zhtaoxiang commented on code in PR #9825:
URL: https://github.com/apache/pinot/pull/9825#discussion_r1038386220
##########
pinot-plugins/pinot-minion-tasks/pinot-minion-builtin-tasks/src/main/java/org/apache/pinot/plugin/minion/tasks/MinionTaskUtils.java:
##########
@@ -67,7 +73,40 @@ static PinotFS getOutputPinotFS(Map<String, String>
taskConfigs, URI fileURI)
return PinotFSFactory.create(fileURIScheme);
}
- static PinotFS getLocalPinotFs() {
+ public static Map<String, String> getPushTaskConfig(String tableName,
Map<String, String> taskConfigs,
+ ClusterInfoAccessor clusterInfoAccessor) {
+ try {
+ String pushMode = IngestionConfigUtils.getPushMode(taskConfigs);
+ Map<String, String> singleFileGenerationTaskConfig = new
HashMap<>(taskConfigs);
+ if (pushMode == null ||
pushMode.contentEquals(BatchConfigProperties.SegmentPushType.TAR.toString())) {
+ singleFileGenerationTaskConfig.put(BatchConfigProperties.PUSH_MODE,
+ BatchConfigProperties.SegmentPushType.TAR.toString());
+ } else {
+ URI outputDirURI = URI.create(clusterInfoAccessor.getDataDir() + "/" +
tableName);
+ String outputDirURIScheme = outputDirURI.getScheme();
+
+ if (!isLocalOutputDir(outputDirURIScheme)) {
+
singleFileGenerationTaskConfig.put(BatchConfigProperties.OUTPUT_SEGMENT_DIR_URI,
outputDirURI.toString());
+ singleFileGenerationTaskConfig.put(BatchConfigProperties.PUSH_MODE,
pushMode);
Review Comment:
nit: should we set push_mode to `metadata` when the provided one is `URI`?
and we should log this change.
##########
pinot-plugins/pinot-minion-tasks/pinot-minion-builtin-tasks/src/main/java/org/apache/pinot/plugin/minion/tasks/BaseMultipleSegmentsConversionExecutor.java:
##########
@@ -276,6 +300,84 @@ public List<SegmentConversionResult>
executeTask(PinotTaskConfig pinotTaskConfig
}
}
+ private void pushSegment(String tableName, Map<String, String> taskConfigs,
URI outputSegmentTarURI,
+ List<Header> headers, List<NameValuePair> parameters) throws Exception {
+ String pushMode = taskConfigs.get(BatchConfigProperties.PUSH_MODE);
+ LOGGER.info("Trying to push Pinot segment with push mode {} from {}",
pushMode, outputSegmentTarURI);
+
+ PushJobSpec pushJobSpec = new PushJobSpec();
+ pushJobSpec.setPushAttempts(DEFUALT_PUSH_ATTEMPTS);
+ pushJobSpec.setPushParallelism(DEFAULT_PUSH_PARALLELISM);
+ pushJobSpec.setPushRetryIntervalMillis(DEFAULT_PUSH_RETRY_INTERVAL_MILLIS);
+
pushJobSpec.setSegmentUriPrefix(taskConfigs.get(BatchConfigProperties.PUSH_SEGMENT_URI_PREFIX));
+
pushJobSpec.setSegmentUriSuffix(taskConfigs.get(BatchConfigProperties.PUSH_SEGMENT_URI_SUFFIX));
+
+ SegmentGenerationJobSpec spec = generatePushJobSpec(tableName,
taskConfigs, pushJobSpec);
+
+ switch
(BatchConfigProperties.SegmentPushType.valueOf(pushMode.toUpperCase())) {
+ case TAR:
+ try (PinotFS pinotFS = MinionTaskUtils.getLocalPinotFs()) {
+ SegmentPushUtils.pushSegments(
+ spec, pinotFS,
Collections.singletonList(outputSegmentTarURI.toString()), headers, parameters);
+ } catch (RetriableOperationException | AttemptsExceededException e) {
+ throw new RuntimeException(e);
+ }
+ break;
+ case METADATA:
+ if
(taskConfigs.containsKey(BatchConfigProperties.OUTPUT_SEGMENT_DIR_URI)) {
+ URI outputSegmentDirURI =
URI.create(taskConfigs.get(BatchConfigProperties.OUTPUT_SEGMENT_DIR_URI));
+ try (PinotFS outputFileFS =
MinionTaskUtils.getOutputPinotFS(taskConfigs, outputSegmentDirURI)) {
+ Map<String, String> segmentUriToTarPathMap =
+
SegmentPushUtils.getSegmentUriToTarPathMap(outputSegmentDirURI, pushJobSpec,
+ new String[]{outputSegmentTarURI.toString()});
+ SegmentPushUtils.sendSegmentUriAndMetadata(spec, outputFileFS,
segmentUriToTarPathMap, headers, parameters);
+ } catch (RetriableOperationException | AttemptsExceededException e) {
+ throw new RuntimeException(e);
+ }
+ } else {
+ throw new RuntimeException("Output dir URI missing for metadata
push");
+ }
+ break;
+ default:
+ throw new UnsupportedOperationException("Unrecognized push mode - " +
pushMode);
+ }
+ }
+
+ private SegmentGenerationJobSpec generatePushJobSpec(String tableName,
Map<String, String> taskConfigs,
+ PushJobSpec pushJobSpec) {
+
+ TableSpec tableSpec = new TableSpec();
+ tableSpec.setTableName(tableName);
+
+ PinotClusterSpec pinotClusterSpec = new PinotClusterSpec();
+
pinotClusterSpec.setControllerURI(taskConfigs.get(BatchConfigProperties.PUSH_CONTROLLER_URI));
+ PinotClusterSpec[] pinotClusterSpecs = new
PinotClusterSpec[]{pinotClusterSpec};
+
+ SegmentGenerationJobSpec spec = new SegmentGenerationJobSpec();
+ spec.setPushJobSpec(pushJobSpec);
+ spec.setTableSpec(tableSpec);
+ spec.setPinotClusterSpecs(pinotClusterSpecs);
+ spec.setAuthToken(taskConfigs.get(BatchConfigProperties.AUTH_TOKEN));
+
+ return spec;
+ }
+
+ private URI moveSegmentToOutputPinotFS(Map<String, String> taskConfigs, File
localSegmentTarFile)
+ throws Exception {
+ URI outputSegmentDirURI =
URI.create(taskConfigs.get(BatchConfigProperties.OUTPUT_SEGMENT_DIR_URI));
+ try (PinotFS outputFileFS = MinionTaskUtils.getOutputPinotFS(taskConfigs,
outputSegmentDirURI)) {
+ URI outputSegmentTarURI = URI.create(outputSegmentDirURI +
localSegmentTarFile.getName());
+ if
(!Boolean.parseBoolean(taskConfigs.get(BatchConfigProperties.OVERWRITE_OUTPUT))
&& outputFileFS.exists(
+ outputSegmentDirURI)) {
Review Comment:
We should check existence of the segment (i.e. `outputSegmentDirURI + / +
segmentName`) but not the `outputSegmentDirURI`, right?
--
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...@pinot.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@pinot.apache.org
For additional commands, e-mail: commits-h...@pinot.apache.org
