Databricks DataEngineering Learning

subahan_dbricks
New Contributor II

I am new to Databricks. I am trying to do the lab work given Databricks DataEngineering course, at workbook 4.1 I am getting below error. Please help to resolve.

Expected one and only one cluster definition.

Edit the config via the JSON interface to remove the second+ cluster definitions

Rishabh-Pandey
Databricks MVP

Detailed Instructions

Here’s how you can edit the JSON configuration:

Step-by-Step Guide:

  1. Access the Cluster Configuration:

    • In Databricks, navigate to the workspace where your notebook or job is located.
    • Go to the Jobs tab or the specific notebook you are trying to configure.
  2. Edit the Configuration:

    • If you are in the Jobs tab:
      • Click on the job you are having issues with.
      • Go to the Configuration or Cluster settings.
      • Look for an option to edit the JSON configuration. It’s often labeled as “Edit in JSON” or similar.
    • If you are editing a notebook directly:
      • Go to the notebook and click on the cluster icon or settings to open the cluster configuration.
  3. Edit the JSON Interface:

  4. Remove the second cluster definitions
{
  "clusters": [
    {
      "cluster_name": "Cluster1",
      "spark_version": "7.3.x-scala2.12",
      "node_type_id": "i3.xlarge",
      "num_workers": 2
    },
    {
      "cluster_name": "Cluster2",
      "spark_version": "7.3.x-scala2.12",
      "node_type_id": "i3.xlarge",
      "num_workers": 2
    }
  ]
}

 

Rishabh Pandey

Thanks Rishabh Pandey for your reply. But when I edit my cluster in JSON it has only one cluster definition as below.

 

{
"num_workers": 0,
"cluster_name": "Abdul Subahan Mohamed Ghouse's Cluster",
"spark_version": "11.3.x-scala2.12",
"spark_conf": {
"spark.master": "local[*, 4]",
"spark.databricks.cluster.profile": "singleNode"
},
"aws_attributes": {
"first_on_demand": 1,
"availability": "SPOT_WITH_FALLBACK",
"zone_id": "auto",
"spot_bid_price_percent": 100,
"ebs_volume_count": 0
},
"node_type_id": "r5dn.large",
"driver_node_type_id": "r5dn.large",
"ssh_public_keys": [],
"custom_tags": {
"ResourceClass": "SingleNode"
},
"spark_env_vars": {},
"autotermination_minutes": 120,
"enable_elastic_disk": true,
"init_scripts": [],
"single_user_name": "subahanma@yahoo.com",
"enable_local_disk_encryption": false,
"data_security_mode": "SINGLE_USER",
"runtime_engine": "PHOTON",
"cluster_id": "0614-025944-suhd45l7"
}

 

However, when I check at View JSON I have below config details, but not do not have the entries in object list to remove easily as you suggested. Would you be able to suggest further. Thanks

{
"cluster_id": "0614-025944-suhd45l7",
"creator_user_name": "subahanma@yahoo.com",
"spark_context_id": 4770338516046754000,
"driver_healthy": true,
"cluster_name": "Abdul Subahan Mohamed Ghouse's Cluster",
"spark_version": "11.3.x-scala2.12",
"spark_conf": {
"spark.master": "local[*, 4]",
"spark.databricks.cluster.profile": "singleNode"
},
"aws_attributes": {
"first_on_demand": 1,
"availability": "SPOT_WITH_FALLBACK",
"zone_id": "auto",
"spot_bid_price_percent": 100
},
"node_type_id": "r5dn.large",
"driver_node_type_id": "r5dn.large",
"custom_tags": {
"ResourceClass": "SingleNode"
},
"autotermination_minutes": 120,
"enable_elastic_disk": true,
"disk_spec": {},
"cluster_source": "UI",
"single_user_name": "subahanma@yahoo.com",
"enable_local_disk_encryption": false,
"instance_source": {
"node_type_id": "r5dn.large"
},
"driver_instance_source": {
"node_type_id": "r5dn.large"
},
"data_security_mode": "SINGLE_USER",
"runtime_engine": "PHOTON",
"effective_spark_version": "11.3.x-photon-scala2.12",
"state": "TERMINATED",
"state_message": "Inactive cluster terminated (inactive for 120 minutes).",
"start_time": 1718333984793,
"terminated_time": 1718343735955,
"last_state_loss_time": 0,
"last_activity_time": 1718334227246,
"last_restarted_time": 1718334277783,
"num_workers": 0,
"default_tags": {
"Vendor": "Databricks",
"Creator": "subahanma@yahoo.com",
"ClusterName": "Abdul Subahan Mohamed Ghouse's Cluster",
"ClusterId": "0614-025944-suhd45l7"
},
"termination_reason": {
"code": "INACTIVITY",
"type": "SUCCESS",
"parameters": {
"inactivity_duration_min": "120"
}
},
"init_scripts_safe_mode": false,
"spec": {
"cluster_name": "Abdul Subahan Mohamed Ghouse's Cluster",
"spark_version": "11.3.x-scala2.12",
"spark_conf": {
"spark.master": "local[*, 4]",
"spark.databricks.cluster.profile": "singleNode"
},
"aws_attributes": {
"first_on_demand": 1,
"availability": "SPOT_WITH_FALLBACK",
"zone_id": "auto",
"spot_bid_price_percent": 100
},
"node_type_id": "r5dn.large",
"driver_node_type_id": "r5dn.large",
"custom_tags": {
"ResourceClass": "SingleNode"
},
"autotermination_minutes": 120,
"enable_elastic_disk": true,
"single_user_name": "subahanma@yahoo.com",
"data_security_mode": "SINGLE_USER",
"runtime_engine": "PHOTON",
"num_workers": 0
}
}

I recreated my compute cluster again under DBA Academy policy as below but still the same error.

{
"id": "2bf80b86-1f70-47c2-af4b-3bad17cca47b",
"pipeline_type": "WORKSPACE",
"clusters": [
{
"label": "default",
"node_type_id": "i3.xlarge",
"driver_node_type_id": "i3.xlarge",
"policy_id": "0001AF378F789E44",
"num_workers": 0
},
{
"label": "maintenance",
"policy_id": "0001AF378F789E44"
}
],
"development": true,
"continuous": false,
"channel": "CURRENT",
"photon": true,
"libraries": [
{
"notebook": {
"path": "/Shared/data-engineering-with-databricks/DE 4 - Delta Live Tables/DE 4.1A - SQL Pipelines/DE 4.1.1 - Orders Pipeline"
}
},
{
"notebook": {
"path": "/Shared/data-engineering-with-databricks/DE 4 - Delta Live Tables/DE 4.1A - SQL Pipelines/DE 4.1.2 - Customers Pipeline"
}
},
{
"notebook": {
"path": "/Shared/data-engineering-with-databricks/DE 4 - Delta Live Tables/DE 4.1A - SQL Pipelines/DE 4.1.3 - Status Pipeline"
}
}
],
"name": "subahanma-91f8-da-delp-pipeline-demo-pipeline_demo: Example Pipeline",
"edition": "ADVANCED",
"storage": "dbfs:/mnt/dbacademy-users/subahanma@yahoo.com/data-engineer-learning-path/pipeline_demo/storage_location",
"configuration": {
"spark.master": "local[*]",
"source": "dbfs:/mnt/dbacademy-users/subahanma@yahoo.com/data-engineer-learning-path/pipeline_demo/stream-source"
},
"target": "subahanma_91f8_da_delp_pipeline_demo",
"data_sampling": false
}

subahan_dbricks
New Contributor II

I am unable to resolve this. Any help would be appreciated. Thanks