News for hackers. Stuff that matters.

ali_hao

Geo-replicated log sounds like a very ambitious and impressive project. As what blog says, the DistributedLog just customizes data placement policy to support geo-replication. Does that mean it runs same stack within datacenter vs across multiple datacenters? What kind of performance it could achieve? I am hoping twitter could disclose more details on that, such as concerns and experiences on geo-replication log, comparison with spanner and CockroachDB.