Microservice Autoscaling via Weighted Priority Resource Allocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Data centers, especially on-premise and edge computing environments, face challenges in accommodating peak workloads due to insufficient compute resources, leading to performance degradation, and traditional autoscaling approaches fail to prioritize microservices effectively based on workload criticality.
Innovation Solution
A method and system for data center monitoring and management that identifies process flows with trace identifiers and weighted priorities, allowing for automatic scaling of microservices based on system resource availability, prioritizing critical workloads during peak periods.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional autoscaling approaches are used, then system resources are increased to accommodate peak workloads, but compute resources become insufficient and performance degradation occurs
Solution Approach 1:
The system changes the parameter of resource allocation from uniform to prioritized based on workload criticality. By assigning weighted priorities to different process flows and adjusting resource allocation parameters accordingly, the system can accommodate peak workloads for critical processes while maintaining performance stability through selective resource distribution.
Solution Approach 2:
The system segments the autoscaling process by individually managing different process flows based on their criticality levels. Each process flow is evaluated and scaled independently according to its weighted priority, allowing the system to allocate resources more effectively during peak periods and prevent performance degradation in critical workflows.
2Ease of operation
If all process flows are treated equally, then resource allocation is simplified, but critical workloads cannot be prioritized during peak periods
Solution Approach 1:
The system applies local quality by assigning different treatment levels to different process flows based on their criticality. Instead of uniform treatment, each process flow receives customized resource allocation decisions according to its weighted priority, enabling critical workloads to be prioritized while maintaining operational simplicity through automated priority-based decisions.
3Productivity
If system resources are increased to handle peak workloads, then workload capacity is improved, but resource efficiency decreases during normal operation
Solution Approach 1:
The system implements dynamic resource allocation that adapts to changing workload conditions. By continuously monitoring process flow execution and adjusting resource allocation in real-time based on actual demand and priority levels, the system can handle peak workloads when necessary while maintaining high resource efficiency during normal operation through selective scaling.
Data Source
AI summary
A system, method, and computer-readable medium for performing a data center management and monitoring operation. The data center management and monitoring operation includes: identifying a plurality of process flows executing on a system, each of the plurality of process flows having a trace identifier and a corresponding weighted priority; identifying a plurality of microservices associated with each of the plurality of process flows; determining when the system does not have enough system resources to execute all of the plurality of process flows; and, automatically scaling each of the plurality of microservices associated with each of the plurality of process flows when the system does not have enough system resources to execute all of the plurality of process flows.