Sign in
latestOpenAPI 3.1.02026-08-23100133183.1 KB

0d66c7340876

Serverless Containers

Update deployment scaling options

patch/v1/container-deployments/{deployment_name}/scaling

Path parameters

deployment_namestring required
Example:my-deployment

Name of the deployment

Request body

min_replica_countnumber

Minimum number of replicas

max_replica_countnumber

Maximum number of replicas

queue_message_ttl_secondsnumber

Duration in seconds after which messages in the queue will be dropped

concurrent_requests_per_replicanumber

Number of requests each replica can process concurrently.

Example request

{
  "min_replica_count": 1,
  "max_replica_count": 50,
  "scale_down_policy": {
    "delay_seconds": 300
  },
  "scale_up_policy": {
    "delay_seconds": 300
  },
  "queue_message_ttl_seconds": 500,
  "concurrent_requests_per_replica": 1,
  "scaling_triggers": {
    "queue_load": {
      "threshold": 2
    },
    "cpu_utilization": {
      "enabled": true,
      "threshold": 80
    },
    "gpu_utilization": {
      "enabled": true,
      "threshold": 80
    }
  }
}

Response

Returns the updated scaling options

min_replica_countnumber required

Minimum number of replicas

max_replica_countnumber required

Maximum number of replicas

queue_message_ttl_secondsnumber required

Duration in seconds after which messages in the queue will be dropped

concurrent_requests_per_replicanumber required

Number of requests each replica can process concurrently.

Example response

{
  "min_replica_count": 1,
  "max_replica_count": 50,
  "scale_down_policy": {
    "delay_seconds": 300
  },
  "scale_up_policy": {
    "delay_seconds": 300
  },
  "queue_message_ttl_seconds": 500,
  "concurrent_requests_per_replica": 1,
  "scaling_triggers": {
    "queue_load": {
      "threshold": 2
    },
    "cpu_utilization": {
      "enabled": true,
      "threshold": 80
    },
    "gpu_utilization": {
      "enabled": true,
      "threshold": 80
    }
  }
}