Workload Controller Reactivating Purged Instances
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Underutilized workloads in computing environments occupy system resources unnecessarily, leading to increased operational costs for customers, as existing solutions either fail to provide efficient resource management or result in downtime when shutting down virtual machines.
Innovation Solution
A workload management system that includes a network traffic monitor, log analyzer, and workload controller to detect and manage underutilized workloads through phased purging and reactivation based on performance metrics and predefined policies, ensuring minimal downtime and cost savings.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If underutilized workloads are shut down to save operational costs, then resource utilization improves, but service availability deteriorates due to downtime
Solution Approach 1:
The system performs preliminary actions by monitoring workloads and identifying underutilized ones before shutting them down. Network traffic monitoring and log analysis are conducted in advance to detect access patterns, allowing the system to predict when workloads will be needed and prevent premature shutdown that would cause downtime.
Solution Approach 2:
The system implements feedback mechanisms through continuous monitoring of network traffic, logs, and workload performance metrics. This feedback loop allows the system to adjust workload management decisions in real-time, reactivating workloads when access is detected and optimizing the balance between cost savings and service availability.
2Loss of energy
If workload purging is performed aggressively to maximize resource efficiency, then operational cost decreases, but workload recovery time increases
Solution Approach 1:
The system performs preliminary monitoring and analysis before purging workloads, maintaining records of workload characteristics, access patterns, and performance metrics. This preliminary information is stored and used to enable rapid workload reconstruction and recovery when needed, significantly reducing recovery time.
Solution Approach 2:
The system creates and maintains copies of workload configurations, metadata, and performance profiles in the workload information database. These copies enable rapid reconstruction of purged workloads without requiring full reinitialization, thereby minimizing recovery time while still achieving resource efficiency through purging.
3Reliability
If all workloads are maintained active to ensure availability, then service reliability improves, but resource utilization deteriorates due to wasted capacity
Solution Approach 1:
The system implements dynamic workload management where the state of workloads (active, purged, or reactivating) changes based on real-time conditions. Workloads are dynamically adjusted between purged and active states according to monitored access patterns, performance metrics, and resource availability, optimizing both reliability and productivity continuously.
Solution Approach 2:
The system changes key parameters such as workload state, resource allocation, and monitoring intensity based on observed conditions. By adjusting these parameters dynamically - purging when underutilized, reactivating when accessed - the system optimizes the trade-off between service availability and resource utilization efficiency.
Data Source
AI summary
Examples described herein relate to a method and a system, for example, a workload controller, for accessing purged workloads. An alert indicative of an attempt to access a purged workload of workloads deployed in a workload environment may be received by the workload controller. The purged workload may include one or both of a deactivated workload or an archived workload. The workload controller may detect the attempt to access the purged workload based on port mirrored data traffic. Further, in some examples, the workload controller may activate the purged workload based on the alert.