Merge pull request #586 from jmlrt/readiness-to-503

[elasticsearch] update readiness probe endpoint

elasticsearch/templates/statefulset.yaml

@@ -216,28 +216,39 @@ spec:
                 # 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
-                      BASIC_AUTH="-u ${ELASTIC_USERNAME}:${ELASTIC_PASSWORD}"
-                    else
-                      BASIC_AUTH=''
-                    fi
-                    curl -XGET -s -k --fail ${BASIC_AUTH} {{ .Values.protocol }}://127.0.0.1:{{ .Values.httpPort }}${path}
-                }
+                if [ -n "${ELASTIC_USERNAME}" ] && [ -n "${ELASTIC_PASSWORD}" ]; then
+                  BASIC_AUTH="-u ${ELASTIC_USERNAME}:${ELASTIC_PASSWORD}"
+                else
+                  BASIC_AUTH=''
+                fi
 
                 if [ -f "${START_FILE}" ]; then
-                    echo 'Elasticsearch is already running, lets check the node is healthy and there are master nodes available'
-                    http "/_cluster/health?timeout=0s"
+                  echo 'Elasticsearch is already running, lets check the node is healthy'
+                  HTTP_CODE=$(curl -XGET -s -k ${BASIC_AUTH} -o /dev/null -w '%{http_code}' {{ .Values.protocol }}://127.0.0.1:{{ .Values.httpPort }}/)
+                  RC=$?
+                  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}"
+                    exit ${RC}
+                  fi
+                  # ready if HTTP code 200, 503 is tolerable if ES version is 6.x
+                  if [[ ${HTTP_CODE} == "200" ]]; then
+                    exit 0
+                  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}"
+                    exit 1
+                  fi
+
                 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
-                    else
-                        echo 'Cluster is not yet ready (request params: "{{ .Values.clusterHealthCheckParams }}" )'
-                        exit 1
-                    fi
+                  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
+                    touch ${START_FILE}
+                    exit 0
+                  else
+                    echo 'Cluster is not yet ready (request params: "{{ .Values.clusterHealthCheckParams }}" )'
+                    exit 1
+                  fi
                 fi
 {{ toYaml .Values.readinessProbe | indent 10 }}
         ports:

elasticsearch/tests/elasticsearch_test.py

@@ -73,7 +73,6 @@ def test_defaults():
 
     assert "curl" in c["readinessProbe"]["exec"]["command"][-1]
     assert "http://127.0.0.1:9200" in c["readinessProbe"]["exec"]["command"][-1]
-    assert "/_cluster/health?timeout=0s" in c["readinessProbe"]["exec"]["command"][-1]
 
     # Resources
     assert c["resources"] == {