Skip to content
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.

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

Upmerge 0.33 to edge #1563

Merged
merged 8 commits into from
May 23, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
60 changes: 27 additions & 33 deletions .github/scripts/delete-aws-resources.sh
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
Expand All @@ -16,7 +16,6 @@
# limitations under the License.
# ------------------------------------------------------------


APP_ID=$1
APP_LABEL='radapp.io/application'
RESOURCE_TYPES='AWS::RDS::DBInstance,AWS::RDS::DBSubnetGroup,AWS::MemoryDB::Cluster,AWS::MemoryDB::SubnetGroup'
Expand All @@ -34,21 +33,16 @@ function delete_aws_resources() {
# Empty the file
truncate -s 0 $DELETED_RESOURCES_FILE

for resource_type in ${RESOURCE_TYPES//,/ }
do
aws cloudcontrol list-resources --type-name "$resource_type" --query "ResourceDescriptions[].Identifier" --output text | tr '\t' '\n' | while read identifier
do
aws cloudcontrol get-resource --type-name "$resource_type" --identifier "$identifier" --query "ResourceDescription.Properties" --output text | while read resource
do
resource_tags=$(jq -c -r .Tags <<< "$resource")
for tag in $(jq -c -r '.[]' <<< "$resource_tags")
do
key=$(jq -r '.Key' <<< "$tag")
value=$(jq -r '.Value' <<< "$tag")
if [[ "$key" == "$APP_LABEL" && "$value" == "$APP_ID" ]]
then
for resource_type in ${RESOURCE_TYPES//,/ }; do
aws cloudcontrol list-resources --type-name "$resource_type" --query "ResourceDescriptions[].Identifier" --output text | tr '\t' '\n' | while read identifier; do
aws cloudcontrol get-resource --type-name "$resource_type" --identifier "$identifier" --query "ResourceDescription.Properties" --output text | while read resource; do
resource_tags=$(jq -c -r .Tags <<<"$resource")
for tag in $(jq -c -r '.[]' <<<"$resource_tags"); do
key=$(jq -r '.Key' <<<"$tag")
value=$(jq -r '.Value' <<<"$tag")
if [[ "$key" == "$APP_LABEL" && "$value" == "$APP_ID" ]]; then
echo "Deleting resource of type: $resource_type with identifier: $identifier"
echo "$identifier\n" >> $DELETED_RESOURCES_FILE
echo "$identifier\n" >>$DELETED_RESOURCES_FILE
aws cloudcontrol delete-resource --type-name "$resource_type" --identifier "$identifier"
fi
done
Expand All @@ -65,28 +59,28 @@ function delete_aws_resources() {

RETRY_COUNT=0
while [ $RETRY_COUNT -lt $MAX_RETRIES ]; do
# Trigger the function to delete the resources
delete_aws_resources
# Trigger the function to delete the resources
delete_aws_resources

# If the function returned 0, then no resources needed to be deleted
# on this run. This means that all resources have been deleted.
if [ $? -eq 0 ]; then
echo "All resources deleted successfully"
break
fi
# If the function returned 0, then no resources needed to be deleted
# on this run. This means that all resources have been deleted.
if [ $? -eq 0 ]; then
echo "All resources deleted successfully"
break
fi

# Still have resources to delete, increase the retry count
RETRY_COUNT=$((RETRY_COUNT + 1))
# Still have resources to delete, increase the retry count
RETRY_COUNT=$((RETRY_COUNT + 1))

# Check if there are more retries left
if [ $RETRY_COUNT -lt $MAX_RETRIES ]; then
# Retry after delay
echo "Retrying in $RETRY_DELAY seconds..."
sleep $RETRY_DELAY
fi
# Check if there are more retries left
if [ $RETRY_COUNT -lt $MAX_RETRIES ]; then
# Retry after delay
echo "Retrying in $RETRY_DELAY seconds..."
sleep $RETRY_DELAY
fi
done

# Check if the maximum number of retries exceeded
if [ $RETRY_COUNT -eq $MAX_RETRIES ]; then
echo "Maximum number of retries exceeded"
echo "Maximum number of retries exceeded"
fi
47 changes: 47 additions & 0 deletions .github/scripts/purge-aws-eks-clusters.sh
Original file line number Diff line number Diff line change
@@ -0,0 +1,47 @@
# ------------------------------------------------------------
# Copyright 2023 The Radius Authors.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# 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.
# ------------------------------------------------------------

#!/bin/bash

# Current time in seconds since epoch
current_time=$(date +%s)

# Age limit in seconds (6 hours * 3600 seconds/hour)
age_limit=$((6 * 3600))

echo "Starting cluster purge script."

# List clusters and their creation times, filter and delete those older than 6 hours and starting with 'eks-samplestest-'
aws eks list-clusters --query "clusters[]" --output text | xargs -I {} aws eks describe-cluster --name {} --query "cluster.{name: name, createdAt: createdAt}" --output text | while read -r created_at name; do
# Convert creation time to seconds since the epoch
# Remove milliseconds and adjust timezone format from "-07:00" to "-0700"
formatted_created_at="${created_at%.*}${created_at##*.}"
formatted_created_at="${formatted_created_at%:*}${formatted_created_at##*:}"

# Convert creation time to seconds
created_at_seconds=$(date -d "$formatted_created_at" +%s)

# Calculate age in seconds
age=$((current_time - created_at_seconds))

# Check if age is greater than age limit and name starts with 'eks-samplestest-'
if [ "$age" -gt "$age_limit" ] && [[ "$name" == eks-samplestest-* ]]; then
echo "Deleting cluster $name older than 6 hours."
eksctl delete cluster --name "$name" --wait --force
else
echo "Cluster $name is not older than 6 hours or does not meet naming criteria."
fi
done
7 changes: 3 additions & 4 deletions .github/scripts/purge-aws-rds-snapshots.sh
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
Expand All @@ -16,8 +16,7 @@

set -xe

aws rds describe-db-snapshots --query 'DBSnapshots[].DBSnapshotIdentifier' --output text > snapshots.txt
for rds_snapshot_identifier in $(cat ./snapshots.txt)
do
aws rds describe-db-snapshots --query 'DBSnapshots[].DBSnapshotIdentifier' --output text >snapshots.txt
for rds_snapshot_identifier in $(cat ./snapshots.txt); do
aws rds delete-db-snapshot --db-snapshot-identifier $rds_snapshot_identifier
done
49 changes: 35 additions & 14 deletions .github/workflows/issues.yaml
Original file line number Diff line number Diff line change
@@ -1,28 +1,49 @@
name: Issues Automation
name: Sync issue to Azure DevOps work item

on:
issues:
types: [opened, edited, deleted, closed, reopened, labeled, unlabeled, assigned]

types:
[opened, edited, deleted, closed, reopened, labeled, unlabeled, assigned]

concurrency:
group: issue-${{ github.event.issue.number }}
cancel-in-progress: false

# Extra permissions needed to login with Entra ID service principal via federated identity
permissions:
id-token: write
issues: write

jobs:
ado:
name: Sync issue to Azure DevOps
runs-on: ubuntu-latest
environment:
name: issues
steps:
- uses: danhellem/[email protected]
# Auth using Azure Service Principals was added as a part of v2.3
# reference: https://github.com/danhellem/github-actions-issue-to-work-item/pull/143
- name: Login to Azure
uses: azure/login@v2
with:
client-id: ${{ vars.AZURE_SP_DEVOPS_SYNC_CLIENT_ID }}
tenant-id: ${{ vars.AZURE_SP_DEVOPS_SYNC_TENANT_ID }}
allow-no-subscriptions: true
- name: Get Azure DevOps token
id: get_ado_token
run:
# The resource ID for Azure DevOps is always 499b84ac-1321-427f-aa17-267ca6975798
# https://learn.microsoft.com/azure/devops/integrate/get-started/authentication/service-principal-managed-identity
echo "ADO_TOKEN=$(az account get-access-token --resource 499b84ac-1321-427f-aa17-267ca6975798 --query "accessToken" --output tsv)" >> $GITHUB_ENV
- name: Sync issue to Azure DevOps
uses: danhellem/[email protected]
env:
ado_token: "${{ secrets.ADO_AOCTO_BOT_TOKEN }}"
github_token: "${{ secrets.GH_RAD_CI_BOT_PAT }}"
ado_organization: "azure-octo"
ado_project: "Incubations"
ado_token: ${{ env.ADO_TOKEN }}
github_token: '${{ secrets.GH_RAD_CI_BOT_PAT }}'
ado_organization: 'azure-octo'
ado_project: 'Incubations'
ado_area_path: "Incubations\\Radius"
ado_iteration_path: "Incubations\\Radius"
ado_wit: "GitHub Issue"
ado_new_state: "New"
ado_active_state: "Active"
ado_close_state: "Closed"
ado_wit: "GitHub Issue"
ado_new_state: 'New'
ado_active_state: 'Active'
ado_close_state: 'Closed'
ado_wit: 'GitHub Issue'
42 changes: 42 additions & 0 deletions .github/workflows/purge-aws-eks-clusters.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,42 @@
name: Purge AWS EKS Clusters

on:
schedule:
# Runs every day at 7 AM
- cron: "0 7 * * *"

env:
GH_TOKEN: ${{ github.token }}
AWS_REGION: us-west-2

jobs:
purge_eks_clusters:
name: Purge AWS EKS Clusters
runs-on: ubuntu-latest
steps:
- name: Checkout code
uses: actions/checkout@v4

- name: Install AWS CLI
run: |
sudo apt-get update
sudo apt-get install -y awscli

- name: Install eksctl
run: |
curl --silent --location "https://github.com/weaveworks/eksctl/releases/latest/download/eksctl_$(uname -s)_amd64.tar.gz" | tar xz -C /tmp
sudo mv /tmp/eksctl /usr/local/bin

- name: Delete old EKS clusters
env:
AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
AWS_REGION: ${{ env.AWS_REGION }}
run: bash .github/scripts/purge-aws-eks-clusters.sh

- name: Create GitHub issue on failure
if: failure() && github.event_name != 'pull_request'
run: |
gh issue create --title "Purge AWS EKS Clusters workflow failed" \
--body "Test failed on ${{ github.repository }}. See [workflow logs](${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}) for more details." \
--repo ${{ github.repository }}
4 changes: 2 additions & 2 deletions .github/workflows/purge-aws-rds-snapshots.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -4,8 +4,8 @@ on:
# Runs at 00:30 and 12:30
- cron: "30 0,12 * * *"
env:
GH_TOKEN: ${{ github.token }}
AWS_REGION: us-west-2
GH_TOKEN: ${{ github.token }}
AWS_REGION: us-west-2
jobs:
purge_rds_snapshots:
name: Purge AWS RDS DBInstance snapshots
Expand Down
23 changes: 16 additions & 7 deletions .github/workflows/purge-test-resources.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -5,10 +5,11 @@ on:
env:
AZURE_RG_DELETE_LIST_FILE: "az_rg_list.txt"
VALID_RESOURCE_WINDOW: 6*60*60
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
jobs:
purge_azure_resources:
name: Azure resources clean-ups
runs-on: [self-hosted, 1ES.Pool=1ES-Radius]
runs-on: [ubuntu-latest]
steps:
- name: Login to Azure
run: |
Expand All @@ -22,13 +23,21 @@ jobs:
- name: List Test Resource Groups
run: |
echo "## Test resource group list" >> $GITHUB_STEP_SUMMARY
az group list --query "[?starts_with(name, 'samplestest-')].{Name:name, creationTime:tags.creationTime}" -o json > resource_groups.json
az group list --query "[?starts_with(name, 'rg-samplestest-')].{Name:name, creationTime:tags.creationTime}" -o json > resource_groups.json

current_time=$(date +%s)
hours_ago=$((current_time - ${{ env.VALID_RESOURCE_WINDOW }}))

jq -r '.[] | select(.creationTime == null || .creationTime < '$hours_ago') | .Name' resource_groups.json > ${{ env.AZURE_RG_DELETE_LIST_FILE}}
jq -r '.[] | {name: .Name, creationTime: .creationTime // "None"}' resource_groups.json > $GITHUB_STEP_SUMMARY
# This jq command processes the data in 'resource_groups.json'.
# For each object in the JSON array, it checks if the 'creationTime' property is null or less than the value of 'hours_ago'.
# Note that the 'creationTime' is converted to a number for the comparison.
# Then the name of the resource group is written to the file specified by the 'AZURE_RG_DELETE_LIST_FILE' environment variable.
jq -r '.[] | select(.creationTime == null // (.creationTime | tonumber) < '$hours_ago') | .Name' resource_groups.json > ${{ env.AZURE_RG_DELETE_LIST_FILE}}

# This jq command also processes the data in 'resource_groups.json'.
# For each object in the JSON array, it outputs a string containing the 'Name' property, and the 'creationTime' property.
# If 'creationTime' is null, it outputs the string "None" instead.
jq -r '.[] | "\(.Name) \(.creationTime // "None")"' resource_groups.json > $GITHUB_STEP_SUMMARY

- name: Delete Azure Resource Groups
run: |
Expand All @@ -40,8 +49,8 @@ jobs:
done

- name: Create GitHub issue on failure
if: ${{ failure() }}
if: failure()
run: |
gh issue create --title "Samples purge test resources failed \
gh issue create --title "Samples purge test resources failed" \
--body "Test failed on ${{ github.repository }}. See [workflow logs](${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}) for more details." \
s--repo ${{ github.repository }}
--repo ${{ github.repository }}
Loading