A.J. Beamon

Remove native resource cleanup in Java finalizers

3

We deprecated the behavior of relying on Java finalizers for native resource cleanup a while ago in release 5.1. This PR now removes this behavior so that we don't have...

When a storage process gets disconnected from the cluster, the cluster builds up a backlog of work for it. When the process rejoins after a long separation (but before it...

Not all binding implementations follow the requirements of fdb_stop_network

6

In the current C API, it is required that `fdb_stop_network` be called and the network thread allowed to complete before terminating the program. It seems we aren't doing this in...

Add support for the new metadata version functionality to the directory layer

8

The new [metadata version](https://github.com/apple/foundationdb/pull/1213) functionality introduced in 6.1 could be helpful in the directory layer for determining whether a cached open directory has been deleted without needing to perform extra...

We had a report that someone configure a multi-region cluster with satellites and had the cluster fail to recover after excluding the satellite processes. This is the status reported by...

Clients fail to send read requests to all replicas

1

We recently encountered a situation where a two-storage-server team was hot with reads. At some point, one of these storage servers started experiencing noticeably more reads than the other. We...