In this post, we’ll discuss how you can quick start MySQL testing using Docker, specifically in a Mac environment.
Like a lot of people, I’m hearing a lot about Docker and it’s got me curious. The Docker ecosystem seems to be moving quickly, however, and simple “getting started” or “how-to” type articles that are easy to find for well-established technologies seem to be out-of-date or non-existent for Docker. I’ve been playing with Docker on Mac for a bit, but it is definitely a second-class citizen in the Docker world. However, I saw Giuseppe’s blog on the new Docker beta for Mac and decided to try it for myself. These steps work for the beta version on a Mac (and probably Windows), but they should work with Linux as well (using the GA release, currently Docker 1.11.1).
The new Docker beta for Mac requires that you register for the beta program, and receive a download code from Docker. I got mine in about a day, but I would assume it won’t be long before the full version is released.
Once installed, I needed to setup some Docker containers for common MySQL versions so that I can easily have some sandboxes. The method I used is below:
A quick summary of what I did above:
I created a network called “test” for my containers to share, essentially this is a dedicated private network between containers. I like this because multiple containers can listen on the same port and I don’t have to fight with ports on my host OS.
I started a MySQL 5.7 image from Oracle’s official MySQL Docker container bound to that test network.
I used the MySQL/shell image (also from Oracle) to initialize the mysqlx plugin on my 5.7 server. Notice I didn’t enter a password because I created the server without one (insecure, but it’s a sandbox).
The shell init uses a temporary container that is removed (–rm) after the run, so you don’t pollute your
a output.
So, now I want to be able to use the standard MySQL command line and/or the new MySQL shell to access this container. To make this really clean, I added some bash aliases:
With these in effect, I can call them directly and pass normal command line options to connect to my mysql57 image just as if I was using a native MySQL CLI binary.
Using the MySQL CLI from the 5.7 image:
Using the MySQL shell:
Now if I want to run check MySQL 5.5 for something, I can just do this:
or, Percona Server:
So all this is nice – once the images are cached locally, spinning new containers up and down is painless and fast. All this sandbox work is cleanly separated from my workstation OS. There are probably other things I’d want to be able to do with this setup that I haven’t figured out yet (e.g., loading data files, running code to connect to these containers, etc.) – but I’ll figure those out in the future.