Github user hmcl commented on a diff in the pull request: https://github.com/apache/storm/pull/2465#discussion_r157537115 --- Diff: external/storm-kafka-client/src/main/java/org/apache/storm/kafka/spout/KafkaSpout.java --- @@ -225,6 +243,25 @@ private long doSeek(TopicPartition tp, OffsetAndMetadata committedOffset) { } } + /** + * Checks If {@link OffsetAndMetadata} was committed by an instance of {@link KafkaSpout} in this topology. + * This info is used to decide if {@link FirstPollOffsetStrategy} should be applied + * + * @param committedOffset {@link OffsetAndMetadata} info committed to Kafka + * @return true if this topology committed this {@link OffsetAndMetadata}, false otherwise + */ + private boolean isOffsetCommittedByThisTopology(OffsetAndMetadata committedOffset) { + try { + final KafkaSpout.Info info = JSON_MAPPER.readValue(committedOffset.metadata(), KafkaSpout.Info.class); + return info.getTopologyId().equals(context.getStormId()); + } catch (IOException e) { + LOG.trace("Failed to deserialize {}. Error likely occurred because the last commit " + --- End diff -- The log messages only get printed in the case of a commit made by a topology running an older version of Storm and until the first commit is done by this topology for each topic-partition. Ater that the first commit logs will no longer occur. I will look into if it makes sense caching this info.
---