Datacenter Benchmarking with CloudSuite 4.0
A benchmark suite consisting of popular first-party cloud workloads in prevalent ISAs
CloudSuite is a benchmark suite for first-party cloud services. The suite consists of eight benchmarks representing popular online services and analytic workloads in datacenters. The benchmarks are based on state-of-the-art open-source real-world software stacks and are containerized for use.
Cloud computing is now the dominant platform to offer scalable online services to a global client base. Today’s popular online services (e.g., web search, social networking, and business analytics) are characterized by massive working sets, deep software stacks, high degrees of request parallelism, and real-time constraints. These characteristics set cloud services apart from desktop (SPEC), parallel (PARSEC), and traditional commercial server workloads (TPC). Thus, we offer CloudSuite, enabling users to analyze their systems with representiative cloud services. CloudSuite also complements emerging first-party workloads (e.g., Microservices) and third-party workloads (e.g., Serverless) with multi-tier monolithic software stacks that remain a backbone for datacenter services.
Version 4.0 includes the following changes:
- It includes a thorough software stack update, reflecting the latest features and bug fixes.
- All benchmarks are available on both x86 and ARM ISAs (and will soon be available on RISC-V), with the ARM server ecosystem fully supporting datacenter services.
- CloudSuite 4.0 facilitates use through enhanced documentation, a simple interface for configuration, and proper guidelines for benchmark tuning.
A tutorial, “Benchmarking scale-out server workloads with CloudSuite 4.0”, will be given on March 26th at ASPLOS 2023.
DATE’17 Talk and Demo
A talk, Server Benchmarking and Design with CloudSuite 3.0, was given on March 28th at DATE 2017.
A tutorial, Server Benchmarking with CloudSuite 3.0, will be presented on April 18th at EuroSys 2016.
We encourage CloudSuite users to subscribe to our GitHub repository and use GitHub issues to request enhancements or
bug fixes, or ask questions.