b3169efa35
Updated stx-monitor to use official Elastic 7.6.0 helm-charts for Kibana, Filebeat, Metricbeat and Logstash. This change included updating the helm-elastic tarball sha to the newest release and updating helm-elastic patches accordingly. Patched the charts to support previous stx-monitor functionality and updated the manifest to conform to the new config format. Change-Id: I03b356b2b7acda0fc8336704784bd870252dd5b8
92 lines
5.1 KiB
Diff
92 lines
5.1 KiB
Diff
From 36ea0e2a2fd6cf6ac8cb19411c14c5ef4d0618f9 Mon Sep 17 00:00:00 2001
|
|
From: Kevin Smith <kevin.smith@windriver.com>
|
|
Date: Mon, 23 Mar 2020 10:43:07 -0400
|
|
Subject: [PATCH 1/1] readiness probe enhancements
|
|
|
|
---
|
|
elasticsearch/templates/statefulset.yaml | 46 +++++++++++++++++++++++++++-----
|
|
elasticsearch/values.yaml | 2 ++
|
|
2 files changed, 41 insertions(+), 7 deletions(-)
|
|
|
|
diff --git a/elasticsearch/templates/statefulset.yaml b/elasticsearch/templates/statefulset.yaml
|
|
index e17d39e..483e1f4 100644
|
|
--- a/elasticsearch/templates/statefulset.yaml
|
|
+++ b/elasticsearch/templates/statefulset.yaml
|
|
@@ -202,7 +202,7 @@ spec:
|
|
# If the node is starting up wait for the cluster to be ready (request params: '{{ .Values.clusterHealthCheckParams }}' )
|
|
# Once it has started only check that the node itself is responding
|
|
START_FILE=/tmp/.es_start_file
|
|
-
|
|
+
|
|
http () {
|
|
local path="${1}"
|
|
if [ -n "${ELASTIC_USERNAME}" ] && [ -n "${ELASTIC_PASSWORD}" ]; then
|
|
@@ -217,13 +217,45 @@ spec:
|
|
echo 'Elasticsearch is already running, lets check the node is healthy and there are master nodes available'
|
|
http "/_cluster/health?timeout=0s"
|
|
else
|
|
- echo 'Waiting for elasticsearch cluster to become ready (request params: "{{ .Values.clusterHealthCheckParams }}" )'
|
|
- if http "/_cluster/health?{{ .Values.clusterHealthCheckParams }}" ; then
|
|
- touch ${START_FILE}
|
|
- exit 0
|
|
+ DATA_NODE=$(printenv node.data)
|
|
+ if [[ "$DATA_NODE" == true ]]; then
|
|
+ # This is a data node, check for health depending on whether we can
|
|
+ # reach the master node and how many data nodes there are.
|
|
+ DATA_NODE_COUNT=$(http "/_cat/nodes?master_timeout=1s" | grep -c data)
|
|
+ echo "data node count = $DATA_NODE_COUNT"
|
|
+ if [[ $DATA_NODE_COUNT -gt 1 ]]; then
|
|
+ # We connected to master and there is more than one data node.
|
|
+ echo 'Waiting for elasticsearch cluster to become ready (request params: "{{ .Values.clusterHealthCheckParams }}" )'
|
|
+ if http "/_cluster/health?{{ .Values.clusterHealthCheckParams }}" ; then
|
|
+ touch ${START_FILE}
|
|
+ exit 0
|
|
+ else
|
|
+ echo 'Cluster is not yet ready (request params: "{{ .Values.clusterHealthCheckParams }}" )'
|
|
+ exit 1
|
|
+ fi
|
|
+ else
|
|
+ # Cannot connect to the master or we are the only data node
|
|
+ # found. Could be DOR, AIO-SX, other host is locked and we
|
|
+ # experienced a pod restart or other similar scenario.
|
|
+ echo "Cannot connect to master or less than 2 data nodes"
|
|
+ echo 'Waiting for elasticsearch cluster to become ready (request params: "{{ .Values.clusterHealthCheckParamsBasic }}" )'
|
|
+ if http "/_cluster/health?{{ .Values.clusterHealthCheckParamsBasic }}" ; then
|
|
+ touch ${START_FILE}
|
|
+ exit 0
|
|
+ else
|
|
+ echo 'Cluster is not yet ready (request params: "{{ .Values.clusterHealthCheckParamsBasic }}" )'
|
|
+ exit 1
|
|
+ fi
|
|
+ fi
|
|
else
|
|
- echo 'Cluster is not yet ready (request params: "{{ .Values.clusterHealthCheckParams }}" )'
|
|
- exit 1
|
|
+ echo 'Waiting for elasticsearch cluster to become ready (request params: "{{ .Values.clusterHealthCheckParams }}" )'
|
|
+ if http "/_cluster/health?{{ .Values.clusterHealthCheckParams }}" ; then
|
|
+ touch ${START_FILE}
|
|
+ exit 0
|
|
+ else
|
|
+ echo 'Cluster is not yet ready (request params: "{{ .Values.clusterHealthCheckParams }}" )'
|
|
+ exit 1
|
|
+ fi
|
|
fi
|
|
fi
|
|
ports:
|
|
diff --git a/elasticsearch/values.yaml b/elasticsearch/values.yaml
|
|
index 0d983eb..ebbae6c 100755
|
|
--- a/elasticsearch/values.yaml
|
|
+++ b/elasticsearch/values.yaml
|
|
@@ -204,6 +204,8 @@ readinessProbe:
|
|
|
|
# https://www.elastic.co/guide/en/elasticsearch/reference/current/cluster-health.html#request-params wait_for_status
|
|
clusterHealthCheckParams: "wait_for_status=green&timeout=1s"
|
|
+# Used for readiness probe when on a data node and only a basic health check is needed.
|
|
+clusterHealthCheckParamsBasic: "local=true"
|
|
|
|
## Use an alternate scheduler.
|
|
## ref: https://kubernetes.io/docs/tasks/administer-cluster/configure-multiple-schedulers/
|
|
--
|
|
1.8.3.1
|
|
|