scxwhite commented on issue #4311:
URL: https://github.com/apache/hudi/issues/4311#issuecomment-1015246379
I reproduced this problem using the following code. In the following code, I
repeatedly update 10000 pieces of data, but if I execute the following code
more than 5 times, the program will report an error.
The problem may occur in clustering. When merging small files, the old
submitted files are
obtained(SparkSizeBasedClusteringPlanStrategy#getFileSlicesEligibleForClustering).
@xushiyan @nsivabalan @vinothchandar @yihua
```
@Test
public void write() {
List<String> data = new ArrayList<>();
List<String> dtList = new ArrayList<>();
dtList.add("197001");
Random random = new Random();
for (int i = 0; i < 100000; i++) {
String dt = dtList.get(random.nextInt(dtList.size()));
data.add("{\"dt\":\"" + dt + "\",\"id\":\"" +
random.nextInt(10000) + "\",\"gmt_modified\":" + System.currentTimeMillis() +
"}");
}
Dataset<String> dataset = sparkSession.createDataset(data,
Encoders.STRING());
Dataset<Row> json = sparkSession.read().json(dataset);
json.printSchema();
int dataKeepTime = 5;
json.selectExpr("dt", "id", "gmt_modified", "'' as name").toDF()
.write()
.format("org.apache.hudi")
.option(HoodieTableConfig.TYPE.key(),
HoodieTableType.MERGE_ON_READ.name())
.option(DataSourceWriteOptions.OPERATION().key(),
WriteOperationType.UPSERT.value())
.option(DataSourceWriteOptions.TABLE_TYPE().key(),
HoodieTableType.MERGE_ON_READ.name())
.option(KeyGeneratorOptions.RECORDKEY_FIELD_NAME.key(), "id")
.option(KeyGeneratorOptions.PARTITIONPATH_FIELD_NAME.key(),
Constants.DT)
.option(KeyGeneratorOptions.HIVE_STYLE_PARTITIONING_ENABLE.key(), true)
.option(HoodieWriteConfig.PRECOMBINE_FIELD_NAME.key(),
Constants.UPDATE_TIME)
.option(HoodieWriteConfig.COMBINE_BEFORE_UPSERT.key(), true)
.option(HoodieWriteConfig.UPSERT_PARALLELISM_VALUE.key(),
200)
.option(HoodieWriteConfig.FINALIZE_WRITE_PARALLELISM_VALUE.key(), 200)
.option(HoodieWriteConfig.WRITE_PAYLOAD_CLASS_NAME.key(),
DefaultHoodieRecordPayload.class.getName())
.option(HoodieWriteConfig.AVRO_EXTERNAL_SCHEMA_TRANSFORMATION_ENABLE.key(),
false)
.option(HoodieWriteConfig.MARKERS_TYPE.key(),
MarkerType.DIRECT.toString())
.option(HoodieCompactionConfig.PAYLOAD_CLASS_NAME.key(),
DefaultHoodieRecordPayload.class.getName())
.option(HoodieCompactionConfig.CLEANER_FILE_VERSIONS_RETAINED.key(),
dataKeepTime)
.option(HoodieCompactionConfig.AUTO_CLEAN.key(), false)
.option(HoodieCompactionConfig.CLEANER_INCREMENTAL_MODE_ENABLE.key(), false)
.option(HoodieCompactionConfig.CLEANER_COMMITS_RETAINED.key(), dataKeepTime)
.option(HoodieCompactionConfig.MIN_COMMITS_TO_KEEP.key(),
dataKeepTime + 1)
.option(HoodieCompactionConfig.MAX_COMMITS_TO_KEEP.key(),
dataKeepTime + 2)
.option(HoodieCompactionConfig.TARGET_IO_PER_COMPACTION_IN_MB.key(), 500 * 1024)
.option(HoodieCompactionConfig.CLEANER_POLICY.key(),
HoodieCleaningPolicy.KEEP_LATEST_FILE_VERSIONS.name())
.option(HoodieCompactionConfig.PARQUET_SMALL_FILE_LIMIT.key(), 128 * 1024 *
1024)
.option(HoodieCompactionConfig.FAILED_WRITES_CLEANER_POLICY.key(),
HoodieFailedWritesCleaningPolicy.EAGER.name())
.option(HoodieStorageConfig.PARQUET_MAX_FILE_SIZE.key(), 256
* 1024 * 1024)
.option(HoodieCompactionConfig.INLINE_COMPACT.key(), true)
.option(HoodieCompactionConfig.INLINE_COMPACT_NUM_DELTA_COMMITS.key(), 1)
.option(HoodieClusteringConfig.INLINE_CLUSTERING.key(), true)
.option(HoodieClusteringConfig.INLINE_CLUSTERING_MAX_COMMITS.key(), 1)
.option(HoodieClusteringConfig.PLAN_STRATEGY_MAX_BYTES_PER_OUTPUT_FILEGROUP.key(),
256 * 1024 * 1024L)
.option(HoodieClusteringConfig.PLAN_STRATEGY_TARGET_FILE_MAX_BYTES.key(), 256 *
1024 * 1024L)
.option(HoodieClusteringConfig.PLAN_STRATEGY_SMALL_FILE_LIMIT.key(), 128 * 1024
* 1024L)
.option(HoodieClusteringConfig.UPDATES_STRATEGY.key(),
SparkRejectUpdateStrategy.class.getName())
.option(HoodieMetadataConfig.ENABLE.key(), true)
.option(HoodieMetadataConfig.MIN_COMMITS_TO_KEEP.key(),
dataKeepTime + 1)
.option(HoodieMetadataConfig.MAX_COMMITS_TO_KEEP.key(),
dataKeepTime + 2)
.option(HoodieMetadataConfig.CLEANER_COMMITS_RETAINED.key(),
dataKeepTime)
.option(HoodieClusteringConfig.PRESERVE_COMMIT_METADATA.key(), true)
.option(HoodiePayloadProps.PAYLOAD_ORDERING_FIELD_PROP_KEY,
Constants.UPDATE_TIME)
.option(HoodiePayloadProps.PAYLOAD_EVENT_TIME_FIELD_PROP_KEY,
Constants.UPDATE_TIME)
.option(HoodieIndexConfig.BLOOM_INDEX_KEYS_PER_BUCKET.key(),
100000)
.option(HoodieIndexConfig.BLOOM_INDEX_PARALLELISM.key(), 200)
.option(HoodieIndexConfig.BLOOM_INDEX_PRUNE_BY_RANGES.key(),
true)
.option(HoodieTableConfig.NAME.key(), "sucx")
.mode(SaveMode.Append)
.save("/tmp/hudi/sucx_test");
long hudi = sparkSession.read().format("hudi")
.load("/tmp/hudi/sucx_test")
.count();
if (hudi > 10000) {
throw new RuntimeException("count grater than 10000:" + hudi);
}
System.out.println("the count is:" + hudi);
}
```
--
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]
