Conversation

Replying to
FWIW the startup that I just joined (Zenith) is building an open source Postgres extension that uses log-structured storage. The design is much closer to Aurora than MyRocks, though - efficiency and write amp are not the main goal. Changes very little within the standard AMs.
2
7
Replying to
Nice paper, have been there too, now you trade one hard problem (managing writeback rate) for another. With a b-tree there is natural feedback when buffer pool is too dirty. With log-structured you usually lose that natural feedback, need new ways to find balance.
1
My work on indexing built on the observation that even when the system seriously misbehaves, most individual pages look just fine, most of the time. So all we need to do is make them look fine *all* of the time (kinda). "The whole is not the sum of its parts" -- applies here too.
1
Replying to
The question I have is given a similar amount of HW: 1) What are read, space & write-amp for b-tree vs this approach? 2) What are other side-effects. b-trees suffer from stalls if checkpoint can't keep up, does this other approach have problems? I don't expect an answer today.
2
Show replies