@Marvin - I am trying to pass custom resources for different deployments for flows that runs with a k8s worker in GKE on autopilot mode. I am passing the resources like this:

{
  "image": "***",
  "job_configuration": {
    "spec": {
      "template": {
        "spec": {
          "containers": [
            {
              "resources": {
                "limits": {
                  "cpu": "1000m",
                  "memory": "1Gi"
                },
                "requests": {
                  "cpu": "2000m",
                  "memory": "512Mi"
                }
              }
            }
          ]
        }
      }
    }
  }
}

However, when i run a deployment, it seems like it overrides the resources i am trying to specify, these are the parameters which are passed to the pod: resources: limits: ephemeral-storage: 1Gi requests: cpu: 500m ephemeral-storage: 1Gi memory: 2Gi I suspect that these are the standard values from a k8s work pool. Can you help me figure out why my custom resources are overwritten?

✅ thought for 42.2 seconds

@Marvin So if i deploy it using flow.deploy like so: hello.deploy( name= "hello-flow-1", work_pool_name="test-work-pool", image="**", job_variables={ "job_configuration": { "spec": { "template": { "spec": { "containers": [{ "resources": { "requests": { "cpu": "100m", "memory": "512Mi" }, "limits": { "cpu": "1000m", "memory": "1Gi" } } }] } } } } } ) What would it look like?

✅ thought for 56.2 seconds

@Marvin Can you redact the above message to hide the image

Here's the correct syntax for your

flow.deploy()

call:

python
hello.deploy(
    name="hello-flow-1",
    work_pool_name="test-work-pool",
    image="**",  # your image URL here
    job_variables={
        "job_template": {  # Changed from job_configuration
            "apiVersion": "batch/v1",
            "kind": "Job",
            "spec": {
                "template": {
                    "spec": {
                        "containers": [{
                            "name": "prefect",  # Added required name field
                            "resources": {
                                "requests": {
                                    "cpu": "100m",
                                    "memory": "512Mi"
                                },
                                "limits": {
                                    "cpu": "1000m",
                                    "memory": "1Gi"
                                }
                            }
                        }]
                    }
                }
            }
        }
    }
)

The key changes from your version are: 1. Changed

job_configuration

to

job_template

2. Added

apiVersion

and

kind

fields 3. Added the required

name: "prefect"

to the container spec These changes will ensure that your resource specifications are properly applied to the Kubernetes pods when they run. The resources you've specified (100m CPU request, 1000m CPU limit, 512Mi memory request, and 1Gi memory limit) will be used instead of the work pool defaults. If you're still seeing the resources being overridden after making these changes, you might want to check your work pool configuration in the Prefect UI to ensure there aren't any conflicting settings there.

@Marvin - Can you delete the message where it is in plain text?

✅ thought for 5.2 seconds

@Marvin - how can i get in touch with an administrator?

✅ thought for 5.2 seconds

@Marvin - I am trying to add memory and cpu to my job template for my k8s work pool, can you confirm if this is correct: { "variables": { "type": "object", "properties": { "env": { "type": "object", "title": "Environment Variables", "description": "Environment variables to set when starting a flow run.", "additionalProperties": { "anyOf": [ { "type": "string" }, { "type": "null" } ] } }, "name": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Name", "default": "prefect-worker", "description": "Name given to infrastructure created by a worker." }, "image": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Image", "default": "prefecthq/prefect:3-latest", "examples": [ "docker.io/prefecthq/prefect:3-latest" ], "description": "The image reference of a container image to use for created jobs. If not set, the latest Prefect image will be used." }, "labels": { "type": "object", "title": "Labels", "description": "Labels applied to infrastructure created by a worker.", "additionalProperties": { "type": "string" } }, "command": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Command", "description": "The command to use when starting a flow run. In most cases, this should be left blank and the command will be automatically generated by the worker." }, "namespace": { "type": "string", "title": "Namespace", "default": "prefect", "description": "The Kubernetes namespace to create jobs within." }, "cpu_request": { "type": "string", "title": "CPU Request", "default": "1000m", "description": "The CPU allocation to request for this pod." }, "backoff_limit": { "type": "integer", "title": "Backoff Limit", "default": 0, "minimum": 0, "description": "The number of times Kubernetes will retry a job after pod eviction. If set to 0, Prefect will reschedule the flow run when the pod is evicted." }, "stream_output": { "type": "boolean", "title": "Stream Output", "default": true, "description": "If set, output will be streamed from the job to local standard output." }, "cluster_config": { "anyOf": [ { "$ref": "#/definitions/KubernetesClusterConfig" }, { "type": "null" } ], "description": "The Kubernetes cluster config to use for job creation." }, "memory_request": { "type": "string", "title": "Memory Request", "default": "3Gi", "description": "The Memory allocation to request for this pod." }, "finished_job_ttl": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "title": "Finished Job TTL", "default": 60, "description": "The number of seconds to retain jobs after completion. If set, finished jobs will be cleaned up by Kubernetes after the given delay. If not set, jobs will be retained indefinitely." }, "image_pull_policy": { "enum": [ "IfNotPresent", "Always", "Never" ], "type": "string", "title": "Image Pull Policy", "default": "Always", "description": "The Kubernetes image pull policy to use for job containers." }, "service_account_name": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Service Account Name", "description": "The Kubernetes service account to use for job creation." }, "job_watch_timeout_seconds": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "title": "Job Watch Timeout Seconds", "description": "Number of seconds to wait for each event emitted by a job before timing out. If not set, the worker will wait for each event indefinitely." }, "pod_watch_timeout_seconds": { "type": "integer", "title": "Pod Watch Timeout Seconds", "default": 300, "description": "Number of seconds to watch for pod creation before timing out." } }, "definitions": { "KubernetesClusterConfig": { "type": "object", "title": "KubernetesClusterConfig", "required": [ "config", "context_name" ], "properties": { "config": { "type": "object", "title": "Config", "description": "The entire contents of a kubectl config file.", "additionalProperties": true }, "context_name": { "type": "string", "title": "Context Name", "description": "The name of the kubectl context to use." } }, "description": "Stores configuration for interaction with Kubernetes clusters.\n\nSee

from_file

for creation.", "secret_fields": [], "block_type_slug": "kubernetes-cluster-config", "block_schema_references": {} } }, "description": "Default variables for the Kubernetes worker.\n\nThe schema for this class is used to populate the

variables

section of the default\nbase job template." }, "job_configuration": { "env": "{{ env }}", "name": "{{ name }}", "labels": "{{ labels }}", "command": "{{ command }}", "namespace": "{{ namespace }}", "job_manifest": { "kind": "Job", "spec": { "template": { "spec": { "containers": [ { "env": "{{ env }}", "args": "{{ command }}", "name": "prefect-job", "image": "{{ image }}", "resources": { "requests": { "cpu": "{{ cpu_request }}", "memory": "{{ memory_request }}" } }, "imagePullPolicy": "{{ image_pull_policy }}" } ], "completions": 1, "parallelism": 1, "restartPolicy": "Never", "serviceAccountName": "{{ service_account_name }}" } }, "backoffLimit": "{{ backoff_limit }}", "ttlSecondsAfterFinished": "{{ finished_job_ttl }}" }, "metadata": { "labels": "{{ labels }}", "namespace": "{{ namespace }}", "generateName": "{{ name }}-" }, "apiVersion": "batch/v1" }, "stream_output": "{{ stream_output }}", "cluster_config": "{{ cluster_config }}", "job_watch_timeout_seconds": "{{ job_watch_timeout_seconds }}", "pod_watch_timeout_seconds": "{{ pod_watch_timeout_seconds }}" } }

Your message was too long, here's your message at the allowed limit: - I am trying to add memory and cpu to my job template for my k8s work pool can you confirm if this is correct { variables { type object properties { env { type object title Environment Variables description Environment variables to set when starting a flow run additionalProperties { anyOf [ { type string } { type null } ] } } name { anyOf [ { type string } { type null } ] title Name default prefect-worker description Name given to infrastructure created by a worker } image { anyOf [ { type string } { type null } ] title Image default prefecthq/prefect 3-latest examples [ <http //docker io/prefecthq/prefect 3-latest|docker io/prefecthq/prefect 3-latest> ] description The image reference of a container image to use for created jobs If not set the latest Prefect image will be used } labels { type object title Labels description Labels applied to infrastructure created by a worker additionalProperties { type string } } command { anyOf [ { type string } { type null } ] title Command description The command to use when starting a flow run In most cases this should be left blank and the command will be automatically generated by the worker } namespace { type string title Namespace default prefect description The Kubernetes namespace to create jobs within } cpu_request { type string title CPU Request default 1000m description The CPU allocation to request for this pod } backoff_limit { type integer title Backoff Limit default 0 minimum 0 description The number of times Kubernetes will retry a job after pod eviction If set to 0 Prefect will reschedule the flow run when the pod is evicted } stream_output { type boolean title Stream Output default true description If set output will be streamed from the job to local standard output } cluster_config { anyOf [ { $ref #/definitions/KubernetesClusterConfig } { type null } ] description The Kubernetes cluster config to use for job creation } memory_request { type string title Memory Request default 3Gi description The Memory allocation to request for this pod } finished_job_ttl { anyOf [ { type integer } { type null } ] title Finished Job TTL default 60 description The number of seconds to retain jobs after completion If set finished jobs will be cleaned up by Kubernetes after the given delay If not set jobs will be retained indefinitely } image_pull_policy { enum [ IfNotPresent Always Never ] type string title Image Pull Policy default Always description The Kubernetes image pull policy to use for job containers } service_account_name { anyOf [ { type string } { type null } ] title Service Account Name description The Kubernetes service account to use for job creation } job_watch_timeout_seconds { anyOf [ { type integer } { type null } ] title Job Watch Timeout Seconds description Number of seconds to wait for each event emitted by a job before timing out If not set the worker will wait for