ScalingConfig¶

class oci.generative_ai.models.ScalingConfig(**kwargs)¶

Bases: object

The auto scaling configuration for the Hosted Application. Defines the minimum and maximum number of replicas. When unspecified, the service applies service-defined default scaling values.

Attributes:

`SCALING_TYPE_CONCURRENCY`	A constant which can be used with the scaling_type property of a ScalingConfig.
`SCALING_TYPE_CPU`	A constant which can be used with the scaling_type property of a ScalingConfig.
`SCALING_TYPE_MEMORY`	A constant which can be used with the scaling_type property of a ScalingConfig.
`SCALING_TYPE_REQUESTS_PER_SECOND`	A constant which can be used with the scaling_type property of a ScalingConfig.
`max_replica`	Gets the max_replica of this ScalingConfig.
`min_replica`	Gets the min_replica of this ScalingConfig.
`scaling_type`	[Required] Gets the scaling_type of this ScalingConfig.
`target_concurrency_threshold`	Gets the target_concurrency_threshold of this ScalingConfig.
`target_cpu_threshold`	Gets the target_cpu_threshold of this ScalingConfig.
`target_memory_threshold`	Gets the target_memory_threshold of this ScalingConfig.
`target_rps_threshold`	Gets the target_rps_threshold of this ScalingConfig.

Methods:

__init__(**kwargs)

Initializes a new ScalingConfig object with values from keyword arguments.

SCALING_TYPE_CONCURRENCY = 'CONCURRENCY'¶: A constant which can be used with the scaling_type property of a ScalingConfig. This constant has a value of “CONCURRENCY”

SCALING_TYPE_CPU = 'CPU'¶: A constant which can be used with the scaling_type property of a ScalingConfig. This constant has a value of “CPU”

SCALING_TYPE_MEMORY = 'MEMORY'¶: A constant which can be used with the scaling_type property of a ScalingConfig. This constant has a value of “MEMORY”

SCALING_TYPE_REQUESTS_PER_SECOND = 'REQUESTS_PER_SECOND'¶: A constant which can be used with the scaling_type property of a ScalingConfig. This constant has a value of “REQUESTS_PER_SECOND”

__init__(**kwargs)¶

Initializes a new ScalingConfig object with values from keyword arguments. The following keyword arguments are supported (corresponding to the getters/setters of this class):

Parameters

min_replica (int) – The value to assign to the min_replica property of this ScalingConfig.
max_replica (int) – The value to assign to the max_replica property of this ScalingConfig.
scaling_type (str) – The value to assign to the scaling_type property of this ScalingConfig. Allowed values for this property are: “CPU”, “MEMORY”, “CONCURRENCY”, “REQUESTS_PER_SECOND”, ‘UNKNOWN_ENUM_VALUE’. Any unrecognized values returned by a service will be mapped to ‘UNKNOWN_ENUM_VALUE’.
target_cpu_threshold (int) – The value to assign to the target_cpu_threshold property of this ScalingConfig.
target_memory_threshold (int) – The value to assign to the target_memory_threshold property of this ScalingConfig.
target_concurrency_threshold (int) – The value to assign to the target_concurrency_threshold property of this ScalingConfig.
target_rps_threshold (int) – The value to assign to the target_rps_threshold property of this ScalingConfig.

property max_replica¶

Gets the max_replica of this ScalingConfig. Maximum number of replicas allowed.

Returns: The max_replica of this ScalingConfig.
Return type: int

property min_replica¶

Gets the min_replica of this ScalingConfig. Minimum number of replicas to keep running.

Returns: The min_replica of this ScalingConfig.
Return type: int

property scaling_type¶

[Required] Gets the scaling_type of this ScalingConfig. scaling type for application.

Allowed values for this property are: “CPU”, “MEMORY”, “CONCURRENCY”, “REQUESTS_PER_SECOND”, ‘UNKNOWN_ENUM_VALUE’. Any unrecognized values returned by a service will be mapped to ‘UNKNOWN_ENUM_VALUE’.

Returns: The scaling_type of this ScalingConfig.
Return type: str

property target_concurrency_threshold¶

Gets the target_concurrency_threshold of this ScalingConfig. number of simultaneous requests that can be processed by each replica.

Returns: The target_concurrency_threshold of this ScalingConfig.
Return type: int

property target_cpu_threshold¶

Gets the target_cpu_threshold of this ScalingConfig. Scale up if average CPU utilization exceeds this threshold.

Returns: The target_cpu_threshold of this ScalingConfig.
Return type: int

property target_memory_threshold¶

Gets the target_memory_threshold of this ScalingConfig. Scale up if average memory utilization exceeds this threshold.

Returns: The target_memory_threshold of this ScalingConfig.
Return type: int

property target_rps_threshold¶

Gets the target_rps_threshold of this ScalingConfig. requests-per-second per replica of an application.

Returns: The target_rps_threshold of this ScalingConfig.
Return type: int