your calculation does not account for the load generation and cross-az network cost
each shard had a 4TiB volume with 65k IOPS and 1,500 mbps of throughput
that's over 13k queries/sec per router core, about 50% of it is spent doing syscalls, the other 50%: parsing, doing grpc, tls, go gc, resolving the shards, waiting for the responses neki is still in platform preview,…
We used r8g.16xlarge instances with EBS disks, no nvmes
your calculation does not account for the load generation and cross-az network cost
each shard had a 4TiB volume with 65k IOPS and 1,500 mbps of throughput
that's over 13k queries/sec per router core, about 50% of it is spent doing syscalls, the other 50%: parsing, doing grpc, tls, go gc, resolving the shards, waiting for the responses neki is still in platform preview,…
We used r8g.16xlarge instances with EBS disks, no nvmes