HealthProbeScenario
Reliability scenarios · Implementation: mlsysim/engine/scenario_definitions/reliability.py.
Construct this scenario with keyword inputs. The fields below show the types and defaults declared by this class.
A readiness probe every interval, failing after timeout, removing after failure_threshold misses.
Notes
Equation: Compose mlsysim.physics.reliability.calc_probe_detection_window.
Assumptions: A fixed-interval probe requires the stated number of misses and uses a fixed timeout.
Excludes: Probe jitter, recovery oscillation, and correlated probe failures are absent.
References
Derivation: this scenario binds its input fields to the referenced implementation contracts: mlsysim.physics.reliability.calc_probe_detection_window. The methods below identify any additional arithmetic.
Examples
>>> from mlsysim import Scenarios
>>> case = Scenarios.InferenceReadinessProbe
>>> type(case.detection_window).__name__
'tuple'Attributes
| Name | Description |
|---|---|
| detection_window | Time bound for a readiness probe to remove an unresponsive instance. Equation: |
| failure_threshold | |
| interval | |
| success_threshold | |
| timeout |
interval
Type: Quantity.
Declared default: required.
timeout
Type: Quantity.
Declared default: required.
failure_threshold
Type: int.
Declared default: required.
success_threshold
Type: int.
Declared default: required.
detection_window
engine.scenario_types.HealthProbeScenario.detection_window
Time bound for a readiness probe to remove an unresponsive instance. Equation: mlsysim.physics.reliability.calc_probe_detection_window(interval, timeout, failure_threshold). Units: time; scheduling follows that helper’s probe assumptions.