Compression Core Scheduling for Low-Latency Decompression
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current compression storage systems experience increased decompression latency due to processing overhead, particularly during unpredicted and random decompression operations, which reduces efficiency and productivity.
Innovation Solution
A scheduling method that assigns decompression operations to idle compression cores, while allocating a minimal number of cores for compression operations, thereby increasing compression latency hidden by the compression cache, thus reducing overall decompression latency visible to users.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If data compression is applied to reduce storage capacity and transmission time, then storage efficiency improves, but decompression latency increases
Solution Approach 1:
The system pre-allocates a dedicated pool of compression cores for decompression operations and maintains them in a ready state. When decompression requests arrive, these pre-prepared cores can immediately process the requests without waiting for resource availability, thereby reducing decompression latency while maintaining compression efficiency through the remaining cores.
2Productivity
If compression processing is performed on all cores, then compression throughput is maximized, but decompression operations experience increased latency
Solution Approach 1:
The system segments the processing cores into two distinct groups: compression cores dedicated to compression operations and decompression cores dedicated to decompression operations. This segmentation allows each group to optimize its respective function without interfering with the other, ensuring that decompression operations have dedicated resources available and experience reduced latency while compression throughput is maintained by the compression core pool.
3Productivity
If compression cores are dynamically allocated to decompression requests, then resource utilization improves, but decompression latency increases due to scheduling overhead
Solution Approach 1:
The system extracts decompression operations from the general-purpose compression core pool and creates a dedicated decompression core pool. This extraction eliminates the scheduling overhead and resource contention that would occur if decompression requests had to compete for or be dynamically allocated to compression cores. The dedicated decompression cores provide guaranteed performance and reduced latency while the compression cores maintain their compression functionality, achieving both goals without dynamic allocation complexity.
Data Source
AI summary
In a compression processing storage system, using a pool of compression cores, the compression cores are assigned to process either compression operations, decompression operations, or decompression and compression operations, which are scheduled for processing. Only decompression operations are assigned to the plurality of compression cores having an idle status, where the idle status represents those of the plurality of compression cores that have yet to process any of the compression operations, decompression operations, and decompression and compression operations during a predetermined threshold period.