live wire
▸IDENTITY · Keycloak 27 plans to remove Fine-Grained Admin Permissions V1 and Token Exchange V1Keycloak project▸AI · Inferact tests vLLM pipeline parallelism for prefill, reporting up to 23% more requests per GPU at a 2-second targetInferact Engineering (November 2026)▸SECURITY · Red Hat updates standard OpenJDK 21 RPMs for Hardened Images after earlier portable-package fixRed Hat Product Errata▸PLATFORM · Red Hat Multiarch Tuning 1.4.1 makes pod placement plugins optional and adds a downgrade caveatRed Hat Product Errata▸SECURITY · Red Hat updates OpenJDK 21 RPMs for Hardened Images to fix Java4ShellRed Hat Product Errata▸PLATFORM · Red Hat tests OpenShift Virtualization 4.22 with 10,000 active VMs during upgradesRed Hat Developer▸AI · vLLM adds day-zero support for Thinking Machines’ looped Inkling 2 MinivLLM Blog▸SECURITY · Red Hat rates OpenShift Dev Spaces 3.31.4 a Critical security updateRed Hat Product Errata▸SECURITY · Quarkus tells 3.27 users to switch from UBI 9 1.23 to 1.24 for the Java4Shell fixQuarkus Blog▸SECURITY · Red Hat issues Critical OpenJDK 25.0.5.1 update for WindowsRed Hat Product Errata▸PLATFORM · Red Hat resolves Lightspeed email outage; about 42 customers may miss daily summariesRed Hat Status▸JAVA · Red Hat details how to diagnose HikariCP connection pool stalls on OpenShiftRed Hat Developer▸SUPPLY CHAIN · Red Hat publishes Renovate presets for Lightwell dependency rebuildsRed Hat Developer▸PLATFORM · Red Hat resumes Lightspeed email delivery after outage, warns of delayed notificationsRed Hat Status▸IDENTITY · Keycloak 27 plans to remove Fine-Grained Admin Permissions V1 and Token Exchange V1Keycloak project▸AI · Inferact tests vLLM pipeline parallelism for prefill, reporting up to 23% more requests per GPU at a 2-second targetInferact Engineering (November 2026)▸SECURITY · Red Hat updates standard OpenJDK 21 RPMs for Hardened Images after earlier portable-package fixRed Hat Product Errata▸PLATFORM · Red Hat Multiarch Tuning 1.4.1 makes pod placement plugins optional and adds a downgrade caveatRed Hat Product Errata▸SECURITY · Red Hat updates OpenJDK 21 RPMs for Hardened Images to fix Java4ShellRed Hat Product Errata▸PLATFORM · Red Hat tests OpenShift Virtualization 4.22 with 10,000 active VMs during upgradesRed Hat Developer▸AI · vLLM adds day-zero support for Thinking Machines’ looped Inkling 2 MinivLLM Blog▸SECURITY · Red Hat rates OpenShift Dev Spaces 3.31.4 a Critical security updateRed Hat Product Errata▸SECURITY · Quarkus tells 3.27 users to switch from UBI 9 1.23 to 1.24 for the Java4Shell fixQuarkus Blog▸SECURITY · Red Hat issues Critical OpenJDK 25.0.5.1 update for WindowsRed Hat Product Errata▸PLATFORM · Red Hat resolves Lightspeed email outage; about 42 customers may miss daily summariesRed Hat Status▸JAVA · Red Hat details how to diagnose HikariCP connection pool stalls on OpenShiftRed Hat Developer▸SUPPLY CHAIN · Red Hat publishes Renovate presets for Lightwell dependency rebuildsRed Hat Developer▸PLATFORM · Red Hat resumes Lightspeed email delivery after outage, warns of delayed notificationsRed Hat Status
upstreambeat.ai
releasePLATFORM

Red Hat Multiarch Tuning 1.4.1 changes what OpenShift teams must check before a downgrade

The operator now accepts namespace-level pod placement configs without a plugins field, but older resource definitions still require it.

By The News Desk· Nov 21, 2026the quick take — two AI hosts go live when you do

Red Hat released Multiarch Tuning Operator 1.4.1 on November 21 with a change to the schema for namespace-scoped PodPlacementConfig resources. The spec.plugins field is now optional. That gives OpenShift teams one less field to specify, but it also creates a difference between rolling back the operator binary and restoring an older custom resource definition (CRD), according to Red Hat’s release advisory.

What changed

Omitting spec.plugins does not turn on any plugins. Red Hat says configurations that already omit the field remain valid after an upgrade. The release also moves the operator’s event reporting to the Kubernetes events.k8s.io/v1 API and ships examples for ClusterPodPlacementConfig, PodPlacementConfig, and ENoExecEvent in the operator bundle. A separate fix addresses a monitoring discovery problem: a transient API failure no longer leaves the operator unable to discover ServiceMonitor and PrometheusRule resources for the rest of the process’s lifetime.

Who should check their rollback plan

The operator is available through the Red Hat Operators catalog in OpenShift Container Platform. Red Hat describes it as a tool for managing workloads in mixed-architecture clusters and in single-architecture clusters moving to a mixed setup. The schema change concerns the namespace-scoped resource; the advisory does not announce the same change for ClusterPodPlacementConfig.

What to do before restoring an older CRD

Check whether the rollback procedure restores a CRD or just rolls back the operator binary. Red Hat says the caveat applies to the CRD, not a binary-only rollback. The CRDs shipped in versions 1.3.0 through 1.3.4 and 1.4.0 are among those that still require spec.plugins. Before reapplying one of those definitions, set spec.plugins to an empty object ({}) on every PodPlacementConfig that omits it, as the advisory directs. Resources without the field do not meet the older schema. The practical change is to check the stored resources before restoring the definition, rather than treating the downgrade as just an operator version change.

Filed by The News Desk. Corrections: desk@upstreambeat.ai · Our standards →

comments · 0

    Comments are moderated before they appear. Your email is used once to confirm it is you — never shown, never sold. Corrections and questions get an answer from the desk when we have one.