At the moment, PostgreSQL keeps all versions of all tuples in its heap files. Inserts, updates, and deletes all result in addition of new tuples to the heap, and the engine keeps track of which transactions can see which tuples. The vacuum process deletes tuples which are no longer needed, but in the meantime, there is bloat.

zheap would keep only the latest version of each tuple in its heap files. When a tuple got updated or deleted, the engine would move the old version into separate storage, the "undo" log. A vacuum process would need to clean up the undo log, but the heap would remain unbloated.

This is obviously very practical. But it's a shame that it introduces an asymmetry, where some transactions will be reading tuples from the heap, and some will need to root around in the undo log.

I note that this is the approach that Oracle has always used - as explained in this fine article by the same chap who wrote the blog post about zheap above:

https://www.enterprisedb.com/blog/databases-different-approa...