You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
UPSTREAM: <carry>: OCPBUGS-62517: Set replicas=1, PDB, and pod anti-affinity for HA topology
Rolling updates in HighlyAvailable clusters leave catalogd and
operator-controller unavailable when the only running pod is evicted
before its replacement is ready.
Fix by defaulting replicas=1 and PDB disabled in the static Helm values
(safe for SNO/External topologies, passes the SNO conformance test that
asserts exactly one replica in SingleReplica topology mode). Add pod
anti-affinity to prefer scheduling replicas on different nodes.
cluster-olm-operator detects the cluster's ControlPlaneTopology at
startup and overrides these values to replicas=2 and PDB enabled when a
HighlyAvailable topology is detected, then re-renders the manifests
before starting controllers. When a topology change is observed at
runtime (exceedingly rare), the operator exits so its deployment
controller restarts it, triggering a fresh Helm render with the correct
values for the new topology.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Signed-off-by: Todd Short <tshort@redhat.com>
0 commit comments