Start M8.1 inventory: stated facts, workload profile and collectors
Record the maintainer-stated host facts (R730xd ~128 GB, 32 GB workers, automatic Harbor publish and Argo CD deploy, existing aevolution-db Secret and its conflicts with the pinned version and role split), the measured evo-server profile (peak RSS ~9.7 MiB, ~0.3% of a core) and a local storage baseline. Add a read-only cluster collector that never fetches Secret data and a by-hand storage latency probe outside the Argo path. Cluster facts remain uninspected pending read-only access. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
+6
-1
@@ -72,7 +72,12 @@ of the live application's configuration:
|
||||
| Path | deploy/kubernetes/dev |
|
||||
| Destination namespace | evolution-dev |
|
||||
| Project | aevolution-dev, or an equivalently restricted project |
|
||||
| Sync | Manual full sync; no automated prune/self-heal |
|
||||
| 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).
|
||||
|
||||
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 +1,110 @@
|
||||
# M8.1 storage latency probe. NOT part of any Argo path: apply by hand, once per
|
||||
# candidate StorageClass, after replacing <STORAGE_CLASS> (left unresolved on
|
||||
# purpose so this file cannot be applied unchanged). It measures the durability
|
||||
# pattern the region host depends on, on a fresh PVC of that class:
|
||||
# - 4 KiB synchronous writes (O_DSYNC), the PostgreSQL WAL-like cost;
|
||||
# - write + fsync + rename + directory fsync of a 40 KiB object (the object
|
||||
# store's publication pattern, ADR-0061);
|
||||
# - 256 MiB sequential write with fdatasync (throughput and capacity sanity).
|
||||
# Results are printed to the Job log. Afterwards delete the Job and the PVC
|
||||
# (kubectl delete job,pvc,networkpolicy -l app.kubernetes.io/name=evo-disk-probe
|
||||
# -n evolution-dev) and record the numbers in docs/infrastructure/INVENTORY.md.
|
||||
# The image is the already-pinned evo-sim runtime (Ubuntu 24.04 coreutils); no
|
||||
# new image is introduced.
|
||||
apiVersion: v1
|
||||
kind: PersistentVolumeClaim
|
||||
metadata:
|
||||
name: evo-disk-probe
|
||||
namespace: evolution-dev
|
||||
labels:
|
||||
app.kubernetes.io/name: evo-disk-probe
|
||||
spec:
|
||||
accessModes: [ReadWriteOnce]
|
||||
storageClassName: <STORAGE_CLASS>
|
||||
resources:
|
||||
requests:
|
||||
storage: 2Gi
|
||||
---
|
||||
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: batch/v1
|
||||
kind: Job
|
||||
metadata:
|
||||
name: evo-disk-probe
|
||||
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
|
||||
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 "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
|
||||
Reference in New Issue
Block a user