What is it about?
We investigate the scalability limits of, and how to improve the scalability of, Erlang a key technology for building internet-scale systems
Featured Image
Why is it important?
Erlang is an effective means of constructing scalable reliable systems, and the Erlang programming language has a well-established and influential (distributed actor) model. This paper is the first comprehensive study of any distributed actor language at this scale, i.e. 100s of hosts, and ~10 000 cores and virtual machines. The paper systematically demonstrates Erlang scalability limits (8 experiments), improvements to VM (10 experiments), language level improvements (1 experiment) and tools (5 illustrated). The performance study reports 4 experiments, based on 2 case studies, and deployed on 4 architectures.
Perspectives
RELEASE was a major (£2.2M) European FP7 project that I coordinated, and this is the first complete presentation of the RELEASE technologies for engineering scalable reliable Erlang systems.
Phil Trinder
University of Glasgow
Read the Original
This page is a summary of: Scaling Reliably, ACM Transactions on Programming Languages and Systems, August 2017, ACM (Association for Computing Machinery),
DOI: 10.1145/3107937.
You can read the full text:
Contributors
The following have contributed to this page
