Merge branch 'master' of https://github.com/kubernetes-incubator/kubespray

README.md

@@ -40,7 +40,7 @@ To deploy the cluster you can use :
 For Vagrant we need to install python dependencies for provisioning tasks.
 Check if Python and pip are installed:
 
-    python -v && pip -v
+    python -V && pip -V
 
 If this returns the version of the software, you're good to go. If not, download and install Python from here <https://www.python.org/downloads/source/>
 Install the necessary requirements
@@ -103,6 +103,7 @@ Supported Components
     -   [weave](https://github.com/weaveworks/weave) v2.3.0
 -   Application
     -   [ingress-nginx](https://github.com/kubernetes/ingress-nginx) v0.15.0
+    -   [cert-manager](https://github.com/jetstack/cert-manager/releases) v0.3.0
 
 Note: kubernetes doesn't support newer docker versions. Among other things kubelet currently breaks on docker's non-standard version numbering (it no longer uses semantic versioning). To ensure auto-updates don't break your cluster look into e.g. yum versionlock plugin or apt pin).
 

cluster.yml

@@ -51,7 +51,7 @@
   any_errors_fatal: "{{ any_errors_fatal | default(true) }}"
   roles:
     - { role: kubespray-defaults}
-    - { role: etcd, tags: etcd, etcd_cluster_setup: true, etcd_events_cluster_setup: true }
+    - { role: etcd, tags: etcd, etcd_cluster_setup: true, etcd_events_cluster_setup: "{{ etcd_events_cluster_enabled }}" }
 
 - hosts: k8s-cluster:calico-rr
   any_errors_fatal: "{{ any_errors_fatal | default(true) }}"

docs/dns-stack.md

@@ -52,13 +52,13 @@ You can modify how Kubespray sets up DNS for your cluster with the variables ``d
 ## dns_mode
 ``dns_mode`` configures how Kubespray will setup cluster DNS. There are four modes available:
 
-#### dnsmasq_kubedns (default)
+#### dnsmasq_kubedns
 This installs an additional dnsmasq DaemonSet which gives more flexibility and lifts some
 limitations (e.g. number of nameservers). Kubelet is instructed to use dnsmasq instead of kubedns/skydns.
 It is configured to forward all DNS queries belonging to cluster services to kubedns/skydns. All
 other queries are forwardet to the nameservers found in ``upstream_dns_servers`` or ``default_resolver``
 
-#### kubedns
+#### kubedns (default)
 This does not install the dnsmasq DaemonSet and instructs kubelet to directly use kubedns/skydns for
 all queries.
 

inventory/sample/group_vars/k8s-cluster.yml

@@ -140,6 +140,9 @@ dns_domain: "{{ cluster_name }}"
 # Path used to store Docker data
 docker_daemon_graph: "/var/lib/docker"
 
+## Used to set docker daemon iptables options to true
+#docker_iptables_enabled: "true"
+
 ## A string of extra options to pass to the docker daemon.
 ## This string should be exactly as you wish it to appear.
 ## An obvious use case is allowing insecure-registry access

roles/docker/defaults/main.yml

@@ -17,7 +17,7 @@ dockerproject_repo_key_info:
 dockerproject_repo_info:
   repos:
 
-docker_dns_servers_strict: yes
+docker_dns_servers_strict: true
 
 docker_container_storage_setup: false
 
@@ -40,3 +40,6 @@ dockerproject_rh_repo_base_url: 'https://yum.dockerproject.org/repo/main/centos/
 dockerproject_rh_repo_gpgkey: 'https://yum.dockerproject.org/gpg'
 dockerproject_apt_repo_base_url: 'https://apt.dockerproject.org/repo'
 dockerproject_apt_repo_gpgkey: 'https://apt.dockerproject.org/gpg'
+
+# Used to set docker daemon iptables options
+docker_iptables_enabled: "false"

roles/docker/tasks/set_facts_dns.yml

@@ -56,7 +56,7 @@
 
 - name: check number of nameservers
   fail:
-    msg: "Too many nameservers. You can relax this check by set docker_dns_servers_strict=no and we will only use the first 3."
+    msg: "Too many nameservers. You can relax this check by set docker_dns_servers_strict=false in all.yml and we will only use the first 3."
   when: docker_dns_servers|length > 3 and docker_dns_servers_strict|bool
 
 - name: rtrim number of nameservers to 3

roles/docker/templates/docker-options.conf.j2

@@ -1,5 +1,5 @@
 [Service]
-Environment="DOCKER_OPTS={{ docker_options|default('') }} --iptables=false"
+Environment="DOCKER_OPTS={{ docker_options|default('') }} --iptables={{ docker_iptables_enabled | default('false') }}"
 {% if docker_mount_flags is defined and docker_mount_flags != "" %}
 MountFlags={{ docker_mount_flags }}
 {% endif %}

roles/download/defaults/main.yml

@@ -132,14 +132,14 @@ kubednsautoscaler_image_repo: "gcr.io/google_containers/cluster-proportional-aut
 kubednsautoscaler_image_tag: "{{ kubednsautoscaler_version }}"
 test_image_repo: busybox
 test_image_tag: latest
-elasticsearch_version: "v2.4.1"
+elasticsearch_version: "v5.6.4"
-elasticsearch_image_repo: "gcr.io/google_containers/elasticsearch"
+elasticsearch_image_repo: "k8s.gcr.io/elasticsearch"
 elasticsearch_image_tag: "{{ elasticsearch_version }}"
-fluentd_version: "1.22"
+fluentd_version: "v2.0.4"
-fluentd_image_repo: "gcr.io/google_containers/fluentd-elasticsearch"
+fluentd_image_repo: "k8s.gcr.io/fluentd-elasticsearch"
 fluentd_image_tag: "{{ fluentd_version }}"
-kibana_version: "v4.6.1"
+kibana_version: "5.6.4"
-kibana_image_repo: "gcr.io/google_containers/kibana"
+kibana_image_repo: "docker.elastic.co/kibana/kibana"
 kibana_image_tag: "{{ kibana_version }}"
 helm_version: "v2.9.1"
 helm_image_repo: "lachlanevenson/k8s-helm"
@@ -160,11 +160,9 @@ ingress_nginx_controller_image_repo: "quay.io/kubernetes-ingress-controller/ngin
 ingress_nginx_controller_image_tag: "0.15.0"
 ingress_nginx_default_backend_image_repo: "gcr.io/google_containers/defaultbackend"
 ingress_nginx_default_backend_image_tag: "1.4"
-cert_manager_version: "v0.2.4"
+cert_manager_version: "v0.3.0"
 cert_manager_controller_image_repo: "quay.io/jetstack/cert-manager-controller"
 cert_manager_controller_image_tag: "{{ cert_manager_version }}"
-cert_manager_ingress_shim_image_repo: "quay.io/jetstack/cert-manager-ingress-shim"
-cert_manager_ingress_shim_image_tag: "{{ cert_manager_version }}"
 
 downloads:
   netcheck_server:
@@ -583,14 +581,6 @@ downloads:
     sha256: "{{ cert_manager_controller_digest_checksum|default(None) }}"
     groups:
       - kube-node
-  cert_manager_ingress_shim:
-    enabled: "{{ cert_manager_enabled }}"
-    container: true
-    repo: "{{ cert_manager_ingress_shim_image_repo }}"
-    tag: "{{ cert_manager_ingress_shim_image_tag }}"
-    sha256: "{{ cert_manager_ingress_shim_digest_checksum|default(None) }}"
-    groups:
-      - kube-node
 
 download_defaults:
   container: false

roles/etcd/defaults/main.yml

@@ -3,6 +3,9 @@
 etcd_cluster_setup: true
 etcd_events_cluster_setup: false
 
+# Set to true to separate k8s events to a different etcd cluster
+etcd_events_cluster_enabled: false
+
 etcd_backup_prefix: "/var/backups"
 etcd_data_dir: "/var/lib/etcd"
 etcd_events_data_dir: "/var/lib/etcd-events"

roles/kubernetes-apps/efk/elasticsearch/templates/efk-clusterrolebinding.yml

@@ -1,9 +1,12 @@
 ---
 kind: ClusterRoleBinding
-apiVersion: rbac.authorization.k8s.io/v1beta1
+apiVersion: rbac.authorization.k8s.io/v1
 metadata:
   name: efk
   namespace: kube-system
+  labels:
+    kubernetes.io/cluster-service: "true"
+    addonmanager.kubernetes.io/mode: Reconcile
 subjects:
   - kind: ServiceAccount
     name: efk

roles/kubernetes-apps/efk/elasticsearch/templates/efk-sa.yml

@@ -6,3 +6,4 @@ metadata:
   namespace: kube-system
   labels:
     kubernetes.io/cluster-service: "true"
+    addonmanager.kubernetes.io/mode: Reconcile

roles/kubernetes-apps/efk/elasticsearch/templates/elasticsearch-deployment.yml.j2

@@ -1,15 +1,17 @@
 ---
-# https://raw.githubusercontent.com/kubernetes/kubernetes/v1.5.2/cluster/addons/fluentd-elasticsearch/es-controller.yaml
+# https://raw.githubusercontent.com/kubernetes/kubernetes/v1.10.2/cluster/addons/fluentd-elasticsearch/es-statefulset.yaml
-apiVersion: extensions/v1beta1
+apiVersion: apps/v1
-kind: Deployment
+kind: StatefulSet
 metadata:
-  name: elasticsearch-logging-v1
+  name: elasticsearch-logging
   namespace: kube-system
   labels:
     k8s-app: elasticsearch-logging
     version: "{{ elasticsearch_image_tag }}"
     kubernetes.io/cluster-service: "true"
+    addonmanager.kubernetes.io/mode: Reconcile
 spec:
+  serviceName: elasticsearch-logging
   replicas: 2
   selector:
     matchLabels:
@@ -53,4 +55,10 @@ spec:
 {% if rbac_enabled %}
       serviceAccountName: efk 
 {% endif %}
+      initContainers:
+      - image: alpine:3.6
+        command: ["/sbin/sysctl", "-w", "vm.max_map_count=262144"]
+        name: elasticsearch-logging-init
+        securityContext:
+          privileged: true
 

roles/kubernetes-apps/efk/fluentd/defaults/main.yml

@@ -1,7 +1,7 @@
 ---
 fluentd_cpu_limit: 0m
-fluentd_mem_limit: 200Mi
+fluentd_mem_limit: 500Mi
 fluentd_cpu_requests: 100m
 fluentd_mem_requests: 200Mi
-fluentd_config_dir: /etc/kubernetes/fluentd
+fluentd_config_dir: /etc/fluent/config.d
-fluentd_config_file: fluentd.conf
+# fluentd_config_file: fluentd.conf

roles/kubernetes-apps/efk/fluentd/templates/fluentd-config.yml.j2

@@ -1,10 +1,19 @@
+---
+# https://raw.githubusercontent.com/kubernetes/kubernetes/release-1.10/cluster/addons/fluentd-elasticsearch/fluentd-es-configmap.yaml
 apiVersion: v1
 kind: ConfigMap
 metadata:
   name: fluentd-config
   namespace: "kube-system"
+  labels:
+    addonmanager.kubernetes.io/mode: Reconcile
 data:
-  {{ fluentd_config_file }}: |
+  system.conf: |-
+    <system>
+      root_dir /tmp/fluentd-buffers/
+    </system>
+
+  containers.input.conf: |-
     # This configuration file for Fluentd / td-agent is used
     # to watch changes to Docker log files. The kubelet creates symlinks that
     # capture the pod name, namespace, container name & Docker container ID
@@ -18,7 +27,6 @@ data:
     # See https://github.com/uken/fluent-plugin-elasticsearch &
     # https://github.com/fabric8io/fluent-plugin-kubernetes_metadata_filter for
     # more information about the plugins.
-    # Maintainer: Jimmi Dyson <jimmidyson@gmail.com>
     #
     # Example
     # =======
@@ -99,63 +107,87 @@ data:
     # This makes it easier for users to search for logs by pod name or by
     # the name of the Kubernetes container regardless of how many times the
     # Kubernetes pod has been restarted (resulting in a several Docker container IDs).
-    #
+
-    # TODO: Propagate the labels associated with a container along with its logs
+    # Json Log Example:
-    # so users can query logs using labels as well as or instead of the pod name
-    # and container name. This is simply done via configuration of the Kubernetes
-    # fluentd plugin but requires secrets to be enabled in the fluent pod. This is a
-    # problem yet to be solved as secrets are not usable in static pods which the fluentd
-    # pod must be until a per-node controller is available in Kubernetes.
-    # Prevent fluentd from handling records containing its own logs. Otherwise
-    # it can lead to an infinite loop, when error in sending one message generates
-    # another message which also fails to be sent and so on.
-    <match fluent.**>
-      type null
-    </match>
-    # Example:
     # {"log":"[info:2016-02-16T16:04:05.930-08:00] Some log text here\n","stream":"stdout","time":"2016-02-17T00:04:05.931087621Z"}
+    # CRI Log Example:
+    # 2016-02-17T00:04:05.931087621Z stdout F [info:2016-02-16T16:04:05.930-08:00] Some log text here
     <source>
-      type tail
+      @id fluentd-containers.log
+      @type tail
       path /var/log/containers/*.log
       pos_file /var/log/es-containers.log.pos
       time_format %Y-%m-%dT%H:%M:%S.%NZ
-      tag kubernetes.*
+      tag raw.kubernetes.*
-      format json
       read_from_head true
+      <parse>
+        @type multi_format
+        <pattern>
+          format json
+          time_key time
+          time_format %Y-%m-%dT%H:%M:%S.%NZ
+        </pattern>
+        <pattern>
+          format /^(?<time>.+) (?<stream>stdout|stderr) [^ ]* (?<log>.*)$/
+          time_format %Y-%m-%dT%H:%M:%S.%N%:z
+        </pattern>
+      </parse>
     </source>
+
+    # Detect exceptions in the log output and forward them as one log entry.
+    <match raw.kubernetes.**>
+      @id raw.kubernetes
+      @type detect_exceptions
+      remove_tag_prefix raw
+      message log
+      stream stream
+      multiline_flush_interval 5
+      max_bytes 500000
+      max_lines 1000
+    </match>
+
+  system.input.conf: |-
     # Example:
     # 2015-12-21 23:17:22,066 [salt.state       ][INFO    ] Completed state [net.ipv4.ip_forward] at time 23:17:22.066081
     <source>
-      type tail
+      @id minion
+      @type tail
       format /^(?<time>[^ ]* [^ ,]*)[^\[]*\[[^\]]*\]\[(?<severity>[^ \]]*) *\] (?<message>.*)$/
       time_format %Y-%m-%d %H:%M:%S
       path /var/log/salt/minion
-      pos_file /var/log/es-salt.pos
+      pos_file /var/log/salt.pos
       tag salt
     </source>
+
     # Example:
     # Dec 21 23:17:22 gke-foo-1-1-4b5cbd14-node-4eoj startupscript: Finished running startup script /var/run/google.startup.script
     <source>
-      type tail
+      @id startupscript.log
+      @type tail
       format syslog
       path /var/log/startupscript.log
       pos_file /var/log/es-startupscript.log.pos
       tag startupscript
     </source>
+
     # Examples:
     # time="2016-02-04T06:51:03.053580605Z" level=info msg="GET /containers/json"
     # time="2016-02-04T07:53:57.505612354Z" level=error msg="HTTP Error" err="No such image: -f" statusCode=404
+    # TODO(random-liu): Remove this after cri container runtime rolls out.
     <source>
-      type tail
+      @id docker.log
+      @type tail
       format /^time="(?<time>[^)]*)" level=(?<severity>[^ ]*) msg="(?<message>[^"]*)"( err="(?<error>[^"]*)")?( statusCode=($<status_code>\d+))?/
       path /var/log/docker.log
       pos_file /var/log/es-docker.log.pos
       tag docker
     </source>
+
     # Example:
     # 2016/02/04 06:52:38 filePurge: successfully removed file /var/etcd/data/member/wal/00000000000006d0-00000000010a23d1.wal
     <source>
-      type tail
+      @id etcd.log
+      @type tail
       # Not parsing this, because it doesn't have anything particularly useful to
       # parse out of it (like severities).
       format none
@@ -163,13 +195,16 @@ data:
       pos_file /var/log/es-etcd.log.pos
       tag etcd
     </source>
+
     # Multi-line parsing is required for all the kube logs because very large log
     # statements, such as those that include entire object bodies, get split into
     # multiple lines by glog.
+
     # Example:
     # I0204 07:32:30.020537    3368 server.go:1048] POST /stats/container/: (13.972191ms) 200 [[Go-http-client/1.1] 10.244.1.3:40537]
     <source>
-      type tail
+      @id kubelet.log
+      @type tail
       format multiline
       multiline_flush_interval 5s
       format_firstline /^\w\d{4}/
@@ -179,10 +214,12 @@ data:
       pos_file /var/log/es-kubelet.log.pos
       tag kubelet
     </source>
+
     # Example:
     # I1118 21:26:53.975789       6 proxier.go:1096] Port "nodePort for kube-system/default-http-backend:http" (:31429/tcp) was open before and is still needed
     <source>
-      type tail
+      @id kube-proxy.log
+      @type tail
       format multiline
       multiline_flush_interval 5s
       format_firstline /^\w\d{4}/
@@ -192,10 +229,12 @@ data:
       pos_file /var/log/es-kube-proxy.log.pos
       tag kube-proxy
     </source>
+
     # Example:
     # I0204 07:00:19.604280       5 handlers.go:131] GET /api/v1/nodes: (1.624207ms) 200 [[kube-controller-manager/v1.1.3 (linux/amd64) kubernetes/6a81b50] 127.0.0.1:38266]
     <source>
-      type tail
+      @id kube-apiserver.log
+      @type tail
       format multiline
       multiline_flush_interval 5s
       format_firstline /^\w\d{4}/
@@ -205,10 +244,12 @@ data:
       pos_file /var/log/es-kube-apiserver.log.pos
       tag kube-apiserver
     </source>
+
     # Example:
     # I0204 06:55:31.872680       5 servicecontroller.go:277] LB already exists and doesn't need update for service kube-system/kube-ui
     <source>
-      type tail
+      @id kube-controller-manager.log
+      @type tail
       format multiline
       multiline_flush_interval 5s
       format_firstline /^\w\d{4}/
@@ -218,10 +259,12 @@ data:
       pos_file /var/log/es-kube-controller-manager.log.pos
       tag kube-controller-manager
     </source>
+
     # Example:
     # W0204 06:49:18.239674       7 reflector.go:245] pkg/scheduler/factory/factory.go:193: watch of *api.Service ended with: 401: The event in requested index is outdated and cleared (the requested history has been cleared [2578313/2577886]) [2579312]
     <source>
-      type tail
+      @id kube-scheduler.log
+      @type tail
       format multiline
       multiline_flush_interval 5s
       format_firstline /^\w\d{4}/
@@ -231,10 +274,12 @@ data:
       pos_file /var/log/es-kube-scheduler.log.pos
       tag kube-scheduler
     </source>
+
     # Example:
     # I1104 10:36:20.242766       5 rescheduler.go:73] Running Rescheduler
     <source>
-      type tail
+      @id rescheduler.log
+      @type tail
       format multiline
       multiline_flush_interval 5s
       format_firstline /^\w\d{4}/
@@ -244,10 +289,12 @@ data:
       pos_file /var/log/es-rescheduler.log.pos
       tag rescheduler
     </source>
+
     # Example:
     # I0603 15:31:05.793605       6 cluster_manager.go:230] Reading config from path /etc/gce.conf
     <source>
-      type tail
+      @id glbc.log
+      @type tail
       format multiline
       multiline_flush_interval 5s
       format_firstline /^\w\d{4}/
@@ -257,10 +304,12 @@ data:
       pos_file /var/log/es-glbc.log.pos
       tag glbc
     </source>
+
     # Example:
     # I0603 15:31:05.793605       6 cluster_manager.go:230] Reading config from path /etc/gce.conf
     <source>
-      type tail
+      @id cluster-autoscaler.log
+      @type tail
       format multiline
       multiline_flush_interval 5s
       format_firstline /^\w\d{4}/
@@ -270,59 +319,123 @@ data:
       pos_file /var/log/es-cluster-autoscaler.log.pos
       tag cluster-autoscaler
     </source>
+
+    # Logs from systemd-journal for interesting services.
+    # TODO(random-liu): Remove this after cri container runtime rolls out.
+    <source>
+      @id journald-docker
+      @type systemd
+      filters [{ "_SYSTEMD_UNIT": "docker.service" }]
+      <storage>
+        @type local
+        persistent true
+      </storage>
+      read_from_head true
+      tag docker
+    </source>
+
+    # <source>
+    #   @id journald-container-runtime
+    #   @type systemd
+    #   filters [{ "_SYSTEMD_UNIT": "{% raw %}{{ container_runtime }} {% endraw %}.service" }]
+    #   <storage>
+    #     @type local
+    #     persistent true
+    #   </storage>
+    #   read_from_head true
+    #   tag container-runtime
+    # </source>
+
+    <source>
+      @id journald-kubelet
+      @type systemd
+      filters [{ "_SYSTEMD_UNIT": "kubelet.service" }]
+      <storage>
+        @type local
+        persistent true
+      </storage>
+      read_from_head true
+      tag kubelet
+    </source>
+
+    <source>
+      @id journald-node-problem-detector
+      @type systemd
+      filters [{ "_SYSTEMD_UNIT": "node-problem-detector.service" }]
+      <storage>
+        @type local
+        persistent true
+      </storage>
+      read_from_head true
+      tag node-problem-detector
+    </source>
+
+  forward.input.conf: |-
+    # Takes the messages sent over TCP
+    <source>
+      @type forward
+    </source>
+
+  monitoring.conf: |-
+    # Prometheus Exporter Plugin
+    # input plugin that exports metrics
+    <source>
+      @type prometheus
+    </source>
+
+    <source>
+      @type monitor_agent
+    </source>
+
+    # input plugin that collects metrics from MonitorAgent
+    <source>
+      @type prometheus_monitor
+      <labels>
+        host ${hostname}
+      </labels>
+    </source>
+
+    # input plugin that collects metrics for output plugin
+    <source>
+      @type prometheus_output_monitor
+      <labels>
+        host ${hostname}
+      </labels>
+    </source>
+
+    # input plugin that collects metrics for in_tail plugin
+    <source>
+      @type prometheus_tail_monitor
+      <labels>
+        host ${hostname}
+      </labels>
+    </source>
+
+  output.conf: |-
+    # Enriches records with Kubernetes metadata
     <filter kubernetes.**>
-      type kubernetes_metadata
+      @type kubernetes_metadata
     </filter>
-    ## Prometheus Exporter Plugin
+
-    ## input plugin that exports metrics
-    #<source>
-    #  type prometheus
-    #</source>
-    #<source>
-    #  type monitor_agent
-    #</source>
-    #<source>
-    #  type forward
-    #</source>
-    ## input plugin that collects metrics from MonitorAgent
-    #<source>
-    #  @type prometheus_monitor
-    #  <labels>
-    #    host ${hostname}
-    #  </labels>
-    #</source>
-    ## input plugin that collects metrics for output plugin
-    #<source>
-    #  @type prometheus_output_monitor
-    #  <labels>
-    #    host ${hostname}
-    #  </labels>
-    #</source>
-    ## input plugin that collects metrics for in_tail plugin
-    #<source>
-    #  @type prometheus_tail_monitor
-    #  <labels>
-    #    host ${hostname}
-    #  </labels>
-    #</source>
     <match **>
-       type elasticsearch
+      @id elasticsearch
-       user "#{ENV['FLUENT_ELASTICSEARCH_USER']}"
+      @type elasticsearch
-       password "#{ENV['FLUENT_ELASTICSEARCH_PASSWORD']}"
+      @log_level info
-       log_level info
       include_tag_key true
       host elasticsearch-logging
       port 9200
       logstash_format true
-       # Set the chunk limit the same as for fluentd-gcp.
+      <buffer>
-       buffer_chunk_limit 2M
+        @type file
-       # Cap buffer memory usage to 2MiB/chunk * 32 chunks = 64 MiB
+        path /var/log/fluentd-buffers/kubernetes.system.buffer
-       buffer_queue_limit 32
+        flush_mode interval
+        retry_type exponential_backoff
+        flush_thread_count 2
         flush_interval 5s
-       # Never wait longer than 5 minutes between retries.
+        retry_forever
-       max_retry_wait 30
+        retry_max_interval 30
-       # Disable the limit on the number of retries (retry forever).
+        chunk_limit_size 2M
-       disable_retry_limit
+        queue_limit_length 8
-       # Use multiple threads for processing.
+        overflow_action block
-       num_threads 8
+      </buffer>
     </match>

roles/kubernetes-apps/efk/fluentd/templates/fluentd-ds.yml.j2

@@ -1,32 +1,42 @@
 ---
-# https://raw.githubusercontent.com/kubernetes/kubernetes/v1.5.2/cluster/addons/fluentd-elasticsearch/es-controller.yaml
+# https://raw.githubusercontent.com/kubernetes/kubernetes/v1.10.2/cluster/addons/fluentd-elasticsearch/fluentd-es-ds.yaml
-apiVersion: extensions/v1beta1
+apiVersion: apps/v1
 kind: DaemonSet
 metadata:
-  name: "fluentd-es-v{{ fluentd_version }}"
+  name: "fluentd-es-{{ fluentd_version }}"
   namespace: "kube-system"
   labels:
     k8s-app: fluentd-es
+    version: "{{ fluentd_version }}"
     kubernetes.io/cluster-service: "true"
-    version: "v{{ fluentd_version }}"
+    addonmanager.kubernetes.io/mode: Reconcile
 spec:
+  selector:
+    matchLabels:
+      k8s-app: fluentd-es
+      version: "{{ fluentd_version }}"
   template:
     metadata:
       labels:
         k8s-app: fluentd-es
         kubernetes.io/cluster-service: "true"
-        version: "v{{ fluentd_version }}"
+        version: "{{ fluentd_version }}"
+      # This annotation ensures that fluentd does not get evicted if the node
+      # supports critical pod annotation based priority scheme.
+      # Note that this does not guarantee admission on the nodes (#40573).
+      annotations:
+        scheduler.alpha.kubernetes.io/critical-pod: ''
     spec:
-      tolerations:
+      priorityClassName: system-node-critical
-        - effect: NoSchedule
+{% if rbac_enabled %}
-          operator: Exists
+      serviceAccountName: efk
+{% endif %}
       containers:
       - name: fluentd-es
         image: "{{ fluentd_image_repo }}:{{ fluentd_image_tag }}"
-        command:
+        env:
-          - '/bin/sh'
+        - name: FLUENTD_ARGS
-          - '-c'
+          value: "--no-supervisor -q"
-          - '/usr/sbin/td-agent -c {{ fluentd_config_dir }}/{{ fluentd_config_file}} 2>&1 >> /var/log/fluentd.log'
         resources:
           limits:
 {% if fluentd_cpu_limit is defined and fluentd_cpu_limit != "0m" %}
@@ -39,22 +49,21 @@ spec:
         volumeMounts:
         - name: varlog
           mountPath: /var/log
-        - name: dockercontainers
+        - name: varlibdockercontainers
           mountPath: "{{ docker_daemon_graph }}/containers"
           readOnly: true
-        - name: config
+        - name: config-volume
           mountPath: "{{ fluentd_config_dir }}"
+      nodeSelector:
+        beta.kubernetes.io/fluentd-ds-ready: "true"
       terminationGracePeriodSeconds: 30
       volumes:
       - name: varlog
         hostPath:
           path: /var/log
-      - name: dockercontainers
+      - name: varlibdockercontainers
         hostPath:
           path: {{ docker_daemon_graph }}/containers
-      - name: config
+      - name: config-volume
         configMap:
           name: fluentd-config
-{% if rbac_enabled %}
-      serviceAccountName: efk 
-{% endif %}

roles/kubernetes-apps/efk/kibana/defaults/main.yml

@@ -4,3 +4,4 @@ kibana_mem_limit: 0M
 kibana_cpu_requests: 100m
 kibana_mem_requests: 0M
 kibana_service_port: 5601
+kibana_base_url: "/api/v1/namespaces/kube-system/services/kibana-logging/proxy"

roles/kubernetes-apps/efk/kibana/templates/kibana-deployment.yml.j2

@@ -1,6 +1,6 @@
 ---
-# https://raw.githubusercontent.com/kubernetes/kubernetes/v1.5.2/cluster/addons/fluentd-kibana/kibana-controller.yaml
+# https://raw.githubusercontent.com/kubernetes/kubernetes/release-1.10/cluster/addons/fluentd-elasticsearch/kibana-deployment.yaml
-apiVersion: extensions/v1beta1
+apiVersion: apps/v1
 kind: Deployment
 metadata:
   name: kibana-logging
@@ -36,10 +36,12 @@ spec:
         env:
           - name: "ELASTICSEARCH_URL"
             value: "http://elasticsearch-logging:{{ elasticsearch_service_port }}"
-{% if kibana_base_url is defined and kibana_base_url != "" %}
+          - name: "SERVER_BASEPATH"
-          - name: "KIBANA_BASE_URL"
             value: "{{ kibana_base_url }}"
-{% endif %}
+          - name: XPACK_MONITORING_ENABLED
+            value: "false"
+          - name: XPACK_SECURITY_ENABLED
+            value: "false"
         ports:
         - containerPort: 5601
           name: ui

roles/kubernetes-apps/helm/defaults/main.yml

@@ -18,3 +18,6 @@ helm_skip_refresh: false
 
 # Override values for the Tiller Deployment manifest.
 # tiller_override: "key1=val1,key2=val2"
+
+# Limit the maximum number of revisions saved per release. Use 0 for no limit.
+# tiller_max_history: 0

roles/kubernetes-apps/helm/tasks/main.yml

@@ -34,6 +34,7 @@
     {% if rbac_enabled %} --service-account=tiller{% endif %}
     {% if tiller_node_selectors is defined %} --node-selectors {{ tiller_node_selectors }}{% endif %}
     {% if tiller_override is defined %} --override {{ tiller_override }}{% endif %}
+    {% if tiller_max_history is defined %} --history-max={{ tiller_max_history }}{% endif %}
   when: (helm_container is defined and helm_container.changed) or (helm_task_result is defined and helm_task_result.changed)
 
 - name: Helm | Set up bash completion

roles/kubernetes-apps/ingress_controller/cert_manager/templates/cert-manager-certificate-crd.yml.j2

@@ -5,7 +5,7 @@ metadata:
   name: certificates.certmanager.k8s.io
   labels:
     app: cert-manager
-    chart: cert-manager-0.2.8
+    chart: cert-manager-v0.3.2
     release: cert-manager
     heritage: Tiller
 spec:

roles/kubernetes-apps/ingress_controller/cert_manager/templates/cert-manager-clusterissuer-crd.yml.j2

@@ -5,7 +5,7 @@ metadata:
   name: clusterissuers.certmanager.k8s.io
   labels:
     app: cert-manager
-    chart: cert-manager-0.2.8
+    chart: cert-manager-v0.3.2
     release: cert-manager
     heritage: Tiller
 spec:

roles/kubernetes-apps/ingress_controller/cert_manager/templates/cert-manager-clusterrole.yml.j2

@@ -5,7 +5,7 @@ metadata:
   name: cert-manager
   labels:
     app: cert-manager
-    chart: cert-manager-0.2.8
+    chart: cert-manager-v0.3.2
     release: cert-manager
     heritage: Tiller
 rules:

roles/kubernetes-apps/ingress_controller/cert_manager/templates/cert-manager-clusterrolebinding.yml.j2

@@ -5,7 +5,7 @@ metadata:
   name: cert-manager
   labels:
     app: cert-manager
-    chart: cert-manager-0.2.8
+    chart: cert-manager-v0.3.2
     release: cert-manager
     heritage: Tiller
 roleRef:

roles/kubernetes-apps/ingress_controller/cert_manager/templates/cert-manager-deploy.yml.j2

@@ -6,11 +6,15 @@ metadata:
   namespace: {{ cert_manager_namespace }}
   labels:
     app: cert-manager
-    chart: cert-manager-0.2.8
+    chart: cert-manager-v0.3.2
     release: cert-manager
     heritage: Tiller
 spec:
   replicas: 1
+  selector:
+    matchLabels:
+      k8s-app: cert-manager
+      release: cert-manager
   template:
     metadata:
       labels:
@@ -25,6 +29,7 @@ spec:
           imagePullPolicy: {{ k8s_image_pull_policy }}
           args:
             - --cluster-resource-namespace=$(POD_NAMESPACE)
+            - --leader-election-namespace=$(POD_NAMESPACE)
           env:
             - name: POD_NAMESPACE
               valueFrom:
@@ -37,15 +42,3 @@ spec:
             limits:
               cpu: {{ cert_manager_cpu_limits }}
               memory: {{ cert_manager_memory_limits }}
-            
-        - name: ingress-shim
-          image: {{ cert_manager_ingress_shim_image_repo }}:{{ cert_manager_ingress_shim_image_tag }}
-          imagePullPolicy: {{ k8s_image_pull_policy }}
-          resources:
-            requests:
-              cpu: {{ cert_manager_cpu_requests }}
-              memory: {{ cert_manager_memory_requests }}
-            limits:
-              cpu: {{ cert_manager_cpu_limits }}
-              memory: {{ cert_manager_memory_limits }}
-            

roles/kubernetes-apps/ingress_controller/cert_manager/templates/cert-manager-issuer-crd.yml.j2

@@ -5,7 +5,7 @@ metadata:
   name: issuers.certmanager.k8s.io
   labels:
     app: cert-manager
-    chart: cert-manager-0.2.8
+    chart: cert-manager-v0.3.2
     release: cert-manager
     heritage: Tiller
 spec:

roles/kubernetes-apps/ingress_controller/cert_manager/templates/cert-manager-sa.yml.j2

@@ -6,6 +6,6 @@ metadata:
   namespace: {{ cert_manager_namespace }}
   labels:
     app: cert-manager
-    chart: cert-manager-0.2.8
+    chart: cert-manager-v0.3.2
     release: cert-manager
     heritage: Tiller

roles/kubernetes-apps/persistent_volumes/openstack/defaults/main.yml

@@ -1,2 +1,7 @@
 ---
 persistent_volumes_enabled: false
+storage_classes:
+  - name: standard
+    is_default: true
+    parameters:
+      availability: nova

roles/kubernetes-apps/persistent_volumes/openstack/tasks/main.yml

@@ -1,21 +1,19 @@
 ---
 - name: Kubernetes Persistent Volumes | Lay down OpenStack Cinder Storage Class template
   template:
-    src: "{{item.file}}"
+    src: "openstack-storage-class.yml.j2"
-    dest: "{{kube_config_dir}}/{{item.file}}"
+    dest: "{{kube_config_dir}}/openstack-storage-class.yml"
-  with_items:
-    - {file: openstack-storage-class.yml, type: StorageClass, name: storage-class }
   register: manifests
   when:
     - inventory_hostname == groups['kube-master'][0]
 
 - name: Kubernetes Persistent Volumes | Add OpenStack Cinder Storage Class
   kube:
-    name: "{{item.item.name}}"
+    name: storage-class
     kubectl: "{{bin_dir}}/kubectl"
-    resource: "{{item.item.type}}"
+    resource: StorageClass
-    filename: "{{kube_config_dir}}/{{item.item.file}}"
+    filename: "{{kube_config_dir}}/openstack-storage-class.yml"
     state: "latest"
-  with_items: "{{ manifests.results }}"
   when:
     - inventory_hostname == groups['kube-master'][0]
+    - manifests.changed

roles/kubernetes-apps/persistent_volumes/openstack/templates/openstack-storage-class.yml

@@ -1,10 +0,0 @@
----
-kind: StorageClass
-apiVersion: storage.k8s.io/v1
-metadata:
-  name: standard
-  annotations:
-    storageclass.kubernetes.io/is-default-class: "true"
-provisioner: kubernetes.io/cinder
-parameters:
-  availability: nova

roles/kubernetes-apps/persistent_volumes/openstack/templates/openstack-storage-class.yml.j2

@@ -0,0 +1,14 @@
+{% for class in storage_classes %}
+---
+kind: StorageClass
+apiVersion: storage.k8s.io/v1
+metadata:
+  name: "{{ class.name }}"
+  annotations:
+    storageclass.kubernetes.io/is-default-class: "{{ class.is_default | default(false) | ternary("true","false") }}"
+provisioner: kubernetes.io/cinder
+parameters:
+{% for key, value in (class.parameters | default({})).items() %}
+  "{{ key }}": "{{ value }}"
+{% endfor %}
+{% endfor %}

roles/kubernetes/master/templates/kube-scheduler-policy.yaml.j2

@@ -2,17 +2,27 @@
 "kind" : "Policy",
 "apiVersion" : "v1",
 "predicates" : [
-    {"name" : "PodFitsHostPorts"},
+    {"name" : "MaxEBSVolumeCount"},
-    {"name" : "PodFitsResources"},
+    {"name" : "MaxGCEPDVolumeCount"},
+    {"name" : "MaxAzureDiskVolumeCount"},
+    {"name" : "MatchInterPodAffinity"},
     {"name" : "NoDiskConflict"},
-    {"name" : "MatchNodeSelector"},
+    {"name" : "GeneralPredicates"},
-    {"name" : "HostName"}
+    {"name" : "CheckNodeMemoryPressure"},
+    {"name" : "CheckNodeDiskPressure"},
+    {"name" : "CheckNodePIDPressure"},
+    {"name" : "CheckNodeCondition"},
+    {"name" : "PodToleratesNodeTaints"},
+    {"name" : "CheckVolumeBinding"}
     ],
 "priorities" : [
+    {"name" : "SelectorSpreadPriority", "weight" : 1},
+    {"name" : "InterPodAffinityPriority", "weight" : 1},
     {"name" : "LeastRequestedPriority", "weight" : 1},
     {"name" : "BalancedResourceAllocation", "weight" : 1},
-    {"name" : "ServiceSpreadingPriority", "weight" : 1},
+    {"name" : "NodePreferAvoidPodsPriority", "weight" : 1},
-    {"name" : "EqualPriority", "weight" : 1}
+    {"name" : "NodeAffinityPriority", "weight" : 1},
+    {"name" : "TaintTolerationPriority", "weight" : 1}
     ],
 "hardPodAffinitySymmetricWeight" : 10
 }

roles/kubernetes/master/templates/kubeadm-config.yaml.j2

@@ -39,7 +39,7 @@ apiServerExtraArgs:
 {% if kube_version | version_compare('v1.9', '>=') %}
   endpoint-reconciler-type: lease
 {% endif %}
-{% if etcd_events_cluster_setup  %}
+{% if etcd_events_cluster_enabled %}
   etcd-servers-overrides: "/events#{{ etcd_events_access_addresses }}"
 {% endif %}
   service-node-port-range: {{ kube_apiserver_node_port_range }}

roles/kubernetes/master/templates/manifests/kube-apiserver.manifest.j2

@@ -30,7 +30,7 @@ spec:
     - apiserver
     - --advertise-address={{ ip | default(ansible_default_ipv4.address) }}
     - --etcd-servers={{ etcd_access_addresses }}
-{%   if etcd_events_cluster_setup  %}
+{%   if etcd_events_cluster_enabled %}
     - --etcd-servers-overrides=/events#{{ etcd_events_access_addresses }}
 {% endif %}
 {%   if kube_version | version_compare('v1.9', '<')  %}

roles/kubernetes/node/templates/vsphere-cloud-config.j2

@@ -14,6 +14,9 @@ server = "{{ vsphere_vcenter_ip }}"
 {% if vsphere_vm_uuid is defined and vsphere_vm_uuid != ""  %}
 vm-uuid = "{{ vsphere_vm_uuid }}"
 {% endif %}
+{% if vsphere_vm_name is defined and vsphere_vm_name != ""  %}
+vm-name = "{{ vsphere_vm_name }}"
+{% endif %}
 {% endif %}
 
 {% if kube_version | version_compare('v1.9.2', '>=') %}

roles/kubernetes/preinstall/tasks/main.yml

@@ -1,4 +1,8 @@
 ---
+# Disable swap
+- import_tasks: swapoff.yml
+  when: disable_swap
+
 - import_tasks: verify-settings.yml
   tags:
     - asserts

roles/kubernetes/preinstall/tasks/swapoff.yml

@@ -0,0 +1,10 @@
+---
+- name: Remove swapfile from /etc/fstab
+  mount:
+    name: swap
+    fstype: swap
+    state: absent
+
+- name: Disable swap
+  command: swapoff -a
+  when: ansible_swaptotal_mb > 0

roles/kubernetes/preinstall/tasks/verify-settings.yml

@@ -17,13 +17,13 @@
 
 - name: Stop if unknown network plugin
   assert:
-    that: network_plugin in ['calico', 'canal', 'flannel', 'weave', 'cloud']
+    that: kube_network_plugin in ['calico', 'canal', 'flannel', 'weave', 'cloud', 'cilium', 'contiv']
-  when: network_plugin is defined
+  when: kube_network_plugin is defined
   ignore_errors: "{{ ignore_assert_errors }}"
 
 - name: Stop if incompatible network plugin and cloudprovider
   assert:
-    that: network_plugin != 'calico'
+    that: kube_network_plugin != 'calico'
     msg: "Azure and Calico are not compatible. See https://github.com/projectcalico/calicoctl/issues/949 for details."
   when: cloud_provider is defined and cloud_provider == 'azure'
   ignore_errors: "{{ ignore_assert_errors }}"

roles/kubernetes/secrets/tasks/check-certs.yml

@@ -33,14 +33,14 @@
        '{{ kube_cert_dir }}/front-proxy-client-key.pem',
        '{{ kube_cert_dir }}/service-account-key.pem',
        {% for host in groups['kube-master'] %}
-       '{{ kube_cert_dir }}/admin-{{ host }}.pem'
+       '{{ kube_cert_dir }}/admin-{{ host }}.pem',
        '{{ kube_cert_dir }}/admin-{{ host }}-key.pem'
        {% if not loop.last %}{{','}}{% endif %}
-       {% endfor %}]
+       {% endfor %},
        {% for host in groups['k8s-cluster'] %}
-       '{{ kube_cert_dir }}/node-{{ host }}.pem'
+       '{{ kube_cert_dir }}/node-{{ host }}.pem',
-       '{{ kube_cert_dir }}/node-{{ host }}-key.pem'
+       '{{ kube_cert_dir }}/node-{{ host }}-key.pem',
-       '{{ kube_cert_dir }}/kube-proxy-{{ host }}.pem'
+       '{{ kube_cert_dir }}/kube-proxy-{{ host }}.pem',
        '{{ kube_cert_dir }}/kube-proxy-{{ host }}-key.pem'
        {% if not loop.last %}{{','}}{% endif %}
        {% endfor %}]

roles/kubespray-defaults/defaults/main.yaml

@@ -12,6 +12,8 @@ kube_api_anonymous_auth: false
 # Default value, but will be set to true automatically if detected
 is_atomic: false
 
+# optional disable the swap
+disable_swap: false
 
 ## Change this to use another Kubernetes version, e.g. a current beta release
 kube_version: v1.10.4
@@ -210,7 +212,7 @@ authorization_modes: ['Node', 'RBAC']
 rbac_enabled: "{{ 'RBAC' in authorization_modes or kubeadm_enabled }}"
 
 # When enabled, API bearer tokens (including service account tokens) can be used to authenticate to the kubelet’s HTTPS endpoint
-kubelet_authentication_token_webhook: false
+kubelet_authentication_token_webhook: true
 
 # When enabled, access to the kubelet API requires authorization by delegation to the API server
 kubelet_authorization_mode_webhook: false
@@ -314,7 +316,7 @@ kube_apiserver_client_key: |-
   {%- endif %}
 
 # Set to true to deploy etcd-events cluster
-etcd_events_cluster_setup: false
+etcd_events_cluster_enabled: false
 
 # Vars for pointing to etcd endpoints
 is_etcd_master: "{{ inventory_hostname in groups['etcd'] }}"

roles/network_plugin/calico/defaults/main.yml

@@ -51,3 +51,5 @@ rbac_resources:
 # * interface=INTERFACE-REGEX
 # see https://docs.projectcalico.org/v3.0/reference/node/configuration#ip-autodetection-methods
 # calico_ip_auto_method: "interface=eth.*"
+
+calico_baremetal_nodename: "{{ inventory_hostname }}"

roles/network_plugin/calico/templates/cni-calico.conflist.j2

@@ -6,7 +6,7 @@
     {% if cloud_provider is defined %}
       "nodename": "{{ calico_kubelet_name.stdout }}",
     {% else %}
-      "nodename": "{{ inventory_hostname }}",
+      "nodename": "{{ calico_baremetal_nodename }}",
     {% endif %}
       "type": "calico",
       "etcd_endpoints": "{{ etcd_access_addresses }}",

roles/remove-node/post-remove/tasks/main.yml

@@ -4,5 +4,6 @@
   command: kubectl delete node {{ item }}
   with_items:
     - "{{ groups['kube-node'] }}"
-  delegate_to: "{{ groups['kube-master'][0] }}"
+  delegate_to: "{{ groups['kube-master']|first }}"
+  run_once: true
   ignore_errors: yes

roles/remove-node/pre-remove/tasks/main.yml

@@ -11,5 +11,6 @@
   with_items:
     - "{{ groups['kube-node'] }}"
   failed_when: false
-  delegate_to: "{{ groups['kube-master'][0] }}"
+  delegate_to: "{{ groups['kube-master']|first }}"
+  run_once: true
   ignore_errors: yes

roles/rkt/tasks/main.yml

@@ -2,3 +2,4 @@
 
 - name: Install rkt
   import_tasks: install.yml
+  when: not ansible_os_family in ["CoreOS", "Container Linux by CoreOS"]

roles/vault/templates/rkt.service.j2

@@ -12,6 +12,8 @@ LimitNOFILE=40000
 # Container has the following internal mount points:
 #   /vault/file/    # File backend storage location
 #   /vault/logs/    # Log files
+ExecStartPre=-/usr/bin/rkt rm --uuid-file=/var/run/vault.uuid
+
 ExecStart=/usr/bin/rkt run \
         --insecure-options=image \
         --volume hosts,kind=host,source=/etc/hosts,readOnly=true \
@@ -29,9 +31,15 @@ ExecStart=/usr/bin/rkt run \
         --volume=etcd-cert-dir,kind=host,source={{ etcd_cert_dir }} \
         --mount=volume=etcd-cert-dir,target={{ etcd_cert_dir }} \
         docker://{{ vault_image_repo }}:{{ vault_image_tag }} \
---name={{ vault_container_name }} --net=host \
+        --uuid-file-save=/var/run/vault.uuid \
+        --name={{ vault_container_name }} \
+        --net=host \
         --caps-retain=CAP_IPC_LOCK \
---exec vault -- server --config={{ vault_config_dir }}/config.json
+        --exec vault -- \
+                server \
+                --config={{ vault_config_dir }}/config.json
+
+ExecStop=-/usr/bin/rkt stop --uuid-file=/var/run/vault.uuid
 
 [Install]
 WantedBy=multi-user.target