Record M8.1 cluster inventory and per-worker storage probe
Summarize the maintainer-collected read-only inventory: RKE2 v1.32.5, an untainted control plane and three 32 GB workers on one hypervisor, no kubelet reservations or quotas, local-path as the only (node-pinned, reclaim Delete) storage, Canal/ingress-nginx/MetalLB/cert-manager, a manually synced aevolution-dev application and no PostgreSQL 18.6. Propose a measured budget and dev placement, and add a ready-to-apply local-path probe with one PVC and Job pinned to each worker. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
+4
-4
@@ -74,10 +74,10 @@ of the live application's configuration:
|
||||
| Project | aevolution-dev, or an equivalently restricted project |
|
||||
| Sync | Manual full sync; no automated prune/self-heal (recommended) |
|
||||
|
||||
The maintainer reports (2026-09-29) that Argo CD currently deploys each Git change
|
||||
automatically. Treat every file under a watched path as live on push, and confirm
|
||||
the actual sync and prune policy with `tools/inventory/collect-cluster.sh`
|
||||
(docs/infrastructure/INVENTORY.md).
|
||||
Inventory (2026-09-29, docs/infrastructure/INVENTORY.md): the live `aevolution-dev`
|
||||
application has no automated sync, which matches this guidance. Other projects'
|
||||
applications do auto-sync with prune. Keep AEvolution durable resources out of any
|
||||
automated-prune application.
|
||||
|
||||
Bootstrap examples in `deploy/argocd/*.yaml.example` are outside the workload
|
||||
path. Replace the Argo namespace and registered cluster API URL, or use its UI.
|
||||
|
||||
@@ -0,0 +1,291 @@
|
||||
# M8.1 storage latency probe for the cluster's only StorageClass, local-path
|
||||
# (rancher.io/local-path: node-local directories, reclaim Delete,
|
||||
# WaitForFirstConsumer). A local-path volume is created on the node that first
|
||||
# runs its pod, so each worker gets its own PVC and Job pinned by hostname.
|
||||
# Generated from disk-probe.yaml.example; outside every Argo path, applied by hand
|
||||
# with the maintainer's approval (2026-09-29):
|
||||
# kubectl apply -f deploy/kubernetes/inventory/disk-probe-local-path.yaml
|
||||
# kubectl wait -n evolution-dev --for=condition=complete --timeout=600s \
|
||||
# job -l app.kubernetes.io/name=evo-disk-probe
|
||||
# kubectl logs -n evolution-dev -l app.kubernetes.io/name=evo-disk-probe --prefix
|
||||
# kubectl delete -f deploy/kubernetes/inventory/disk-probe-local-path.yaml
|
||||
# Deleting the PVCs deletes the probe data (reclaim Delete); nothing else is touched.
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
name: evo-disk-probe
|
||||
namespace: evolution-dev
|
||||
labels:
|
||||
app.kubernetes.io/name: evo-disk-probe
|
||||
spec:
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: evo-disk-probe
|
||||
policyTypes: [Ingress, Egress] # No traffic in or out.
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: PersistentVolumeClaim
|
||||
metadata:
|
||||
name: evo-disk-probe-w1
|
||||
namespace: evolution-dev
|
||||
labels:
|
||||
app.kubernetes.io/name: evo-disk-probe
|
||||
spec:
|
||||
accessModes: [ReadWriteOnce]
|
||||
storageClassName: local-path
|
||||
resources:
|
||||
requests:
|
||||
storage: 2Gi
|
||||
---
|
||||
apiVersion: batch/v1
|
||||
kind: Job
|
||||
metadata:
|
||||
name: evo-disk-probe-w1
|
||||
namespace: evolution-dev
|
||||
labels:
|
||||
app.kubernetes.io/name: evo-disk-probe
|
||||
spec:
|
||||
backoffLimit: 0
|
||||
activeDeadlineSeconds: 600
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: evo-disk-probe
|
||||
spec:
|
||||
restartPolicy: Never
|
||||
automountServiceAccountToken: false
|
||||
imagePullSecrets:
|
||||
- name: harbor-pull
|
||||
nodeSelector:
|
||||
kubernetes.io/hostname: rke2-worker-1
|
||||
securityContext:
|
||||
runAsNonRoot: true
|
||||
runAsUser: 10001
|
||||
runAsGroup: 10001
|
||||
fsGroup: 10001
|
||||
seccompProfile:
|
||||
type: RuntimeDefault
|
||||
containers:
|
||||
- name: probe
|
||||
# Same repository and digest as deploy/kubernetes/dev (verified run 1399).
|
||||
image: registry.aeternalisgames.com/aeternalis/aevolution@sha256:0c6c6e1ac28de2ce0648fd0992ca694963e303ef5c9414fe5ac668937136800d
|
||||
command: ["/bin/bash", "-c"]
|
||||
args:
|
||||
- |
|
||||
set -eu
|
||||
cd /data
|
||||
ns() { date +%s%N; }
|
||||
echo "node=rke2-worker-1 filesystem: $(df -hT /data | tail -1)"
|
||||
t0=$(ns)
|
||||
dd if=/dev/zero of=dsync.bin bs=4k count=1000 oflag=dsync status=none
|
||||
t1=$(ns)
|
||||
echo "dsync_4k_writes=1000 mean_us=$(( (t1 - t0) / 1000 / 1000 ))"
|
||||
head -c 40960 /dev/urandom > payload.src
|
||||
mkdir -p objects
|
||||
worst=0; t0=$(ns)
|
||||
for i in $(seq 1 200); do
|
||||
s=$(ns)
|
||||
dd if=payload.src of=objects/.tmp status=none conv=fsync
|
||||
mv objects/.tmp objects/o$i
|
||||
sync objects
|
||||
e=$(( ($(ns) - s) / 1000 )); [ "$e" -gt "$worst" ] && worst=$e
|
||||
done
|
||||
t1=$(ns)
|
||||
echo "object_publish_40k=200 mean_us=$(( (t1 - t0) / 200 / 1000 )) max_us=$worst"
|
||||
t0=$(ns)
|
||||
dd if=/dev/zero of=seq.bin bs=1M count=256 conv=fdatasync status=none
|
||||
t1=$(ns)
|
||||
echo "sequential_256m_ms=$(( (t1 - t0) / 1000000 ))"
|
||||
rm -rf dsync.bin payload.src objects seq.bin
|
||||
resources:
|
||||
requests: {cpu: 100m, memory: 64Mi}
|
||||
limits: {cpu: 500m, memory: 128Mi}
|
||||
securityContext:
|
||||
allowPrivilegeEscalation: false
|
||||
readOnlyRootFilesystem: true
|
||||
capabilities:
|
||||
drop: [ALL]
|
||||
volumeMounts:
|
||||
- {name: data, mountPath: /data}
|
||||
volumes:
|
||||
- name: data
|
||||
persistentVolumeClaim:
|
||||
claimName: evo-disk-probe-w1
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: PersistentVolumeClaim
|
||||
metadata:
|
||||
name: evo-disk-probe-w2
|
||||
namespace: evolution-dev
|
||||
labels:
|
||||
app.kubernetes.io/name: evo-disk-probe
|
||||
spec:
|
||||
accessModes: [ReadWriteOnce]
|
||||
storageClassName: local-path
|
||||
resources:
|
||||
requests:
|
||||
storage: 2Gi
|
||||
---
|
||||
apiVersion: batch/v1
|
||||
kind: Job
|
||||
metadata:
|
||||
name: evo-disk-probe-w2
|
||||
namespace: evolution-dev
|
||||
labels:
|
||||
app.kubernetes.io/name: evo-disk-probe
|
||||
spec:
|
||||
backoffLimit: 0
|
||||
activeDeadlineSeconds: 600
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: evo-disk-probe
|
||||
spec:
|
||||
restartPolicy: Never
|
||||
automountServiceAccountToken: false
|
||||
imagePullSecrets:
|
||||
- name: harbor-pull
|
||||
nodeSelector:
|
||||
kubernetes.io/hostname: rke2-worker-2
|
||||
securityContext:
|
||||
runAsNonRoot: true
|
||||
runAsUser: 10001
|
||||
runAsGroup: 10001
|
||||
fsGroup: 10001
|
||||
seccompProfile:
|
||||
type: RuntimeDefault
|
||||
containers:
|
||||
- name: probe
|
||||
# Same repository and digest as deploy/kubernetes/dev (verified run 1399).
|
||||
image: registry.aeternalisgames.com/aeternalis/aevolution@sha256:0c6c6e1ac28de2ce0648fd0992ca694963e303ef5c9414fe5ac668937136800d
|
||||
command: ["/bin/bash", "-c"]
|
||||
args:
|
||||
- |
|
||||
set -eu
|
||||
cd /data
|
||||
ns() { date +%s%N; }
|
||||
echo "node=rke2-worker-2 filesystem: $(df -hT /data | tail -1)"
|
||||
t0=$(ns)
|
||||
dd if=/dev/zero of=dsync.bin bs=4k count=1000 oflag=dsync status=none
|
||||
t1=$(ns)
|
||||
echo "dsync_4k_writes=1000 mean_us=$(( (t1 - t0) / 1000 / 1000 ))"
|
||||
head -c 40960 /dev/urandom > payload.src
|
||||
mkdir -p objects
|
||||
worst=0; t0=$(ns)
|
||||
for i in $(seq 1 200); do
|
||||
s=$(ns)
|
||||
dd if=payload.src of=objects/.tmp status=none conv=fsync
|
||||
mv objects/.tmp objects/o$i
|
||||
sync objects
|
||||
e=$(( ($(ns) - s) / 1000 )); [ "$e" -gt "$worst" ] && worst=$e
|
||||
done
|
||||
t1=$(ns)
|
||||
echo "object_publish_40k=200 mean_us=$(( (t1 - t0) / 200 / 1000 )) max_us=$worst"
|
||||
t0=$(ns)
|
||||
dd if=/dev/zero of=seq.bin bs=1M count=256 conv=fdatasync status=none
|
||||
t1=$(ns)
|
||||
echo "sequential_256m_ms=$(( (t1 - t0) / 1000000 ))"
|
||||
rm -rf dsync.bin payload.src objects seq.bin
|
||||
resources:
|
||||
requests: {cpu: 100m, memory: 64Mi}
|
||||
limits: {cpu: 500m, memory: 128Mi}
|
||||
securityContext:
|
||||
allowPrivilegeEscalation: false
|
||||
readOnlyRootFilesystem: true
|
||||
capabilities:
|
||||
drop: [ALL]
|
||||
volumeMounts:
|
||||
- {name: data, mountPath: /data}
|
||||
volumes:
|
||||
- name: data
|
||||
persistentVolumeClaim:
|
||||
claimName: evo-disk-probe-w2
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: PersistentVolumeClaim
|
||||
metadata:
|
||||
name: evo-disk-probe-w3
|
||||
namespace: evolution-dev
|
||||
labels:
|
||||
app.kubernetes.io/name: evo-disk-probe
|
||||
spec:
|
||||
accessModes: [ReadWriteOnce]
|
||||
storageClassName: local-path
|
||||
resources:
|
||||
requests:
|
||||
storage: 2Gi
|
||||
---
|
||||
apiVersion: batch/v1
|
||||
kind: Job
|
||||
metadata:
|
||||
name: evo-disk-probe-w3
|
||||
namespace: evolution-dev
|
||||
labels:
|
||||
app.kubernetes.io/name: evo-disk-probe
|
||||
spec:
|
||||
backoffLimit: 0
|
||||
activeDeadlineSeconds: 600
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: evo-disk-probe
|
||||
spec:
|
||||
restartPolicy: Never
|
||||
automountServiceAccountToken: false
|
||||
imagePullSecrets:
|
||||
- name: harbor-pull
|
||||
nodeSelector:
|
||||
kubernetes.io/hostname: rke2-worker-3
|
||||
securityContext:
|
||||
runAsNonRoot: true
|
||||
runAsUser: 10001
|
||||
runAsGroup: 10001
|
||||
fsGroup: 10001
|
||||
seccompProfile:
|
||||
type: RuntimeDefault
|
||||
containers:
|
||||
- name: probe
|
||||
# Same repository and digest as deploy/kubernetes/dev (verified run 1399).
|
||||
image: registry.aeternalisgames.com/aeternalis/aevolution@sha256:0c6c6e1ac28de2ce0648fd0992ca694963e303ef5c9414fe5ac668937136800d
|
||||
command: ["/bin/bash", "-c"]
|
||||
args:
|
||||
- |
|
||||
set -eu
|
||||
cd /data
|
||||
ns() { date +%s%N; }
|
||||
echo "node=rke2-worker-3 filesystem: $(df -hT /data | tail -1)"
|
||||
t0=$(ns)
|
||||
dd if=/dev/zero of=dsync.bin bs=4k count=1000 oflag=dsync status=none
|
||||
t1=$(ns)
|
||||
echo "dsync_4k_writes=1000 mean_us=$(( (t1 - t0) / 1000 / 1000 ))"
|
||||
head -c 40960 /dev/urandom > payload.src
|
||||
mkdir -p objects
|
||||
worst=0; t0=$(ns)
|
||||
for i in $(seq 1 200); do
|
||||
s=$(ns)
|
||||
dd if=payload.src of=objects/.tmp status=none conv=fsync
|
||||
mv objects/.tmp objects/o$i
|
||||
sync objects
|
||||
e=$(( ($(ns) - s) / 1000 )); [ "$e" -gt "$worst" ] && worst=$e
|
||||
done
|
||||
t1=$(ns)
|
||||
echo "object_publish_40k=200 mean_us=$(( (t1 - t0) / 200 / 1000 )) max_us=$worst"
|
||||
t0=$(ns)
|
||||
dd if=/dev/zero of=seq.bin bs=1M count=256 conv=fdatasync status=none
|
||||
t1=$(ns)
|
||||
echo "sequential_256m_ms=$(( (t1 - t0) / 1000000 ))"
|
||||
rm -rf dsync.bin payload.src objects seq.bin
|
||||
resources:
|
||||
requests: {cpu: 100m, memory: 64Mi}
|
||||
limits: {cpu: 500m, memory: 128Mi}
|
||||
securityContext:
|
||||
allowPrivilegeEscalation: false
|
||||
readOnlyRootFilesystem: true
|
||||
capabilities:
|
||||
drop: [ALL]
|
||||
volumeMounts:
|
||||
- {name: data, mountPath: /data}
|
||||
volumes:
|
||||
- name: data
|
||||
persistentVolumeClaim:
|
||||
claimName: evo-disk-probe-w3
|
||||
Reference in New Issue
Block a user