github/kubernetes
1
0
Fork 0
mirror of https://github.com/k3s-io/kubernetes.git synced 2025-07-24 12:15:52 +00:00
Code Issues Projects Releases Wiki Activity

local-up-cluster kube-proxy terminated error

Browse Source 
When using hack/local-up-cluster.sh deploy local cluster, it
failed with following message "kube-proxy terminated unexpectedly"
and "Failed to retrieve node info: nodes "127.0.0.1" not found" in
kube-proxy.log.

The root reason for this error is miss boot order of kubernetes
services in local-up-cluster.sh, kube-proxy and kubectl daemon.

When starting kube-proxy, it would check node information. And
these information are collected by kubelet daemon. However, in
the shell script, kube-proxy service start before kubelet daemon.

This patch changed the boot order of kubelet daemon and kube-proxy
and check if node stats ready for kube-proxy start.

Signed-off-by: Howard Zhang <howard.zhang@arm.com>
This commit is contained in:
howard 2019-09-05 17:26:39 +08:00 committed by Howard Zhang
parent 6cb788c80e
commit 6ca5e0ed4d
2 changed files with 40 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
hack/lib/util.sh
View File

@ -64,6 +64,24 @@ kube::util::wait_for_url() {
return 1
}
# Example: kube::util::wait_for_success 120 5 "kubectl get nodes|grep localhost"
# arguments: wait time, sleep time, shell command
# returns 0 if the shell command get output, 1 otherwise.
kube::util::wait_for_success(){
local wait_time="$1"
local sleep_time="$2"
local cmd="$3"
while [ "$wait_time" -gt 0 ]; do
if eval "$cmd"; then
return 0
else
sleep "$sleep_time"
wait_time=$((wait_time-sleep_time))
fi
done
return 1
}
# Example: kube::util::trap_add 'echo "in trap DEBUG"' DEBUG
# See: http://stackoverflow.com/questions/3338030/multiple-bash-traps-for-the-same-signal
kube::util::trap_add() {

25
hack/local-up-cluster.sh
View File

@ -670,6 +670,19 @@ function start_cloud_controller_manager {
export CLOUD_CTLRMGR_PID=$!
}
function wait_node_ready(){
# check the nodes information after kubelet daemon start
local nodes_stats="${KUBECTL} --kubeconfig '${CERT_DIR}/admin.kubeconfig' get nodes"
local node_name=$KUBELET_HOST
local system_node_wait_time=30
local interval_time=2
kube::util::wait_for_success "$system_node_wait_time" "$interval_time" "$nodes_stats | grep $node_name"
if [ $? == "1" ]; then
echo "time out on waiting $node_name info"
exit 1
fi
}
function start_kubelet {
KUBELET_LOG=${LOG_DIR}/kubelet.log
mkdir -p "${POD_MANIFEST_PATH}" &>/dev/null || sudo mkdir -p "${POD_MANIFEST_PATH}"
@ -784,6 +797,10 @@ function start_kubelet {
function start_kubeproxy {
PROXY_LOG=${LOG_DIR}/kube-proxy.log
# wait for kubelet collect node information
echo "wait kubelet ready"
wait_node_ready
cat <<EOF > /tmp/kube-proxy.yaml
apiVersion: kubeproxy.config.k8s.io/v1alpha1
kind: KubeProxyConfiguration
@ -997,9 +1014,6 @@ if [[ "${START_MODE}" != "kubeletonly" ]]; then
if [[ "${EXTERNAL_CLOUD_PROVIDER:-}" == "true" ]]; then
start_cloud_controller_manager
fi
if [[ "${START_MODE}" != "nokubeproxy" ]]; then
start_kubeproxy
fi
start_kubescheduler
start_kubedns
if [[ "${ENABLE_NODELOCAL_DNS:-}" == "true" ]]; then
@ -1025,6 +1039,11 @@ if [[ "${START_MODE}" != "nokubelet" ]]; then
esac
fi
if [[ "${START_MODE}" != "kubeletonly" ]]; then
if [[ "${START_MODE}" != "nokubeproxy" ]]; then
start_kubeproxy
fi
fi
if [[ -n "${PSP_ADMISSION}" && "${AUTHORIZATION_MODE}" = *RBAC* ]]; then
create_psp_policy
fi