Preferential Session Loading in Data Centers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data center configurations often result in unnecessary latency and increased potential for service disruption due to geographic separation, as clients may be routed to another data center for service during normal operations, even if the original data center can handle the request efficiently.
Innovation Solution
Implementing an autonomous system that manages global sessions by preferring service requests to be fulfilled within the original data center, using routing and configuration tables to route requests locally unless necessary, thus minimizing latency and reducing the likelihood of service disruptions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If data centers are geographically separated for redundancy, then reliability is improved, but latency increases and service disruption risk increases
Solution Approach 1:
The system segments service requests into two categories: routine requests handled locally at the original data center, and exceptional requests routed to the secondary data center. This segmentation allows the system to maintain geographic separation for reliability while confining most processing to a single location to minimize latency.
Solution Approach 2:
The patent introduces routing tables and configuration tables as intermediaries that intelligently direct service requests. These tables act as mediators that determine whether requests should be handled locally or routed remotely, optimizing the balance between reliability and latency without requiring direct client awareness of data center topology.
2Reliability
If clients are routed to secondary data center for redundancy, then service continuity is improved, but potential for service disruption increases
Solution Approach 1:
The system performs preliminary actions by pre-configuring routing tables and configuration tables before service disruptions occur. These tables are预先 prepared to direct routine requests to the original data center, ensuring that under normal conditions, service continuity is maintained without requiring active routing to the secondary center, thereby minimizing disruption risk.
Solution Approach 2:
Instead of the conventional approach where the secondary data center actively receives backup traffic, this patent inverts the approach by having the routing infrastructure actively prevent traffic from reaching the secondary center during normal operation. The secondary data center remains in standby mode, and only receives traffic when explicitly routed due to failures, thereby reducing its exposure to service disruptions.
Data Source
AI summary
A method comprises receiving, at a system from an application server, a request for a service, the system comprising two or more global session databases, and the request associated with a session; identifying among the two or more global session databases, a first global session database to fulfill the request based on a criteria; storing, by the application server, the session at the first global session database; and transmitting, by the session, data associated with the request for the service in accordance with a configuration table. Additional methods, systems, and non-transitory computer-readable media or computer program products provide similar or alternative functionality.


