2.2.1.1 About Automatic Service Placement

Exascale system components are implemented using a series of clustered software services. This topic describes the default automatic placement of the Exascale storage services.

By default, Exascale uses automatic service placement to ensure that the required Exascale storage services are available across the Exascale cluster. If Exascale detects that a storage service is not running, the service instance is automatically restarted on another node.

The following outlines the default automatic service placement methodology for Exascale storage services:

• Cluster Services (EGS)

  Every Exascale cluster contains five EGS instances.

  For Exascale clusters with five or more Exadata storage servers, one EGS instance runs on each of the first five storage servers.

  For Exascale configurations with fewer than five storage servers, one EGS instance runs on each Exadata storage server, and the remaining EGS instances run on the Exadata compute nodes to make up the required total of five. In a bare-metal configuration, EGS compute node instances run on the server operating system. In a configuration with compute nodes running on virtual machines (VMs), EGS compute node instances run in the hypervisor.

• Control Services (ERS)

  For Exascale clusters with five or more Exadata storage servers, a total of five ERS instances are distributed across the Exadata storage servers. The first three ERS instances contain front-end and back-end processes, and the final two instances only contain back-end processes.

  For Exascale configurations with fewer than five storage servers, one ERS instance runs on each storage server. The first three ERS instances contain front-end and back-end processes, and the remaining instances only contain back-end processes.

• System Vault Manager (SYSEDS) and User Vault Manager (USREDS)

  For Exascale clusters with five or more Exadata storage servers, a total of five SYSEDS instances and five USREDS instances are distributed across the Exadata storage servers.

  For Exascale configurations with fewer than five storage servers, one SYSEDS instance and one USREDS instance runs on each storage server.

• Block Store Manager (BSM) and Block Store Worker (BSW)

  By default, a total of three BSM instances and three BSW instances are distributed across the Exadata storage servers.

In all cases, the Exascale storage service instances are automatically distributed across the available storage servers with the aim of evenly distributing the overall workload.

In addition to the Exascale storage services governed by automatic service placement, every storage server that is associated with the Exascale cluster also contains the Instance Failure Detection (IFD) service and the core Exadata cell services: Cell Server (CELLSRV), Management Server (MS), and Restart Server (RS).