How deeply does Machine Learning Platform Engineering cover liveness check?

Explains periodic endpoint calls and restart behavior, but does not provide probe configuration details.

Liveness check

As explained in Machine Learning Platform Engineering

A periodic check that determines whether a running workload should be restarted because its process is no longer healthy.

A liveness check periodically calls a service endpoint to determine whether a running pod is alive and can continue its main process. When the check fails, Kubernetes may restart the pod to recover from a fault. section 10.4.1

In a BentoML service deployed to Kubernetes:

The liveness probe calls /healthz and reports whether the pod is alive. section 10.4.1
The readiness probe calls /readyz and determines whether the pod should receive traffic; readiness additionally requires operational request handling. section 10.4.1
BentoML provides these health-check endpoints out of the box, alongside Prometheus metrics for service observability. section 10.4.1

How Machine Learning Platform Engineering covers it

Cover of Machine Learning Platform Engineering

liveBook manning.com

Read Machine Learning Platform Engineering on liveBook Get the book at manning.com

Also explained in

liveBook manning.com

Kubernetes in Action, Second EditionA liveness probe is a Kubernetes health check that determines whether a container's application is functioning and can trigger container termination after failure.
liveBook manning.com

Kubernetes for DevelopersA liveness probe is a Kubernetes health check that determines whether a running container is still functioning and should be allowed to continue running.
liveBook manning.com

Learn Docker in a Month of Lunches, Second EditionA liveness probe is a Kubernetes container probe that determines whether a container should be restarted.
liveBook manning.com

Quarkus in ActionA Kubernetes liveness probe periodically determines whether a container should be restarted because its application is no longer recoverable.
liveBook manning.com

Spring in Action, Sixth EditionA liveness probe is a health indicator that tells an orchestrator whether an application is healthy enough to continue running without being restarted.
liveBook manning.com

Bootstrapping Microservices, Second Edition: With Docker, Kubernetes, GitHub Actions, and TerraformA liveness probe is a Kubernetes health-check configuration that determines whether a container or pod is still functioning and should continue running.

Compare how 7 books explain liveness check →

Related concepts

health checkkind of · A health check is an assessment or probe that determines whether a system, service, or component is functioning acceptably according to defined criteria.
Kubernetesused by · Kubernetes is an open-source platform for orchestrating and automating the deployment, scaling, and management of containerized workloads across computing clusters.
readiness checkcontrasts with · A readiness check is a health probe that determines whether a running service or workload is prepared to receive requests or traffic.
exec probeincludes · An exec probe is a Kubernetes probe that runs a command inside a container and evaluates whether it exits successfully.
health check endpointuses · A health check endpoint is an API endpoint that reports whether an application or service is operating correctly or ready to handle requests.

This explainer was generated by Manning's knowledge graph from the text of Machine Learning Platform Engineering. The section links point to the parts of the book it draws on.