> So a little bit of data loss is okay, but a lot isn't?
No data loss is OK. However, delaying acknowledgement to the network client requesting the db update often is OK. Especially if your protocol allows many simultaneous requests to be in flight with asynchronous completion notification. (Similar to how TCQ on a hard drive works)
Right now it's very hard to do this type of workload efficiently. That's a pity because with write-notifications you could do it with zero extra I/O cost.
No data loss is OK. However, delaying acknowledgement to the network client requesting the db update often is OK. Especially if your protocol allows many simultaneous requests to be in flight with asynchronous completion notification. (Similar to how TCQ on a hard drive works)
Right now it's very hard to do this type of workload efficiently. That's a pity because with write-notifications you could do it with zero extra I/O cost.