VictoriaMetrics Anomaly Detection Quick Start

For service introduction visit README page and Overview of how vmanomaly works.

How to install and run vmanomaly#

To run vmanomaly, you need to have VictoriaMetrics Enterprise license. You can get a trial license key here.

The following options are available:

Note: Starting from v1.13.0 there is a mode to keep anomaly detection models on host filesystem after fit stage (instead of keeping them in-memory by default); This may lead to noticeable reduction of RAM used on bigger setups. See instructions here.

Docker#

To run vmanomaly, you need to have VictoriaMetrics Enterprise license. You can get a trial license key here.

Below are the steps to get vmanomaly up and running inside a Docker container:

  1. Pull Docker image:
docker pull victoriametrics/vmanomaly:latest
  1. (Optional step) tag the vmanomaly Docker image:
docker image tag victoriametrics/vmanomaly:latest vmanomaly
  1. Start the vmanomaly Docker container with a license file, use the command below. Make sure to replace YOUR_LICENSE_FILE_PATH, and YOUR_CONFIG_FILE_PATH with your specific details:
export YOUR_LICENSE_FILE_PATH=path/to/license/file
export YOUR_CONFIG_FILE_PATH=path/to/config/file
docker run -it -v $YOUR_LICENSE_FILE_PATH:/license \
               -v $YOUR_CONFIG_FILE_PATH:/config.yml \
               vmanomaly /config.yml \
               --license-file=/license

See also:

Kubernetes with Helm charts#

To run vmanomaly, you need to have VictoriaMetrics Enterprise license. You can get a trial license key here.

You can run vmanomaly in Kubernetes environment with these Helm charts.

How to configure vmanomaly#

To run vmanomaly you need to set up configuration file in yaml format.

Here is an example of config file that will run Facebook Prophet model, that will be retrained every 2 hours on 14 days of previous data. It will generate inference (including anomaly_score metric) every 1 minute.

scheduler:
  infer_every: "1m"
  fit_every: "2h"
  fit_window: "14d"

models:
  prophet_model:
    class: "prophet"  # or "model.prophet.ProphetModel" until v1.13.0
    args:
      interval_width: 0.98

reader:
  datasource_url: "http://victoriametrics:8428/" # [YOUR_DATASOURCE_URL]
  sampling_period: "1m"
  queries: 
    # define your queries with MetricsQL - https://docs.victoriametrics.com/metricsql/
    cache: "sum(rate(vm_cache_entries))"

writer:
  datasource_url:  "http://victoriametrics:8428/" # [YOUR_DATASOURCE_URL]

Next steps:

  • Define how often to run and make inferences in the scheduler section of a config file.
  • Setup the datasource to read data from in the reader section.
  • Specify where and how to store anomaly detection metrics in the writer section.
  • Configure built-in models parameters according to your needs in the models section.
  • Integrate your custom models with vmanomaly.
  • Define queries for input data using MetricsQL.

Check also#

Here are other materials that you might find useful: