News for hackers. Stuff that matters.

A comment on Cassandra at Apple: 1000s of Clusters, 300k Nodes, 100 PB. Parent comment

Re:Cassandra at Apple: 1000s of Clusters, 300k Nodes, 100 PB by _benedict on Sunday October 09, 2022 @01:12PM (#33143129)
LWTs were added for a very simple reason: stronger isolation where the performance trade-off makes sense. Nothing to do with the GP comment.

Until recently they were indeed slow over the WAN, and they remain slow under heavy contention. They are now faster than peer features for WAN reads.

However, the claim that they have many bugs needs to be backed up. I just finished overhauling Paxos in Cassandra and it is now one of the most thoroughly tested distributed consensus implementations around.

[ Parent | on HN ]
Re:Cassandra at Apple: 1000s of Clusters, 300k Nodes, 100 PB by skyde on Sunday October 09, 2022 @07:00PM (#33146122)
LWT is still the only way to guarantee your write don’t random disappear and that conditional update are really conditional.

LWT still have awful performance compared to a write request with same guarantee in any other database.

[ Parent | on HN ]