RFR: 8292698: Improve performance of DataInputStream

[Daniel Fuchs]

On Sun, 21 Aug 2022 07:21:08 GMT, Alan Bateman <alanb at openjdk.org> wrote:

> 'in' is a protected field so it requires thinking about subclasses that might change 'in', say when the input stream is asynchronously closed. BufferedInputStream is an example of a FilterInputStream that sets 'in' to null when asynchronously closed. There are other examples that change the underlying input stream to one that returns EOF when closed. So it might be that changing readChar/readInt/readLong is okay but it would have a bigger effect on readFully, skip and the other methods. So I think this is a case of proceeding with caution as there may be more gong on.

On the other hand I don't see anything checking for `in == null`, so if `in` was null a `NullPointerException` exception would occur, which I doubt is the behavior that the subclass is expecting. I agree that caution is warranted, but if `in` is actually set to `null` by subclasses we should probably double check how/when they rely in their super class behavior: some bugs might be lurking.

-------------

PR: https://git.openjdk.org/jdk/pull/9956