Merge pull request #19 from uswitch/AIRSHIP-3913-move-node-problem-detector

Airship 3913 move node problem detector

Author: giorgia-amici

.drone.yml

@@ -0,0 +1 @@
+service.rvu.co.uk/brand: airship

.github/rvu/labels.yaml

@@ -0,0 +1,27 @@
+name: push
+on: push
+permissions:
+    contents: read
+    id-token: write
+jobs:
+    build:
+        runs-on: ubuntu-latest
+        steps:
+          - uses: actions/checkout@v4
+          - name: Login to Quay.io
+            uses: docker/login-action@v3
+            with:
+              registry: quay.io
+              username: ${{ secrets.QUAY_USERNAME }}
+              password: ${{ secrets.QUAY_PASSWORD }}
+          - id: meta
+            uses: docker/metadata-action@v5
+            with:
+              images: quay.io/uswitch/node-problem-detector
+              tags: type=sha,prefix=,format=long
+          - uses: docker/build-push-action@v6
+            with:
+              context: .
+              labels: ${{ steps.meta.outputs.labels }}
+              push: true
+              tags: ${{ steps.meta.outputs.tags }}

.github/workflows/push.yaml

@@ -1 +1,16 @@
-Adding our own scripts to https://github.com/kubernetes/node-problem-detector
+# Node Problem Detector custom scripts
+
+Adding our own scripts to https://github.com/kubernetes/node-problem-detector and sharing them in case you might find those handy for you use cases. 
+
+
+The scripts details can be found in `/config/plugin/` but ultimately, they are:
+* `launch-config-drift`: a way to check if your instances launch template has diverged from your asg launch template
+* `spot-termination`: uses the `meta-data/spot/instance-action endpoint` to check EC2 Spot Instance interruption notice 
+* `local-dns-resolver`: checks the response status value received (if any) from the local dns resolver ip
+* `upstream-dns-resolver`: check if we receive an IPv4 address for a given A record.
+* `uptime`: every 5 seconds, checks if the information detailing how long the system has been on since its last restart is acceptable (to us the threshold being 604800 seconds) 
+
+
+## Notes
+*July 2024 -* The custom `node problem detector` image is now stored in the `uswitch/node_problem_detectr` repository on Quay.
+<br>

README.md

@@ -16,7 +16,7 @@ then
 fi
 
 instance="$(echo "${instances}" | jq '.AutoScalingInstances[0]')"
-instance_launch_config="$(echo "${instance}" | jq -r .LaunchConfigurationName)"
+instance_launch_config="$(echo "${instance}" | jq -r .LaunchTemplate.LaunchTemplateName)"
 instance_asg="$(echo "${instance}" | jq -r .AutoScalingGroupName)"
 
 asgs="$(aws autoscaling describe-auto-scaling-groups --auto-scaling-group-names ${instance_asg})"
@@ -26,11 +26,11 @@ then
     exit $UNKNOWN
 fi
 
-asg_launch_config="$(echo "${asgs}" | jq -r '.AutoScalingGroups[0].LaunchConfigurationName')"
+asg_launch_config="$(echo "${asgs}" | jq -r '.AutoScalingGroups[0].MixedInstancesPolicy.LaunchTemplate.LaunchTemplateSpecification.LaunchTemplateName')"
 
 if [ "${instance_launch_config}" = "${asg_launch_config}" ]
 then
     exit $OK
 else
     exit $NONOK
-fi
+fi