OmniOperator, OmniMV, OmniShuffle, OmniAdvisor, and OmniHBaseGSI

A storage-compute coupled networking architecture is recommended for the subfeatures. Storage nodes and compute nodes are shared to maximize the computing acceleration effect in big data scenarios. If OmniShuffle and OmniOperator are used together, you are also advised to plan the network based on this section. If OmniData and OmniOperator are used together, a storage-compute decoupled networking architecture is recommended instead.

The example environment planned in this document for OmniOperator, OmniMV, OmniShuffle, OmniAdvisor, and OmniHBaseGSIconsists of four servers, which are one management node and three compute nodes. The coupled storage and compute network is used. In the following, we will be using HDFS as the storage node for illustration:

• The management node is server1 for managing tasks.
• The compute nodes are agent1, agent2, and agent3, which are used to run OmniOperator, OmniMV, and OmniShuffle query engine services and store datasets.

A server can function as a management node and a compute node at the same time. In single-node mode, operations performed on the management node or compute node mentioned in the following sections are performed on the same node. Figure 1 shows the networking diagram.