Skip to content

Commit

Permalink
[elasticsearch] Fix issue with readinessProbe causing outages
Browse files Browse the repository at this point in the history
The `readinessProbe` was updated in elastic#586, however this appears to have
introduced a bug which can cause the pod to report as ready before it
actually is, due to a lack of quoting around the URL query params,
combined with the use of '&'.

This commit reworks the `readinessProbe` to correctly quote things.

Reintroduced the `http` function, and added support for passing `args`
in addition to the `path`.
Also borrowed the `set --` pattern from the Kibana chart.
  • Loading branch information
Gavin Williams committed May 20, 2020
1 parent fe52a62 commit 19c0904
Showing 1 changed file with 20 additions and 10 deletions.
30 changes: 20 additions & 10 deletions elasticsearch/templates/statefulset.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -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
Expand All @@ -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
Expand Down

0 comments on commit 19c0904

Please sign in to comment.