Resource Management System for Array Controller Latency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Data handling systems with multiple servers face performance degradation due to input/output latency issues caused by unmanaged resource consumption, particularly in array controller systems where internal queues become overwhelmed, leading to long latencies.
Innovation Solution
A method that monitors queue depth in critical resource queues, prevents subsequent commands from client/server combinations that exceed resource consumption thresholds, and manages resource usage by queuing identifiers on a waiting list, re-enabling commands as resource consumption declines, ensuring fair allocation and optimal usage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If hosts generate and supply more input/output traffic to array controllers, then resource utilization and productivity improve, but input/output latency increases and performance degrades
Solution Approach 1:
The array controller monitors queue depth in critical resource queues and uses this feedback to dynamically adjust host input/output traffic. When queue depth exceeds a threshold, the controller prevents subsequent commands from being issued, creating a feedback loop that maintains optimal latency while maximizing throughput
Solution Approach 2:
The system dynamically adjusts the level of host input/output traffic based on real-time resource consumption conditions. The controller transitions between allowing normal traffic flow and preventing subsequent commands based on queue depth thresholds, making the system adaptive to changing load conditions
2Productivity
If array controllers increase internal queue capacity to handle more traffic, then processing capability improves, but device complexity and resource consumption increase
Solution Approach 1:
The system segments hosts into different categories based on their resource consumption patterns. By identifying and managing hosts that exceed thresholds separately from normal hosts, the controller can apply different traffic management policies without restructuring the entire queue system
Solution Approach 2:
The system changes the operational parameters of host input/output traffic by preventing subsequent commands when thresholds are exceeded. This parameter change (from allowing to blocking commands) controls resource consumption without requiring physical queue expansion
3Productivity
If hosts supply maximum work to array controllers, then resource utilization improves, but acceptable latency cannot be maintained
Solution Approach 1:
The monitoring and prevention mechanism provides continuous feedback that regulates host work supply. Hosts supply maximum work when resources are available, but feedback from queue depth monitoring automatically reduces work supply by preventing subsequent commands when latency thresholds would be violated
Data Source
AI summary
A method of managing critical resource usage comprises monitoring queue depth in at least one critical resource queue for a high level of resource consumption and preventing subsequent commands of a client/server combination in response to a command that increases resource consumption to the high level. The method further comprises queuing an identifier of the client/server combination on a waiting queue, removing the client/server combination identifier from the waiting queue in queuing order as resource consumption declines, and enabling commands of the client/server combination.