[HUDI-4038] Avoid calling getDataSize after every record written
#5497
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,87 @@ | ||
| /* | ||
| * Licensed to the Apache Software Foundation (ASF) under one | ||
| * or more contributor license agreements. See the NOTICE file | ||
| * distributed with this work for additional information | ||
| * regarding copyright ownership. The ASF licenses this file | ||
| * to you under the Apache License, Version 2.0 (the | ||
| * "License"); you may not use this file except in compliance | ||
| * with the License. You may obtain a copy of the License at | ||
| * | ||
| * http://www.apache.org/licenses/LICENSE-2.0 | ||
| * | ||
| * Unless required by applicable law or agreed to in writing, software | ||
| * distributed under the License is distributed on an "AS IS" BASIS, | ||
| * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
| * See the License for the specific language governing permissions and | ||
| * limitations under the License. | ||
| */ | ||
|
|
||
| package org.apache.hudi.io.storage; | ||
|
|
||
| import org.apache.hadoop.fs.Path; | ||
| import org.apache.hudi.common.fs.FSUtils; | ||
| import org.apache.hudi.common.fs.HoodieWrapperFileSystem; | ||
| import org.apache.parquet.hadoop.ParquetFileWriter; | ||
| import org.apache.parquet.hadoop.ParquetWriter; | ||
| import org.apache.parquet.hadoop.api.WriteSupport; | ||
|
|
||
| import java.io.IOException; | ||
| import java.util.concurrent.atomic.AtomicLong; | ||
|
|
||
| /** | ||
| * Base class of Hudi's custom {@link ParquetWriter} implementations | ||
| * | ||
| * @param <R> target type of the object being written into Parquet files (for ex, | ||
| * {@code IndexedRecord}, {@code InternalRow}) | ||
| */ | ||
| public abstract class HoodieBaseParquetWriter<R> extends ParquetWriter<R> { | ||
|
|
||
| private static final int WRITTEN_RECORDS_THRESHOLD_FOR_FILE_SIZE_CHECK = 1000; | ||
|
|
||
| private final AtomicLong writtenRecordCount = new AtomicLong(0); | ||
| private final long maxFileSize; | ||
| private long lastCachedDataSize = -1; | ||
|
|
||
| public HoodieBaseParquetWriter(Path file, | ||
| HoodieBaseParquetConfig<? extends WriteSupport<R>> parquetConfig) throws IOException { | ||
| super(HoodieWrapperFileSystem.convertToHoodiePath(file, parquetConfig.getHadoopConf()), | ||
| ParquetFileWriter.Mode.CREATE, | ||
| parquetConfig.getWriteSupport(), | ||
| parquetConfig.getCompressionCodecName(), | ||
| parquetConfig.getBlockSize(), | ||
| parquetConfig.getPageSize(), | ||
| parquetConfig.getPageSize(), | ||
| parquetConfig.dictionaryEnabled(), | ||
| DEFAULT_IS_VALIDATING_ENABLED, | ||
| DEFAULT_WRITER_VERSION, | ||
| FSUtils.registerFileSystem(file, parquetConfig.getHadoopConf())); | ||
|
|
||
| // We cannot accurately measure the snappy compressed output file size. We are choosing a | ||
| // conservative 10% | ||
| // TODO - compute this compression ratio dynamically by looking at the bytes written to the | ||
| // stream and the actual file size reported by HDFS | ||
| this.maxFileSize = parquetConfig.getMaxFileSize() | ||
| + Math.round(parquetConfig.getMaxFileSize() * parquetConfig.getCompressionRatio()); | ||
| } | ||
|
|
||
| public boolean canWrite() { | ||
| // TODO we can actually do evaluation more accurately: | ||
|
Member
There was a problem hiding this comment. +1 to the overall idea. but here is the deal - the size may not update until a row group is actually flushed out to storage. so What pattern did you observe on writes to S3? is the I see the code here. which should respect the buffered data?
Contributor
Author
There was a problem hiding this comment.
It won't: it always returns accurate metric, b/c
With the second being the problem -- it always traverse all of the cached all groups to accurately calculate the in-memory footprint (and there's no internal caching). So what ended up happening it kept growing the buffer for the whole file (120Mb) not flushing in until closure which was making traversals quadratic in runtime. |
||
| // if we cache last data size check, since we account for how many records | ||
|
Member
There was a problem hiding this comment. Can we file a JIRA for this follow on work, after verifying the realtime ness of the
Contributor
Author
There was a problem hiding this comment. I validated that |
||
| // were written we can accurately project avg record size, and therefore | ||
| // estimate how many more records we can write before cut off | ||
| if (lastCachedDataSize == -1 || getWrittenRecordCount() % WRITTEN_RECORDS_THRESHOLD_FOR_FILE_SIZE_CHECK == 0) { | ||
| lastCachedDataSize = getDataSize(); | ||
| } | ||
| return lastCachedDataSize < maxFileSize; | ||
| } | ||
|
|
||
| @Override | ||
| public void write(R object) throws IOException { | ||
| super.write(object); | ||
| writtenRecordCount.incrementAndGet(); | ||
| } | ||
|
|
||
| protected long getWrittenRecordCount() { | ||
| return writtenRecordCount.get(); | ||
| } | ||
| } | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.