Job Concurrency Hints for Parallel Processing Overhead Reduction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Distributed database systems face inefficiencies due to high overhead costs associated with scheduling and initiating numerous small jobs, leading to overloading of processors and reduced processing efficiency.

Innovation Solution

A method that utilizes a job concurrency hint to select and manage the number and type of jobs sent to a processor, balancing the load by considering current and historical job data, thereby reducing initiation and scheduling overhead.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If numerous small jobs are scheduled for processing, then the utilization of processor resources increases, but the overhead costs for scheduling and initiating jobs increase significantly

Engineering Contradiction:

Improveprocessor resource utilizationVSAvoidscheduling and initiation overhead

Core Design Contradiction:

ProductivityVSLoss of energy

Solution Approach 1:

The patent merges multiple small jobs into larger composite jobs to reduce the frequency of job scheduling and initiation operations. By combining several individual job units into a single composite job that processes multiple data sets sequentially, the system maintains processor utilization while significantly reducing the overhead associated with repeated job scheduling and initialization operations.

Inventive Principle:

Principle #5Merging (Combining)

2Productivity

If the number of jobs in the job scheduler is increased, then more work can be processed in parallel, but the processor becomes overloaded and efficiency decreases

Engineering Contradiction:

Improveparallel processing capacityVSAvoidprocessor efficiency

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The patent implements dynamic job submission based on real-time processor load conditions. The system continuously monitors processor utilization and adjusts the rate of job submission accordingly, submitting jobs when processor capacity is available and pausing when the processor is overloaded. This dynamic approach maintains optimal parallel processing capacity while preventing processor overload and efficiency degradation.

Inventive Principle:

Principle #15Dynamics

3Adaptability or versatility

If small jobs are frequently scheduled, then detailed processing tasks can be executed, but the initiation overhead for each job reduces overall efficiency

Engineering Contradiction:

Improveprocessing task granularityVSAvoidinitiation overhead time

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The patent combines multiple fine-grained processing tasks into a single composite job that executes sequentially. Instead of scheduling numerous small jobs for individual data set processing, the system creates composite jobs that process multiple data sets in sequence, thereby maintaining task granularity and adaptability while dramatically reducing the time lost to repeated job initiation overhead.

Inventive Principle:

Principle #5Merging (Combining)

Data Source

PatentUS10459760B2Optimizing job execution in parallel processing with improved job scheduling using job currency hints

Publication Date: 2019.10.29 SAP SE

AI summary

Scheduling jobs from an application based on a job concurrency hint. The job concurrency hint providing an indication of the number and/or size of the jobs that can be handled by the job scheduler. The scheduling of the jobs based on the job concurrency hint including selecting the number and/or size of the jobs to pass to the job scheduler for execution by a thread in a core of a processor.