Cloud Request Routing by Tenant-Server Group Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional cloud computing environments require each application server to store significant amounts of static data for all tenants, leading to increased memory footprint and processing overhead due to inefficient request distribution policies.
Innovation Solution
Implement load balancing by assigning tenants to server groups based on historical traffic data, reducing the number of servers that need to store and manage static data for each tenant, and optimizing request distribution within these groups.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional request distribution policies are used where each application server stores static data for all tenants, then all servers can handle any tenant request, but memory footprint and processing overhead increase significantly
Solution Approach 1:
The patent segments the system into tenant groups and server groups, where each server group stores static data for only one tenant group rather than all tenants. This segmentation reduces the memory footprint on each server while maintaining the capability to handle tenant requests through load balancing between groups.
Solution Approach 2:
Each server group is assigned specific local quality characteristics by storing static data for a particular tenant group, rather than having uniform data storage across all servers. This local specialization reduces overall memory requirements while preserving request handling adaptability through the load balancer's ability to route requests to appropriate server groups.
2Adaptability or versatility
If each application server stores static data for all tenants, then complete tenant support is available, but processing overhead increases due to inefficient request distribution
Solution Approach 1:
The patent divides tenants into separate tenant groups, each associated with specific server groups. This segmentation eliminates the need for each server to process and manage static data for all tenants, reducing processing overhead while maintaining complete tenant support through the load balancing mechanism that routes requests to the appropriate server group.
Solution Approach 2:
The load balancer acts as an intermediary that manages the mapping between tenants and server groups. It handles the complexity of request distribution and server group selection, reducing the processing overhead on individual application servers while ensuring complete tenant support is maintained through intelligent routing.
3Quantity of substance
If tenants are distributed across fewer server groups, then memory footprint per server is reduced, but request distribution efficiency may be impacted
Solution Approach 1:
The patent implements dynamic load balancing that monitors and adjusts the distribution of tenant requests across server groups in real-time. This dynamic approach ensures that even with fewer server groups per tenant, request handling efficiency is maintained by actively optimizing the routing decisions based on current system state, preventing any degradation in productivity.
Data Source
AI summary
Methods, systems, and computer-readable storage media for receiving a first request parameter for each of the plurality of tenants, receiving a second request parameter for each of the plurality of tenants, assigning the plurality of tenants to an N plurality of tenant groups based on the first request parameter for each of the plurality of tenants, assigning each tenant in the N plurality of tenant groups to a server group in an M plurality of server groups based on the second request parameter for each of the plurality of tenants, and directing, by a load balancer, tenant requests of tenants in the plurality of tenants to servers based on the M plurality of server groups.