Self-managed installation and maintenance > Backup and restore > Back up procedure > Back up inference servers

Backup Inference Servers¶

DataRobot uses inference servers as part of its serverless predictions offering. If the associated serverless resources are not backed up, customers will be unable to make predictions using model deployments after the restore.

To ensure inference servers are properly backed up, you must include the following Kubernetes Custom Resource Definitions (CRDs) in your backup procedure:

executionenvironments.predictions.datarobot.com
inferenceservers.predictions.datarobot.com

Back up Kubernetes CRDs¶

Note

You must fulfill the prerequisites before proceeding.

To back up the Kubernetes CRDs:

echo "executionenvironments.predictions.datarobot.com backup started"
mkdir -p $BACKUP_LOCATION/predictions/executionenvironments
for ee in $(kubectl get executionenvironments.predictions.datarobot.com -n $NAMESPACE -o name); do
    echo $ee;
    kubectl get ${ee} -n $NAMESPACE -o yaml > $BACKUP_LOCATION/predictions/executionenvironments/${ee#*/}.yaml;
done
echo "executionenvironments.predictions.datarobot.com backup finished"


echo "inferenceservers.predictions.datarobot.com backup started"
mkdir -p $BACKUP_LOCATION/predictions/inferenceservers
for is in $(kubectl get inferenceservers.predictions.datarobot.com -n $NAMESPACE -o name); do
    echo $is;
    kubectl get ${is} -n $NAMESPACE -o yaml > $BACKUP_LOCATION/predictions/inferenceservers/${is#*/}.yaml;
done
echo "inferenceservers.predictions.datarobot.com backup finished"