Distributed Failover for Multi-Tenant Server Farms
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Multi-tenant server farms face challenges in minimizing downtime during server failures, as existing failover techniques often result in unacceptably high durations of unavailability, leading to consumer dissatisfaction and potential loss of reputation for service providers.
Innovation Solution
A system and method for distributed failover in multi-tenant server farms, where each tenant's data is replicated to a different standby server, with a failover manager determining optimal placements of tenants across available servers to minimize downtime, using a replicated tenant placement selector and loader to quickly activate standby servers upon failure.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional failover techniques are used to ensure data availability, then data loss is prevented, but downtime during failover becomes unacceptably high
Solution Approach 1:
The patent applies preliminary action by pre-positioning replicated tenants on standby servers before failures occur. The system maintains replicated tenants in advance on backup servers, so when a failure happens, the failover can immediately activate the pre-positioned replica without needing to replicate data during the failure event, thus reducing downtime while ensuring data availability
2Loss of time
If replicated tenants are distributed across multiple standby servers, then failover time is reduced, but system complexity increases
Solution Approach 1:
The patent applies segmentation by dividing the failover process into independent parallel operations across multiple standby servers. Each standby server independently hosts and can activate a replicated tenant, allowing simultaneous failover operations rather than sequential processing. This segmentation reduces total failover time while the modular structure helps manage system complexity through clear separation of responsibilities
3Productivity
If optimal placement of replicated tenants is implemented, then resource utilization is optimized, but computational overhead for placement selection increases
Solution Approach 1:
The patent applies parameter changes by optimizing the placement of replicated tenants based on load time characteristics and server capabilities. The system selects placement parameters (which standby server hosts which replicated tenant) to minimize total failover time, balancing the distribution of replicated tenants across servers based on their loading speeds and capacity, thus optimizing resource utilization while managing computational overhead through focused optimization criteria
Data Source
AI summary
A failover manager may be configured to determine a plurality of tenants executable on a server of a plurality of servers, each tenant being a virtual machine executable on the server in communication with at least one corresponding user. The failover manager may include a replicated tenant placement selector configured to dispatch a first replicated tenant for a first tenant of the plurality of tenants to a first standby server of the plurality of servers, and configured to dispatch a second replicated tenant for a second tenant of the plurality of tenants to a second standby server of the plurality of servers. The failover manager also may include a replicated tenant loader configured to activate, based on a failure of the server, the first replicated tenant on the first standby server to replace the first tenant, and the second replicated tenant on the second standby server to replace the second tenant.