Publication details

R. Andreoli, T. Cucinotta. "Inducing Huge Tail Latency on a MongoDB deployment," in Proceedings of the 11th IEEE International Conference on Cloud Engineering (IC2E 2023), September 25-28, 2023, Boston, Massachussets, USA.

Abstract

The NoSQL paradigm has emerged as the leading design choice for cloud providers offering highly scalable storage services. Contrary to traditional relational databases, NoSQL architectures are capable of ingesting the ever-growing volume of nowadays’ data-driven applications characterized by low-latency and high-throughput requirements. However, in this context, it is difficult to build an ultra-scalable, high-performance storage engine that can sustain an arbitrary number of concurrent clients. A common technique to increase throughput is minimizing the OS overhead, quantified as the number of context switches, through busy waiting (or “spinning”). While this simple synchronization mechanism proves to be beneficial in the high-performance computing (HPC) community, it requires special care to avoid wasting resources and counter-intuitive behaviors. In this paper, we address an instance of “unsafe” busy waiting in WiredTiger, the underlying storage engine of MongoDB, which leads to a consistent, excessive increase of tail latency in high contention scenarios.

See paper on publisher's website

Download paper

DOI: 10.1109/IC2E59103.2023.00020

BibTeX entry:

@inproceedings{Andreoli_2023,
     title={Inducing Huge Tail Latency on a MongoDB deployment},
     url={http://dx.doi.org/10.1109/IC2E59103.2023.00020},
     DOI={10.1109/ic2e59103.2023.00020},
     booktitle={2023 IEEE International Conference on Cloud Engineering (IC2E)},
     publisher={IEEE},
     author={Andreoli, Remo and Cucinotta, Tommaso},
     year={2023},
     month=sep }

Last updated on
07 November 2024