An embedded db is used to cache sample-encode results. The current db sled isn't an ideal for here as it doesn't support concurrent access from multiple processes. There have also been a couple of reported db corruption cases, presumably from killing the process.
So time to try a different one. I'd prefer a nosql kv store but maybe sqlite will end up best?
An embedded db is used to cache sample-encode results. The current db sled isn't an ideal for here as it doesn't support concurrent access from multiple processes. There have also been a couple of reported db corruption cases, presumably from killing the process.
So time to try a different one. I'd prefer a nosql kv store but maybe sqlite will end up best?