Dynamic Computing Cluster Scaling via Endpoint Migration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Cluster-based computing solutions face inefficiencies in resource allocation due to fluctuating or limited duration resource requirements, leading to underutilization and increased costs, particularly during periods of low demand, and scaling these clusters is complicated by data transfer and service downtime.
Innovation Solution
A method for dynamically scaling computing clusters by creating a new cluster with adjusted node numbers or types in response to utilization thresholds, using a cluster control interface to initiate data copying from the current cluster, allowing for seamless transition with minimal downtime and maintaining efficient resource allocation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If computing resources are scaled to accommodate maximum resource requirements, then reliability is improved, but resource utilization efficiency deteriorates
Solution Approach 1:
The patent implements dynamic scaling of computing clusters by automatically adding or removing nodes based on real-time resource utilization thresholds. The system transitions from static over-provisioning to dynamic adaptation, adjusting cluster size to match actual demand while maintaining reliability during peak loads and improving efficiency during low-utilization periods.
2Productivity
If computing cluster is scaled to maintain efficient resource utilization, then resource utilization efficiency is improved, but service continuity deteriorates
Solution Approach 1:
The system performs preliminary actions by pre-warming new nodes before traffic switching, copying necessary data and configurations in advance. This preparation ensures that nodes are ready to handle traffic immediately upon activation, minimizing service disruption during scaling operations.
Solution Approach 2:
The patent introduces a traffic switching mechanism that acts as an intermediary between old and new nodes during scaling operations. Traffic can be gradually shifted from old nodes to new nodes, allowing for seamless transitions that maintain service continuity while enabling efficient resource utilization through dynamic scaling.
3Adaptability or versatility
If data transfer is performed during cluster scaling, then adaptability is improved, but service downtime increases
Solution Approach 1:
Data transfer and node preparation are performed as preliminary actions before traffic switching occurs. New nodes are pre-configured and data is copied in advance, so that when scaling is triggered, the actual service disruption is minimized to just the traffic switching moment rather than the entire data transfer duration.
Data Source
AI summary
A currently operating computing cluster that has multiple nodes storing cluster data may be scaled. A cluster scaling request may be received for the current cluster indicating a change in a number or type of nodes in the current cluster. In response to receiving the cluster scaling request, a new cluster may be created as indicated in the cluster scaling request, a copy of the cluster data from the current cluster to the nodes in the new cluster may be initiated, a network endpoint for the current cluster may be moved to the new cluster, and the current cluster may be disabled. The current cluster may, in some embodiments, respond to read access requests during the copy of the cluster data.