[kaushiks]

For the 16 byte (on x86_64) header (markOop, klass *).

[jcdavis]

The header is only 12 bytes with compressedOops (which most people use), but the long is aligned on an 8 byte boundary so the advantage is wasted here.

[alblue]

And even if the long wasn't on an aligned boundary, the object itself is. So you either have padding at the start or end of the object.