I'd be interested to see comparisons/benchmarks against FoundationDB. DynamoDB transactions make dynamo a serious alternative to FDB now. I can see the two manage advantages for FDB being: 1) you can deploy it on premise (which is potentially important for some B2B companies), 2) it shuffles data around so that hot-spotting of a cluster is eliminated (which dynamo appears to still suffer from).
On shrinking a cluster: you'll want to use the fdbcli to "exclude" nodes. Should be pretty straight forward (search the docs for the word "exclude").
On write amplification: a factor of 3x is not actually that unusual. The default RocksDB size amplification is 2x, and I've seen performant LSM trees with about 3x write amplification.
On the single threaded bottleneck: this is an inherent issue you have when you put your database over a network connection. LMDB can do 10k/100k+ reads/sec on a single thread since it's just doing syscalls. As soon as you start to need to distribute your database across more than 1 machine you start to need to parallelize you work for high throughput.