as `log` based on the majority of the classes.



##########
core/src/main/java/kafka/server/ReplicaFetcherTierStateMachine.java:
##########
@@ -0,0 +1,246 @@
+/*
+ * 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 kafka.server;
+
+import kafka.cluster.Partition;
+import kafka.log.LeaderOffsetIncremented$;
+import kafka.log.UnifiedLog;
+import kafka.log.remote.RemoteLogManager;
+import kafka.server.checkpoints.LeaderEpochCheckpointFile;
+import kafka.server.epoch.EpochEntry;
+import org.apache.kafka.common.KafkaException;
+import org.apache.kafka.common.TopicPartition;
+import org.apache.kafka.common.message.OffsetForLeaderEpochResponseData.EpochEndOffset;
+import org.apache.kafka.common.message.OffsetForLeaderEpochRequestData.OffsetForLeaderPartition;
+import org.apache.kafka.common.protocol.Errors;
+
+import java.io.BufferedReader;
+import java.io.File;
+import java.io.IOException;
+import java.io.InputStream;
+import java.io.InputStreamReader;
+import java.nio.charset.StandardCharsets;
+import java.nio.file.Files;
+import java.nio.file.StandardCopyOption;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Optional;
+
+import org.apache.kafka.common.requests.FetchRequest.PartitionData;
+import org.apache.kafka.common.utils.Utils;
+import org.apache.kafka.server.common.CheckpointFile;
+import org.apache.kafka.server.log.remote.storage.RemoteLogSegmentMetadata;
+import org.apache.kafka.server.log.remote.storage.RemoteStorageException;
+import org.apache.kafka.server.log.remote.storage.RemoteStorageManager;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+import scala.Option;
+import scala.Tuple2;
+import scala.collection.JavaConverters;
+import scala.collection.immutable.Seq;
+
+/**
+ The replica fetcher tier state machine follows a state machine progression.
+
+ Currently, the tier state machine follows a synchronous execution and only the start is needed.
+ There is no need to advance the state.
+
+ When started, the tier state machine will fetch the local log start offset of the
+ leader and then build the follower's remote log aux state until the leader's
+ local log start offset.
+ */
+public class ReplicaFetcherTierStateMachine implements TierStateMachine {
+    private static final Logger LOGGER = LoggerFactory.getLogger(ReplicaFetcherTierStateMachine.class);
+
+    private LeaderEndPoint leader;
+    private ReplicaManager replicaMgr;
+    private Integer fetchBackOffMs;

Review Comment:
   Should we introduce this when we have async implementation with `maybeAdvanceState`?



##########
core/src/main/java/kafka/server/ReplicaFetcherTierStateMachine.java:
##########
@@ -0,0 +1,246 @@
+/*
+ * 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 kafka.server;
+
+import kafka.cluster.Partition;
+import kafka.log.LeaderOffsetIncremented$;
+import kafka.log.UnifiedLog;
+import kafka.log.remote.RemoteLogManager;
+import kafka.server.checkpoints.LeaderEpochCheckpointFile;
+import kafka.server.epoch.EpochEntry;
+import org.apache.kafka.common.KafkaException;
+import org.apache.kafka.common.TopicPartition;
+import org.apache.kafka.common.message.OffsetForLeaderEpochResponseData.EpochEndOffset;
+import org.apache.kafka.common.message.OffsetForLeaderEpochRequestData.OffsetForLeaderPartition;
+import org.apache.kafka.common.protocol.Errors;
+
+import java.io.BufferedReader;
+import java.io.File;
+import java.io.IOException;
+import java.io.InputStream;
+import java.io.InputStreamReader;
+import java.nio.charset.StandardCharsets;
+import java.nio.file.Files;
+import java.nio.file.StandardCopyOption;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Optional;
+
+import org.apache.kafka.common.requests.FetchRequest.PartitionData;
+import org.apache.kafka.common.utils.Utils;
+import org.apache.kafka.server.common.CheckpointFile;
+import org.apache.kafka.server.log.remote.storage.RemoteLogSegmentMetadata;
+import org.apache.kafka.server.log.remote.storage.RemoteStorageException;
+import org.apache.kafka.server.log.remote.storage.RemoteStorageManager;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+import scala.Option;
+import scala.Tuple2;
+import scala.collection.JavaConverters;
+import scala.collection.immutable.Seq;
+
+/**
+ The replica fetcher tier state machine follows a state machine progression.
+
+ Currently, the tier state machine follows a synchronous execution and only the start is needed.
+ There is no need to advance the state.
+
+ When started, the tier state machine will fetch the local log start offset of the
+ leader and then build the follower's remote log aux state until the leader's
+ local log start offset.
+ */
+public class ReplicaFetcherTierStateMachine implements TierStateMachine {
+    private static final Logger LOGGER = LoggerFactory.getLogger(ReplicaFetcherTierStateMachine.class);
+
+    private LeaderEndPoint leader;
+    private ReplicaManager replicaMgr;
+    private Integer fetchBackOffMs;
+
+    public ReplicaFetcherTierStateMachine(LeaderEndPoint leader,
+                                          ReplicaManager replicaMgr,
+                                          Integer fetchBackOffMs) {
+        this.leader = leader;
+        this.replicaMgr = replicaMgr;
+        this.fetchBackOffMs = fetchBackOffMs;
+    }
+
+
+    public PartitionFetchState start(TopicPartition topicPartition,
+                                     PartitionFetchState currentFetchState,
+                                     PartitionData fetchPartitionData) throws Exception {
+
+        Tuple2<Object, Object> epochAndLeaderStartOffset = leader.fetchEarliestLocalOffset(topicPartition, currentFetchState.currentLeaderEpoch());
+        int epoch = (int) epochAndLeaderStartOffset._1;
+        long leaderStartOffset = (long) epochAndLeaderStartOffset._2;

Review Comment:
   nit: may want to rename it as `leaderLocalStartOffset`



##########
core/src/main/java/kafka/server/ReplicaFetcherTierStateMachine.java:
##########
@@ -0,0 +1,246 @@
+/*
+ * 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 kafka.server;
+
+import kafka.cluster.Partition;
+import kafka.log.LeaderOffsetIncremented$;
+import kafka.log.UnifiedLog;
+import kafka.log.remote.RemoteLogManager;
+import kafka.server.checkpoints.LeaderEpochCheckpointFile;
+import kafka.server.epoch.EpochEntry;
+import org.apache.kafka.common.KafkaException;
+import org.apache.kafka.common.TopicPartition;
+import org.apache.kafka.common.message.OffsetForLeaderEpochResponseData.EpochEndOffset;
+import org.apache.kafka.common.message.OffsetForLeaderEpochRequestData.OffsetForLeaderPartition;
+import org.apache.kafka.common.protocol.Errors;
+
+import java.io.BufferedReader;
+import java.io.File;
+import java.io.IOException;
+import java.io.InputStream;
+import java.io.InputStreamReader;
+import java.nio.charset.StandardCharsets;
+import java.nio.file.Files;
+import java.nio.file.StandardCopyOption;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Optional;
+
+import org.apache.kafka.common.requests.FetchRequest.PartitionData;
+import org.apache.kafka.common.utils.Utils;
+import org.apache.kafka.server.common.CheckpointFile;
+import org.apache.kafka.server.log.remote.storage.RemoteLogSegmentMetadata;
+import org.apache.kafka.server.log.remote.storage.RemoteStorageException;
+import org.apache.kafka.server.log.remote.storage.RemoteStorageManager;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+import scala.Option;
+import scala.Tuple2;
+import scala.collection.JavaConverters;
+import scala.collection.immutable.Seq;
+
+/**
+ The replica fetcher tier state machine follows a state machine progression.
+
+ Currently, the tier state machine follows a synchronous execution and only the start is needed.
+ There is no need to advance the state.
+
+ When started, the tier state machine will fetch the local log start offset of the
+ leader and then build the follower's remote log aux state until the leader's
+ local log start offset.
+ */
+public class ReplicaFetcherTierStateMachine implements TierStateMachine {
+    private static final Logger LOGGER = LoggerFactory.getLogger(ReplicaFetcherTierStateMachine.class);
+
+    private LeaderEndPoint leader;
+    private ReplicaManager replicaMgr;
+    private Integer fetchBackOffMs;
+
+    public ReplicaFetcherTierStateMachine(LeaderEndPoint leader,
+                                          ReplicaManager replicaMgr,
+                                          Integer fetchBackOffMs) {
+        this.leader = leader;
+        this.replicaMgr = replicaMgr;
+        this.fetchBackOffMs = fetchBackOffMs;
+    }
+
+
+    public PartitionFetchState start(TopicPartition topicPartition,
+                                     PartitionFetchState currentFetchState,
+                                     PartitionData fetchPartitionData) throws Exception {
+
+        Tuple2<Object, Object> epochAndLeaderStartOffset = leader.fetchEarliestLocalOffset(topicPartition, currentFetchState.currentLeaderEpoch());

Review Comment:
   nit: It is better to be specific here like `epochAndLeaderLocalStartOffset`.



-- 
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: jira-unsubscribe@kafka.apache.org

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