Coordinator Node Task Impact Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In distributed computing environments, it is challenging to determine and manage the impact of user-initiated tasks on one node due to system/maintenance tasks executing on the same or another node, leading to difficulties in workload management across nodes.
Innovation Solution
A coordinator node distributes tasks across a cluster of nodes, determining the workload of storage drive devices on participant nodes and adjusting the number of threads on initiator nodes based on workload thresholds to dynamically reduce or increase the impact of tasks, using statistical data to identify 'hot' or 'cold' disks and applying impact policies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If system/maintenance tasks execute on the same node or another node, then system maintenance can be performed, but the impact on user-initiated tasks cannot be determined or managed effectively
Solution Approach 1:
The patent introduces a coordinator node as an intermediary that mediates between participant nodes (where tasks execute) and initiator nodes (where tasks are launched). The coordinator collects workload information from participant nodes and determines impact levels, enabling indirect measurement of task impact without requiring direct monitoring on each node. This resolves the difficulty of detecting task impact across distributed nodes.
Solution Approach 2:
The system implements feedback mechanisms where participant nodes report their workload status to the coordinator, which then determines impact levels and communicates back to initiator nodes. This feedback loop enables continuous monitoring and management of task impact, allowing the system to adapt task execution based on current workload conditions while maintaining system maintenance capabilities.
2Productivity
If tasks are distributed across multiple nodes, then system productivity increases, but workload management complexity increases
Solution Approach 1:
The patent segments the distributed system into distinct roles: coordinator nodes (for management), participant nodes (for task execution), and initiator nodes (for task submission). This segmentation allows workload management functions to be separated from task execution functions, reducing the complexity each individual node must handle while maintaining high overall productivity through distributed task execution.
Solution Approach 2:
The coordinator node performs multiple functions including collecting workload information, determining impact levels, and managing task distribution. This multi-functionality consolidates management complexity into a single node type, allowing participant and initiator nodes to focus on their primary functions while the coordinator handles the complexity of workload management across the distributed system.
3Speed
If the number of threads on initiator nodes is increased, then task execution speed improves, but the impact on storage drive devices increases
Solution Approach 1:
The system dynamically adjusts the number of threads on initiator nodes based on real-time workload conditions of storage drive devices. When storage drives are under heavy load, the coordinator reduces the number of threads on initiator nodes to decrease impact. When storage drives have available capacity, the coordinator increases threads to improve execution speed. This dynamic adjustment resolves the contradiction between speed and storage impact.
Solution Approach 2:
The coordinator changes the parameter of thread count on initiator nodes based on measured workload conditions. By monitoring storage drive utilization and adjusting the thread count parameter accordingly, the system optimizes task execution speed while preventing excessive impact on storage drives. This parameter adjustment allows the system to adapt to changing conditions and balance performance with resource protection.
Data Source
AI summary
Embodiments are directed towards managing an impact of a plurality of system and/or maintenance tasks distributed across a plurality of nodes. At least one initiator node may provide at least one disk request to at least one disk on at least one participant node. Each disk on each participant node with a workload, such as request wait time, above a maximum threshold and/or below a minimum threshold may be determined. If a disk is determined to have a workload above a maximum threshold and/or below a minimum threshold, then an impact of respective tasks on initiator nodes that provided requests to the determined disks may be reduced and/or increased, respectively. In some embodiments, an initiator node may reduce or increase an impact of a task by reducing or increasing a number of threads executing on that initiator node for that task.