Is Performance of Object Storage Predictable for Serverless I/O Workloads? A Comparative Study

Serverless architectures abstract resource provisioning away from the user. However, this property may be at odds with performance. One example of this is Function as a Service (FaaS), where the lack of network addressability compels developers to resort to serverless storage services such as AWS S3 to share (intermediate) data between the functions. For IO-bound workflows, the literature has shown that the performance of parallel reads and writes highly depends on the level of parallelism. Simply put, both an excess or a deficiency in the number of functions may lead to longer IO times. The good news is that the provisioning of functions is fast. Consequently, it is feasible to auto-provision the serverless functions to the optimal number to minimize IO latency. For this, the performance of object storage must be predictable and consistent. We confirmed this in the past for IBM COS. And in this paper, we show that the same occurs to AWS S3. Concretely, we prove that the optimal level of parallelism for parallel reads and writes can be approximated analytically for AWS S3.