Releases: zhaohany/io-for-docker
Release 1.0.0
Release v1.0.0
IO Benchmark Testing for Docker Environments
This release introduces io-for-docker, an open-source Docker image for IO benchmark testing. The image includes FIO, a flexible I/O tester and benchmark tool, to conduct sequential read, sequential write, random read, and random write IO testing in both runq and runc Docker environments.
Usage
Edit the jobfile
Before running the benchmark test, make sure to edit the FIO jobfile to customize the test parameters according to your requirements.
Build Docker Image
To build the io-for-docker image, follow these steps:
- Clone the repository:
git clone https://github.com/your-username/io-for-docker.git
cd io-for-docker
- Build the Docker image:
docker build -t io-for-docker .
Run the Benchmark Test
To perform the IO benchmark testing with io-for-docker in the desired Docker runtime, use one of the following commands:
Using runq runtime:
docker run --runtime=runq -v $(pwd)/hostmount:/vmmount --rm io-for-docker
Using runc runtime:
docker run --runtime=runc -v $(pwd)/hostmount:/vmmount --rm io-for-docker
Debugging
If you encounter any issues during the benchmark testing, refer to the debugging section in the io-for-docker repository for troubleshooting steps and solutions.
View the Result
The benchmark test will generate output that can be analyzed to understand the performance of the IO operations. Check the io-for-docker repository for details on how to access and interpret the results.
Clean Up Space
After the benchmark testing, you can clean up space as follows:
Remove the contents of the "hostmount" directory (Please be cautious, as this will remove all files and directories in "hostmount"):
rm -r ./hostmount/*
Note: This may remove your other projects, so make sure to take appropriate precautions.
Additionally, you can prune unused Docker data to free up disk space:
docker system prune --volumes
Known Issues
There is a known issue with FIO being unable to open the "jobfile.fio" jobfile. The io-for-docker repository is actively working to address this issue, and updates will be provided as they become available.
Feel free to try out io-for-docker and provide feedback or report any issues you encounter. Happy benchmarking!