Files
kubernetes/cluster/addons/fluentd-gcp/fluentd-gcp-ds.yaml
Bryan Moyles a844523c20 Find most recent modified date for fluentd buffers recursively.
Due to updates in Fluent v0.14, the buffers directory modified date is no
longer updated when files inside the directory are changed. Therefore we
must find the most recent modified date recursively to fix liveness probe.
2018-03-12 15:28:55 -04:00

118 lines
4.2 KiB
YAML

apiVersion: extensions/v1beta1
kind: DaemonSet
metadata:
name: fluentd-gcp-v3.0.0
namespace: kube-system
labels:
k8s-app: fluentd-gcp
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: Reconcile
version: v3.0.0
spec:
updateStrategy:
type: RollingUpdate
template:
metadata:
labels:
k8s-app: fluentd-gcp
kubernetes.io/cluster-service: "true"
version: v3.0.0
# 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).
annotations:
scheduler.alpha.kubernetes.io/critical-pod: ''
spec:
priorityClassName: system-node-critical
serviceAccountName: fluentd-gcp
dnsPolicy: Default
containers:
- name: fluentd-gcp
image: gcr.io/stackdriver-agents/stackdriver-logging-agent:{{ fluentd_gcp_version }}
volumeMounts:
- name: varlog
mountPath: /var/log
- name: varlibdockercontainers
mountPath: /var/lib/docker/containers
readOnly: true
- name: libsystemddir
mountPath: /host/lib
readOnly: true
- name: config-volume
mountPath: /etc/google-fluentd/config.d
# Liveness probe is aimed to help in situarions where fluentd
# silently hangs for no apparent reasons until manual restart.
# The idea of this probe is that if fluentd is not queueing or
# flushing chunks for 5 minutes, something is not right. If
# you want to change the fluentd configuration, reducing amount of
# logs fluentd collects, consider changing the threshold or turning
# liveness probe off completely.
livenessProbe:
initialDelaySeconds: 600
periodSeconds: 60
exec:
command:
- '/bin/sh'
- '-c'
- >
LIVENESS_THRESHOLD_SECONDS=${LIVENESS_THRESHOLD_SECONDS:-300};
STUCK_THRESHOLD_SECONDS=${LIVENESS_THRESHOLD_SECONDS:-900};
if [ ! -e /var/log/fluentd-buffers ];
then
exit 1;
fi;
touch -d "${STUCK_THRESHOLD_SECONDS} seconds ago" /tmp/marker-stuck;
if [[ -z "$(find /var/log/fluentd-buffers -type f -newer /tmp/marker-stuck -print -quit)" ]];
then
rm -rf /var/log/fluentd-buffers;
exit 1;
fi;
touch -d "${LIVENESS_THRESHOLD_SECONDS} seconds ago" /tmp/marker-liveness;
if [[ -z "$(find /var/log/fluentd-buffers -type f -newer /tmp/marker-liveness -print -quit)" ]];
then
exit 1;
fi;
# BEGIN_PROMETHEUS_TO_SD
- name: prometheus-to-sd-exporter
image: k8s.gcr.io/prometheus-to-sd:v0.2.4
command:
- /monitor
- --stackdriver-prefix={{ prometheus_to_sd_prefix }}/addons
- --api-override={{ prometheus_to_sd_endpoint }}
- --source=fluentd:http://localhost:24231?whitelisted=stackdriver_successful_requests_count,stackdriver_failed_requests_count,stackdriver_ingested_entries_count,stackdriver_dropped_entries_count
- --pod-id=$(POD_NAME)
- --namespace-id=$(POD_NAMESPACE)
env:
- name: POD_NAME
valueFrom:
fieldRef:
fieldPath: metadata.name
- name: POD_NAMESPACE
valueFrom:
fieldRef:
fieldPath: metadata.namespace
# END_PROMETHEUS_TO_SD
nodeSelector:
beta.kubernetes.io/fluentd-ds-ready: "true"
tolerations:
- key: "node.alpha.kubernetes.io/ismaster"
effect: "NoSchedule"
- operator: "Exists"
effect: "NoExecute"
- operator: "Exists"
effect: "NoSchedule"
terminationGracePeriodSeconds: 30
volumes:
- name: varlog
hostPath:
path: /var/log
- name: varlibdockercontainers
hostPath:
path: /var/lib/docker/containers
- name: libsystemddir
hostPath:
path: /usr/lib64
- name: config-volume
configMap:
name: fluentd-gcp-config-v1.2.4