Re:Why `fsync()`: Losing unsynced data on a single node lead...
by jvanlightly on Tuesday May 16, 2023 @12:32PM
(#35964218)
Protocol Aware Recovery is really needed if you want Raft to tolerate disk corruption. https://www.usenix.org/conference/fast18/presentation/alagap...
[ Parent
| on HN ]
Re:Why `fsync()`: Losing unsynced data on a single node lead...
by agallego on Tuesday May 16, 2023 @01:34PM
(#35965115)
the blog posts mentions that it is for any protocol that is non bft
Re:Why `fsync()`: Losing unsynced data on a single node lead...
by genxyz on Tuesday May 16, 2023 @02:26PM
(#35965727)
> Protocol Aware Recovery is really needed if you want Raft to tolerate disk corruption
I believe OP does not make any claims about arbitrary log corruption. Neither raft nor Kafka protocol can handle it. It is about losing tail of the log due to fsync failures or rather lack of fsyncs.