Katib Configuration Overview

How to make changes in Katib configuration

This page describes information about Katib config.

Katib config is the Kubernetes Config Map that contains information about:

  1. Current Metrics Collectors (key = metrics-collector-sidecar)
  2. Current Algorithms (Suggestions) (key = suggestion).

Katib Config Map must be deployed in KATIB_CORE_NAMESPACE namespace with katib-config name. Katib controller parses Katib config when you submit Experiment.

You can edit this Config Map even after deploying Katib.

If you deploy Katib in Kubeflow namespace, to edit Katib config run this:

kubectl edit configMap katib-config -n kubeflow

Metrics Collector Sidecar settings

These settings are related to Katib Metrics Collectors, where:

  • key = metrics-collector-sidecar
  • value = corresponding settings JSON for each Metrics Collector.

Example for the File Metrics Collector with all settings:

  1. metrics-collector-sidecar: |-
  2. {
  3.   "File": {
  4.     "image": "gcr.io/kubeflow-images-public/katib/v1alpha3/file-metrics-collector",
  5.     "imagePullPolicy": "Always",
  6.     "resources": {
  7.       "requests": {
  8.         "memory": "200Mi",
  9.         "cpu": "250m",
  10.         "ephemeral-storage": "200Mi"
  11.       },
  12.       "limits": {
  13.         "memory": "1Gi",
  14.         "cpu": "500m",
  15.         "ephemeral-storage": "2Gi"
  16.       }
  17.     }
  18.   },
  19.   ...
  20. }

All of these settings except image can be omitted. If you don’t specify any other settings, default value is be set.

  1. image - Docker image name for the File Metrics Collector.

    Must be specified.

  2. imagePullPolicy - File Metrics Collector container image pull policy.

    Default value is IfNotPresent.

  3. resources - File Metrics Collector container resources. In the above example you can see how to specify limits and requests. Currently, you can specify only memory, cpu and ephemeral-storage resource.

    Default values for the requests are:

    • memory = 10Mi.
    • cpu = 50m.
    • ephemeral-storage = 500Mi.

    Default values for the limits are:

    • memory = 100Mi.
    • cpu = 500m.
    • ephemeral-storage = 5Gi.

Suggestion settings

These settings are related to Katib suggestions, where:

  • key = suggestion
  • value = corresponding settings JSON for each algorithm.

If you want to use new algorithm, you must update Katib config with the new suggestion.

Example for the random suggestion with all settings:

  1. suggestion: |-
  2. {
  3.   "random": {
  4.     "image": "gcr.io/kubeflow-images-public/katib/v1alpha3/suggestion-hyperopt",
  5.     "imagePullPolicy": "Always",
  6.     "resources": {
  7.       "requests": {
  8.         "memory": "100Mi",
  9.         "cpu": "100m",
  10.         "ephemeral-storage": "100Mi"
  11.       },
  12.       "limits": {
  13.         "memory": "500Mi",
  14.         "cpu": "500m",
  15.         "ephemeral-storage": "3Gi"
  16.       }
  17.     },
  18.     "serviceAccountName": "suggestion-serviceaccount"
  19.   },
  20.   ...
  21. }

All of these settings except image can be omitted. If you don’t specify any other settings, default value is be set.

  1. image - Docker image name for the random suggestion. Must be specified

    Image name example: gcr.io/kubeflow-images-public/katib/v1alpha3/<suggestion-name>

    For each algorithm (suggestion) you can specify one of the following suggestion names in Docker image:

    Suggestion nameList of supported algorithmsDescription
    suggestion-hyperoptrandom, tpeHyperopt optimization framework
    suggestion-chocolategrid, random, quasirandom, bayesianoptimization, mocmaesChocolate optimization framework
    suggestion-skoptbayesianoptimizationScikit-optimize optimization framework
    suggestion-goptunacmaes, random, tpeGoptuna optimization framework
    suggestion-hyperbandhyperbandKatib Hyperband implementation
    suggestion-enasenasKatib ENAS implementation
    suggestion-dartsdartsKatib DARTS implementation

  2. imagePullPolicy - Random suggestion container image pull policy.

    Default value is IfNotPresent.

  3. resources - Random suggestion container resources. In the above example you can see how to specify limits and requests. Currently, you can specify only memory, cpu and ephemeral-storage resource.

    Default values for the requests are:

    • memory = 10Mi.
    • cpu = 50m.
    • ephemeral-storage = 500Mi.

    Default values for the limits are:

    • memory = 100Mi.
    • cpu = 500m.
    • ephemeral-storage = 5Gi.

  4. serviceAccountName - Random suggestion container service account. In the above example, suggestion-serviceaccount service account is used for each Experiment with random algorithm, until you change or delete this service account from the Katib config.

    By default suggestion pod doesn’t have specific service account. In that case, Suggestion pod uses default service account.

Last modified 11.08.2020: Remove outdated banner for Katib docs (#2088) (5f29767a)