Service Request Routing via Latency-Based Host Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems for routing service requests in decentralized enterprise computing environments face challenges in ensuring seamless service discovery, reliable request routing, and transparent capacity addition, especially in the presence of host failures and network partitions.
Innovation Solution
A computer-implemented method that routes service requests by receiving a request, discovering candidate hosts based on measured latencies, and selecting a host from a hierarchical organization of hosts to dispatch the request, utilizing a logical model with leaf nodes and zones to optimize routing decisions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If services are replicated across multiple hosts in different data centers to improve scaleability and availability, then service availability and scaleability are improved, but system complexity and difficulty of managing service discovery and request routing increase
Solution Approach 1:
The system segments the distributed service infrastructure into hierarchical zones (e.g., data center zones, regional zones, global zones) that organize hosts and services into manageable groups. Each zone maintains local service discovery information, reducing the complexity of managing global service replication while maintaining availability across multiple data centers.
Solution Approach 2:
The patent introduces intermediary components including a service registry that maintains service information, load balancers that manage request distribution, and DNS-based service discovery mechanisms that translate service names to host locations. These intermediaries abstract the complexity of service replication and routing from individual applications.
2Quantity of substance
If a decentralized service framework is used to meet processing requirements with low-cost server resources, then cost efficiency is improved, but reliability under host failures and network partitions deteriorates
Solution Approach 1:
The system dynamically changes routing parameters based on host health status and network conditions. When hosts fail or network partitions occur, the service registry updates service location information and routing policies adjust to redirect requests away from failed components, maintaining reliability despite using numerous low-cost servers.
Solution Approach 2:
The patent implements health check mechanisms and failure detection systems that monitor host status beforehand. When failures are detected, the system proactively updates routing information and redirects traffic before affected hosts can impact service delivery, cushioning against the reliability issues inherent in decentralized architectures.
3Loss of time
If service requests are routed to hosts based on measured latencies, then end-to-end latency is reduced, but the complexity of implementing and maintaining latency measurement and selection logic increases
Solution Approach 1:
The system performs preliminary latency measurements and host selection before actual service requests arrive. Load balancers and service registry maintain pre-computed routing tables based on historical latency data and current system state, allowing requests to be routed efficiently without real-time complexity while still achieving low latency.
Solution Approach 2:
The patent implements feedback loops where latency measurements from service requests are continuously collected and used to update routing decisions. The service registry and load balancers adjust routing policies based on measured performance, creating a self-optimizing system that reduces latency while managing complexity through automated adaptation.
Data Source
AI summary
A computer-implemented method routes service requests to services in a service framework provided by a plurality of hosts. The method comprises receiving a service request for a service in the service framework and discovering a plurality of candidate hosts that host the service. The plurality of candidate hosts are a subset of the plurality of hosts. The method further comprises selecting a candidate host from the plurality of candidate hosts based on measured latencies for the plurality of candidate hosts and routing the service request to the selected candidate host.