jnturton commented on a change in pull request #2463:
URL: https://github.com/apache/drill/pull/2463#discussion_r809190253
##########
File path:
exec/java-exec/src/main/java/org/apache/drill/exec/store/parquet/compression/DrillCompressionCodecFactory.java
##########
@@ -80,38 +99,56 @@ public DrillCompressionCodecFactory(Configuration config,
ByteBufferAllocator al
}
@Override
- public BytesInputCompressor getCompressor(CompressionCodecName codecName) {
+ public synchronized BytesInputCompressor getCompressor(CompressionCodecName
codecName) {
if (AIRCOMPRESSOR_CODECS.contains(codecName)) {
return airCompressors.computeIfAbsent(
codecName,
c -> new AirliftBytesInputCompressor(codecName, allocator)
);
+ } else if (codecName != CompressionCodecName.SNAPPY) {
+ // Work around PARQUET-2126: construct a new codec factory every time to
+ // avoid a concurrrency bug c.f. DRILL-8139. Remove once PARQUET-2126 is
+ // fixed. Snappy is immune because of the thread safety in the Xerial
lib.
+ CompressionCodecFactory ccf =
CodecFactory.createDirectCodecFactory(config, allocator, pageSize);
+ // hold onto a reference for later release()
+ singleUseFactories.add(ccf);
+ return ccf.getCompressor(codecName);
} else {
return parqCodecFactory.getCompressor(codecName);
}
}
@Override
- public BytesInputDecompressor getDecompressor(CompressionCodecName
codecName) {
+ public synchronized BytesInputDecompressor
getDecompressor(CompressionCodecName codecName) {
if (AIRCOMPRESSOR_CODECS.contains(codecName)) {
return airCompressors.computeIfAbsent(
codecName,
c -> new AirliftBytesInputCompressor(codecName, allocator)
);
+ } else if (codecName != CompressionCodecName.SNAPPY) {
Review comment:
@vvysotskyi oh of course, snappy is in aircompressor now.
--
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]