From 4fe7143f82c03a49b54193fda89cbc0cb360cd45 Mon Sep 17 00:00:00 2001
From: redixin <redixin@users.noreply.github.com>
Date: Tue, 8 Jan 2019 07:18:12 +0200
Subject: [PATCH] [incubator/etcd] Fix rejoin after failure (#9195)

Signed-off-by: Sergey Skripnick <sskripnick@mirantis.com>
---
 incubator/etcd/Chart.yaml                 |  2 +-
 incubator/etcd/templates/statefulset.yaml | 22 ++++++++++++----------
 2 files changed, 13 insertions(+), 11 deletions(-)

diff --git a/incubator/etcd/Chart.yaml b/incubator/etcd/Chart.yaml
index 89f2bf27a4..14979d6e35 100755
--- a/incubator/etcd/Chart.yaml
+++ b/incubator/etcd/Chart.yaml
@@ -1,6 +1,6 @@
 name: etcd
 home: https://github.com/coreos/etcd
-version: 0.6.0
+version: 0.6.1
 appVersion: 2.2.5
 description: Distributed reliable key-value store for the most critical data of a
   distributed system.
diff --git a/incubator/etcd/templates/statefulset.yaml b/incubator/etcd/templates/statefulset.yaml
index d588a1aa64..1a856e5364 100644
--- a/incubator/etcd/templates/statefulset.yaml
+++ b/incubator/etcd/templates/statefulset.yaml
@@ -106,13 +106,23 @@ spec:
                 etcdctl member list | grep http://${HOSTNAME}.${SET_NAME}:2380 | cut -d':' -f1 | cut -d'[' -f1
             }
 
+            # we should wait for other pods to be up before trying to join
+            # otherwise we got "no such host" errors when trying to resolve other members
+            for i in $(seq 0 $((${INITIAL_CLUSTER_SIZE} - 1))); do
+                while true; do
+                    echo "Waiting for ${SET_NAME}-${i}.${SET_NAME} to come up"
+                    ping -W 1 -c 1 ${SET_NAME}-${i}.${SET_NAME} > /dev/null && break
+                    sleep 1s
+                done
+            done
+
             # re-joining after failure?
             if [ -e /var/run/etcd/default.etcd ]; then
                 echo "Re-joining etcd member"
                 member_id=$(cat /var/run/etcd/member_id)
 
                 # re-join member
-                ETCDCTL_ENDPOINT=$(eps) etcdctl member update ${member_id} http://${HOSTNAME}.${SET_NAME}:2380
+                ETCDCTL_ENDPOINT=$(eps) etcdctl member update ${member_id} http://${HOSTNAME}.${SET_NAME}:2380 | true
                 exec etcd --name ${HOSTNAME} \
                     --listen-peer-urls http://0.0.0.0:2380 \
                     --listen-client-urls http://0.0.0.0:2379\
@@ -160,14 +170,6 @@ spec:
                     --initial-cluster-state ${ETCD_INITIAL_CLUSTER_STATE}
             fi
 
-            for i in $(seq 0 $((${INITIAL_CLUSTER_SIZE} - 1))); do
-                while true; do
-                    echo "Waiting for ${SET_NAME}-${i}.${SET_NAME} to come up"
-                    ping -W 1 -c 1 ${SET_NAME}-${i}.${SET_NAME} > /dev/null && break
-                    sleep 1s
-                done
-            done
-
             PEERS=""
             for i in $(seq 0 $((${INITIAL_CLUSTER_SIZE} - 1))); do
                 PEERS="${PEERS}${PEERS:+,}${SET_NAME}-${i}=http://${SET_NAME}-${i}.${SET_NAME}:2380"
@@ -207,4 +209,4 @@ spec:
       volumes:
       - name: datadir
         emptyDir: {}
-  {{- end }}
\ No newline at end of file
+  {{- end }}