[elasticsearch] Fix issue with readinessProbe causing outages

BREAKING_CHANGES.md

@@ -4,6 +4,7 @@
 
 
 - [7.7.0 - 2020/05/13](#770---20200513)
+  - [Known Issues](#known-issues)
   - [GA support](#ga-support)
   - [New branching model](#new-branching-model)
   - [Filebeat container inputs](#filebeat-container-inputs)
@@ -26,6 +27,11 @@
 
 ## 7.7.0 - 2020/05/13
 
+### Known Issues
+
+Elasticsearch nodes could be restarted too quickly during an upgrade or rolling restart, potentially resulting in service disruption.
+This is due to a bug introduced by the changes to the Elasticsearch `readinessProbe` in [#586][].
+
 ### GA support
 
 Elasticsearch, Kibana, Filebeat and Metricbeat are moving from beta to GA and
@@ -163,6 +169,7 @@ volumeClaimTemplate:
 [#540]: https://github.com/elastic/helm-charts/pull/540
 [#568]: https://github.com/elastic/helm-charts/pull/568
 [#572]: https://github.com/elastic/helm-charts/pull/572
+[#586]: https://github.com/elastic/helm-charts/pull/586
 [#621]: https://github.com/elastic/helm-charts/pull/621
 [container input]: https://www.elastic.co/guide/en/beats/filebeat/7.7/filebeat-input-container.html
 [docker input]: https://www.elastic.co/guide/en/beats/filebeat/7.7/filebeat-input-docker.html

elasticsearch/templates/statefulset.yaml

@@ -213,22 +213,32 @@ spec:
               - -c
               - |
                 #!/usr/bin/env bash -e
-                # If the node is starting up wait for the cluster to be ready (request params: '{{ .Values.clusterHealthCheckParams }}' )
+                # 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
 
-                if [ -n "${ELASTIC_USERNAME}" ] && [ -n "${ELASTIC_PASSWORD}" ]; then
-                  BASIC_AUTH="-u ${ELASTIC_USERNAME}:${ELASTIC_PASSWORD}"
-                else
-                  BASIC_AUTH=''
-                fi
+                http () {
+                  local path="${1}"
+                  local args="${2}"
+                  set -- -XGET -s
+
+                  if [ "$args" != "" ]; then
+                    set -- "$@" $args
+                  fi
+
+                  if [ -n "${ELASTIC_USERNAME}" ] && [ -n "${ELASTIC_PASSWORD}" ]; then
+                    set -- "$@" -u "${ELASTIC_USERNAME}:${ELASTIC_PASSWORD}"
+                  fi
+
+                  curl --output /dev/null -k "$@" "{{ .Values.protocol }}://127.0.0.1:{{ .Values.httpPort }}${path}"
+                }
 
                 if [ -f "${START_FILE}" ]; then
                   echo 'Elasticsearch is already running, lets check the node is healthy'
-                  HTTP_CODE=$(curl -XGET -s -k ${BASIC_AUTH} -o /dev/null -w '%{http_code}' {{ .Values.protocol }}://127.0.0.1:{{ .Values.httpPort }}/)
+                  HTTP_CODE=$(http "/" "-w %{http_code}")
                   RC=$?
                   if [[ ${RC} -ne 0 ]]; then
-                    echo "curl -XGET -s -k \${BASIC_AUTH} -o /dev/null -w '%{http_code}' {{ .Values.protocol }}://127.0.0.1:{{ .Values.httpPort }}/ failed with RC ${RC}"
+                    echo "curl --output /dev/null -k -XGET -s -w '%{http_code}' \${BASIC_AUTH} {{ .Values.protocol }}://127.0.0.1:{{ .Values.httpPort }}/ failed with RC ${RC}"
                     exit ${RC}
                   fi
                   # ready if HTTP code 200, 503 is tolerable if ES version is 6.x
@@ -237,13 +247,13 @@ spec:
                   elif [[ ${HTTP_CODE} == "503" && "{{ include "elasticsearch.esMajorVersion" . }}" == "6" ]]; then
                     exit 0
                   else
-                    echo "curl -XGET -s -k \${BASIC_AUTH} -o /dev/null -w '%{http_code}' {{ .Values.protocol }}://127.0.0.1:{{ .Values.httpPort }}/ failed with HTTP code ${HTTP_CODE}"
+                    echo "curl --output /dev/null -k -XGET -s -w '%{http_code}' \${BASIC_AUTH} {{ .Values.protocol }}://127.0.0.1:{{ .Values.httpPort }}/ failed with HTTP code ${HTTP_CODE}"
                     exit 1
                   fi
 
                 else
                   echo 'Waiting for elasticsearch cluster to become ready (request params: "{{ .Values.clusterHealthCheckParams }}" )'
-                  if curl -XGET -s -k --fail ${BASIC_AUTH} {{ .Values.protocol }}://127.0.0.1:{{ .Values.httpPort }}/_cluster/health?{{ .Values.clusterHealthCheckParams }} ; then
+                  if http "/_cluster/health?{{ .Values.clusterHealthCheckParams }}" "--fail" ; then
                     touch ${START_FILE}
                     exit 0
                   else