Add audit logging support with a default logging policy

Enable Kubernetes API audit logging with a default logging policy. When
desired, users can provide their custom audit policy rules using an
ansible variable.

Fixes #138

Signed-off-by: Alexander Brand <alexbrand09@gmail.com>

ansible/roles/kubernetes-common/defaults/main.yml

@@ -16,6 +16,22 @@ kubernetes_common_kubeadm_config:
   controlPlaneEndpoint: "{{ kubernetes_common_api_fqdn }}"
   apiServerExtraArgs:
     "endpoint-reconciler-type": "lease"
+    "audit-policy-file": "/etc/kubernetes/apiserver-audit-policy.yaml"
+    "audit-log-path": "/var/log/kubernetes/kube-apiserver-audit.log"
+    "audit-log-maxage": "30" # days
+    "audit-log-maxsize": "100" # megabytes
+    "audit-log-maxbackup": "1"
+  apiServerExtraVolumes:
+  - name: audit-policy
+    hostPath: /etc/kubernetes/apiserver-audit-policy.yaml
+    mountPath: /etc/kubernetes/apiserver-audit-policy.yaml
+    writable: false
+    pathType: File
+  - name: audit-logs
+    hostPath: /var/log/kubernetes
+    mountPath: /var/log/kubernetes
+    writable: true
+    pathType: DirectoryOrCreate
   apiServerCertSANs: "{{ kubernetes_common_api_ip | kube_lookup_hostname(kubernetes_common_api_fqdn, True) }}"
   etcd:
     external:

ansible/roles/kubernetes-common/templates/etc/kubernetes/apiserver-audit-policy.yaml

@@ -0,0 +1,162 @@
+apiVersion: audit.k8s.io/v1beta1
+kind: Policy
+rules:
+{% if kubernetes_common_audit_policy_rules is defined and kubernetes_common_audit_policy_rules != "" %}
+{{ kubernetes_common_audit_policy_rules | indent(2, true) }}
+{% else %}
+  # Default rules obtained from https://github.com/kubernetes/kubernetes/blob/v1.13.5/cluster/gce/gci/configure-helper.sh#L752
+  # The following requests were manually identified as high-volume and low-risk,
+  # so drop them.
+  - level: None
+    users: ["system:kube-proxy"]
+    verbs: ["watch"]
+    resources:
+      - group: "" # core
+        resources: ["endpoints", "services", "services/status"]
+  - level: None
+    # Ingress controller reads 'configmaps/ingress-uid' through the unsecured port.
+    # TODO(#46983): Change this to the ingress controller service account.
+    users: ["system:unsecured"]
+    namespaces: ["kube-system"]
+    verbs: ["get"]
+    resources:
+      - group: "" # core
+        resources: ["configmaps"]
+  - level: None
+    users: ["kubelet"] # legacy kubelet identity
+    verbs: ["get"]
+    resources:
+      - group: "" # core
+        resources: ["nodes", "nodes/status"]
+  - level: None
+    userGroups: ["system:nodes"]
+    verbs: ["get"]
+    resources:
+      - group: "" # core
+        resources: ["nodes", "nodes/status"]
+  - level: None
+    users:
+      - system:kube-controller-manager
+      - system:kube-scheduler
+      - system:serviceaccount:kube-system:endpoint-controller
+    verbs: ["get", "update"]
+    namespaces: ["kube-system"]
+    resources:
+      - group: "" # core
+        resources: ["endpoints"]
+  - level: None
+    users: ["system:apiserver"]
+    verbs: ["get"]
+    resources:
+      - group: "" # core
+        resources: ["namespaces", "namespaces/status", "namespaces/finalize"]
+  - level: None
+    users: ["cluster-autoscaler"]
+    verbs: ["get", "update"]
+    namespaces: ["kube-system"]
+    resources:
+      - group: "" # core
+        resources: ["configmaps", "endpoints"]
+  # Don't log HPA fetching metrics.
+  - level: None
+    users:
+      - system:kube-controller-manager
+    verbs: ["get", "list"]
+    resources:
+      - group: "metrics.k8s.io"
+  # Don't log these read-only URLs.
+  - level: None
+    nonResourceURLs:
+      - /healthz*
+      - /version
+      - /swagger*
+  # Don't log events requests.
+  - level: None
+    resources:
+      - group: "" # core
+        resources: ["events"]
+  # node and pod status calls from nodes are high-volume and can be large, don't log responses for expected updates from nodes
+  - level: Request
+    users: ["kubelet", "system:node-problem-detector", "system:serviceaccount:kube-system:node-problem-detector"]
+    verbs: ["update","patch"]
+    resources:
+      - group: "" # core
+        resources: ["nodes/status", "pods/status"]
+    omitStages:
+      - "RequestReceived"
+  - level: Request
+    userGroups: ["system:nodes"]
+    verbs: ["update","patch"]
+    resources:
+      - group: "" # core
+        resources: ["nodes/status", "pods/status"]
+    omitStages:
+      - "RequestReceived"
+  # deletecollection calls can be large, don't log responses for expected namespace deletions
+  - level: Request
+    users: ["system:serviceaccount:kube-system:namespace-controller"]
+    verbs: ["deletecollection"]
+    omitStages:
+      - "RequestReceived"
+  # Secrets, ConfigMaps, and TokenReviews can contain sensitive & binary data,
+  # so only log at the Metadata level.
+  - level: Metadata
+    resources:
+      - group: "" # core
+        resources: ["secrets", "configmaps"]
+      - group: authentication.k8s.io
+        resources: ["tokenreviews"]
+    omitStages:
+      - "RequestReceived"
+  # Get repsonses can be large; skip them.
+  - level: Request
+    verbs: ["get", "list", "watch"]
+    resources:
+      - group: "" # core
+      - group: "admissionregistration.k8s.io"
+      - group: "apiextensions.k8s.io"
+      - group: "apiregistration.k8s.io"
+      - group: "apps"
+      - group: "authentication.k8s.io"
+      - group: "authorization.k8s.io"
+      - group: "autoscaling"
+      - group: "batch"
+      - group: "certificates.k8s.io"
+      - group: "extensions"
+      - group: "metrics.k8s.io"
+      - group: "networking.k8s.io"
+      - group: "policy"
+      - group: "rbac.authorization.k8s.io"
+      - group: "scheduling.k8s.io"
+      - group: "settings.k8s.io"
+      - group: "storage.k8s.io"
+    omitStages:
+      - "RequestReceived"
+  # Default level for known APIs
+  - level: RequestResponse
+    resources:
+      - group: "" # core
+      - group: "admissionregistration.k8s.io"
+      - group: "apiextensions.k8s.io"
+      - group: "apiregistration.k8s.io"
+      - group: "apps"
+      - group: "authentication.k8s.io"
+      - group: "authorization.k8s.io"
+      - group: "autoscaling"
+      - group: "batch"
+      - group: "certificates.k8s.io"
+      - group: "extensions"
+      - group: "metrics.k8s.io"
+      - group: "networking.k8s.io"
+      - group: "policy"
+      - group: "rbac.authorization.k8s.io"
+      - group: "scheduling.k8s.io"
+      - group: "settings.k8s.io"
+      - group: "storage.k8s.io"
+    omitStages:
+      - "RequestReceived"
+  # Default level for all other requests.
+  - level: Metadata
+    omitStages:
+      - "RequestReceived"
+{% endif %}

ansible/roles/kubernetes-master/defaults/main.yml

@@ -1 +1,2 @@
 ---
+kubernetes_common_audit_policy_rules: []

ansible/roles/kubernetes-master/tasks/main.yml

@@ -18,6 +18,11 @@
     immediate: True
   when: ansible_distribution == 'CentOS' or ansible_distribution == 'Red Hat Enterprise Linux'
 
+- name: drop api-server audit policy template
+  template:
+    dest: /etc/kubernetes/apiserver-audit-policy.yaml
+    src: etc/kubernetes/apiserver-audit-policy.yaml
+
 - include_tasks: install.yml
   when: wardroom_action == 'install'
 

ansible/roles/kubernetes-master/templates/etc/kubernetes/apiserver-audit-policy.yaml

@@ -0,0 +1,162 @@
+apiVersion: audit.k8s.io/v1beta1
+kind: Policy
+rules:
+{% if kubernetes_common_audit_policy_rules|length > 0 %}
+{{ kubernetes_common_audit_policy_rules | indent(2, true) }}
+{% else %}
+  # Default rules obtained from https://github.com/kubernetes/kubernetes/blob/v1.13.5/cluster/gce/gci/configure-helper.sh#L752
+  # The following requests were manually identified as high-volume and low-risk,
+  # so drop them.
+  - level: None
+    users: ["system:kube-proxy"]
+    verbs: ["watch"]
+    resources:
+      - group: "" # core
+        resources: ["endpoints", "services", "services/status"]
+  - level: None
+    # Ingress controller reads 'configmaps/ingress-uid' through the unsecured port.
+    # TODO(#46983): Change this to the ingress controller service account.
+    users: ["system:unsecured"]
+    namespaces: ["kube-system"]
+    verbs: ["get"]
+    resources:
+      - group: "" # core
+        resources: ["configmaps"]
+  - level: None
+    users: ["kubelet"] # legacy kubelet identity
+    verbs: ["get"]
+    resources:
+      - group: "" # core
+        resources: ["nodes", "nodes/status"]
+  - level: None
+    userGroups: ["system:nodes"]
+    verbs: ["get"]
+    resources:
+      - group: "" # core
+        resources: ["nodes", "nodes/status"]
+  - level: None
+    users:
+      - system:kube-controller-manager
+      - system:kube-scheduler
+      - system:serviceaccount:kube-system:endpoint-controller
+    verbs: ["get", "update"]
+    namespaces: ["kube-system"]
+    resources:
+      - group: "" # core
+        resources: ["endpoints"]
+  - level: None
+    users: ["system:apiserver"]
+    verbs: ["get"]
+    resources:
+      - group: "" # core
+        resources: ["namespaces", "namespaces/status", "namespaces/finalize"]
+  - level: None
+    users: ["cluster-autoscaler"]
+    verbs: ["get", "update"]
+    namespaces: ["kube-system"]
+    resources:
+      - group: "" # core
+        resources: ["configmaps", "endpoints"]
+  # Don't log HPA fetching metrics.
+  - level: None
+    users:
+      - system:kube-controller-manager
+    verbs: ["get", "list"]
+    resources:
+      - group: "metrics.k8s.io"
+  # Don't log these read-only URLs.
+  - level: None
+    nonResourceURLs:
+      - /healthz*
+      - /version
+      - /swagger*
+  # Don't log events requests.
+  - level: None
+    resources:
+      - group: "" # core
+        resources: ["events"]
+  # node and pod status calls from nodes are high-volume and can be large, don't log responses for expected updates from nodes
+  - level: Request
+    users: ["kubelet", "system:node-problem-detector", "system:serviceaccount:kube-system:node-problem-detector"]
+    verbs: ["update","patch"]
+    resources:
+      - group: "" # core
+        resources: ["nodes/status", "pods/status"]
+    omitStages:
+      - "RequestReceived"
+  - level: Request
+    userGroups: ["system:nodes"]
+    verbs: ["update","patch"]
+    resources:
+      - group: "" # core
+        resources: ["nodes/status", "pods/status"]
+    omitStages:
+      - "RequestReceived"
+  # deletecollection calls can be large, don't log responses for expected namespace deletions
+  - level: Request
+    users: ["system:serviceaccount:kube-system:namespace-controller"]
+    verbs: ["deletecollection"]
+    omitStages:
+      - "RequestReceived"
+  # Secrets, ConfigMaps, and TokenReviews can contain sensitive & binary data,
+  # so only log at the Metadata level.
+  - level: Metadata
+    resources:
+      - group: "" # core
+        resources: ["secrets", "configmaps"]
+      - group: authentication.k8s.io
+        resources: ["tokenreviews"]
+    omitStages:
+      - "RequestReceived"
+  # Get repsonses can be large; skip them.
+  - level: Request
+    verbs: ["get", "list", "watch"]
+    resources:
+      - group: "" # core
+      - group: "admissionregistration.k8s.io"
+      - group: "apiextensions.k8s.io"
+      - group: "apiregistration.k8s.io"
+      - group: "apps"
+      - group: "authentication.k8s.io"
+      - group: "authorization.k8s.io"
+      - group: "autoscaling"
+      - group: "batch"
+      - group: "certificates.k8s.io"
+      - group: "extensions"
+      - group: "metrics.k8s.io"
+      - group: "networking.k8s.io"
+      - group: "policy"
+      - group: "rbac.authorization.k8s.io"
+      - group: "scheduling.k8s.io"
+      - group: "settings.k8s.io"
+      - group: "storage.k8s.io"
+    omitStages:
+      - "RequestReceived"
+  # Default level for known APIs
+  - level: RequestResponse
+    resources:
+      - group: "" # core
+      - group: "admissionregistration.k8s.io"
+      - group: "apiextensions.k8s.io"
+      - group: "apiregistration.k8s.io"
+      - group: "apps"
+      - group: "authentication.k8s.io"
+      - group: "authorization.k8s.io"
+      - group: "autoscaling"
+      - group: "batch"
+      - group: "certificates.k8s.io"
+      - group: "extensions"
+      - group: "metrics.k8s.io"
+      - group: "networking.k8s.io"
+      - group: "policy"
+      - group: "rbac.authorization.k8s.io"
+      - group: "scheduling.k8s.io"
+      - group: "settings.k8s.io"
+      - group: "storage.k8s.io"
+    omitStages:
+      - "RequestReceived"
+  # Default level for all other requests.
+  - level: Metadata
+    omitStages:
+      - "RequestReceived"
+{% endif %}