DLFaaS:Serverless Platform for Data-Intensive Tasks Based on Interval Access Patterns

Serverless architecture is a novel paradigm in cloud computing.The increasing trend in applications is shifting towards serverless platforms to achieve on-demand payment and elastic scalability. However, for data-intensive functions, using serverless architectures can result in performance losses due to frequent data transfers, incurring significant time overhead for data movement. Current serverless systems lack optimization for data migration times in tasks involving data-intensive functions. We conducted an analysis of serverless architecture, function invocation patterns, and latency for data-intensive functions. We found that the lack of awareness of access patterns for these functions leads to inefficient cache eviction, resulting in low cache hit rates. Additionally, bursty calls result in repeated remote storage accesses, contributing to time overhead in data-intensive tasks. Therefore, we proposed a serverless platform based on function invocation patterns, optimized for data-intensive tasks. Specifically, we designed a two-tier caching queue, where data objects accessed multiple times for read and write operations were cached based on historical access patterns. These objects were placed in different cache lists according to various time intervals. We employed an eviction strategy based on function access intervals to enhance overall hit rates. Compared to popular existing solutions, we reduced time latency by 32.1% and improved cache hit rates by 12%.