Ship Computer or Data? Why not both?

https://www.usenix.org/conference/nsdi21/presentation/you

• Different computation intensity, measure the tput achieved at specific latency target

• How do we know when we don't know underlying workload?

• Rate limiting: latency

• Request arbitration: optimal fraction of request using ...

• Accommodate different target, but not a combination of targets

• Ship data

  • in distributed system, more flexible to deploy

• Ship code

  • Cannot re-deploy (interrupt the service)

  • Run-time changes of the server-extension

• Partial computation on server side

  • More fine-grained placement

  • Limitation: request rate is so high

    • Overhead?

• dimension for evaluating data moving cost

Now:

• cost is the latency, not the network bandwidth