fix: add detached script to join cluster (#363)

* fix: add detached script to join cluster

* fix: review comments

* fix: add pod name sed fix

Dockerfile

@@ -14,6 +14,7 @@ ENV DOCKER_VERNEMQ_KUBERNETES_LABEL_SELECTOR="app=vernemq" \
     PATH="/vernemq/bin:$PATH" \
     VERNEMQ_VERSION="1.13.0"
 COPY --chown=10000:10000 bin/vernemq.sh /usr/sbin/start_vernemq
+COPY --chown=10000:10000 bin/join_cluster.sh /usr/sbin/join_cluster
 COPY --chown=10000:10000 files/vm.args /vernemq/etc/vm.args
 
 # Note that the following copies a binary package under EULA (requiring a paid subscription).

bin/join_cluster.sh

@@ -0,0 +1,69 @@
+#!/usr/bin/env bash
+
+SECRETS_KUBERNETES_DIR="/var/run/secrets/kubernetes.io/serviceaccount"
+DOCKER_VERNEMQ_KUBERNETES_CLUSTER_NAME=${DOCKER_VERNEMQ_KUBERNETES_CLUSTER_NAME:-cluster.local}
+
+if [ -d "${SECRETS_KUBERNETES_DIR}" ] ; then
+    # Let's get the namespace if it isn't set
+    DOCKER_VERNEMQ_KUBERNETES_NAMESPACE=${DOCKER_VERNEMQ_KUBERNETES_NAMESPACE:-$(cat "${SECRETS_KUBERNETES_DIR}/namespace")}
+fi
+
+insecure=""
+if env | grep "DOCKER_VERNEMQ_KUBERNETES_INSECURE" -q; then
+    echo "Using curl with \"--insecure\" argument to access kubernetes API without matching SSL certificate"
+    insecure="--insecure"
+fi
+
+function k8sCurlGet () {
+    local urlPath=$1
+
+    local hostname="kubernetes.default.svc.${DOCKER_VERNEMQ_KUBERNETES_CLUSTER_NAME}"
+    local certsFile="${SECRETS_KUBERNETES_DIR}/ca.crt"
+    local token=$(cat ${SECRETS_KUBERNETES_DIR}/token)
+    local header="Authorization: Bearer ${token}"
+    local url="https://${hostname}/${urlPath}"
+
+    curl -sS ${insecure} --cacert ${certsFile} -H "${header}" ${url} \
+      || ( echo "### Error on accessing URL ${url}" )
+}
+
+try_join() {
+  local exit_code=0
+  if env | grep "DOCKER_VERNEMQ_DISCOVERY_KUBERNETES" -q; then
+      # Let's set our nodename correctly
+      # https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.19/#list-pod-v1-core
+      podList=$(k8sCurlGet "api/v1/namespaces/${DOCKER_VERNEMQ_KUBERNETES_NAMESPACE}/pods?labelSelector=${DOCKER_VERNEMQ_KUBERNETES_LABEL_SELECTOR}")
+      kube_pod_names=$(echo ${podList} | jq '.items[].spec.hostname' | sed 's/"//g' | tr '\n' ' ' | sed 's/ *$//')
+      VERNEMQ_KUBERNETES_SUBDOMAIN=${DOCKER_VERNEMQ_KUBERNETES_SUBDOMAIN:-$(echo ${podList} | jq '.items[0].spec.subdomain' | tr '\n' '"' | sed 's/"//g')}
+
+      for kube_pod_name in $kube_pod_names; do
+          if [[ $kube_pod_name == "null" ]]; then
+              echo "Kubernetes discovery selected, but no pods found. Maybe we're the first?"
+              echo "Anyway, we won't attempt to join any cluster."
+              exit 0
+          fi
+
+          if [[ $kube_pod_name != "$MY_POD_NAME" ]]; then
+              discoveryHostname="${kube_pod_name}.${VERNEMQ_KUBERNETES_SUBDOMAIN}.${DOCKER_VERNEMQ_KUBERNETES_NAMESPACE}.svc.${DOCKER_VERNEMQ_KUBERNETES_CLUSTER_NAME}"
+              echo "Will join an existing Kubernetes cluster with discovery node at ${discoveryHostname}"
+              vmq-admin cluster show | grep "VerneMQ@${discoveryHostname}" > /dev/null || exit_code=$?
+              if [ $exit_code -eq 0 ]; then
+                  echo "We have already joined the cluster - no extra work required."
+                  exit 0
+              else
+                  echo "We have yet to join the cluster - attempting manual join..."
+                  vmq-admin cluster join discovery-node="VerneMQ@${discoveryHostname}"
+                  sleep 2
+              fi
+              break
+          fi
+      done
+  else
+      exit 0
+  fi
+}
+
+while true
+do
+    try_join
+done;

bin/vernemq.sh

@@ -139,6 +139,7 @@ if [ -d "${SECRETS_KUBERNETES_DIR}" ] ; then
 fi
 
 # Set up kubernetes node discovery
+start_join_cluster=0
 if env | grep "DOCKER_VERNEMQ_DISCOVERY_KUBERNETES" -q; then
     # Let's set our nodename correctly
     # https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.19/#list-pod-v1-core
@@ -162,6 +163,7 @@ if env | grep "DOCKER_VERNEMQ_DISCOVERY_KUBERNETES" -q; then
         fi
         if [[ $kube_pod_name != $MY_POD_NAME ]]; then
             discoveryHostname="${kube_pod_name}.${VERNEMQ_KUBERNETES_SUBDOMAIN}.${DOCKER_VERNEMQ_KUBERNETES_NAMESPACE}.svc.${DOCKER_VERNEMQ_KUBERNETES_CLUSTER_NAME}"
+            start_join_cluster=1
             echo "Will join an existing Kubernetes cluster with discovery node at ${discoveryHostname}"
             echo "-eval \"vmq_server_cmd:node_join('VerneMQ@${discoveryHostname}')\"" >> ${VERNEMQ_VM_ARGS_FILE}
             echo "Did I previously leave the cluster? If so, purging old state."
@@ -339,4 +341,8 @@ trap 'sigterm_handler' SIGTERM
 # Start VerneMQ
 /vernemq/bin/vernemq console -noshell -noinput $@ &
 pid=$!
+if [ $start_join_cluster  -eq 1 ]; then
+    mkdir -p /var/log/vernemq/log
+    join_cluster > /var/log/vernemq/log/join_cluster.log &
+fi
 wait $pid