DaemonSet 在每个合格节点各起一个 Pod

(
set -euo pipefail
: "${CONTEXT:?Set the authorized kubectl context}"
: "${NAMESPACE:?Set the DaemonSet namespace}"
: "${DAEMONSET:?Set the DaemonSet name}"
: "${INTENDED_NODES:?Set the independent node-name to UID JSON file}"
umask 077
tmp=$(mktemp -d)
trap 'rm -rf -- "$tmp"' EXIT
k=(kubectl --context "$CONTEXT" --request-timeout=15s)
"${k[@]}" -n "$NAMESPACE" get ds "$DAEMONSET" -o json > "$tmp/before.json"
"${k[@]}" get nodes -o json > "$tmp/nodes.json"
"${k[@]}" -n "$NAMESPACE" get pods -o json > "$tmp/pods.json"
"${k[@]}" -n "$NAMESPACE" get ds "$DAEMONSET" -o json > "$tmp/after.json"
python3 - "$tmp" "$INTENDED_NODES" "$NAMESPACE" "$DAEMONSET" <<'PY'
import collections, json, pathlib, sys
root, roster, namespace, name = sys.argv[1:]
def require(ok, message):
    if not ok:
        raise SystemExit(message)
def unique(pairs):
    result = {}
    for key, value in pairs:
        require(key not in result, "Duplicate JSON key")
        result[key] = value
    return result
def load(path):
    return json.loads(pathlib.Path(path).read_text(), object_pairs_hook=unique)
def ready(obj):
    return any(c.get("type") == "Ready" and c.get("status") == "True"
               for c in obj.get("status", {}).get("conditions", []))
a, b = (load(pathlib.Path(root) / (x + ".json")) for x in ("before", "after"))
for ds in (a, b):
    require(ds["kind"] == "DaemonSet" and ds["apiVersion"] == "apps/v1",
            "Wrong resource type")
    require(ds["metadata"]["namespace"] == namespace and
            ds["metadata"]["name"] == name, "Wrong DaemonSet identity")
    require(ds["metadata"].get("uid") and not ds["metadata"].get("deletionTimestamp"),
            "Missing UID or deleting DaemonSet")
require(all(a["metadata"][k] == b["metadata"][k] for k in ("uid", "generation")),
        "DaemonSet changed during collection; retry")
uid = a["metadata"]["uid"]
expected = load(roster)
require(isinstance(expected, dict) and expected and
        all(isinstance(k, str) and k and isinstance(v, str) and v
            for k, v in expected.items()), "Use a nonempty node-name to UID map")
node_items = load(pathlib.Path(root) / "nodes.json")["items"]
nodes = {n["metadata"]["name"]: n for n in node_items}
require(len(nodes) == len(node_items), "Duplicate node names")
wrong_nodes = sorted(n for n in expected if n not in nodes or
                     nodes[n]["metadata"]["uid"] != expected[n])
unready_nodes = sorted(n for n in expected if n in nodes and not ready(nodes[n]))
rows, seen = [], set()
for pod in load(pathlib.Path(root) / "pods.json")["items"]:
    m = pod["metadata"]
    require(m["namespace"] == namespace, "Wrong Pod namespace")
    if not any(o.get("controller") is True and o.get("uid") == uid and
               o.get("kind") == "DaemonSet" and o.get("apiVersion") == "apps/v1"
               and o.get("name") == name for o in m.get("ownerReferences", [])):
        continue
    require(m.get("uid") and m["uid"] not in seen, "Missing or duplicate Pod UID")
    seen.add(m["uid"])
    node = pod["spec"].get("nodeName", "")
    phase = pod.get("status", {}).get("phase", "Unknown")
    terminating = bool(m.get("deletionTimestamp"))
    rows.append(dict(pod=m["name"], uid=m["uid"], node=node, phase=phase,
                     ready=ready(pod) and phase == "Running" and not terminating,
                     terminating=terminating,
                     revision=m.get("labels", {}).get("controller-revision-hash")))
counts = collections.Counter(r["node"] for r in rows if r["node"])
ready_nodes = {r["node"] for r in rows if r["ready"] and r["node"]}
issues = dict(node_identity_mismatch=wrong_nodes, node_not_ready=unready_nodes,
              missing_ready=sorted(set(expected) - ready_nodes),
              unexpected_owned_nodes=sorted(set(counts) - set(expected)),
              multiple_pods=sorted(n for n, count in counts.items() if count > 1),
              unassigned=[r["uid"] for r in rows if not r["node"]],
              unready_pods=[r["uid"] for r in rows if not r["ready"]])
print(json.dumps(dict(namespace=namespace, daemonset=name, uid=uid,
                     intended=expected, pods=rows, issues=issues), indent=2))
sys.exit(1 if any(issues.values()) else 0)
PY
)