snleee commented on code in PR #9825:
URL: https://github.com/apache/pinot/pull/9825#discussion_r1036255304
##########
pinot-plugins/pinot-minion-tasks/pinot-minion-builtin-tasks/src/main/java/org/apache/pinot/plugin/minion/tasks/BaseMultipleSegmentsConversionExecutor.java:
##########
@@ -242,6 +256,17 @@ public List<SegmentConversionResult>
executeTask(PinotTaskConfig pinotTaskConfig
new
BasicHeader(FileUploadDownloadClient.CustomHeaders.SEGMENT_ZK_METADATA_CUSTOM_MAP_MODIFIER,
segmentZKMetadataCustomMapModifier.toJsonString());
+ String pushMode = configs.get(BatchConfigProperties.PUSH_MODE);
Review Comment:
Can we use the uniform naming convention? Is `pushMode` and `PushType`
different thing?
##########
pinot-plugins/pinot-minion-tasks/pinot-minion-builtin-tasks/src/main/java/org/apache/pinot/plugin/minion/tasks/BaseMultipleSegmentsConversionExecutor.java:
##########
@@ -276,6 +299,87 @@ 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);
+
+ URI outputSegmentDirURI = null;
+ if (taskConfigs.containsKey(BatchConfigProperties.OUTPUT_SEGMENT_DIR_URI))
{
+ outputSegmentDirURI =
URI.create(taskConfigs.get(BatchConfigProperties.OUTPUT_SEGMENT_DIR_URI));
+ }
+ try (PinotFS outputFileFS = MinionTaskUtils.getOutputPinotFS(taskConfigs,
outputSegmentDirURI)) {
+ switch
(BatchConfigProperties.SegmentPushType.valueOf(pushMode.toUpperCase())) {
+ case TAR:
+ try (PinotFS pinotFS = MinionTaskUtils.getLocalPinotFs()) {
+ SegmentPushUtils.pushSegments(
+ spec, pinotFS, Arrays.asList(outputSegmentTarURI.toString()),
headers, parameters);
+ } catch (RetriableOperationException | AttemptsExceededException e) {
+ throw new RuntimeException(e);
+ }
+ break;
+ case METADATA:
+ try {
+ 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);
+ }
+ 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 {
+ if
(!taskConfigs.containsKey(BatchConfigProperties.OUTPUT_SEGMENT_DIR_URI)) {
+ return localSegmentTarFile.toURI();
+ }
+ 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)) {
+ LOGGER.warn("Not overwrite existing output segment tar file: {}",
outputFileFS.exists(outputSegmentDirURI));
Review Comment:
What's the default value of `OVERWRITE_OUTPUT`? I think that it's `false`?
If the user doesn't pay attention to this config, they may get the false
impression that the data gets refreshed (because the minion job succeeded)
while it's actually not.
##########
pinot-integration-tests/src/test/java/org/apache/pinot/integration/tests/MergeRollupMinionClusterIntegrationTest.java:
##########
@@ -79,15 +81,18 @@ public class MergeRollupMinionClusterIntegrationTest
extends BaseClusterIntegrat
protected final File _segmentDir1 = new File(_tempDir, "segmentDir1");
protected final File _segmentDir2 = new File(_tempDir, "segmentDir2");
protected final File _segmentDir3 = new File(_tempDir, "segmentDir3");
+ protected final File _segmentDir4 = new File(_tempDir, "segmentDir4");
protected final File _tarDir1 = new File(_tempDir, "tarDir1");
protected final File _tarDir2 = new File(_tempDir, "tarDir2");
protected final File _tarDir3 = new File(_tempDir, "tarDir3");
+ protected final File _tarDir4 = new File(_tempDir, "tarDir4");
@BeforeClass
public void setUp()
throws Exception {
- TestUtils.ensureDirectoriesExistAndEmpty(_tempDir, _segmentDir1,
_segmentDir2, _segmentDir3, _tarDir1, _tarDir2,
- _tarDir3);
+ TestUtils.ensureDirectoriesExistAndEmpty(_tempDir,
Review Comment:
This is based on the pinot formatter?
--
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]
