Process Hash Matching for Low-Overhead Performance Collection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The increasing volume of performance information in information processing systems leads to high measurement and communication overhead, affecting processor and network loads, and reduces measurement accuracy due to the need to switch measured performance information during processes.
Innovation Solution
The system determines process identity using hash values of related information to selectively measure and transmit only partially different performance information, reducing the number of types measured during a single process execution.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If performance information is collected for all processes, then measurement completeness is improved, but measurement overhead and processor load increase
Solution Approach 1:
The patent segments performance information collection by process identity. Instead of collecting all performance information uniformly, the system identifies processes through hash values of related information (command line, working directory, environment variables) and selectively collects performance information based on process identity matching, thereby reducing unnecessary measurements while maintaining completeness for relevant processes
Solution Approach 2:
The patent applies partial action by collecting performance information only for processes that need to be measured, rather than all processes. The system determines which processes require measurement by comparing hash values of related information, and only collects performance data for processes that match the identification criteria, reducing overall measurement overhead while maintaining sufficient measurement coverage
2Measurement precision
If performance information is collected at constant intervals, then measurement accuracy is improved, but communication overhead and network load increase
Solution Approach 1:
The patent implements dynamic performance information collection based on process identity changes. Instead of collecting information at fixed intervals regardless of process state, the system dynamically adjusts collection based on whether process identity has changed (detected through hash value comparison of related information). This reduces communication overhead during stable states while maintaining accuracy when processes change identity
Solution Approach 2:
The system uses feedback from process identity detection to control performance information collection. By continuously monitoring process identity through hash value comparison and using this feedback to determine when collection is needed, the system avoids unnecessary communications while maintaining measurement accuracy for identity-changing events
3Loss of information
If all performance information is transmitted, then analysis completeness is improved, but communication overhead increases
Solution Approach 1:
The patent extracts only the necessary performance information for analysis by first identifying processes through hash values of related information. The system extracts performance information only for processes that match the identification criteria, filtering out unnecessary data while maintaining completeness for relevant processes, thereby reducing overall data volume transmitted
Data Source
AI summary
A computer-readable recording medium has stored therein a program for causing a computer to execute a process for collecting performance information, the process including: obtaining one or more pieces of related information related to each of a plurality of processes, including a first process and a second process, to be executed in an information processing apparatus, calculating one or more hash values of each of the plurality of processes by inputting each of values of the one or more pieces of the related information obtained for each of the plurality of processes into respective corresponding hash functions, and when the plurality of hash values calculated for the first process at least partially match the plurality of hash values calculated for the second process, measuring, while the second process is being executed, second performance information at least partly different from first performance information, the first information being measured while the first process is being executed.