apache / apache/geaflow

Execution plan optimization for cases where a graph computation or graph traversal operator is followed directly by a sink

Open
#364 1 comment 1 reaction 0 assignees View on GitHub
hacktoberfest hard issue
Dominant language
Java
Stars
808
Forks
188
Avg merge
3d 22h
Merged PRs (30d)
2

Description

【需求描述】
1. 特定图计算/图遍历case执行计划优化:
当前存在如下场景,图遍历/图计算Node之后仅有Sink(或Map)节点Node时,执行时需要将遍历或计算的结果通过网络shuffle到下游节点。这里实际上可以进行优化,针对上述场景只需要local shuffle直接forward到本地下游节点输出即可。

【期望产出】
1. 针对特定场景优化执行计划和执行流程,以实现性能的优化。同时补充plan优化case以及e2e用例并跑通。

如有疑问请联系: @cbqiao @Loognqiang

Contributor guide

Open the contributing guide

Research direction

Start by tracing how execution plans handle a graph computation or traversal node followed directly by a sink or map node, then identify the plan-optimization and execution-flow entry points. Add the requested plan-optimization and end-to-end cases, and confirm that the optimized local-forward path runs successfully and improves the targeted scenario.

Written by the indexing model from the issue text.

Assessment

Tech stack
java
Domain
distributed-systems, performance, stream-processing
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.