alibaba / alibaba/euler

图存储的内存占用,以及split算子体现在何处?

Open
#287 4 comments 0 reactions 0 assignees View on GitHub
Dominant language
C++
Stars
2.9k
Forks
553
PR merge metrics
No merged PRs in 30d

Description

想请教关于euler 2.0的几个问题

1. 目前的图结构加载起来后是以什么形式存在?是以邻接表的形式完全存在内存中吗,还是只存点和边的id在内存,具体的features单独存? 如果不是全部在内存中,是以什么形式,耗费的内存大概占图大小的多少比例呢?
2. 文档里面说的分布式自动添加split和merge算子的代码位置具体在哪里呢,我看IDSplit好像并没有被实际调用?这个op主要好处是dag分布式情况下优化起来更方便吗
3. 目前分布式下对于一些多跳采样的操作,看文档描述感觉仍然要等前一度的点返回了才能进行下一度的采样,感觉dag并行调度的优势似乎没有办法充分得到体现?

看了文档和一点点代码之后有些疑问,不知道是否愿意帮忙答疑一下,谢谢!

Contributor guide

No contributing guide indexed for this repository

Research direction

Start with the Euler 2.0 documentation and the IDSplit references mentioned in the issue. Trace where distributed split and merge operators are documented or invoked, then compare that with the descriptions of graph loading and multi-hop sampling. Done means the storage model, operator locations, and scheduling behavior are documented clearly.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
distributed-systems, documentation
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.