Storage Controller Asynchronous Event Reporting for VM Workload
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In multi-tenant cloud environments, the increasing number of virtual machines on storage devices leads to increased host overhead due to polling-based workload monitoring, which is inefficient and resource-intensive.
Innovation Solution
A storage device configured with a non-volatile memory device and a storage controller that sets and monitors workload thresholds for virtual machines, sending asynchronous event interrupts to the host when these thresholds are exceeded, thereby reducing host overhead.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If polling-based workload monitoring is used, then the host can monitor workload for each virtual machine, but the host overhead increases as the number of virtual machines increases
Solution Approach 1:
The storage device performs self-monitoring of workload by counting read/write commands locally, and self-reporting when thresholds are exceeded. This eliminates the need for the host to continuously poll for workload information, thereby reducing host overhead while maintaining accurate workload monitoring.
Solution Approach 2:
The storage device implements a feedback mechanism where it monitors its own workload, compares it against predefined thresholds, and automatically sends interrupt signals to the host when thresholds are exceeded. This closed-loop feedback system enables efficient workload monitoring without continuous host intervention.
2Productivity
If the number of virtual machines per storage device increases, then storage capacity utilization improves, but host overhead increases due to polling requirements
Solution Approach 1:
Each virtual machine's workload is monitored independently by the storage device itself, which counts commands and tracks thresholds locally. This self-monitoring capability allows the system to scale the number of virtual machines without proportionally increasing host overhead, as the storage device handles monitoring for all virtual machines.
3Ease of operation
If polling-based monitoring is used, then the host has control over workload monitoring, but resource consumption increases
Solution Approach 1:
The storage device autonomously monitors workload and generates feedback signals (interrupts) to the host only when necessary (when thresholds are exceeded). This event-driven feedback mechanism maintains host control over workload monitoring while dramatically reducing continuous resource consumption compared to polling-based approaches.
Data Source
AI summary
Disclosed is a storage device configured to receive a read command or a write command from a host device, the storage device comprising, a non-volatile memory device configured to store data, and a storage controller configured to operate at least one virtual machine to control the non-volatile memory device, store a workload threshold of the at least one virtual machine according to settings received from the host device, and send an asynchronous event interrupt to the host device based on the workload threshold, wherein the storage controller is further configured to, store the workload threshold for the at least one virtual machine, monitor read commands or write commands received from the host device to count and update a workload, and determine whether to send the asynchronous event interrupt based on the workload and the workload threshold.