Cassandra at Apple: 1000s of Clusters, 300k Nodes, 100 PB

Re:Cassandra at Apple: 1000s of Clusters, 300k Nodes, 100 PB by rockwotj on Saturday October 08, 2022 @10:13PM (#33137743)

> The fun thing is Cassandra was born at FB but they don’t run any Cassandra clusters there anymore.

Isn't Intragram mostly Cassandra?

[ Parent | on HN ]

Re:Cassandra at Apple: 1000s of Clusters, 300k Nodes, 100 PB by WookieRushing on Saturday October 08, 2022 @10:33PM (#33137819)

It wasn’t when I last saw it. Rocksandra ended up being a stepping stone to fbs most common distributed db, zippydb https://engineering.fb.com/2021/08/06/core-data/zippydb/

Zippydb is honestly one of the best parts of fb infra. It let you select levels of consistency vs latency

[ Parent | on HN ]

Re:Cassandra at Apple: 1000s of Clusters, 300k Nodes, 100 PB by petersellers on Sunday October 09, 2022 @02:30AM (#33138708)

> Zippydb is honestly one of the best parts of fb infra. It let you select levels of consistency vs latency

How is that different from Cassandra's Tunable consistency model?

[ Parent | on HN ]