[jira] [Created] (FLINK-17330) Avoid scheduling deadlocks caused by intra-logical-region ALL-to-ALL blocking edges

[Shang Yuanchun (Jira)]

Zhu Zhu created FLINK-17330:
-------------------------------

             Summary: Avoid scheduling deadlocks caused by intra-logical-region ALL-to-ALL blocking edges
                 Key: FLINK-17330
                 URL: https://issues.apache.org/jira/browse/FLINK-17330
             Project: Flink
          Issue Type: Sub-task
          Components: Runtime / Coordination
    Affects Versions: 1.11.0
            Reporter: Zhu Zhu
             Fix For: 1.11.0


Imagine a job like this:
A --(pipelined FORWARD)--> B --(blocking ALL-to-ALL)--> D
A --(pipelined FORWARD)--> C --(pipelined FORWARD)--> D
parallelism=2 for all vertices.

We will have 2 execution pipelined regions:
R1={A1, B1, C1, D1}, R2={A2, B2, C2, D2}

R1 has a cross-region input edge (B2->D1).
R2 has a cross-region input edge (B1->D2).

Scheduling deadlock will happen since we schedule a region only when all its inputs are consumable (i.e. blocking partitions to be finished). Because R1 can be scheduled only if R2 finishes, while R2 can be scheduled only if R1 finishes.

To avoid this, one solution is to force a logical pipelined region with intra-region ALL-to-ALL blocking edges to form one only execution pipelined region, so that there would not be cyclic input dependency between regions.
Besides that, we should also pay attention to avoid cyclic cross-region POINTWISE blocking edges.



--
This message was sent by Atlassian Jira
(v8.3.4#803005)