umustafi commented on a change in pull request #3461:
URL: https://github.com/apache/gobblin/pull/3461#discussion_r801035053
##########
File path:
gobblin-data-management/src/test/java/org/apache/gobblin/data/management/copy/CopySourceTest.java
##########
@@ -196,6 +196,114 @@ public void testSubmitUnfulfilledRequestEvents()
Assert.assertEquals(fileSet.getTotalSizeInBytes(), 75);
}
+ @Test(expectedExceptions = IOException.class)
+ public void testFailIfAllAllocationRequestsRejected()
+ throws IOException, NoSuchMethodException, InvocationTargetException,
IllegalAccessException {
+ SourceState state = new SourceState();
+
+ state.setProp(ConfigurationKeys.SOURCE_FILEBASED_FS_URI, "file:///");
+ state.setProp(ConfigurationKeys.WRITER_FILE_SYSTEM_URI, "file:///");
+ state.setProp(ConfigurationKeys.DATA_PUBLISHER_FINAL_DIR, "/target/dir");
+ state.setProp(DatasetUtils.DATASET_PROFILE_CLASS_KEY,
+ TestCopyablePartitionableDatasedFinder.class.getCanonicalName());
+ state.setProp(CopySource.MAX_CONCURRENT_LISTING_SERVICES, 2);
+ state.setProp(CopyConfiguration.MAX_COPY_PREFIX + ".size", "50");
+ state.setProp(CopyConfiguration.MAX_COPY_PREFIX + ".copyEntities", "2");
+ state.setProp(CopyConfiguration.STORE_REJECTED_REQUESTS_KEY,
+
RequestAllocatorConfig.StoreRejectedRequestsConfig.ALL.name().toLowerCase());
+ state.setProp(ConfigurationKeys.METRICS_CUSTOM_BUILDERS,
"org.apache.gobblin.metrics.ConsoleEventReporterFactory");
+
+ CopySource source = new CopySource();
+
+ final FileSystem sourceFs = HadoopUtils.getSourceFileSystem(state);
+ final FileSystem targetFs = HadoopUtils.getWriterFileSystem(state, 1, 0);
+
+ int maxThreads = state
+ .getPropAsInt(CopySource.MAX_CONCURRENT_LISTING_SERVICES,
CopySource.DEFAULT_MAX_CONCURRENT_LISTING_SERVICES);
+
+ final CopyConfiguration copyConfiguration =
CopyConfiguration.builder(targetFs, state.getProperties()).build();
+
+ MetricContext metricContext = Instrumented.getMetricContext(state,
CopySource.class);
+ EventSubmitter eventSubmitter = new EventSubmitter.Builder(metricContext,
CopyConfiguration.COPY_PREFIX).build();
+ DatasetsFinder<CopyableDatasetBase> datasetFinder = DatasetUtils
+ .instantiateDatasetFinder(state.getProperties(), sourceFs,
CopySource.DEFAULT_DATASET_PROFILE_CLASS_KEY,
+ eventSubmitter, state);
+
+ IterableDatasetFinder<CopyableDatasetBase> iterableDatasetFinder =
+ datasetFinder instanceof IterableDatasetFinder ?
(IterableDatasetFinder<CopyableDatasetBase>) datasetFinder
+ : new IterableDatasetFinderImpl<>(datasetFinder);
+
+ Iterator<CopyableDatasetRequestor> requesterIteratorWithNulls = Iterators
+ .transform(iterableDatasetFinder.getDatasetsIterator(),
+ new CopyableDatasetRequestor.Factory(targetFs, copyConfiguration,
log));
+ Iterator<CopyableDatasetRequestor> requesterIterator =
+ Iterators.filter(requesterIteratorWithNulls,
Predicates.<CopyableDatasetRequestor>notNull());
+
+ Method m = CopySource.class.getDeclaredMethod("createRequestAllocator",
CopyConfiguration.class, int.class);
+ m.setAccessible(true);
+ PriorityIterableBasedRequestAllocator<FileSet<CopyEntity>> allocator =
+ (PriorityIterableBasedRequestAllocator<FileSet<CopyEntity>>)
m.invoke(source, copyConfiguration, maxThreads);
+ Iterator<FileSet<CopyEntity>> prioritizedFileSets =
+ allocator.allocateRequests(requesterIterator,
copyConfiguration.getMaxToCopy());
+ List<FileSet<CopyEntity>> fileSetList =
allocator.getRequestsExceedingAvailableResourcePool();
+ Assert.assertEquals(fileSetList.size(), 2);
Review comment:
where are the # of datasets coming from? The configurations above only
determine the max number of copy entities and size right? There might be
something I'm not seeing where the dataset finder finds many files from the
copy source.
--
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]
