From 9c6808cb8918239513f5b01351c8731b2a833955 Mon Sep 17 00:00:00 2001
From: Peter Sprygada <psprygada@datum.net>
Date: Sun, 2 Aug 2026 20:03:44 -0400
Subject: [PATCH 1/2] feat: add operational hardening defaults to fabric-router
 DaemonSet
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Adds livenessProbe (pidof zebra/bgpd), resource requests/limits, a
preStop hook for graceful FRR shutdown, and rollingUpdate strategy —
all standard, environment-agnostic defaults for an FRR DaemonSet so
every consumer (prod, staging, containerlab) gets them without needing
a per-environment patch.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
---
 config/fabric/daemonset.yaml | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/config/fabric/daemonset.yaml b/config/fabric/daemonset.yaml
index 35c6e84..82a44ea 100644
--- a/config/fabric/daemonset.yaml
+++ b/config/fabric/daemonset.yaml
@@ -9,6 +9,10 @@ spec:
   selector:
     matchLabels:
       app.kubernetes.io/name: fabric-router
+  updateStrategy:
+    type: RollingUpdate
+    rollingUpdate:
+      maxUnavailable: 1
   template:
     metadata:
       labels:
@@ -75,12 +79,32 @@ spec:
       containers:
         - name: frr
           image: ghcr.io/datum-cloud/fabric-router:latest
+          lifecycle:
+            preStop:
+              exec:
+                command:
+                  - /usr/lib/frr/frrinit.sh
+                  - stop
           securityContext:
             capabilities:
               add:
                 - NET_ADMIN
                 - NET_RAW
                 - SYS_ADMIN
+          livenessProbe:
+            exec:
+              command:
+                - sh
+                - -c
+                - pidof zebra bgpd
+            initialDelaySeconds: 10
+            periodSeconds: 30
+          resources:
+            requests:
+              cpu: 50m
+              memory: 64Mi
+            limits:
+              memory: 256Mi
           volumeMounts:
             - name: frr-etc
               mountPath: /etc/frr

From 9861ef14d3742f4f234e0a8083626d487d10ffa1 Mon Sep 17 00:00:00 2001
From: Peter Sprygada <psprygada@datum.net>
Date: Sun, 2 Aug 2026 20:17:55 -0400
Subject: [PATCH 2/2] fix: harden fabric-router probes and add
 priorityClass/dnsPolicy
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Research against Calico/MetalLB/Cilium's production FRR/BGP DaemonSets
surfaced several gaps versus real-world practice:

- pidof zebra bgpd only proves the processes are resident, not that
  they're responsive, and passes as long as any one of the named
  processes is alive. Replace with per-daemon vtysh checks
  (`vtysh -d <daemon> -c "show version"`) — verified via FRR source
  that `vtysh -c "show daemons"` silently omits unreachable daemons
  from its exit code, so it wouldn't have caught a dead bgpd either.
- Add a startupProbe so a slow config load (peer groups, route-maps,
  prefix-lists) doesn't get killed by liveness before it's up.
- Add priorityClassName: system-node-critical, matching calico-node
  and cilium-agent, so the speaker isn't evicted under node pressure.
- Add dnsPolicy: ClusterFirstWithHostNet, required alongside
  hostNetwork: true and missing before now.
- Bump cpu request 50m -> 100m to absorb BFD/convergence bursts.

terminationGracePeriodSeconds is intentionally left untouched:
calico-node and MetalLB's speaker both ship low values (0s and 2s)
rather than stretching it to match BGP hold-timers, relying on BFD
for fast peer-side failure detection instead of a k8s-side graceful
drain.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
---
 config/fabric/daemonset.yaml | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/config/fabric/daemonset.yaml b/config/fabric/daemonset.yaml
index 82a44ea..2b23175 100644
--- a/config/fabric/daemonset.yaml
+++ b/config/fabric/daemonset.yaml
@@ -19,6 +19,8 @@ spec:
         app.kubernetes.io/name: fabric-router
     spec:
       hostNetwork: true
+      dnsPolicy: ClusterFirstWithHostNet
+      priorityClassName: system-node-critical
       # FRR here establishes the underlay eBGP session to the physical fabric
       # and brings up the node's lo address, both of which galactic-router
       # depends on before it can start — so this must tolerate NotReady the
@@ -91,17 +93,27 @@ spec:
                 - NET_ADMIN
                 - NET_RAW
                 - SYS_ADMIN
+          startupProbe:
+            exec:
+              command:
+                - sh
+                - -c
+                - vtysh -d zebra -c "show version" && vtysh -d bgpd -c "show version"
+            periodSeconds: 5
+            failureThreshold: 30
           livenessProbe:
             exec:
               command:
                 - sh
                 - -c
-                - pidof zebra bgpd
+                - vtysh -d zebra -c "show version" && vtysh -d bgpd -c "show version"
             initialDelaySeconds: 10
             periodSeconds: 30
+            timeoutSeconds: 5
+            failureThreshold: 5
           resources:
             requests:
-              cpu: 50m
+              cpu: 100m
               memory: 64Mi
             limits:
               memory: 256Mi