Skip to content

Update operator installation readiness check #1010

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 7 commits into from
May 3, 2020
Merged

Update operator installation readiness check #1010

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
2befaae
Add note regarding private operator load balancer initializing
deliahu May 3, 2020
79eb6f1
Add 30 minute cluster validation timeout
deliahu May 3, 2020
63d7cdd
Update message
deliahu May 3, 2020
1321a64
Add operator curl timeout
deliahu May 3, 2020
981c05d
Remove extra print
deliahu May 3, 2020
701ce28
Update install.sh
deliahu May 3, 2020
d60e5fa
Update cluster.go
deliahu May 3, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions cli/cmd/cluster.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -153,7 +153,7 @@ var _upCmd = &cobra.Command{
exit.Error(err)
}
if exitCode == nil || *exitCode != 0 {
helpStr := "\nDebugging tips (may not apply to this error):"
helpStr := "\nDebugging tips (may or may not apply to this error):"
helpStr += fmt.Sprintf("\n* if your cluster started spinning up but was unable to provision instances, additional error information may be found in the activity history of your cluster's autoscaling groups (select each autoscaling group and click the \"Activity History\" tab): https://console.aws.amazon.com/ec2/autoscaling/home?region=%s#AutoScalingGroups:", *clusterConfig.Region)
helpStr += fmt.Sprintf("\n* if your cluster started spinning up, please ensure that your CloudFormation stacks for this cluster have been fully deleted before trying to spin up this cluster again: https://console.aws.amazon.com/cloudformation/home?region=%s#/stacks?filteringText=-%s-", *clusterConfig.Region, clusterConfig.ClusterName)
fmt.Println(helpStr)
Expand Down Expand Up @@ -219,7 +219,7 @@ var _updateCmd = &cobra.Command{
exit.Error(err)
}
if exitCode == nil || *exitCode != 0 {
helpStr := "\nDebugging tips (may not apply to this error):"
helpStr := "\nDebugging tips (may or may not apply to this error):"
helpStr += fmt.Sprintf("\n* if your cluster was unable to provision instances, additional error information may be found in the activity history of your cluster's autoscaling groups (select each autoscaling group and click the \"Activity History\" tab): https://console.aws.amazon.com/ec2/autoscaling/home?region=%s#AutoScalingGroups:", *clusterConfig.Region)
fmt.Println(helpStr)
exit.Error(ErrorClusterUpdate(out + helpStr))
Expand Down
17 changes: 15 additions & 2 deletions manager/install.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -202,7 +202,11 @@ function main() {
python update_cli_config.py "/.cortex/cli.yaml" "$CORTEX_ENV_NAME" "$operator_endpoint" "$CORTEX_AWS_ACCESS_KEY_ID" "$CORTEX_AWS_SECRET_ACCESS_KEY"
echo "✓"

echo -e "\ncortex is ready!"
if [ "$arg1" != "--update" ] && [ "$CORTEX_OPERATOR_LOAD_BALANCER_SCHEME" == "internal" ]; then
echo -e "\ncortex is ready! (it may take a few minutes for your private operator load balancer to finish initializing, but you may now set up VPC Peering)"
else
echo -e "\ncortex is ready!"
fi
}

function setup_configmap() {
Expand Down Expand Up @@ -269,6 +273,8 @@ function setup_istio() {
function validate_cortex() {
set +e

validation_start_time="$(date +%s)"

echo -n "￮ waiting for load balancers "

operator_load_balancer="waiting"
Expand All @@ -278,6 +284,13 @@ function validate_cortex() {
operator_endpoint=""

while true; do
# 30 minute timeout
now="$(date +%s)"
if [ "$now" -ge "$(($validation_start_time+1800))" ]; then
echo -e "\n\ntimeout has occurred when validating your cortex cluster"
exit 1
fi

echo -n "."
sleep 3

Expand Down Expand Up @@ -315,7 +328,7 @@ function validate_cortex() {

if [ "$CORTEX_OPERATOR_LOAD_BALANCER_SCHEME" == "internet-facing" ]; then
if [ "$operator_endpoint_reachable" != "ready" ]; then
if ! curl $operator_endpoint >/dev/null 2>&1; then
if ! curl --max-time 3 $operator_endpoint >/dev/null 2>&1; then
continue
fi
operator_endpoint_reachable="ready"
Expand Down