GraphScope
GraphScope copied to clipboard
🔨 🍇 💻 🚀 GraphScope: A One-Stop Large-Scale Graph Computing System from Alibaba | 一站式图计算系统
**Describe the bug** Similar to issue #1753, GraphScope failed to compile app grape while running build-in graph algorithms. **To Reproduce** ```python import graphscope graphscope.set_option(show_log=True) test_edges_path = "/tmp/test.csv" sess = graphscope.get_default_session()...
**Describe the bug** Pegasus engine has updated many times, but its bench modules have not beed updated with the engine. Therefore, the bench modules now have many errors to be...
**Is your feature request related to a problem? Please describe.** In GraphScope's current version, starting a pegasus cluster needs to know all servers' IPs. It is not friendly in a...
**描述:** 在交互式查询引擎中,对于带有过滤条件的查询,计算会从存储中读取数据后进行过滤。由于目前我们采用的是 share-nothing 架构,计算和存储在同个进程,所以这种方式不会引入性能问题。但是后面我们计划向计算存储分离的架构演进,这样就需要把过滤条件下推到存储,从而减少计算和存储之间的数据交互。 **产出目标:** 1. 存储支持带有过滤条件的查询 (包括行过滤和列过滤) 2. 使用带有过滤条件的存储接口重新实现现有计算逻辑
As title, pass the following test with an eager mode session. ```python # add the same label "group" edges with different src dst labels def test_multi_src_dst_edge_loader(): graph = graphscope_session.g() graph...
GraphX provides several builtin apps, we shall override them will grape-based implementation. - [x] SSSP - [x] PageRank - [x] CC - [x] Stronly-CC - [x] Triangle count
**Is your feature request related to a problem? Please describe.** A clear and concise description of what the problem is. Ex. I'm always frustrated when [...] **Describe the solution you'd...
In order to mitigate the pressure of dealing with graphs with billions of vertices. Since the global vertex map implementation saves a copy of all vertices in each partition, scale...
背景 ----- `Operator` 是 `Kubernetes` 的扩展软件,它利用 [custom-resources](https://kubernetes.io/zh/docs/concepts/extend-kubernetes/api-extension/custom-resources/) 管理应用及其组件。 `Operator` 允许你在不修改 `Kubernetes` 自身代码的情况下,通过为一个或多个自定义资源关联[Controller](https://kubernetes.io/zh/docs/concepts/architecture/controller/) 来扩展集群的能力 `Operator` 的开发是为了处理 Kubernetes 控制器无法处理的复杂、有状态的应用程序。虽然像 `StatefulSets` 这样的 `Kubernetes` 控制器非常适合部署、维护和扩展简单的无状态应用程序,但它们无法处理对有状态资源的访问,或者无法升级、伸缩和备份更复杂的集群应用程序(如数据库)。 了解更多关于 `Operator` 的细节: https://kubernetes.io/docs/concepts/extend-kubernetes/operator/ GraphScope 的 `Kubernetes` 部署方式是复杂,有状态的部署,我们希望通过 `Operator`...
**Describe the bug** v0.13.0 K8S graphscope cluster will be unavailable after execute analytical_engine computing many time.(not test 0.14.0 yet) The edge data is 3.2G, and vertex data is 140M. Analytical_engine...