mirror of
https://github.com/k3s-io/kubernetes.git
synced 2025-07-21 19:01:49 +00:00
Merge pull request #50082 from crassirostris/cleanup-fluentd-es
Automatic merge from submit-queue (batch tested with PRs 48532, 50054, 50082) Refactored the fluentd-es addon Refactor fluentd-elasticsearch addon: - Decrease the number of files by moving RBAC-related objects in the same files where they're used - Move the fluentd configuration out of the image - Don't use PVC to avoid leaking resources in e2e tests - Fluentd now ingest docker and kubelet logs that are written to journald - Disable X-Pack, because it's not free Fixes https://github.com/kubernetes/kubernetes/issues/41462 Fixes https://github.com/kubernetes/kubernetes/issues/49816 Fixes https://github.com/kubernetes/kubernetes/issues/48973 Fixes https://github.com/kubernetes/kubernetes/issues/49450 @aknuds1 @coffeepac Could you please take a look? ```release-note Fluentd DaemonSet in the fluentd-elasticsearch addon is configured via ConfigMap and includes journald plugin Elasticsearch StatefulSet in the fluentd-elasticsearch addon uses local storage instead of PVC by default ```
This commit is contained in:
Kubernetes Submit Queue
GitHub
commit
70b4db2023
@ -1,45 +1,82 @@
|
||||
# Elasticsearch Add-On
|
||||
This add-on consists of a combination of
|
||||
[Elasticsearch](https://www.elastic.co/products/elasticsearch), [Fluentd](http://www.fluentd.org/)
|
||||
and [Kibana](https://www.elastic.co/products/elasticsearch). Elasticsearch is a search engine
|
||||
that is responsible for storing our logs and allowing for them to be queried. Fluentd sends
|
||||
log messages from Kubernetes to Elasticsearch, whereas Kibana is a graphical interface for
|
||||
viewing and querying the logs stored in Elasticsearch.
|
||||
|
||||
This add-on consists of a combination of [Elasticsearch][elasticsearch],
|
||||
[Fluentd][fluentd] and [Kibana][kibana]. Elasticsearch is a search engine
|
||||
that is responsible for storing our logs and allowing for them to be queried.
|
||||
Fluentd sends log messages from Kubernetes to Elasticsearch, whereas Kibana
|
||||
is a graphical interface for viewing and querying the logs stored in
|
||||
Elasticsearch.
|
||||
|
||||
**Note:** this addon should **not** be used as-is in production. This is
|
||||
an example and you should treat is as such. Please see at least the
|
||||
[Security](#security) and the [Storage](#storage) sections for more
|
||||
information.
|
||||
|
||||
## Elasticsearch
|
||||
Elasticsearch is deployed as a
|
||||
[StatefulSet](https://kubernetes.io/docs/concepts/workloads/controllers/statefulset/), which
|
||||
is like a Deployment, but allows for maintaining state on storage volumes.
|
||||
|
||||
### Authentication
|
||||
Elasticsearch has basic authentication enabled by default, in our configuration the credentials
|
||||
are at their default values, i.e. username 'elastic' and password 'changeme'. In order to change
|
||||
them, please read up on [the official documentation](https://www.elastic.co/guide/en/x-pack/current/setting-up-authentication.html#reset-built-in-user-passwords).
|
||||
Elasticsearch is deployed as a [StatefulSet][statefulSet], which is like
|
||||
a Deployment, but allows for maintaining state on storage volumes.
|
||||
|
||||
### Security
|
||||
|
||||
Elasticsearch has capabilities to enable authorization using
|
||||
[X-Pack plugin][xPack]. See configuration parameter `xpack.security.enabled`
|
||||
in Elasticsearch and Kibana configurations. It can also be set via
|
||||
`XPACK_SECURITY_ENABLED` env variable. After enabling the feature,
|
||||
follow [official documentation][setupCreds] to set up credentials in
|
||||
Elasticsearch and Kibana. Don't forget to propagate those credentials also to
|
||||
Fluentd in its [configuration][fluentdCreds], using for example
|
||||
[environment variables][fluentdEnvVar]. You can utilize [ConfigMaps][configMap]
|
||||
and [Secrets][secret] to store credentials in the Kubernetes apiserver.
|
||||
|
||||
### Initialization
|
||||
|
||||
The Elasticsearch Statefulset manifest specifies that there shall be an
|
||||
[init container](https://kubernetes.io/docs/concepts/workloads/pods/init-containers/) executing
|
||||
before Elasticsearch containers themselves, in order to ensure that the kernel state variable
|
||||
`vm.max_map_count` is at least 262144, since this is a requirement of Elasticsearch.
|
||||
You may remove the init container if you know that your host OS meets this requirement.
|
||||
[init container][initContainer] executing before Elasticsearch containers
|
||||
themselves, in order to ensure that the kernel state variable
|
||||
`vm.max_map_count` is at least 262144, since this is a requirement of
|
||||
Elasticsearch. You may remove the init container if you know that your host
|
||||
OS meets this requirement.
|
||||
|
||||
### Storage
|
||||
The Elasticsearch StatefulSet will claim a storage volume 'elasticsearch-logging',
|
||||
of the standard
|
||||
[StorageClass](https://kubernetes.io/docs/concepts/storage/persistent-volumes/#storageclasses),
|
||||
that by default will be 100 Gi per replica. Please adjust this to your needs (including
|
||||
possibly choosing a more suitable StorageClass).
|
||||
|
||||
The Elasticsearch StatefulSet will use the [EmptyDir][emptyDir] volume to
|
||||
store data. EmptyDir is erased when the pod terminates, here it is used only
|
||||
for testing purposes. **Important:** please change the storage to persistent
|
||||
volume claim before actually using this StatefulSet in your setup!
|
||||
|
||||
## Fluentd
|
||||
Fluentd is deployed as a
|
||||
[DaemonSet](https://kubernetes.io/docs/concepts/workloads/controllers/daemonset/) which spawns a
|
||||
pod on each node that reads logs, generated by kubelet, container runtime and containers and
|
||||
sends them to Elasticsearch.
|
||||
|
||||
*Please note that for Fluentd to work, every Kubernetes node must be labeled*
|
||||
`beta.kubernetes.io/fluentd-ds-ready=true`, as otherwise Fluentd will ignore them.
|
||||
Fluentd is deployed as a [DaemonSet][daemonSet] which spawns a pod on each
|
||||
node that reads logs, generated by kubelet, container runtime and containers
|
||||
and sends them to Elasticsearch.
|
||||
|
||||
Learn more at: https://kubernetes.io/docs/tasks/debug-application-cluster/logging-elasticsearch-kibana
|
||||
**Note:** in order for Fluentd to work, every Kubernetes node must be labeled
|
||||
with `beta.kubernetes.io/fluentd-ds-ready=true`, as otherwise the Fluentd
|
||||
DaemonSet will ignore them.
|
||||
|
||||
Learn more in the [official Kubernetes documentation][k8sElasticsearchDocs].
|
||||
|
||||
### Known problems
|
||||
|
||||
Since Fluentd talks to the Elasticsearch service inside the cluster, instances
|
||||
on masters won't work, because masters have no kube-proxy. Don't mark masters
|
||||
with a label mentioned in the previous paragraph or add a taint on them to
|
||||
avoid Fluentd pods scheduling there.
|
||||
|
||||
[fluentd]: http://www.fluentd.org/
|
||||
[elasticsearch]: https://www.elastic.co/products/elasticsearch
|
||||
[kibana]: https://www.elastic.co/products/kibana
|
||||
[xPack]: https://www.elastic.co/products/x-pack
|
||||
[setupCreds]: https://www.elastic.co/guide/en/x-pack/current/setting-up-authentication.html#reset-built-in-user-passwords
|
||||
[fluentdCreds]: https://github.com/uken/fluent-plugin-elasticsearch#user-password-path-scheme-ssl_verify
|
||||
[fluentdEnvVar]: https://docs.fluentd.org/v0.12/articles/faq#how-can-i-use-environment-variables-to-configure-parameters-dynamically
|
||||
[configMap]: https://kubernetes.io/docs/tasks/configure-pod-container/configmap/
|
||||
[secret]: https://kubernetes.io/docs/concepts/configuration/secret/
|
||||
[statefulSet]: https://kubernetes.io/docs/concepts/workloads/controllers/statefulset
|
||||
[initContainer]: https://kubernetes.io/docs/concepts/workloads/pods/init-containers/
|
||||
[emptyDir]: https://kubernetes.io/docs/concepts/storage/volumes#emptydir
|
||||
[daemonSet]: https://kubernetes.io/docs/concepts/workloads/controllers/daemonset/
|
||||
[k8sElasticsearchDocs]: https://kubernetes.io/docs/tasks/debug-application-cluster/logging-elasticsearch-kibana
|
||||
|
||||
[]()
|
||||
|
||||
|
||||
@ -1,7 +0,0 @@
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: environment
|
||||
namespace: kube-system
|
||||
data:
|
||||
elasticsearch-user: elastic
|
||||
@ -1,8 +0,0 @@
|
||||
apiVersion: v1
|
||||
kind: Secret
|
||||
metadata:
|
||||
name: environment
|
||||
namespace: kube-system
|
||||
type: Opaque
|
||||
data:
|
||||
elasticsearch-password: Y2hhbmdlbWU=
|
||||
@ -1,17 +0,0 @@
|
||||
kind: ClusterRole
|
||||
apiVersion: rbac.authorization.k8s.io/v1beta1
|
||||
metadata:
|
||||
name: elasticsearch-logging
|
||||
labels:
|
||||
k8s-app: elasticsearch-logging
|
||||
kubernetes.io/cluster-service: "true"
|
||||
addonmanager.kubernetes.io/mode: Reconcile
|
||||
rules:
|
||||
- apiGroups:
|
||||
- ""
|
||||
resources:
|
||||
- "services"
|
||||
- "namespaces"
|
||||
- "endpoints"
|
||||
verbs:
|
||||
- "get"
|
||||
@ -1,18 +0,0 @@
|
||||
kind: ClusterRoleBinding
|
||||
apiVersion: rbac.authorization.k8s.io/v1beta1
|
||||
metadata:
|
||||
namespace: kube-system
|
||||
name: elasticsearch-logging
|
||||
labels:
|
||||
k8s-app: elasticsearch-logging
|
||||
kubernetes.io/cluster-service: "true"
|
||||
addonmanager.kubernetes.io/mode: Reconcile
|
||||
subjects:
|
||||
- kind: ServiceAccount
|
||||
name: elasticsearch-logging
|
||||
namespace: kube-system
|
||||
apiGroup: ""
|
||||
roleRef:
|
||||
kind: ClusterRole
|
||||
name: elasticsearch-logging
|
||||
apiGroup: ""
|
||||
@ -14,22 +14,12 @@
|
||||
|
||||
FROM docker.elastic.co/elasticsearch/elasticsearch:5.5.1
|
||||
|
||||
USER root
|
||||
|
||||
RUN mkdir /data
|
||||
RUN chown -R elasticsearch:elasticsearch /data
|
||||
|
||||
WORKDIR /usr/share/elasticsearch
|
||||
|
||||
VOLUME ["/data"]
|
||||
EXPOSE 9200 9300
|
||||
|
||||
USER elasticsearch
|
||||
COPY elasticsearch_logging_discovery bin/
|
||||
COPY config/elasticsearch.yml config/
|
||||
COPY config/log4j2.properties config/
|
||||
COPY run.sh bin/
|
||||
COPY elasticsearch_logging_discovery run.sh bin/
|
||||
COPY config/elasticsearch.yml config/log4j2.properties config/
|
||||
|
||||
USER root
|
||||
RUN chown -R elasticsearch:elasticsearch config
|
||||
RUN chown -R elasticsearch:elasticsearch ./
|
||||
CMD ["bin/run.sh"]
|
||||
|
||||
@ -12,19 +12,19 @@
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
.PHONY: elasticsearch_logging_discovery build push
|
||||
.PHONY: binary build push
|
||||
|
||||
# The current value of the tag to be used for building and
|
||||
# pushing an image to gcr.io
|
||||
TAG = v5.5.1
|
||||
PREFIX = gcr.io/google-containers
|
||||
IMAGE = elasticsearch
|
||||
TAG = v5.5.1-1
|
||||
|
||||
build: elasticsearch_logging_discovery
|
||||
docker build --pull -t gcr.io/google_containers/elasticsearch:$(TAG) .
|
||||
build:
|
||||
docker build --pull -t $(PREFIX)/$(IMAGE):$(TAG) .
|
||||
|
||||
push:
|
||||
gcloud docker -- push gcr.io/google_containers/elasticsearch:$(TAG)
|
||||
gcloud docker -- push $(PREFIX)/$(IMAGE):$(TAG)
|
||||
|
||||
elasticsearch_logging_discovery:
|
||||
binary:
|
||||
CGO_ENABLED=0 GOOS=linux go build -a -ldflags "-w" elasticsearch_logging_discovery.go
|
||||
|
||||
clean:
|
||||
|
||||
@ -12,3 +12,6 @@ path.data: /data
|
||||
network.host: 0.0.0.0
|
||||
|
||||
discovery.zen.minimum_master_nodes: ${MINIMUM_MASTER_NODES}
|
||||
|
||||
xpack.security.enabled: false
|
||||
xpack.monitoring.enabled: false
|
||||
|
||||
@ -1,10 +0,0 @@
|
||||
apiVersion: v1
|
||||
kind: ServiceAccount
|
||||
metadata:
|
||||
name: elasticsearch-logging
|
||||
namespace: kube-system
|
||||
labels:
|
||||
k8s-app: elasticsearch-logging
|
||||
version: v1
|
||||
kubernetes.io/cluster-service: "true"
|
||||
addonmanager.kubernetes.io/mode: Reconcile
|
||||
@ -1,11 +1,60 @@
|
||||
apiVersion: apps/v1beta1
|
||||
kind: StatefulSet
|
||||
# RBAC authn and authz
|
||||
apiVersion: v1
|
||||
kind: ServiceAccount
|
||||
metadata:
|
||||
name: elasticsearch-logging-v1
|
||||
name: elasticsearch-logging
|
||||
namespace: kube-system
|
||||
labels:
|
||||
k8s-app: elasticsearch-logging
|
||||
version: v1
|
||||
kubernetes.io/cluster-service: "true"
|
||||
addonmanager.kubernetes.io/mode: Reconcile
|
||||
---
|
||||
kind: ClusterRole
|
||||
apiVersion: rbac.authorization.k8s.io/v1beta1
|
||||
metadata:
|
||||
name: elasticsearch-logging
|
||||
labels:
|
||||
k8s-app: elasticsearch-logging
|
||||
kubernetes.io/cluster-service: "true"
|
||||
addonmanager.kubernetes.io/mode: Reconcile
|
||||
rules:
|
||||
- apiGroups:
|
||||
- ""
|
||||
resources:
|
||||
- "services"
|
||||
- "namespaces"
|
||||
- "endpoints"
|
||||
verbs:
|
||||
- "get"
|
||||
---
|
||||
kind: ClusterRoleBinding
|
||||
apiVersion: rbac.authorization.k8s.io/v1beta1
|
||||
metadata:
|
||||
namespace: kube-system
|
||||
name: elasticsearch-logging
|
||||
labels:
|
||||
k8s-app: elasticsearch-logging
|
||||
kubernetes.io/cluster-service: "true"
|
||||
addonmanager.kubernetes.io/mode: Reconcile
|
||||
subjects:
|
||||
- kind: ServiceAccount
|
||||
name: elasticsearch-logging
|
||||
namespace: kube-system
|
||||
apiGroup: ""
|
||||
roleRef:
|
||||
kind: ClusterRole
|
||||
name: elasticsearch-logging
|
||||
apiGroup: ""
|
||||
---
|
||||
# Elasticsearch deployment itself
|
||||
apiVersion: apps/v1beta1
|
||||
kind: StatefulSet
|
||||
metadata:
|
||||
name: elasticsearch-logging
|
||||
namespace: kube-system
|
||||
labels:
|
||||
k8s-app: elasticsearch-logging
|
||||
version: v5.5.1
|
||||
kubernetes.io/cluster-service: "true"
|
||||
addonmanager.kubernetes.io/mode: Reconcile
|
||||
spec:
|
||||
@ -14,17 +63,17 @@ spec:
|
||||
selector:
|
||||
matchLabels:
|
||||
k8s-app: elasticsearch-logging
|
||||
version: v1
|
||||
version: v5.5.1
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
k8s-app: elasticsearch-logging
|
||||
version: v1
|
||||
version: v5.5.1
|
||||
kubernetes.io/cluster-service: "true"
|
||||
spec:
|
||||
serviceAccountName: elasticsearch-logging
|
||||
containers:
|
||||
- image: gcr.io/google_containers/elasticsearch:v5.5.1
|
||||
- image: gcr.io/google-containers/elasticsearch:v5.5.1-1
|
||||
name: elasticsearch-logging
|
||||
resources:
|
||||
# need more cpu upon initialization, therefore burstable class
|
||||
@ -47,17 +96,15 @@ spec:
|
||||
valueFrom:
|
||||
fieldRef:
|
||||
fieldPath: metadata.namespace
|
||||
volumes:
|
||||
- name: elasticsearch-logging
|
||||
emptyDir: {}
|
||||
# Elasticsearch requires vm.max_map_count to be at least 262144.
|
||||
# If your OS already sets up this number to a higher value, feel free
|
||||
# to remove this init container.
|
||||
initContainers:
|
||||
- image: alpine:3.6
|
||||
command: ["/sbin/sysctl", "-w", "vm.max_map_count=262144"]
|
||||
name: elasticsearch-logging-init
|
||||
securityContext:
|
||||
privileged: true
|
||||
volumeClaimTemplates:
|
||||
- metadata:
|
||||
name: elasticsearch-logging
|
||||
spec:
|
||||
accessModes: ["ReadWriteOnce"]
|
||||
resources:
|
||||
requests:
|
||||
storage: 100Gi
|
||||
|
||||
@ -1,18 +0,0 @@
|
||||
kind: ClusterRole
|
||||
apiVersion: rbac.authorization.k8s.io/v1beta1
|
||||
metadata:
|
||||
name: fluentd-es
|
||||
labels:
|
||||
k8s-app: fluentd-es
|
||||
kubernetes.io/cluster-service: "true"
|
||||
addonmanager.kubernetes.io/mode: Reconcile
|
||||
rules:
|
||||
- apiGroups:
|
||||
- ""
|
||||
resources:
|
||||
- "namespaces"
|
||||
- "pods"
|
||||
verbs:
|
||||
- "get"
|
||||
- "watch"
|
||||
- "list"
|
||||
@ -1,17 +0,0 @@
|
||||
kind: ClusterRoleBinding
|
||||
apiVersion: rbac.authorization.k8s.io/v1beta1
|
||||
metadata:
|
||||
name: fluentd-es
|
||||
labels:
|
||||
k8s-app: fluentd-es
|
||||
kubernetes.io/cluster-service: "true"
|
||||
addonmanager.kubernetes.io/mode: Reconcile
|
||||
subjects:
|
||||
- kind: ServiceAccount
|
||||
name: fluentd-es
|
||||
namespace: kube-system
|
||||
apiGroup: ""
|
||||
roleRef:
|
||||
kind: ClusterRole
|
||||
name: fluentd-es
|
||||
apiGroup: ""
|
||||
362
cluster/addons/fluentd-elasticsearch/fluentd-es-configmap.yaml
Normal file
362
cluster/addons/fluentd-elasticsearch/fluentd-es-configmap.yaml
Normal file
@ -0,0 +1,362 @@
|
||||
kind: ConfigMap
|
||||
apiVersion: v1
|
||||
data:
|
||||
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
|
||||
# to the docker logs for pods in the /var/log/containers directory on the host.
|
||||
# If running this fluentd configuration in a Docker container, the /var/log
|
||||
# directory should be mounted in the container.
|
||||
#
|
||||
# These logs are then submitted to Elasticsearch which assumes the
|
||||
# installation of the fluent-plugin-elasticsearch & the
|
||||
# fluent-plugin-kubernetes_metadata_filter plugins.
|
||||
# See https://github.com/uken/fluent-plugin-elasticsearch &
|
||||
# https://github.com/fabric8io/fluent-plugin-kubernetes_metadata_filter for
|
||||
# more information about the plugins.
|
||||
#
|
||||
# Example
|
||||
# =======
|
||||
# A line in the Docker log file might look like this JSON:
|
||||
#
|
||||
# {"log":"2014/09/25 21:15:03 Got request with path wombat\n",
|
||||
# "stream":"stderr",
|
||||
# "time":"2014-09-25T21:15:03.499185026Z"}
|
||||
#
|
||||
# The time_format specification below makes sure we properly
|
||||
# parse the time format produced by Docker. This will be
|
||||
# submitted to Elasticsearch and should appear like:
|
||||
# $ curl 'http://elasticsearch-logging:9200/_search?pretty'
|
||||
# ...
|
||||
# {
|
||||
# "_index" : "logstash-2014.09.25",
|
||||
# "_type" : "fluentd",
|
||||
# "_id" : "VBrbor2QTuGpsQyTCdfzqA",
|
||||
# "_score" : 1.0,
|
||||
# "_source":{"log":"2014/09/25 22:45:50 Got request with path wombat\n",
|
||||
# "stream":"stderr","tag":"docker.container.all",
|
||||
# "@timestamp":"2014-09-25T22:45:50+00:00"}
|
||||
# },
|
||||
# ...
|
||||
#
|
||||
# The Kubernetes fluentd plugin is used to write the Kubernetes metadata to the log
|
||||
# record & add labels to the log record if properly configured. This enables users
|
||||
# to filter & search logs on any metadata.
|
||||
# For example a Docker container's logs might be in the directory:
|
||||
#
|
||||
# /var/lib/docker/containers/997599971ee6366d4a5920d25b79286ad45ff37a74494f262e3bc98d909d0a7b
|
||||
#
|
||||
# and in the file:
|
||||
#
|
||||
# 997599971ee6366d4a5920d25b79286ad45ff37a74494f262e3bc98d909d0a7b-json.log
|
||||
#
|
||||
# where 997599971ee6... is the Docker ID of the running container.
|
||||
# The Kubernetes kubelet makes a symbolic link to this file on the host machine
|
||||
# in the /var/log/containers directory which includes the pod name and the Kubernetes
|
||||
# container name:
|
||||
#
|
||||
# synthetic-logger-0.25lps-pod_default_synth-lgr-997599971ee6366d4a5920d25b79286ad45ff37a74494f262e3bc98d909d0a7b.log
|
||||
# ->
|
||||
# /var/lib/docker/containers/997599971ee6366d4a5920d25b79286ad45ff37a74494f262e3bc98d909d0a7b/997599971ee6366d4a5920d25b79286ad45ff37a74494f262e3bc98d909d0a7b-json.log
|
||||
#
|
||||
# The /var/log directory on the host is mapped to the /var/log directory in the container
|
||||
# running this instance of Fluentd and we end up collecting the file:
|
||||
#
|
||||
# /var/log/containers/synthetic-logger-0.25lps-pod_default_synth-lgr-997599971ee6366d4a5920d25b79286ad45ff37a74494f262e3bc98d909d0a7b.log
|
||||
#
|
||||
# This results in the tag:
|
||||
#
|
||||
# var.log.containers.synthetic-logger-0.25lps-pod_default_synth-lgr-997599971ee6366d4a5920d25b79286ad45ff37a74494f262e3bc98d909d0a7b.log
|
||||
#
|
||||
# The Kubernetes fluentd plugin is used to extract the namespace, pod name & container name
|
||||
# which are added to the log message as a kubernetes field object & the Docker container ID
|
||||
# is also added under the docker field object.
|
||||
# The final tag is:
|
||||
#
|
||||
# kubernetes.var.log.containers.synthetic-logger-0.25lps-pod_default_synth-lgr-997599971ee6366d4a5920d25b79286ad45ff37a74494f262e3bc98d909d0a7b.log
|
||||
#
|
||||
# And the final log record look like:
|
||||
#
|
||||
# {
|
||||
# "log":"2014/09/25 21:15:03 Got request with path wombat\n",
|
||||
# "stream":"stderr",
|
||||
# "time":"2014-09-25T21:15:03.499185026Z",
|
||||
# "kubernetes": {
|
||||
# "namespace": "default",
|
||||
# "pod_name": "synthetic-logger-0.25lps-pod",
|
||||
# "container_name": "synth-lgr"
|
||||
# },
|
||||
# "docker": {
|
||||
# "container_id": "997599971ee6366d4a5920d25b79286ad45ff37a74494f262e3bc98d909d0a7b"
|
||||
# }
|
||||
# }
|
||||
#
|
||||
# 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).
|
||||
|
||||
# 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"}
|
||||
<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>
|
||||
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
|
||||
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>
|
||||
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
|
||||
</filter>
|
||||
|
||||
<match **>
|
||||
type elasticsearch
|
||||
log_level info
|
||||
include_tag_key true
|
||||
host elasticsearch-logging
|
||||
port 9200
|
||||
logstash_format true
|
||||
# Set the chunk limits.
|
||||
buffer_chunk_limit 2M
|
||||
buffer_queue_limit 8
|
||||
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 2
|
||||
</match>
|
||||
metadata:
|
||||
name: fluentd-es-config-v0.1.0
|
||||
namespace: kube-system
|
||||
labels:
|
||||
addonmanager.kubernetes.io/mode: Reconcile
|
||||
@ -1,20 +1,67 @@
|
||||
apiVersion: extensions/v1beta1
|
||||
kind: DaemonSet
|
||||
apiVersion: v1
|
||||
kind: ServiceAccount
|
||||
metadata:
|
||||
name: fluentd-es-v1.24
|
||||
name: fluentd-es
|
||||
namespace: kube-system
|
||||
labels:
|
||||
k8s-app: fluentd-es
|
||||
kubernetes.io/cluster-service: "true"
|
||||
addonmanager.kubernetes.io/mode: Reconcile
|
||||
version: v1.24
|
||||
---
|
||||
kind: ClusterRole
|
||||
apiVersion: rbac.authorization.k8s.io/v1beta1
|
||||
metadata:
|
||||
name: fluentd-es
|
||||
labels:
|
||||
k8s-app: fluentd-es
|
||||
kubernetes.io/cluster-service: "true"
|
||||
addonmanager.kubernetes.io/mode: Reconcile
|
||||
rules:
|
||||
- apiGroups:
|
||||
- ""
|
||||
resources:
|
||||
- "namespaces"
|
||||
- "pods"
|
||||
verbs:
|
||||
- "get"
|
||||
- "watch"
|
||||
- "list"
|
||||
---
|
||||
kind: ClusterRoleBinding
|
||||
apiVersion: rbac.authorization.k8s.io/v1beta1
|
||||
metadata:
|
||||
name: fluentd-es
|
||||
labels:
|
||||
k8s-app: fluentd-es
|
||||
kubernetes.io/cluster-service: "true"
|
||||
addonmanager.kubernetes.io/mode: Reconcile
|
||||
subjects:
|
||||
- kind: ServiceAccount
|
||||
name: fluentd-es
|
||||
namespace: kube-system
|
||||
apiGroup: ""
|
||||
roleRef:
|
||||
kind: ClusterRole
|
||||
name: fluentd-es
|
||||
apiGroup: ""
|
||||
---
|
||||
apiVersion: extensions/v1beta1
|
||||
kind: DaemonSet
|
||||
metadata:
|
||||
name: fluentd-es
|
||||
namespace: kube-system
|
||||
labels:
|
||||
k8s-app: fluentd-es
|
||||
version: v2.0.0
|
||||
kubernetes.io/cluster-service: "true"
|
||||
addonmanager.kubernetes.io/mode: Reconcile
|
||||
spec:
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
k8s-app: fluentd-es
|
||||
kubernetes.io/cluster-service: "true"
|
||||
version: v1.24
|
||||
version: v2.0.0
|
||||
# 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).
|
||||
@ -24,27 +71,13 @@ spec:
|
||||
serviceAccountName: fluentd-es
|
||||
containers:
|
||||
- name: fluentd-es
|
||||
image: gcr.io/google_containers/fluentd-elasticsearch:1.24
|
||||
command:
|
||||
- '/bin/sh'
|
||||
- '-c'
|
||||
- '/usr/sbin/td-agent $FLUENTD_ARGS'
|
||||
image: gcr.io/google-containers/fluentd-elasticsearch:v2.0.0
|
||||
env:
|
||||
- name: FLUENTD_ARGS
|
||||
value: -q
|
||||
- name: FLUENT_ELASTICSEARCH_USER
|
||||
valueFrom:
|
||||
configMapKeyRef:
|
||||
name: environment
|
||||
key: elasticsearch-user
|
||||
- name: FLUENT_ELASTICSEARCH_PASSWORD
|
||||
valueFrom:
|
||||
secretKeyRef:
|
||||
name: environment
|
||||
key: elasticsearch-password
|
||||
value: --no-supervisor -q
|
||||
resources:
|
||||
limits:
|
||||
memory: 200Mi
|
||||
memory: 500Mi
|
||||
requests:
|
||||
cpu: 100m
|
||||
memory: 200Mi
|
||||
@ -54,6 +87,11 @@ spec:
|
||||
- name: varlibdockercontainers
|
||||
mountPath: /var/lib/docker/containers
|
||||
readOnly: true
|
||||
- name: libsystemddir
|
||||
mountPath: /host/lib
|
||||
readOnly: true
|
||||
- name: config-volume
|
||||
mountPath: /etc/fluent/config.d
|
||||
nodeSelector:
|
||||
beta.kubernetes.io/fluentd-ds-ready: "true"
|
||||
terminationGracePeriodSeconds: 30
|
||||
@ -64,3 +102,10 @@ spec:
|
||||
- name: varlibdockercontainers
|
||||
hostPath:
|
||||
path: /var/lib/docker/containers
|
||||
# It is needed to copy systemd library to decompress journals
|
||||
- name: libsystemddir
|
||||
hostPath:
|
||||
path: /usr/lib64
|
||||
- name: config-volume
|
||||
configMap:
|
||||
name: fluentd-es-config-v0.1.0
|
||||
|
||||
@ -15,28 +15,45 @@
|
||||
# This Dockerfile will build an image that is configured
|
||||
# to run Fluentd with an Elasticsearch plug-in and the
|
||||
# provided configuration file.
|
||||
# TODO(a-robinson): Use a lighter base image, e.g. some form of busybox.
|
||||
# The image acts as an executable for the binary /usr/sbin/td-agent.
|
||||
# Note that fluentd is run with root permssion to allow access to
|
||||
# log files with root only access under /var/log/containers/*
|
||||
# Please see http://docs.fluentd.org/articles/install-by-deb for more
|
||||
# information about installing fluentd using deb package.
|
||||
|
||||
FROM gcr.io/google_containers/ubuntu-slim:0.6
|
||||
FROM gcr.io/google-containers/debian-base-amd64:0.1
|
||||
|
||||
# Ensure there are enough file descriptors for running Fluentd.
|
||||
RUN ulimit -n 65536
|
||||
COPY Gemfile /Gemfile
|
||||
|
||||
# Disable prompts from apt.
|
||||
ENV DEBIAN_FRONTEND noninteractive
|
||||
# 1. Install & configure dependencies.
|
||||
# 2. Install fluentd via ruby.
|
||||
# 3. Remove build dependencies.
|
||||
# 4. Cleanup leftover caches & files.
|
||||
RUN BUILD_DEPS="make gcc g++ libc6-dev ruby-dev" \
|
||||
&& clean-install $BUILD_DEPS \
|
||||
ca-certificates \
|
||||
libjemalloc1 \
|
||||
liblz4-1 \
|
||||
ruby \
|
||||
&& echo 'gem: --no-document' >> /etc/gemrc \
|
||||
&& gem install --file Gemfile \
|
||||
&& apt-get purge -y --auto-remove \
|
||||
-o APT::AutoRemove::RecommendsImportant=false \
|
||||
$BUILD_DEPS \
|
||||
&& rm -rf /tmp/* \
|
||||
/var/lib/apt/lists/* \
|
||||
/usr/lib/ruby/gems/*/cache/*.gem \
|
||||
/var/log/* \
|
||||
/var/tmp/* \
|
||||
# Ensure fluent has enough file descriptors
|
||||
&& ulimit -n 65536
|
||||
|
||||
# Copy the Fluentd configuration file.
|
||||
COPY td-agent.conf /etc/td-agent/td-agent.conf
|
||||
# Copy the Fluentd configuration file for logging Docker container logs.
|
||||
COPY fluent.conf /etc/fluent/fluent.conf
|
||||
COPY run.sh /run.sh
|
||||
|
||||
COPY build.sh /tmp/build.sh
|
||||
RUN /tmp/build.sh
|
||||
# Expose prometheus metrics.
|
||||
EXPOSE 80
|
||||
|
||||
ENV LD_PRELOAD /opt/td-agent/embedded/lib/libjemalloc.so
|
||||
ENV LD_PRELOAD=/usr/lib/x86_64-linux-gnu/libjemalloc.so.1
|
||||
|
||||
# Run the Fluentd service.
|
||||
ENTRYPOINT ["td-agent"]
|
||||
# Start Fluentd to pick up our config that watches Docker container logs.
|
||||
CMD /run.sh $FLUENTD_ARGS
|
||||
|
||||
@ -0,0 +1,9 @@
|
||||
source 'https://rubygems.org'
|
||||
|
||||
gem 'fluentd', '~>0.12.32'
|
||||
gem 'activesupport', '~>4.2.6'
|
||||
gem 'fluent-plugin-kubernetes_metadata_filter', '~>0.27.0'
|
||||
gem 'fluent-plugin-elasticsearch', '~>1.9.5'
|
||||
gem 'fluent-plugin-systemd', '~>0.0.8'
|
||||
gem 'fluent-plugin-prometheus', '~>0.3.0'
|
||||
gem 'oj', '~>2.18.1'
|
||||
@ -14,12 +14,12 @@
|
||||
|
||||
.PHONY: build push
|
||||
|
||||
PREFIX = gcr.io/google_containers
|
||||
PREFIX = gcr.io/google-containers
|
||||
IMAGE = fluentd-elasticsearch
|
||||
TAG = 1.24
|
||||
TAG = v2.0.0
|
||||
|
||||
build:
|
||||
docker build --pull -t $(PREFIX)/$(IMAGE):$(TAG) .
|
||||
|
||||
push:
|
||||
gcloud docker --server=gcr.io -- push $(PREFIX)/$(IMAGE):$(TAG)
|
||||
gcloud docker -- push $(PREFIX)/$(IMAGE):$(TAG)
|
||||
|
||||
@ -1,10 +1,14 @@
|
||||
# Collecting Docker Log Files with Fluentd and Elasticsearch
|
||||
This directory contains the source files needed to make a Docker image
|
||||
that collects Docker container log files using [Fluentd](http://www.fluentd.org/)
|
||||
and sends them to an instance of [Elasticsearch](http://www.elasticsearch.org/).
|
||||
This image is designed to be used as part of the [Kubernetes](https://github.com/kubernetes/kubernetes)
|
||||
cluster bring up process. The image resides at DockerHub under the name
|
||||
[kubernetes/fluentd-elasticsearch](https://registry.hub.docker.com/u/kubernetes/fluentd-elasticsearch/).
|
||||
that collects Docker container log files using [Fluentd][fluentd]
|
||||
and sends them to an instance of [Elasticsearch][elasticsearch].
|
||||
This image is designed to be used as part of the [Kubernetes][kubernetes]
|
||||
cluster bring up process. The image resides at GCR under the name
|
||||
[gcr.io/google-containers/fluentd-elasticsearch][image].
|
||||
|
||||
[fluentd]: http://www.fluentd.org/
|
||||
[elasticsearch]: https://www.elastic.co/products/elasticsearch
|
||||
[kubernetes]: https://kubernetes.io
|
||||
[image]: https://gcr.io/google-containers/fluentd-elasticsearch
|
||||
|
||||
[]()
|
||||
[]()
|
||||
|
||||
@ -1,48 +0,0 @@
|
||||
#!/bin/sh
|
||||
|
||||
# Copyright 2017 The Kubernetes Authors.
|
||||
#
|
||||
# Licensed under the Apache License, Version 2.0 (the "License");
|
||||
# you may not use this file except in compliance with the License.
|
||||
# You may obtain a copy of the License at
|
||||
#
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
#
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
|
||||
# Install prerequisites.
|
||||
apt-get update
|
||||
|
||||
apt-get install -y -q --no-install-recommends \
|
||||
curl ca-certificates make g++ sudo bash
|
||||
|
||||
# Install Fluentd.
|
||||
/usr/bin/curl -sSL https://toolbelt.treasuredata.com/sh/install-ubuntu-xenial-td-agent2.sh | sh
|
||||
|
||||
# Change the default user and group to root.
|
||||
# Needed to allow access to /var/log/docker/... files.
|
||||
sed -i -e "s/USER=td-agent/USER=root/" -e "s/GROUP=td-agent/GROUP=root/" /etc/init.d/td-agent
|
||||
|
||||
# Install the Elasticsearch Fluentd plug-in.
|
||||
# http://docs.fluentd.org/articles/plugin-management
|
||||
td-agent-gem install --no-document fluent-plugin-kubernetes_metadata_filter -v 0.27.0
|
||||
td-agent-gem install --no-document fluent-plugin-elasticsearch -v 1.9.5
|
||||
td-agent-gem install --no-document fluent-plugin-prometheus -v 0.3.0
|
||||
|
||||
# Remove docs and postgres references
|
||||
rm -rf /opt/td-agent/embedded/share/doc \
|
||||
/opt/td-agent/embedded/share/gtk-doc \
|
||||
/opt/td-agent/embedded/lib/postgresql \
|
||||
/opt/td-agent/embedded/bin/postgres \
|
||||
/opt/td-agent/embedded/share/postgresql
|
||||
|
||||
apt-get remove -y make g++
|
||||
apt-get autoremove -y
|
||||
apt-get clean -y
|
||||
|
||||
rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
|
||||
@ -0,0 +1,8 @@
|
||||
# This is the root config file, which only includes components of the actual configuration
|
||||
|
||||
# Do not collect fluentd's own logs to avoid infinite loops.
|
||||
<match fluent.**>
|
||||
type null
|
||||
</match>
|
||||
|
||||
@include /etc/fluent/config.d/*.conf
|
||||
29
cluster/addons/fluentd-elasticsearch/fluentd-es-image/run.sh
Executable file
29
cluster/addons/fluentd-elasticsearch/fluentd-es-image/run.sh
Executable file
@ -0,0 +1,29 @@
|
||||
#!/bin/sh
|
||||
|
||||
# Copyright 2017 The Kubernetes Authors.
|
||||
#
|
||||
# Licensed under the Apache License, Version 2.0 (the "License");
|
||||
# you may not use this file except in compliance with the License.
|
||||
# You may obtain a copy of the License at
|
||||
#
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
#
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
# These steps must be executed once the host /var and /lib volumes have
|
||||
# been mounted, and therefore cannot be done in the docker build stage.
|
||||
|
||||
# For systems without journald
|
||||
mkdir -p /var/log/journal
|
||||
|
||||
# Copy host libsystemd into image to avoid compatibility issues.
|
||||
if [ ! -z "$(ls /host/lib/libsystemd* 2>/dev/null)" ]; then
|
||||
rm /lib/x86_64-linux-gnu/libsystemd*
|
||||
cp -a /host/lib/libsystemd* /lib/x86_64-linux-gnu/
|
||||
fi
|
||||
|
||||
/usr/local/bin/fluentd $@
|
||||
@ -1,344 +0,0 @@
|
||||
# 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
|
||||
# to the docker logs for pods in the /var/log/containers directory on the host.
|
||||
# If running this fluentd configuration in a Docker container, the /var/log
|
||||
# directory should be mounted in the container.
|
||||
#
|
||||
# These logs are then submitted to Elasticsearch which assumes the
|
||||
# installation of the fluent-plugin-elasticsearch & the
|
||||
# fluent-plugin-kubernetes_metadata_filter plugins.
|
||||
# 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
|
||||
# =======
|
||||
# A line in the Docker log file might look like this JSON:
|
||||
#
|
||||
# {"log":"2014/09/25 21:15:03 Got request with path wombat\n",
|
||||
# "stream":"stderr",
|
||||
# "time":"2014-09-25T21:15:03.499185026Z"}
|
||||
#
|
||||
# The time_format specification below makes sure we properly
|
||||
# parse the time format produced by Docker. This will be
|
||||
# submitted to Elasticsearch and should appear like:
|
||||
# $ curl 'http://elasticsearch-logging:9200/_search?pretty'
|
||||
# ...
|
||||
# {
|
||||
# "_index" : "logstash-2014.09.25",
|
||||
# "_type" : "fluentd",
|
||||
# "_id" : "VBrbor2QTuGpsQyTCdfzqA",
|
||||
# "_score" : 1.0,
|
||||
# "_source":{"log":"2014/09/25 22:45:50 Got request with path wombat\n",
|
||||
# "stream":"stderr","tag":"docker.container.all",
|
||||
# "@timestamp":"2014-09-25T22:45:50+00:00"}
|
||||
# },
|
||||
# ...
|
||||
#
|
||||
# The Kubernetes fluentd plugin is used to write the Kubernetes metadata to the log
|
||||
# record & add labels to the log record if properly configured. This enables users
|
||||
# to filter & search logs on any metadata.
|
||||
# For example a Docker container's logs might be in the directory:
|
||||
#
|
||||
# /var/lib/docker/containers/997599971ee6366d4a5920d25b79286ad45ff37a74494f262e3bc98d909d0a7b
|
||||
#
|
||||
# and in the file:
|
||||
#
|
||||
# 997599971ee6366d4a5920d25b79286ad45ff37a74494f262e3bc98d909d0a7b-json.log
|
||||
#
|
||||
# where 997599971ee6... is the Docker ID of the running container.
|
||||
# The Kubernetes kubelet makes a symbolic link to this file on the host machine
|
||||
# in the /var/log/containers directory which includes the pod name and the Kubernetes
|
||||
# container name:
|
||||
#
|
||||
# synthetic-logger-0.25lps-pod_default_synth-lgr-997599971ee6366d4a5920d25b79286ad45ff37a74494f262e3bc98d909d0a7b.log
|
||||
# ->
|
||||
# /var/lib/docker/containers/997599971ee6366d4a5920d25b79286ad45ff37a74494f262e3bc98d909d0a7b/997599971ee6366d4a5920d25b79286ad45ff37a74494f262e3bc98d909d0a7b-json.log
|
||||
#
|
||||
# The /var/log directory on the host is mapped to the /var/log directory in the container
|
||||
# running this instance of Fluentd and we end up collecting the file:
|
||||
#
|
||||
# /var/log/containers/synthetic-logger-0.25lps-pod_default_synth-lgr-997599971ee6366d4a5920d25b79286ad45ff37a74494f262e3bc98d909d0a7b.log
|
||||
#
|
||||
# This results in the tag:
|
||||
#
|
||||
# var.log.containers.synthetic-logger-0.25lps-pod_default_synth-lgr-997599971ee6366d4a5920d25b79286ad45ff37a74494f262e3bc98d909d0a7b.log
|
||||
#
|
||||
# The Kubernetes fluentd plugin is used to extract the namespace, pod name & container name
|
||||
# which are added to the log message as a kubernetes field object & the Docker container ID
|
||||
# is also added under the docker field object.
|
||||
# The final tag is:
|
||||
#
|
||||
# kubernetes.var.log.containers.synthetic-logger-0.25lps-pod_default_synth-lgr-997599971ee6366d4a5920d25b79286ad45ff37a74494f262e3bc98d909d0a7b.log
|
||||
#
|
||||
# And the final log record look like:
|
||||
#
|
||||
# {
|
||||
# "log":"2014/09/25 21:15:03 Got request with path wombat\n",
|
||||
# "stream":"stderr",
|
||||
# "time":"2014-09-25T21:15:03.499185026Z",
|
||||
# "kubernetes": {
|
||||
# "namespace": "default",
|
||||
# "pod_name": "synthetic-logger-0.25lps-pod",
|
||||
# "container_name": "synth-lgr"
|
||||
# },
|
||||
# "docker": {
|
||||
# "container_id": "997599971ee6366d4a5920d25b79286ad45ff37a74494f262e3bc98d909d0a7b"
|
||||
# }
|
||||
# }
|
||||
#
|
||||
# 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:
|
||||
# {"log":"[info:2016-02-16T16:04:05.930-08:00] Some log text here\n","stream":"stdout","time":"2016-02-17T00:04:05.931087621Z"}
|
||||
<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>
|
||||
|
||||
# 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>
|
||||
|
||||
<filter kubernetes.**>
|
||||
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>
|
||||
@ -1,9 +0,0 @@
|
||||
apiVersion: v1
|
||||
kind: ServiceAccount
|
||||
metadata:
|
||||
name: fluentd-es
|
||||
namespace: kube-system
|
||||
labels:
|
||||
k8s-app: fluentd-es
|
||||
kubernetes.io/cluster-service: "true"
|
||||
addonmanager.kubernetes.io/mode: Reconcile
|
||||
@ -27,10 +27,14 @@ spec:
|
||||
requests:
|
||||
cpu: 100m
|
||||
env:
|
||||
- name: "ELASTICSEARCH_URL"
|
||||
value: "http://elasticsearch-logging:9200"
|
||||
- name: "SERVER_BASEPATH"
|
||||
value: "/api/v1/proxy/namespaces/kube-system/services/kibana-logging"
|
||||
- name: ELASTICSEARCH_URL
|
||||
value: http://elasticsearch-logging:9200
|
||||
- name: SERVER_BASEPATH
|
||||
value: /api/v1/proxy/namespaces/kube-system/services/kibana-logging
|
||||
- name: XPACK_MONITORING_ENABLED
|
||||
value: "false"
|
||||
- name: XPACK_SECURITY_ENABLED
|
||||
value: "false"
|
||||
ports:
|
||||
- containerPort: 5601
|
||||
name: ui
|
||||
|
||||
@ -28,15 +28,6 @@ spec:
|
||||
containers:
|
||||
- name: fluentd-gcp
|
||||
image: gcr.io/google-containers/fluentd-gcp:2.0.8
|
||||
# If fluentd consumes its own logs, the following situation may happen:
|
||||
# fluentd fails to send a chunk to the server => writes it to the log =>
|
||||
# tries to send this message to the server => fails to send a chunk and so on.
|
||||
# Writing to a file, which is not exported to the back-end prevents it.
|
||||
# It also allows to increase the fluentd verbosity by default.
|
||||
command:
|
||||
- '/bin/sh'
|
||||
- '-c'
|
||||
- '/run.sh $FLUENTD_ARGS'
|
||||
env:
|
||||
- name: FLUENTD_ARGS
|
||||
value: --no-supervisor -q
|
||||
|
||||
Loading…
Reference in New Issue
Block a user