cryptoe commented on code in PR #15965:
URL: https://github.com/apache/druid/pull/15965#discussion_r1555604306
##########
extensions-core/multi-stage-query/src/main/java/org/apache/druid/msq/exec/ControllerImpl.java:
##########
@@ -1714,12 +1727,122 @@ private void publishSegmentsIfNeeded(
//noinspection unchecked
@SuppressWarnings("unchecked")
- final Set<DataSegment> segments = (Set<DataSegment>)
queryKernel.getResultObjectForStage(finalStageId);
+ Set<DataSegment> segments = (Set<DataSegment>)
queryKernel.getResultObjectForStage(finalStageId);
+
+ boolean storeCompactionState =
QueryContext.of(task.getQuerySpec().getQuery().getContext())
+ .getBoolean(
+
Tasks.STORE_COMPACTION_STATE_KEY,
+
Tasks.DEFAULT_STORE_COMPACTION_STATE
+ );
+
+ if (!segments.isEmpty() && storeCompactionState) {
+ DataSourceMSQDestination destination = (DataSourceMSQDestination)
task.getQuerySpec().getDestination();
+ if (!destination.isReplaceTimeChunks()) {
+ // Store compaction state only for replace queries.
+ log.warn(
+ "storeCompactionState flag set for a non-REPLACE query [%s].
Ignoring the flag for now.",
+ queryDef.getQueryId()
+ );
+ } else {
+ DataSchema dataSchema = ((SegmentGeneratorFrameProcessorFactory)
queryKernel
+
.getStageDefinition(finalStageId).getProcessorFactory()).getDataSchema();
+
+ ShardSpec shardSpec =
segments.stream().findFirst().get().getShardSpec();
+
+ Function<Set<DataSegment>, Set<DataSegment>>
compactionStateAnnotateFunction = addCompactionStateToSegments(
+ task(),
+ context.jsonMapper(),
+ dataSchema,
+ shardSpec,
+ queryDef.getQueryId()
+ );
+ segments = compactionStateAnnotateFunction.apply(segments);
+ }
+ }
log.info("Query [%s] publishing %d segments.", queryDef.getQueryId(),
segments.size());
publishAllSegments(segments);
}
}
+ private static Function<Set<DataSegment>, Set<DataSegment>>
addCompactionStateToSegments(
+ MSQControllerTask task,
+ ObjectMapper jsonMapper,
+ DataSchema dataSchema,
+ ShardSpec shardSpec,
+ String queryId
+ )
+ {
+ final MSQTuningConfig tuningConfig = task.getQuerySpec().getTuningConfig();
+ PartitionsSpec partitionSpec;
+
+ if (Objects.equals(shardSpec.getType(), ShardSpec.Type.SINGLE)) {
+ String partitionDimension = ((SingleDimensionShardSpec)
shardSpec).getDimension();
+ partitionSpec = new SingleDimensionPartitionsSpec(
+ tuningConfig.getRowsPerSegment(),
+ null,
+ partitionDimension,
+ false
+ );
+ } else if (Objects.equals(shardSpec.getType(), ShardSpec.Type.RANGE)) {
+ List<String> partitionDimensions = ((DimensionRangeShardSpec)
shardSpec).getDimensions();
+ partitionSpec = new DimensionRangePartitionsSpec(
+ tuningConfig.getRowsPerSegment(),
+ null,
+ partitionDimensions,
+ false
+ );
+ } else if (Objects.equals(shardSpec.getType(), ShardSpec.Type.NUMBERED)) {
+ // There is currently no way of specifying either maxRowsPerSegment or
maxTotalRows for an MSQ task.
+ // Hence using null for both which ends up translating to
DEFAULT_MAX_ROWS_PER_SEGMENT for maxRowsPerSegment.
+ partitionSpec = new DynamicPartitionsSpec(null, null);
Review Comment:
maybe use this spec :
https://github.com/apache/druid/blob/c72e69a8c8aff192a22f5f198e61722380832380/extensions-core/multi-stage-query/src/main/java/org/apache/druid/msq/indexing/MSQTuningConfig.java#L118
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
