Method and device of fault recovery based on super-fusion configuration

Abstract

The present invention discloses a method and device of fault recovery based on super-fusion configuration. The method comprises: collecting parameter information of each host in a super-fusion configuration platform and module information included by each tenant; comparing the parameter information of the hosts with preset fault parameters, and determining whether there is a host required being subjected to tenant migration or not according to a comparison result, if yes, generating a migration event, wherein the migration event carries a source host required being subjected to tenant migration and identification information of a target host; and selecting corresponding tenants to be migrated from the source host according to the type of the migration event, taking all the modules included by each tenant to be migrated as a migration object, and uniformly migrating the migration object into the target host according to the identification information of the target host. The method and device of fault recovery based on super-fusion configuration can migrate a plurality of modules included by the tenants into the same target host to avoid excessive flow hop count so as to avoid time delay increasing of network transmission and improve the transmission efficiency.

Description

technical field [0001] The present invention relates to the technical field of hardware fault recovery, in particular to a fault recovery method and device based on a hyper-converged architecture. Background technique [0002] HCI (Hyper-Converged Infrastructure): Hyper-converged infrastructure is also called hyper-converged architecture, which means that the same set of unit equipment (x86 server) not only has resources and technologies such as computing, network, storage and server virtualization, but also It also includes elements such as cache acceleration, deduplication, online data compression, backup software, and snapshot technology. Under this architecture, multiple host nodes are aggregated through the network to realize modular seamless horizontal expansion and form a unified resource pool. [0003] Tenant: Refers to customers who use system or computer computing resources. In multi-tenant technology, tenants include all data that can be identified as designated u...

AI Technical Summary

Problems solved by technology

This virtually increases the number of traffic hops

[0009] (2) Increase network transmission delay

[0010] While increasing the number of traffic hops, it will also increase the delay of network transmission. In extreme cases, data packet loss will occur, affecting user experience and low transmission efficiency.

Images