> that means they need to touch a disk upon each write or update
They don't fsync the wal on every write, it's probably done as group commit every x seconds or every x MB.
They don't fsync the wal on every write, it's probably done as group commit every x seconds or every x MB.
> I would expect stronger guarantees from databases.
You can configure it and get lower performance.
> Maybe it's inpractical to expect this in cloud environments...
For benchmarks they use raid0 on local disks(not EBS) in aws vps.