Fix issue with etcd pod startup

Etcd pod fails to start with file not found error.
The error is being caused because the pod is stuck
in an infinite loop as the readiness probe is not true.
Since, we are anyway checking the pod status, we removed
the readiness probe as it is not needed.
Bumped up version of etcd to 3.2.24
This fixes a known issue:
https://github.com/etcd-io/etcd/pull/4861

Issue-ID: MULTICLOUD-660
Change-Id: I815766b4a8f187d88bb2fcdb71e9d6e24b277d25
Signed-off-by: Kiran Kamineni <kiran.k.kamineni@intel.com>

2 files changed, 10 insertions, 20 deletions

diff --git a/kubernetes/common/etcd/templates/statefulset.yaml b/kubernetes/common/etcd/templates/statefulset.yaml
index 8b6a53454e..7190c5bca0 100644
--- a/kubernetes/common/etcd/templates/statefulset.yaml
+++ b/kubernetes/common/etcd/templates/statefulset.yaml
@@ -11,7 +11,6 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-
 apiVersion: apps/v1beta1
 kind: StatefulSet
 metadata:
@@ -55,17 +54,12 @@ spec:
           name: {{ .Values.service.clientPortName }}
         {{- if eq .Values.liveness.enabled true }}
         livenessProbe:
-          exec:
-            command: ["/bin/sh", "-c", "etcdctl cluster-health | grep -w healthy" ]
-            initialDelaySeconds: {{ .Values.liveness.initialDelaySeconds }}
-            periodSeconds: {{ .Values.liveness.periodSeconds }}
-            timeoutSeconds: {{ .Values.liveness.timeoutSeconds }}
-          {{ end -}}
-        readinessProbe:
-          exec:
-            command: ["/bin/sh", "-c", "etcdctl cluster-health | grep -w healthy" ]
-            initialDelaySeconds: {{ .Values.readiness.initialDelaySeconds }}
-            periodSeconds: {{ .Values.readiness.periodSeconds }}
+          tcpSocket:
+            port: {{ .Values.service.clientInternalPort }}
+          initialDelaySeconds: {{ .Values.liveness.initialDelaySeconds }}
+          periodSeconds: {{ .Values.liveness.periodSeconds }}
+          timeoutSeconds: {{ .Values.liveness.timeoutSeconds }}
+        {{ end -}}
         resources:
 {{ include "common.resources" . | indent 10 }}
         env:
@@ -142,7 +136,7 @@ spec:
             done
 
             # re-joining after failure?
-            if [ -e /var/run/etcd/default.etcd ]; then
+            if [[ -e /var/run/etcd/default.etcd && -f /var/run/etcd/member_id ]]; then
                 echo "Re-joining etcd member"
                 member_id=$(cat /var/run/etcd/member_id)
 
diff --git a/kubernetes/common/etcd/values.yaml b/kubernetes/common/etcd/values.yaml
index 341e35cf77..7f53d22248 100644
--- a/kubernetes/common/etcd/values.yaml
+++ b/kubernetes/common/etcd/values.yaml
@@ -25,7 +25,7 @@ global:
 
 #repository: etcd
 repository: "k8s.gcr.io"
-image: "etcd-amd64:2.2.5"
+image: "etcd-amd64:3.2.24"
 pullPolicy: Always
 
 # default number of instances in the StatefulSet
@@ -38,16 +38,12 @@ affinity: {}
 # probe configuration parameters
 liveness:
   initialDelaySeconds: 90
-  periodSeconds: 10
-  timeoutSeconds: 10
+  periodSeconds: 30
+  timeoutSeconds: 5
   # necessary to disable liveness probe when setting breakpoints
   # in debugger so K8s doesn't restart unresponsive container
   enabled: true
 
-readiness:
-  initialDelaySeconds: 90
-  periodSeconds: 10
-
 persistence:
   enabled: false
   ## etcd data Persistent Volume Storage Class