apurtell commented on pull request #3691: URL: https://github.com/apache/hbase/pull/3691#issuecomment-926269774
I spent some time today optimizing the LZMA codec. Yes, it is a super slow compressor (by design), but actually decompression is faster than both gzip and bzip2, if... XZ for Java has an option where you can implement a cache for byte and int arrays to speed things up, and so I did that, also optimizing the zeroing of those arrays with Unsafe. The pure Java decompressor is now faster than our native Hadoop codec, for what it's worth. -- 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]
