Using Cluster Loader | Scaling and Performance Guide | OpenShift Container Platform 3.11

What Cluster Loader Does
Installing Cluster Loader
Running Cluster Loader
Configuring Cluster Loader
- Configuration Fields
- Example Cluster Loader Configuration File
Known Issues

What Cluster Loader Does

Cluster Loader is a tool that deploys large numbers of various objects to a cluster, which creates user-defined cluster objects. Build, configure, and run Cluster Loader to measure performance metrics of your OpenShift Container Platform deployment at various cluster states.

Installing Cluster Loader

Cluster Loader is included in the atomic-openshift-tests package. To install it, run:

$ yum install atomic-openshift-tests

After installation, the test executable extended.test is located in /usr/libexec/atomic-openshift/extended.test.

Running Cluster Loader

Set the KUBECONFIG variable to the location of the administrator kubeconfig:
```
$ export KUBECONFIG=${KUBECONFIG-$HOME/.kube/config}
```

Execute Cluster Loader using the built-in test configuration, which deploys five template builds and waits for them to complete:

$ cd /usr/libexec/atomic-openshift/

$ ./extended.test --ginkgo.focus="Load cluster"

Alternatively, execute Cluster Loader with a user-defined configuration by adding the flag for --viper-config:

$ ./extended.test --ginkgo.focus="Load cluster" --viper-config=config/test (1)

1	In this example, there is a subdirectory called *config/* with a configuration file called *test.yml*. In the command line, exclude the extension of the configuration file, as the tool will automatically determine the file type and extension.

Configuring Cluster Loader

Create multiple namespaces (projects), which contain multiple templates or pods.

Locate the configuration files for Cluster Loader in the config/ subdirectory. The pod files and template files referenced in these configuration examples are found in the content/ subdirectory.

Configuration Fields

Table 1. Top-level Cluster Loader Fields
Field	Description
`cleanup`	Set to `true` or `false`. One definition per configuration. If set to `true`, `cleanup` will delete all namespaces (projects) created by Cluster Loader at the end of the test.
`projects`	A sub-object with one or many definition(s). Under `projects`, each namespace to create is defined and `projects` has several mandatory subheadings.
`tuningsets`	A sub-object with one definition per configuration. `tuningsets` allows the user to define a tuning set to add configurable timing to project or object creation (pods, templates, and so on).
`sync`	An optional sub-object with one definition per configuration. Adds synchronization possibilities during object creation.

Table 2. Fields under `projects`
Field	Description
`num`	An integer. One definition of the count of how many projects to create.
`basename`	A string. One definition of the base name for the project. The count of identical namespaces will be appended to `Basename` to prevent collisions.
`tuning`	A string. One definition of what tuning set you want to apply to the objects, which you deploy inside this namespace.
`ifexists`	A string containing either `reuse` or `delete`. Defines what the tool does if it finds a project or namespace that has the same name of the project or namespace it creates during execution.
`configmaps`	A list of key-value pairs. The key is the configmap name and the value is a path to a file from which you create the configmap.
`secrets`	A list of key-value pairs. The key is the secret name and the value is a path to a file from which you create the secret.
`pods`	A sub-object with one or many definition(s) of pods to deploy.
`templates`	A sub-object with one or many definition(s) of templates to deploy.

Table 3. Fields under `pods` and `templates`
Field	Description
`total`	This field is not used.
`num`	An integer. The number of pods or templates to deploy.
`image`	A string. The container image URL to a repository where it can be pulled.
`basename`	A string. One definition of the base name for the template (or pod) that you want to create.
`file`	A string. The path to a local file, which is either a PodSpec or template to be created.
`parameters`	Key-value pairs. Under `parameters`, you can specify a list of values to override in the pod or template.

Table 4. Fields under `tuningsets`
Field	Description
`name`	A string. The name of the tuning set which will match the name specified when defining a tuning in a project.
`pods`	A sub-object identifying the `tuningsets` that will apply to pods.
`templates`	A sub-object identifying the `tuningsets` that will apply to templates.

Table 5. Fields under `tuningsets` `pods` or `tuningsets` `templates`
Field	Description
`stepping`	A sub-object. A stepping configuration used if you want to create an object in a step creation pattern.
`rate_limit`	A sub-object. A rate-limiting tuning set configuration to limit the object creation rate.

Table 6. Fields under `tuningsets` `pods` or `tuningsets` `templates`, `stepping`
Field	Description
`stepsize`	An integer. How many objects to create before pausing object creation.
`pause`	An integer. How many seconds to pause after creating the number of objects defined in `stepsize`.
`timeout`	An integer. How many seconds to wait before failure if the object creation is not successful.
`delay`	An integer. How many milliseconds (ms) to wait between creation requests.

Table 7. Fields under `sync`
Field	Description
`server`	A sub-object with `enabled` and `port` fields. The boolean `enabled` defines whether to start a HTTP server for pod synchronization. The integer `port` defines the HTTP server port to listen on (`9090` by default).
`running`	A boolean. Wait for pods with labels matching `selectors` to go into `Running` state.
`succeeded`	A boolean. Wait for pods with labels matching `selectors` to go into `Completed` state.
`selectors`	A list of selectors to match pods in `Running` or `Completed` states.
`timeout`	A string. The synchronization timeout period to wait for pods in `Running` or `Completed` states. For values that are not `0`, use units: [ns\|us\|ms\|s\|m\|h].

Example Cluster Loader Configuration File

Cluster Loader’s configuration file is a basic YAML file:

provider: local (1)
ClusterLoader:
  cleanup: true
  projects:
    - num: 1
      basename: clusterloader-cakephp-mysql
      tuning: default
      ifexists: reuse
      templates:
        - num: 1
          file: ./examples/quickstarts/cakephp-mysql.json

    - num: 1
      basename: clusterloader-dancer-mysql
      tuning: default
      ifexists: reuse
      templates:
        - num: 1
          file: ./examples/quickstarts/dancer-mysql.json

    - num: 1
      basename: clusterloader-django-postgresql
      tuning: default
      ifexists: reuse
      templates:
        - num: 1
          file: ./examples/quickstarts/django-postgresql.json

    - num: 1
      basename: clusterloader-nodejs-mongodb
      tuning: default
      ifexists: reuse
      templates:
        - num: 1
          file: ./examples/quickstarts/nodejs-mongodb.json

    - num: 1
      basename: clusterloader-rails-postgresql
      tuning: default
      templates:
        - num: 1
          file: ./examples/quickstarts/rails-postgresql.json

  tuningsets: (2)
    - name: default
      pods:
        stepping: (3)
          stepsize: 5
          pause: 0 s
        rate_limit: (4)
          delay: 0 ms

1	Optional setting for end-to-end tests. Set to `local` to avoid extra log messages.
2	The tuning sets allow rate limiting and stepping, the ability to create several batches of pods while pausing in between sets. Cluster Loader monitors completion of the previous step before continuing.
3	Stepping will pause for `M` seconds after each `N` objects are created.
4	Rate limiting will wait `M` milliseconds between the creation of objects.

Known Issues

If the IDENTIFIER parameter is not defined in user templates, template creation fails with error: unknown parameter name "IDENTIFIER". If you deploy templates, add this parameter to your template to avoid this error:

{
  "name": "IDENTIFIER",
  "description": "Number to append to the name of resources",
  "value": "1"
}

If you deploy pods, adding the parameter is unnecessary.