A suite of benchmarks for monitoring performance of cloud virtual machines (VMs).
This component runs the benchmark specified in the configuration file using the Randomized Multiple Trials (RMT) methodology, a simpler version of the Randomized Multiple Interleaved Trials (RMIT) approach. The results are saved into the benchmark_result
file along with information about the server.
# init
virtualenv env
source env/bin/activate
pip install -r requirements.txt
# edit the config file and then run
python main.py
- sysbench: sysbench is a scriptable multi-threaded benchmark tool
- CPU
- memory
- threads
- fileio
- nench: VPS benchmark script — based on the popular bench.sh, plus CPU and ioping tests, and dual-stack IPv4 and v6 speedtests by default
- CPUBenchmark: run a simple CPU benchmark
- DDBenchmark: dd command is used to monitor the writing performance of a disk device on a Linux and Unix-like system
- DownloadBenchmark: download a sample file
- ai-benchmark: AI Benchmark Alpha is an open source python library for evaluating AI performance of various hardware platforms, including CPUs, GPUs and TPUs.
- gunicorn web server + wrk: wrk is a modern HTTP benchmarking tool capable of generating significant load when run on a single multi-core CPU
The result of the benchmark is composed by:
- return code:
- 0: the benchmark exits without errors
- otherwise: an error occurred during the execution of the benchmark
- result: the raw result/output of the benchmark