Merge pull request #2763 from ameukam/update_efk_stack

Update efk stack
pull/2926/head
Rong Zhang 2018-06-24 19:01:32 +08:00 committed by GitHub
commit 2ef05fb3b7
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
9 changed files with 263 additions and 126 deletions

View File

@ -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_image_repo: "gcr.io/google_containers/elasticsearch"
elasticsearch_version: "v5.6.4"
elasticsearch_image_repo: "k8s.gcr.io/elasticsearch"
elasticsearch_image_tag: "{{ elasticsearch_version }}"
fluentd_version: "1.22"
fluentd_image_repo: "gcr.io/google_containers/fluentd-elasticsearch"
fluentd_version: "v2.0.4"
fluentd_image_repo: "k8s.gcr.io/fluentd-elasticsearch"
fluentd_image_tag: "{{ fluentd_version }}"
kibana_version: "v4.6.1"
kibana_image_repo: "gcr.io/google_containers/kibana"
kibana_version: "5.6.4"
kibana_image_repo: "docker.elastic.co/kibana/kibana"
kibana_image_tag: "{{ kibana_version }}"
helm_version: "v2.9.1"
helm_image_repo: "lachlanevenson/k8s-helm"

View File

@ -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

View File

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

View File

@ -1,15 +1,17 @@
---
# https://raw.githubusercontent.com/kubernetes/kubernetes/v1.5.2/cluster/addons/fluentd-elasticsearch/es-controller.yaml
apiVersion: extensions/v1beta1
kind: Deployment
# https://raw.githubusercontent.com/kubernetes/kubernetes/v1.10.2/cluster/addons/fluentd-elasticsearch/es-statefulset.yaml
apiVersion: apps/v1
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

View File

@ -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_file: fluentd.conf
fluentd_config_dir: /etc/fluent/config.d
# fluentd_config_file: fluentd.conf

View File

@ -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
# 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:
# Json Log 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.*
format json
tag raw.kubernetes.*
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
user "#{ENV['FLUENT_ELASTICSEARCH_USER']}"
password "#{ENV['FLUENT_ELASTICSEARCH_PASSWORD']}"
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_chunk_limit 2M
# Cap buffer memory usage to 2MiB/chunk * 32 chunks = 64 MiB
buffer_queue_limit 32
flush_interval 5s
# Never wait longer than 5 minutes between retries.
max_retry_wait 30
# Disable the limit on the number of retries (retry forever).
disable_retry_limit
# Use multiple threads for processing.
num_threads 8
</match>
@id elasticsearch
@type elasticsearch
@log_level info
include_tag_key true
host elasticsearch-logging
port 9200
logstash_format true
<buffer>
@type file
path /var/log/fluentd-buffers/kubernetes.system.buffer
flush_mode interval
retry_type exponential_backoff
flush_thread_count 2
flush_interval 5s
retry_forever
retry_max_interval 30
chunk_limit_size 2M
queue_limit_length 8
overflow_action block
</buffer>
</match>

View File

@ -1,32 +1,42 @@
---
# https://raw.githubusercontent.com/kubernetes/kubernetes/v1.5.2/cluster/addons/fluentd-elasticsearch/es-controller.yaml
apiVersion: extensions/v1beta1
# https://raw.githubusercontent.com/kubernetes/kubernetes/v1.10.2/cluster/addons/fluentd-elasticsearch/fluentd-es-ds.yaml
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:
- effect: NoSchedule
operator: Exists
priorityClassName: system-node-critical
{% if rbac_enabled %}
serviceAccountName: efk
{% endif %}
containers:
- name: fluentd-es
image: "{{ fluentd_image_repo }}:{{ fluentd_image_tag }}"
command:
- '/bin/sh'
- '-c'
- '/usr/sbin/td-agent -c {{ fluentd_config_dir }}/{{ fluentd_config_file}} 2>&1 >> /var/log/fluentd.log'
env:
- name: FLUENTD_ARGS
value: "--no-supervisor -q"
resources:
limits:
{% if fluentd_cpu_limit is defined and fluentd_cpu_limit != "0m" %}
@ -34,27 +44,26 @@ spec:
{% endif %}
memory: {{ fluentd_mem_limit }}
requests:
cpu: {{ fluentd_cpu_requests }}
cpu: {{ fluentd_cpu_requests }}
memory: {{ fluentd_mem_requests }}
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
configMap:
name: fluentd-config
{% if rbac_enabled %}
serviceAccountName: efk
{% endif %}
- name: config-volume
configMap:
name: fluentd-config

View File

@ -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"

View File

@ -1,6 +1,6 @@
---
# https://raw.githubusercontent.com/kubernetes/kubernetes/v1.5.2/cluster/addons/fluentd-kibana/kibana-controller.yaml
apiVersion: extensions/v1beta1
# https://raw.githubusercontent.com/kubernetes/kubernetes/release-1.10/cluster/addons/fluentd-elasticsearch/kibana-deployment.yaml
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: "KIBANA_BASE_URL"
- name: "SERVER_BASEPATH"
value: "{{ kibana_base_url }}"
{% endif %}
- name: XPACK_MONITORING_ENABLED
value: "false"
- name: XPACK_SECURITY_ENABLED
value: "false"
ports:
- containerPort: 5601
name: ui