FAILURE RESILIENCY PROVISIONING

摘要

Aspects of provisioning computing units based on improved failure resiliency are described. In one embodiment, an infrastructure component shared between a pair of computing units is identified. A failure rate for the infrastructure component is obtained, and a failure probability for a class of assigned computing units is computed based in part on the failure rate. A spread request related to the class of assigned computing units is also received. In response to the spread request, an altered composition of computing units is determined, and a difference between a failure probability for the altered composition of computing units and the failure probability for the class of assigned computing units is computed. In one embodiment, when a spread score improvement value associated with the difference meets a spread criteria of the spread request, the altered composition of computing units may be provisioned for use.

主权项

1. A non-transitory computer-readable medium embodying a program executable in a computing device, the program comprising:
code that, for at least one pair of computing units in a class of assigned computing units, identifies a plurality of infrastructure components shared between the at least one pair of computing units; code that obtains a failure rate for individual ones of the plurality of infrastructure components; code that, based in part on the failure rate for the individual ones of the plurality of infrastructure components, computes a failure correlation for the at least one pair of computing units; code that computes a failure probability for the class of assigned computing units based in part on the failure correlation; code that, in response to receipt of a spread request related to the class of assigned computing units, determines an altered composition of the class of assigned computing units; code that computes a difference in failure resiliency between the failure probability for the class of assigned computing units and a failure probability for the altered composition of the class of assigned computing units; and code that provisions the altered composition of the class of assigned computing units when the difference in failure resiliency meets a spread criteria of the spread request.