WIP

charts/fluentd-es-logging/.helmignore

@@ -0,0 +1,21 @@
+# Patterns to ignore when building packages.
+# This supports shell glob matching, relative path matching, and
+# negation (prefixed with !). Only one pattern per line.
+.DS_Store
+# Common VCS dirs
+.git/
+.gitignore
+.bzr/
+.bzrignore
+.hg/
+.hgignore
+.svn/
+# Common backup files
+*.swp
+*.bak
+*.tmp
+*~
+# Various IDEs
+.project
+.idea/
+*.tmproj

charts/fluentd-es-logging/Chart.yaml

@@ -0,0 +1,4 @@
+apiVersion: v1
+description: A Helm chart for Kubernetes
+name: fluentd-es-logging
+version: 0.1.0

charts/fluentd-es-logging/README.md

@@ -0,0 +1,8 @@
+# Fluentd ES Logging
+Charts for using fluentd in K8s to log to elasticsearch. These charts are an
+improvement over the stock cluster addon, including functionality to correctly
+aggregate multi-line JVM stacktraces.
+
+
+# Status
+WIP

charts/fluentd-es-logging/files/fluentd-confg/containers.input.conf

@@ -0,0 +1,9 @@
+ <source>
+   @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
+   read_from_head true
+ </source>

charts/fluentd-es-logging/files/fluentd-confg/forward.input.conf

@@ -0,0 +1,4 @@
+# Takes the messages sent over TCP
+<source>
+  @type forward
+</source>

charts/fluentd-es-logging/files/fluentd-confg/monitoring.conf

@@ -0,0 +1,29 @@
+# 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>

charts/fluentd-es-logging/files/fluentd-confg/system.input.conf

@@ -0,0 +1,169 @@
+# 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
+  format /^(?<time>[^ ]* [^ ,]*)[^\[]*\[[^\]]*\]\[(?<severity>[^ \]]*) *\] (?<message>.*)$/
+  time_format %Y-%m-%d %H:%M:%S
+  path /var/log/salt/minion
+  pos_file /var/log/es-salt.pos
+  tag salt
+</source>
+# Example:
+# Dec 21 23:17:22 gke-foo-1-1-4b5cbd14-node-4eoj startupscript: Finished running startup script /var/run/google.startup.script
+<source>
+  @type tail
+  format syslog
+  path /var/log/startupscript.log
+  pos_file /var/log/es-startupscript.log.pos
+  tag startupscript
+</source>
+# Examples:
+# time="2016-02-04T06:51:03.053580605Z" level=info msg="GET /containers/json"
+# time="2016-02-04T07:53:57.505612354Z" level=error msg="HTTP Error" err="No such image: -f" statusCode=404
+<source>
+  @type tail
+  format /^time="(?<time>[^)]*)" level=(?<severity>[^ ]*) msg="(?<message>[^"]*)"( err="(?<error>[^"]*)")?( statusCode=($<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
+  # Not parsing this, because it doesn't have anything particularly useful to
+  # parse out of it (like severities).
+  format none
+  path /var/log/etcd.log
+  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
+  format multiline
+  multiline_flush_interval 5s
+  format_firstline /^\w\d{4}/
+  format1 /^(?<severity>\w)(?<time>\d{4} [^\s]*)\s+(?<pid>\d+)\s+(?<source>[^ \]]+)\] (?<message>.*)/
+  time_format %m%d %H:%M:%S.%N
+  path /var/log/kubelet.log
+  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
+  format multiline
+  multiline_flush_interval 5s
+  format_firstline /^\w\d{4}/
+  format1 /^(?<severity>\w)(?<time>\d{4} [^\s]*)\s+(?<pid>\d+)\s+(?<source>[^ \]]+)\] (?<message>.*)/
+  time_format %m%d %H:%M:%S.%N
+  path /var/log/kube-proxy.log
+  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
+  format multiline
+  multiline_flush_interval 5s
+  format_firstline /^\w\d{4}/
+  format1 /^(?<severity>\w)(?<time>\d{4} [^\s]*)\s+(?<pid>\d+)\s+(?<source>[^ \]]+)\] (?<message>.*)/
+  time_format %m%d %H:%M:%S.%N
+  path /var/log/kube-apiserver.log
+  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
+  format multiline
+  multiline_flush_interval 5s
+  format_firstline /^\w\d{4}/
+  format1 /^(?<severity>\w)(?<time>\d{4} [^\s]*)\s+(?<pid>\d+)\s+(?<source>[^ \]]+)\] (?<message>.*)/
+  time_format %m%d %H:%M:%S.%N
+  path /var/log/kube-controller-manager.log
+  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
+  format multiline
+  multiline_flush_interval 5s
+  format_firstline /^\w\d{4}/
+  format1 /^(?<severity>\w)(?<time>\d{4} [^\s]*)\s+(?<pid>\d+)\s+(?<source>[^ \]]+)\] (?<message>.*)/
+  time_format %m%d %H:%M:%S.%N
+  path /var/log/kube-scheduler.log
+  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
+  format multiline
+  multiline_flush_interval 5s
+  format_firstline /^\w\d{4}/
+  format1 /^(?<severity>\w)(?<time>\d{4} [^\s]*)\s+(?<pid>\d+)\s+(?<source>[^ \]]+)\] (?<message>.*)/
+  time_format %m%d %H:%M:%S.%N
+  path /var/log/rescheduler.log
+  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
+  format multiline
+  multiline_flush_interval 5s
+  format_firstline /^\w\d{4}/
+  format1 /^(?<severity>\w)(?<time>\d{4} [^\s]*)\s+(?<pid>\d+)\s+(?<source>[^ \]]+)\] (?<message>.*)/
+  time_format %m%d %H:%M:%S.%N
+  path /var/log/glbc.log
+  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
+  format multiline
+  multiline_flush_interval 5s
+  format_firstline /^\w\d{4}/
+  format1 /^(?<severity>\w)(?<time>\d{4} [^\s]*)\s+(?<pid>\d+)\s+(?<source>[^ \]]+)\] (?<message>.*)/
+  time_format %m%d %H:%M:%S.%N
+  path /var/log/cluster-autoscaler.log
+  pos_file /var/log/es-cluster-autoscaler.log.pos
+  tag cluster-autoscaler
+</source>
+# Logs from systemd-journal for interesting services.
+<source>
+  @type systemd
+  filters [{ "_SYSTEMD_UNIT": "docker.service" }]
+  pos_file /var/log/gcp-journald-docker.pos
+  read_from_head true
+  tag docker
+</source>
+<source>
+  @type systemd
+  filters [{ "_SYSTEMD_UNIT": "kubelet.service" }]
+  pos_file /var/log/gcp-journald-kubelet.pos
+  read_from_head true
+  tag kubelet
+</source>
+<source>
+  @type systemd
+  filters [{ "_SYSTEMD_UNIT": "node-problem-detector.service" }]
+  pos_file /var/log/gcp-journald-node-problem-detector.pos
+  read_from_head true
+  tag node-problem-detector
+</source>

charts/fluentd-es-logging/requirements.lock

@@ -0,0 +1,6 @@
+dependencies:
+- name: elasticsearch
+  repository: https://kubernetes-charts-incubator.storage.googleapis.com/
+  version: 0.2.0
+digest: sha256:dd8f87932ce352492583eab8e442092653463c0874ee0f52d41798e37e4d5a41
+generated: 2017-10-31T10:06:49.087580424-04:00

charts/fluentd-es-logging/requirements.yaml

@@ -0,0 +1,5 @@
+dependencies:
+  - name: elasticsearch
+    version: 0.2.0
+    repository: https://kubernetes-charts-incubator.storage.googleapis.com/
+    condition: elasticsearch.provide

charts/fluentd-es-logging/templates/_helpers.tpl

@@ -0,0 +1,16 @@
+{{/* vim: set filetype=mustache: */}}
+{{/*
+Expand the name of the chart.
+*/}}
+{{- define "name" -}}
+{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" -}}
+{{- end -}}
+
+{{/*
+Create a default fully qualified app name.
+We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec).
+*/}}
+{{- define "fullname" -}}
+{{- $name := default .Chart.Name .Values.nameOverride -}}
+{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" -}}
+{{- end -}}