[Java] Investigate potential performance improvement of compression codec

In response to the discussion in https://github.com/apache/arrow/pull/8949/files#r588046787

There are some performance penalties in the implementation of the compression codecs (e.g. data copying between heap/off-heap data). We need to revise the code to improve the performance.

We should also provide some benchmarks to validate that the performance actually improves.

**Reporter**: [Liya Fan](https://issues.apache.org/jira/browse/ARROW-11901) / @liyafan82

_{**Note**: *This issue was originally created as [ARROW-11901](https://issues.apache.org/jira/browse/ARROW-11901). Please see the [migration documentation](https://github.com/apache/arrow/issues/14542) for further details.*}

Start with the compression codec implementation and the discussion in the linked pull request, focusing on the noted heap/off-heap data copying. Add benchmarks for the relevant codecs and use them to verify that any revised implementation improves performance.

Written by the indexing model from the issue text.