#low-latency #operator #distributed #data-flow #zenoh #composable #run-time

dora-coordinator

dora goal is to be a low latency, composable, and distributed data flow

36 releases

0.3.4 May 20, 2024
0.3.3 Apr 11, 2024
0.3.2 Jan 29, 2024
0.3.0 Nov 3, 2023
0.1.0 Jun 24, 2022

#2 in #data-flow

Download history 11/week @ 2024-02-19 25/week @ 2024-02-26 10/week @ 2024-03-11 13/week @ 2024-04-01 256/week @ 2024-04-08 15/week @ 2024-04-15 4/week @ 2024-04-29 151/week @ 2024-05-13 191/week @ 2024-05-20 6/week @ 2024-05-27 27/week @ 2024-06-03

375 downloads per month
Used in dora-cli

Apache-2.0

55KB
1.5K SLoC

Coordinator

Prototype for a process/library-based dora-rs implementation, instead of framework-based. The idea is that each operator is compiled as a separate executable. The dora-coordinator runtime is responsible for reading the dataflow descriptor file and launching the operators accordingly. The operators use a common library called dora-api, which implements the communication layer based on zenoh.

This approach has the following advantages:

  • Less overhead
    • No data transfer between a runtime and the operator
    • The compiler can inline and optimize the full process
  • More flexibility
    • Operators can be sync or async
    • They can decide how many threads and which execution model they use
    • The OS ensures fair share of resources (e.g. CPU time) -> no need to cooperate with other operators
    • Operators get all inputs immediately -> no need for input rules
    • Keeping local state is easily possible
  • Separate address spaces
    • The operators are isolated from each other.

There are drawbacks too, for example:

  • Less control
    • Processes run independently -> need to cooperate with the runtime, e.g. on stop signals
    • Operator migration is more difficult
  • Operators are always isolated
    • No way of using in-memory channels
    • Local sockets and shared memory should be still possible

Dependencies

~13–29MB
~424K SLoC