Dynamic Job Task Division for Grid Computing Resource Allocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing distributed processing methods for jobs in grid computing face challenges such as inability to handle first-time jobs without profiles, inaccurate resource allocation, difficulty in transferring jobs to suitable resource environments, and reliance on centralized management for job scheduling, which limits flexibility and scalability.
Innovation Solution
A method and system for dynamically and autonomously dividing jobs into tasks and reallocating them across multiple computers based on real-time resource availability, using a center console to manage task distribution and execution, allowing for flexible resource assignment and adaptable job processing to meet service level agreements and objectives.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If a whole job is transferred to another resource environment as a unit, then the job can be relocated without modifying application layer code, but it is difficult to find a suitable transfer destination when the resource environment operates at high usage ratio
Solution Approach 1:
The patent divides a job into multiple independent tasks that can be transferred separately to different resource environments. Instead of moving the entire job as a single unit, individual tasks are segmented and can be allocated to available resources independently, solving the problem of finding suitable transfer destinations when resources are heavily utilized.
2Productivity
If task loads of all nodes are always checked and stored in shared memory, then dynamic load distribution can be achieved, but it is not guaranteed that a node with lower task load can always be located when needed
Solution Approach 1:
The patent implements a feedback mechanism where nodes continuously report their task load status to the shared memory, and this information is used to dynamically allocate tasks. The system monitors resource availability and adjusts task distribution based on real-time feedback, ensuring that tasks are reliably allocated to nodes with sufficient capacity while maintaining dynamic load distribution.
3Productivity
If job scheduling is performed only by a management server with centralized management of all computer information, then job scheduling can be performed based on operational status, but the system lacks flexibility and scalability
Solution Approach 1:
The patent enables each node to independently make scheduling decisions based on local resource status and task requirements, rather than requiring centralized control for every decision. This distributed approach allows nodes to autonomously evaluate their own capacity and accept or reject tasks locally, improving system flexibility and scalability while maintaining efficient job scheduling based on operational status.
4Manufacturing precision
If tasks are divided and transferred to another computer when completion time requirements are not met, then job completion requirements can be satisfied, but the process requires repeated estimation and division cycles
Solution Approach 1:
The patent performs preliminary estimation of task completion time before actual execution and division. By calculating expected completion times in advance based on task characteristics and resource capacity, the system can proactively identify tasks that may not meet completion requirements and pre-divide them into smaller sub-tasks, reducing the need for repeated estimation and division cycles during execution.
Data Source
AI summary
To implement job execution in which resource assignment and change of the assignment can be dynamically and autonomously performed so as to meet requirements of a job in a job and resource environment in which the operational status cannot be forecasted in advance. A job that can be divided into a selected number of tasks is provided to one computer of a plurality of computers connected via networks, and job tasks are processed with the one computer for predetermined time. A progress rate of task processing for the predetermined time is calculated, and completion time for task processing on the one computer is estimated on the basis of the progress rate and the predetermined time. It is determined whether the estimated completion time meets requirements of the job. When the estimated completion time meets the requirements, job tasks are processed with the one computer, and results are generated. When the estimated completion time does not meet the requirements, job tasks are divided into tasks to be left on the one computer and tasks to be transferred to another computer. The left job tasks are processed with the one computer for further predetermined time, and simultaneously, the tasks to be transferred are transferred to the other computer and the other computer is caused to process the transferred tasks.