Compare commits

..

No commits in common. "master" and "v0.7.3" have entirely different histories.

17 changed files with 112 additions and 386 deletions

View File

@ -2,22 +2,6 @@
Various toolchain bits and pieces shared between projects
# Quickstart
Create top-level Makefile
```
REGISTRY := <your-registry>
IMAGE := <image_name>
REGION := <AWS region of your registry>
include .ci/podman.mk
```
Add subtree to your project:
```
git subtree add --prefix .ci https://git.zero-downtime.net/ZeroDownTime/ci-tools-lib.git master --squash
```
## Jenkins
Shared groovy libraries

View File

@ -1,63 +0,0 @@
#!/usr/bin/env python3
import argparse
import boto3
parser = argparse.ArgumentParser(
description='Implement basic public ECR lifecycle policy')
parser.add_argument('--repo', dest='repositoryName', action='store', required=True,
help='Name of the public ECR repository')
parser.add_argument('--keep', dest='keep', action='store', default=10, type=int,
help='number of tagged images to keep, default 10')
parser.add_argument('--dev', dest='delete_dev', action='store_true',
help='also delete in-development images only having tags like v0.1.1-commitNr-githash')
args = parser.parse_args()
client = boto3.client('ecr-public', region_name='us-east-1')
images = client.describe_images(repositoryName=args.repositoryName)[
"imageDetails"]
untagged = []
kept = 0
# actual Image
# imageManifestMediaType: 'application/vnd.oci.image.manifest.v1+json'
# image Index
# imageManifestMediaType: 'application/vnd.oci.image.index.v1+json'
# Sort by date uploaded
for image in sorted(images, key=lambda d: d['imagePushedAt'], reverse=True):
# Remove all untagged
# if registry uses image index all actual images will be untagged anyways
if 'imageTags' not in image:
untagged.append({"imageDigest": image['imageDigest']})
# print("Delete untagged image {}".format(image["imageDigest"]))
continue
# check for dev tags
if args.delete_dev:
_delete = True
for tag in image["imageTags"]:
# Look for at least one tag NOT beign a SemVer dev tag
if "-" not in tag:
_delete = False
if _delete:
print("Deleting development image {}".format(image["imageTags"]))
untagged.append({"imageDigest": image['imageDigest']})
continue
if kept < args.keep:
kept = kept+1
print("Keeping tagged image {}".format(image["imageTags"]))
continue
else:
print("Deleting tagged image {}".format(image["imageTags"]))
untagged.append({"imageDigest": image['imageDigest']})
deleted_images = client.batch_delete_image(
repositoryName=args.repositoryName, imageIds=untagged)
if deleted_images["imageIds"]:
print("Deleted images: {}".format(deleted_images["imageIds"]))

View File

@ -1,84 +1,56 @@
# Parse version from latest git semver tag
GIT_TAG ?= $(shell git describe --tags --match v*.*.* 2>/dev/null || git rev-parse --short HEAD 2>/dev/null)
GIT_BRANCH ?= $(shell git rev-parse --abbrev-ref HEAD 2>/dev/null)
GTAG=$(shell git describe --tags --match v*.*.* 2>/dev/null || git rev-parse --short HEAD 2>/dev/null)
TAG ?= $(shell echo $(GTAG) | awk -F '-' '{ print $$1 "-" $$2 }' | sed -e 's/-$$//')
TAG ::= $(GIT_TAG)
# append branch name to tag if NOT main nor master
ifeq (,$(filter main master, $(GIT_BRANCH)))
# If branch is substring of tag, omit branch name
ifeq ($(findstring $(GIT_BRANCH), $(GIT_TAG)),)
# only append branch name if not equal tag
ifneq ($(GIT_TAG), $(GIT_BRANCH))
# Sanitize GIT_BRANCH to allowed Docker tag character set
TAG = $(GIT_TAG)-$(shell echo $$GIT_BRANCH | sed -e 's/[^a-zA-Z0-9]/-/g')
endif
endif
ifeq ($(TRIVY_REMOTE),)
TRIVY_OPTS := image
else
TRIVY_OPTS := client --remote ${TRIVY_REMOTE}
endif
ARCH ::= amd64
ALL_ARCHS ::= amd64 arm64
_ARCH = $(or $(filter $(ARCH),$(ALL_ARCHS)),$(error $$ARCH [$(ARCH)] must be exactly one of "$(ALL_ARCHS)"))
.PHONY: build test scan push clean
ifneq ($(TRIVY_REMOTE),)
TRIVY_OPTS ::= --server $(TRIVY_REMOTE)
endif
all: test
.SILENT: ; # no need for @
.ONESHELL: ; # recipes execute in same shell
.NOTPARALLEL: ; # wait for this target to finish
.EXPORT_ALL_VARIABLES: ; # send all vars to shell
.PHONY: all # All targets are accessible for user
.DEFAULT: help # Running Make will run the help target
help: ## Show Help
grep -E '^[a-zA-Z_-]+:.*?## .*$$' .ci/podman.mk | awk 'BEGIN {FS = ":.*?## "}; {printf "\033[36m%-30s\033[0m %s\n", $$1, $$2}'
build:
@docker image exists $(IMAGE):$(TAG) || \
docker build --rm -t $(IMAGE):$(TAG) --build-arg TAG=$(TAG) .
prepare:: ## custom step on the build agent before building
test: build rm-test-image
@test -f Dockerfile.test && \
{ docker build --rm -t $(IMAGE):$(TAG)-test --from=$(IMAGE):$(TAG) -f Dockerfile.test . && \
docker run --rm --env-host -t $(IMAGE):$(TAG)-test; } || \
echo "No Dockerfile.test found, skipping test"
fmt:: ## auto format source
scan: build
@echo "Scanning $(IMAGE):$(TAG) using Trivy"
@trivy $(TRIVY_OPTS) $(IMAGE):$(TAG)
lint:: ## Lint source
push: build
@aws ecr-public get-login-password --region $(REGION) | docker login --username AWS --password-stdin $(REGISTRY)
@docker tag $(IMAGE):$(TAG) $(REGISTRY)/$(IMAGE):$(TAG) $(REGISTRY)/$(IMAGE):latest
docker push $(REGISTRY)/$(IMAGE):$(TAG)
docker push $(REGISTRY)/$(IMAGE):latest
build: ## Build the app
buildah build --rm --layers -t $(IMAGE):$(TAG)-$(_ARCH) --build-arg TAG=$(TAG) --build-arg ARCH=$(_ARCH) --platform linux/$(_ARCH) .
clean: rm-test-image rm-image
test:: ## test built artificats
scan: ## Scan image using trivy
echo "Scanning $(IMAGE):$(TAG)-$(_ARCH) using Trivy $(TRIVY_REMOTE)"
trivy image $(TRIVY_OPTS) --quiet --no-progress localhost/$(IMAGE):$(TAG)-$(_ARCH)
# first tag and push all actual images
# create new manifest for each tag and add all available TAG-ARCH before pushing
push: ecr-login ## push images to registry
for t in $(TAG) latest $(EXTRA_TAGS); do \
echo "Tagging image with $(REGISTRY)/$(IMAGE):$${t}-$(ARCH)"
buildah tag $(IMAGE):$(TAG)-$(_ARCH) $(REGISTRY)/$(IMAGE):$${t}-$(_ARCH); \
buildah manifest rm $(IMAGE):$$t || true; \
buildah manifest create $(IMAGE):$$t; \
for a in $(ALL_ARCHS); do \
buildah manifest add $(IMAGE):$$t $(REGISTRY)/$(IMAGE):$(TAG)-$$a; \
done; \
echo "Pushing manifest $(IMAGE):$$t"
buildah manifest push --all $(IMAGE):$$t docker://$(REGISTRY)/$(IMAGE):$$t; \
done
ecr-login: ## log into AWS ECR public
aws ecr-public get-login-password --region $(REGION) | podman login --username AWS --password-stdin $(REGISTRY)
rm-remote-untagged: ## delete all remote untagged and in-dev images, keep 10 tagged
echo "Removing all untagged and in-dev images from $(IMAGE) in $(REGION)"
.ci/ecr_public_lifecycle.py --repo $(IMAGE) --dev
clean:: ## clean up source folder
# Delete all untagged images
.PHONY: rm-remote-untagged
rm-remote-untagged:
@echo "Removing all untagged images from $(IMAGE) in $(REGION)"
@aws ecr-public batch-delete-image --repository-name $(IMAGE) --region $(REGION) --image-ids $$(for image in $$(aws ecr-public describe-images --repository-name $(IMAGE) --region $(REGION) --output json | jq -r '.imageDetails[] | select(.imageTags | not ).imageDigest'); do echo -n "imageDigest=$$image "; done)
.PHONY: rm-image
rm-image:
test -z "$$(podman image ls -q $(IMAGE):$(TAG)-$(_ARCH))" || podman image rm -f $(IMAGE):$(TAG)-$(_ARCH) > /dev/null
test -z "$$(podman image ls -q $(IMAGE):$(TAG)-$(_ARCH))" || echo "Error: Removing image failed"
@test -z "$$(docker image ls -q $(IMAGE):$(TAG))" || docker image rm -f $(IMAGE):$(TAG) > /dev/null
@test -z "$$(docker image ls -q $(IMAGE):$(TAG))" || echo "Error: Removing image failed"
## some useful tasks during development
ci-pull-upstream: ## pull latest shared .ci subtree
git subtree pull --prefix .ci ssh://git@git.zero-downtime.net/ZeroDownTime/ci-tools-lib.git master --squash -m "Merge latest ci-tools-lib"
# Ensure we run the tests by removing any previous runs
.PHONY: rm-test-image
rm-test-image:
@test -z "$$(docker image ls -q $(IMAGE):$(TAG)-test)" || docker image rm -f $(IMAGE):$(TAG)-test > /dev/null
@test -z "$$(docker image ls -q $(IMAGE):$(TAG)-test)" || echo "Error: Removing test image failed"
create-repo: ## create new AWS ECR public repository
aws ecr-public create-repository --repository-name $(IMAGE) --region $(REGION)
.DEFAULT:
@echo "$@ not implemented. NOOP"

View File

@ -2,33 +2,24 @@
def call(Map config=[:]) {
pipeline {
options {
disableConcurrentBuilds()
}
agent {
node {
label 'podman-aws-trivy'
}
}
stages {
stage('Prepare') {
// get tags
steps {
sh 'mkdir -p reports'
// we set pull tags as project adv. options
// pull tags
//withCredentials([gitUsernamePassword(credentialsId: 'gitea-jenkins-user')]) {
// sh 'git fetch -q --tags ${GIT_URL}'
//}
// Optional project specific preparations
sh 'make prepare'
sh 'git fetch -q --tags ${GIT_URL} +refs/heads/${BRANCH_NAME}:refs/remotes/origin/${BRANCH_NAME}'
}
}
// Build using rootless podman
stage('Build') {
steps {
sh 'make build GIT_BRANCH=$GIT_BRANCH'
sh 'make build'
}
}
@ -40,13 +31,13 @@ def call(Map config=[:]) {
// Scan via trivy
stage('Scan') {
environment {
TRIVY_FORMAT = "template"
TRIVY_OUTPUT = "reports/trivy.html"
}
steps {
// we always scan and create the full json report
sh 'TRIVY_FORMAT=json TRIVY_OUTPUT="reports/trivy.json" make scan'
// render custom full html report
sh 'trivy convert -f template -t @/home/jenkins/html.tpl -o reports/trivy.html reports/trivy.json'
sh 'mkdir -p reports'
sh 'make scan'
publishHTML target: [
allowMissing: true,
alwaysLinkToLastBuild: true,
@ -56,33 +47,25 @@ def call(Map config=[:]) {
reportName: 'TrivyScan',
reportTitles: 'TrivyScan'
]
sh 'echo "Trivy report at: $BUILD_URL/TrivyScan"'
// fail build if issues found above trivy threshold
// Scan again and fail on CRITICAL vulns, if not overridden
script {
if ( config.trivyFail ) {
sh "TRIVY_SEVERITY=${config.trivyFail} trivy convert --report summary --exit-code 1 reports/trivy.json"
if (config.trivyFail == 'NONE') {
echo 'trivyFail == NONE, review Trivy report manually. Proceeding ...'
} else {
sh "TRIVY_EXIT_CODE=1 TRIVY_SEVERITY=${config.trivyFail} make scan"
}
}
}
}
// Push to container registry if not PR
// incl. basic registry retention removing any untagged images
// Push to ECR
stage('Push') {
when { not { changeRequest() } }
steps {
sh 'make push'
sh 'make rm-remote-untagged'
}
}
// generic clean
stage('cleanup') {
steps {
sh 'make clean'
}
}
}
}
}

2
.gitignore vendored
View File

@ -59,5 +59,3 @@ reports/
# virtualenv
venv/
ENV/
aws-lambda-rie

View File

@ -1,16 +1,13 @@
# https://aws.amazon.com/blogs/aws/new-for-aws-lambda-container-image-support/
# libexec is missing from >=3.17
ARG RUNTIME_VERSION="3.9"
ARG DISTRO_VERSION="3.15"
# Stage 1 - bundle base image + runtime
FROM python:3.12-alpine3.19 AS python-alpine
ARG ALPINE="v3.19"
FROM python:${RUNTIME_VERSION}-alpine${DISTRO_VERSION} AS python-alpine
# Install GCC (Alpine uses musl but we compile and link dependencies with GCC)
RUN echo "@kubezero https://cdn.zero-downtime.net/alpine/${ALPINE}/kubezero" >> /etc/apk/repositories && \
wget -q -O /etc/apk/keys/stefan@zero-downtime.net-61bb6bfb.rsa.pub https://cdn.zero-downtime.net/alpine/stefan@zero-downtime.net-61bb6bfb.rsa.pub
RUN apk -U --no-cache upgrade && \
apk --no-cache add \
RUN apk upgrade -U --available --no-cache && \
apk add --no-cache \
libstdc++
@ -19,17 +16,18 @@ FROM python-alpine AS build-image
ARG TAG="latest"
# Install aws-lambda-cpp build dependencies
RUN apk --no-cache add \
RUN apk upgrade -U --available --no-cache && \
apk add --no-cache \
build-base \
libtool \
autoconf \
automake \
libexecinfo-dev \
make \
cmake \
libcurl \
libffi-dev \
openssl-dev \
libexecinfo-dev@kubezero
openssl-dev
# cargo
# Install requirements
@ -40,7 +38,7 @@ RUN export MAKEFLAGS="-j$(nproc)" && \
# Install our app
COPY app.py /app
# Set internal __version__ to our own container TAG
# Ser version to our TAG
RUN sed -i -e "s/^__version__ =.*/__version__ = \"${TAG}\"/" /app/app.py
# Stage 3 - final runtime image

26
Dockerfile.test Normal file
View File

@ -0,0 +1,26 @@
FROM setviacmdline:latest
# Install additional tools for tests
COPY dev-requirements.txt .flake8 .
RUN export MAKEFLAGS="-j$(nproc)" && \
pip install -r dev-requirements.txt
# Unit Tests / Static / Style etc.
COPY tests/ tests/
RUN flake8 app.py tests && \
codespell app.py tests
# Get aws-lambda run time emulator
ADD https://github.com/aws/aws-lambda-runtime-interface-emulator/releases/latest/download/aws-lambda-rie /usr/local/bin/aws-lambda-rie
RUN chmod 0755 /usr/local/bin/aws-lambda-rie && \
mkdir -p tests
# Install pytest
RUN pip install pytest --target /app
# Add our tests
ADD tests /app/tests
# Run tests
ENTRYPOINT []
CMD [ "/usr/local/bin/python", "-m", "pytest", "tests", "--capture=tee-sys" ]

View File

@ -3,21 +3,3 @@ IMAGE := sns-alert-hub
REGION := us-east-1
include .ci/podman.mk
SOURCE := app.py tests/test_aws-lambda-rie.py
test:: aws-lambda-rie
./run_tests.sh "$(IMAGE):$(TAG)-$(_ARCH)"
fmt::
autopep8 -i -a $(SOURCE)
lint::
flake8 $(SOURCE)
codespell $(SOURCE)
clean::
rm -rf .pytest_cache __pycache__ aws-lambda-rie
aws-lambda-rie:
wget https://github.com/aws/aws-lambda-runtime-interface-emulator/releases/latest/download/aws-lambda-rie && chmod 0755 aws-lambda-rie

View File

@ -3,10 +3,6 @@
## Abstract
AWS SNS/Lambda central alert hub taking SNS messages, parsing and formatting them before sending them to any messaging service, like Slack, Matrix, etc
## Tests
All env variables are forwarded into the test container.
Simply set WEBHOOK_URL accordingly before running `make test`.
## Resources
- https://gallery.ecr.aws/zero-downtime/sns-alert-hub
- https://github.com/caronc/apprise

92
app.py
View File

@ -39,8 +39,7 @@ else:
# Ensure slack URLs use ?blocks=yes
if "slack.com" in WEBHOOK_URL:
scheme, netloc, path, query_string, fragment = urllib.parse.urlsplit(
WEBHOOK_URL)
scheme, netloc, path, query_string, fragment = urllib.parse.urlsplit(WEBHOOK_URL)
query_params = urllib.parse.parse_qs(query_string)
query_params["blocks"] = ["yes"]
new_query_string = urllib.parse.urlencode(query_params, doseq=True)
@ -57,8 +56,7 @@ asset.app_url = "https://zero-downtime.net"
asset.image_url_mask = (
"https://cdn.zero-downtime.net/assets/zdt/apprise/{TYPE}-{XY}{EXTENSION}"
)
asset.app_id = "{} / {} {}".format("cloudbender",
__version__, "zero-downtime.net")
asset.app_id = "{} / {} {}".format("cloudbender", __version__, "zero-downtime.net")
apobj = apprise.Apprise(asset=asset)
apobj.add(WEBHOOK_URL)
@ -98,16 +96,11 @@ def handler(event, context):
msg = {}
pass
body = ""
title = ""
msg_type = apprise.NotifyType.INFO
# CloudWatch Alarm ?
if "AlarmName" in msg:
title = "AWS Cloudwatch Alarm"
# Discard NewStateValue == OK && OldStateValue == INSUFFICIENT_DATA as
# these are triggered by installing new Alarms and only cause confusion
# Discard NewStateValue == OK && OldStateValue == INSUFFICIENT_DATA as these are triggered by installing new Alarms and only cause confusion
if msg["NewStateValue"] == "OK" and msg["OldStateValue"] == "INSUFFICIENT_DATA":
logger.info(
"Discarding Cloudwatch Metrics Alarm as state is OK and previous state was insufficient data, most likely new alarm being installed"
@ -140,12 +133,13 @@ def handler(event, context):
pass
body = body + "\n\n_{}_".format(msg_context)
apobj.notify(body=body, title=title, notify_type=msg_type)
elif "Source" in msg and msg["Source"] == "CloudBender":
title = "AWS EC2 - CloudBender"
try:
msg_context = "{account} - {region} - {host} ({instance}) <https://{region}.console.aws.amazon.com/ec2/home?region={region}#AutoScalingGroupDetails:id={asg};view=activity|{artifact} ASG>".format(
msg_context = "{account} - {region} - {host} ({instance}) <https://{region}.console.aws.amazon.com/ec2/autoscaling/home?region={region}#AutoScalingGroups:id={asg};view=history|{artifact} ASG>".format(
account=get_alias(msg["AWSAccountId"]),
region=msg["Region"],
asg=msg["Asg"],
@ -181,6 +175,7 @@ def handler(event, context):
body = body + "\n```{}```".format(msg["Attachment"])
body = body + "\n\n_{}_".format(msg_context)
apobj.notify(body=body, title=title, notify_type=msg_type)
elif "receiver" in msg and msg["receiver"] == "alerthub-notifications":
@ -239,74 +234,13 @@ def handler(event, context):
except KeyError:
pass
# ElasticCache snapshot notifications
elif "ElastiCache:SnapshotComplete" in msg:
title = "ElastiCache Snapshot complete."
body = "Snapshot taken on {}".format(
msg["ElastiCache:SnapshotComplete"])
# ElasticCache replacement notifications
elif "ElastiCache:NodeReplacementScheduled" in msg:
title = "ElastiCache node replacement scheduled"
body = "{} will be replaced between {} and {}".format(
msg["ElastiCache:NodeReplacementScheduled"], msg["Start Time"], msg["End Time"])
# ElasticCache replacement notifications
elif "ElastiCache:CacheNodeReplaceStarted" in msg:
title = "ElastiCache fail over stareted"
body = "for node {}".format(msg["ElastiCache:CacheNodeReplaceStarted"])
# ElasticCache replacement notifications
elif "ElastiCache:FailoverComplete" in msg:
title = "ElastiCache fail over complete"
body = "for node {}".format(msg["ElastiCache:FailoverComplete"])
# ElasticCache update notifications
elif "ElastiCache:ServiceUpdateAvailableForNode" in msg:
title = "ElastiCache update available"
body = "for node {}".format(msg["ElastiCache:ServiceUpdateAvailableForNode"])
elif "ElastiCache:ServiceUpdateAvailable" in msg:
title = "ElastiCache update available"
body = "for Group {}".format(msg["ElastiCache:ServiceUpdateAvailable"])
# known RDS events
elif "Event Source" in msg and msg['Event Source'] in ["db-instance", "db-cluster-snapshot", "db-snapshot"]:
try:
title = msg["Event Message"]
try:
name = " ({}).".format(
msg["Tags"]["Name"])
except (KeyError, IndexError):
name = ""
body = "RDS {}: <{}|{}>{}\n<{}|Event docs>".format(msg["Event Source"].replace("db-", ""),
msg["Identifier Link"], msg["Source ID"], name, msg["Event ID"])
except KeyError:
msg_type = apprise.NotifyType.WARNING
body = sns["Message"]
pass
# Basic ASG events
elif "Event" in msg and msg["Event"] in ["autoscaling:EC2_INSTANCE_TERMINATE", "autoscaling:EC2_INSTANCE_LAUNCH"]:
title = msg["Description"]
body = msg["Cause"]
try:
msg_context = "{account} - {region} - <https://{region}.console.aws.amazon.com/ec2/home?region={region}#AutoScalingGroupDetails:id={asg};view=activity|{asg} ASG>".format(
region=region,
account=get_alias(msg["AccountId"]),
asg=msg["AutoScalingGroupName"],
)
body = body + "\n\n_{}_".format(msg_context)
except KeyError:
pass
# Finally send each parsed alert
apobj.notify(body=body, title=title, notify_type=msg_type)
else:
title = "Unknown message type"
msg_type = apprise.NotifyType.WARNING
body = sns["Message"]
if not apobj.notify(body=body, title=title, notify_type=msg_type):
logger.error("Error during notify!")
apobj.notify(
body=body,
title="Unknown message type",
notify_type=apprise.NotifyType.WARNING,
)

View File

@ -1,4 +1,3 @@
pytest
autopep8
flake8
codespell

View File

@ -1,10 +0,0 @@
{
"$schema": "https://docs.renovatebot.com/renovate-schema.json",
"extends": [
"config:recommended",
":label(renovate)",
":semanticCommits",
"group:allNonMajor"
],
"prHourlyLimit": 0
}

View File

@ -1,4 +1,4 @@
boto3==1.34.84
apprise==1.7.6
humanize==4.9.0
awslambdaric==2.0.11
boto3
apprise
humanize
awslambdaric

View File

@ -1,17 +0,0 @@
#!/bin/sh -ex
IMAGE=$1
ctr=$(buildah from $IMAGE)
trap "buildah rm $ctr" EXIT
buildah copy $ctr dev-requirements.txt .flake8 .
buildah copy $ctr aws-lambda-rie
buildah copy $ctr tests/ tests/
buildah run $ctr pip install -r dev-requirements.txt --target .
buildah run $ctr python -m flake8 app.py
buildah run $ctr python -m codespell_lib app.py
buildah run $ctr python -m pytest tests -c tests/pytest.ini --capture=tee-sys

View File

@ -9,13 +9,8 @@ from requests.packages.urllib3.util.retry import Retry
s = requests.Session()
retries = Retry(
total=3,
backoff_factor=1,
status_forcelist=[
502,
503,
504],
allowed_methods="POST")
total=3, backoff_factor=1, status_forcelist=[502, 503, 504], allowed_methods="POST"
)
s.mount("http://", HTTPAdapter(max_retries=retries))
@ -23,7 +18,7 @@ class Test:
@classmethod
def setup_class(cls):
cls.p = subprocess.Popen(
"./aws-lambda-rie python -m awslambdaric app.handler", shell=True
"aws-lambda-rie python -m awslambdaric app.handler", shell=True
)
@classmethod
@ -65,54 +60,3 @@ class Test:
r' { "Records": [ { "EventSource": "aws:sns", "EventVersion": "1.0", "EventSubscriptionArn": "arn:aws:sns:eu-central-1:123456789012:AlertHub:0e7ce1ba-c3e4-4264-bae1-4eb71c91235a", "Sns": { "Type": "Notification", "MessageId": "10ae86eb-9ddc-5c2f-806c-df6ecb6bde42", "TopicArn": "arn:aws:sns:eu-central-1:123456789012:AlertHub", "Subject": null, "Message": "{\"receiver\":\"alerthub-notifications\",\"status\":\"resolved\",\"alerts\":[{\"status\":\"resolved\",\"labels\":{\"alertname\":\"KubeDeploymentReplicasMismatch\",\"awsAccount\":\"123456789012\",\"awsRegion\":\"us-west-2\",\"clusterName\":\"test-cluster\",\"container\":\"kube-state-metrics\",\"deployment\":\"example-job\",\"endpoint\":\"http\",\"instance\":\"10.244.202.71:8080\",\"job\":\"kube-state-metrics\",\"namespace\":\"default\",\"pod\":\"metrics-kube-state-metrics-56546f44c7-h57jx\",\"prometheus\":\"monitoring/metrics-kube-prometheus-st-prometheus\",\"service\":\"metrics-kube-state-metrics\",\"severity\":\"warning\"},\"annotations\":{\"description\":\"Deployment default/example-job has not matched the expected number of replicas for longer than 15 minutes.\",\"runbook_url\":\"https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedeploymentreplicasmismatch\",\"summary\":\"Deployment has not matched the expected number of replicas.\"},\"startsAt\":\"2021-09-29T12:36:11.394Z\",\"endsAt\":\"2021-09-29T14:51:11.394Z\",\"generatorURL\":\"https://prometheus.dev.example.com/graph?g0.expr=%28kube_deployment_spec_replicas%7Bjob%3D%22kube-state-metrics%22%7D+%3E+kube_deployment_status_replicas_available%7Bjob%3D%22kube-state-metrics%22%7D%29+and+%28changes%28kube_deployment_status_replicas_updated%7Bjob%3D%22kube-state-metrics%22%7D%5B10m%5D%29+%3D%3D+0%29\\u0026g0.tab=1\",\"fingerprint\":\"59ad2f1a4567b43b\"},{\"status\":\"firing\",\"labels\":{\"alertname\":\"KubeVersionMismatch\",\"awsRegion\":\"eu-central-1\",\"clusterName\":\"test\",\"prometheus\":\"monitoring/metrics-kube-prometheus-st-prometheus\",\"severity\":\"warning\"},\"annotations\":{\"description\":\"There are 2 different semantic versions of Kubernetes components running.\",\"runbook_url\":\"https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeversionmismatch\",\"summary\":\"Different semantic versions of Kubernetes components running.\"},\"startsAt\":\"2021-08-04T13:17:40.31Z\",\"endsAt\":\"0001-01-01T00:00:00Z\",\"generatorURL\":\"https://prometheus/graph?g0.expr=count%28count+by%28git_version%29+%28label_replace%28kubernetes_build_info%7Bjob%21~%22kube-dns%7Ccoredns%22%7D%2C+%22git_version%22%2C+%22%241%22%2C+%22git_version%22%2C+%22%28v%5B0-9%5D%2A.%5B0-9%5D%2A%29.%2A%22%29%29%29+%3E+1\\u0026g0.tab=1\",\"fingerprint\":\"5f94d4a22730c666\"}],\"groupLabels\":{\"job\":\"kube-state-metrics\"},\"commonLabels\":{\"alertname\":\"KubeDeploymentReplicasMismatch\",\"awsAccount\":\"123456789012\",\"awsRegion\":\"us-west-2\",\"clusterName\":\"test-cluster\",\"container\":\"kube-state-metrics\",\"deployment\":\"example-job\",\"endpoint\":\"http\",\"instance\":\"10.244.202.71:8080\",\"job\":\"kube-state-metrics\",\"namespace\":\"default\",\"pod\":\"metrics-kube-state-metrics-56546f44c7-h57jx\",\"prometheus\":\"monitoring/metrics-kube-prometheus-st-prometheus\",\"service\":\"metrics-kube-state-metrics\",\"severity\":\"warning\"},\"commonAnnotations\":{\"description\":\"Deployment default/example-job has not matched the expected number of replicas for longer than 15 minutes.\",\"runbook_url\":\"https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedeploymentreplicasmismatch\",\"summary\":\"Deployment has not matched the expected number of replicas.\"},\"externalURL\":\"https://alertmanager.dev.example.com\",\"version\":\"4\",\"groupKey\":\"{}:{job=\\\"kube-state-metrics\\\"}\",\"truncatedAlerts\":0}\n", "Timestamp": "2021-08-05T03:01:11.233Z", "SignatureVersion": "1", "Signature": "pSUYO7LDIfzCbBrp/S2HXV3/yzls3vfYy+2di6HsKG8Mf+CV97RLnen15ieAo3eKA8IfviZIzyREasbF0cwfUeruHPbW1B8kO572fDyV206zmUxvR63r6oM6OyLv9XKBmvyYHKawkOgHZHEMP3v1wMIIHK2W5KbJtXoUcks5DVamooVb9iFF58uqTf+Ccy31bOL4tFyMR9nr8NU55vEIlGEVno8A9Q21TujdZTg0V0BmRgPafcic96udWungjmfhZ005378N32u2hlLj6BRneTpHHSXHBw4wKZreKpX+INZwiZ4P8hzVfgRvAIh/4gXN9+0UJSHgnsaqUcLDNoLZTQ==", "SigningCertUrl": "https://sns.eu-central-1.amazonaws.com/SimpleNotificationService-010a507c1833636cd94bdb98bd93083a.pem", "UnsubscribeUrl": "https://sns.eu-central-1.amazonaws.com/?Action=Unsubscribe&SubscriptionArn=arn:aws:sns:eu-central-1:123456789012:AlertHub:0e7ce1ba-c3e4-4264-bae1-4eb71c91235a", "MessageAttributes": {} } } ] }'
)
self.send_event(event)
# ElastiCache snaphshot
def test_elasticache_snapshot(self):
event = json.loads(
r' {"Records": [{"EventSource": "aws:sns", "EventVersion": "1.0", "EventSubscriptionArn": "arn:aws:sns:eu-central-1:123456789012:AlertHub:0e7ce1ba-c3e4-4264-bae1-4eb71c91235a", "Sns": {"Type": "Notification", "MessageId": "10ae86eb-9ddc-5c2f-806c-df6ecb6bde42", "TopicArn": "arn:aws:sns:eu-central-1:123456789012:AlertHub", "Subject": null, "Message": "{\"ElastiCache:SnapshotComplete\":\"redis-prod-0002-001\"}" }}]}'
)
self.send_event(event)
# RDS
def test_rds_event(self):
event = json.loads(
r''' {
"Records": [
{
"EventSource": "aws:sns",
"EventVersion": "1.0",
"EventSubscriptionArn": "arn:aws:sns:us-west-2:123456789012:AlertHub:63470449-620d-44ce-971f-ad9582804b13",
"Sns": {
"Type": "Notification",
"MessageId": "ef1f821c-a04f-5c5c-9dff-df498532069b",
"TopicArn": "arn:aws:sns:us-west-2:123456789012:AlertHub",
"Subject": "RDS Notification Message",
"Message": "{\"Event Source\":\"db-cluster-snapshot\",\"Event Time\":\"2023-08-15 07:03:24.491\",\"Identifier Link\":\"https://console.aws.amazon.com/rds/home?region=us-west-2#snapshot:engine=aurora;id=rds:projectdb-cluster-2023-08-15-07-03\",\"Source ID\":\"rds:projectdb-cluster-2023-08-15-07-03\",\"Source ARN\":\"arn:aws:rds:us-west-2:123456789012:cluster-snapshot:rds:projectdb-cluster-2023-08-15-07-03\",\"Event ID\":\"http://docs.aws.amazon.com/AmazonRDS/latest/UserGuide/USER_Events.Messages.html#RDS-EVENT-0168\",\"Event Message\":\"Creating automated cluster snapshot\",\"Tags\":{}}",
"Timestamp": "2023-08-15T07:03:25.289Z",
"SignatureVersion": "1",
"Signature": "mRtx+ddS1uzF3alGDWnDtUkAz+Gno8iuv0wPwkeBJPe1LAcKTXVteYhQdP2BB5ZunPlWXPSDsNtFl8Eh6v4/fcdukxH/czc6itqgGiciQ3DCICLvOJrvrVVgsVvHgOA/Euh8wryzxeQ3HJ/nmF9sg/PtuKyxvGxyO7NSFJrRKkqwkuG1Wr/8gcN3nrenqNTzKiC16kzVuKISWgXM1jqbsleQ4MyBcjq61LRwODKB8tc8vJ6PLGOs4Lrc3qeruCqF3Tzpl43680RsaRBBn1SLycwFVdB1kpHSXuk+YJQ6BS7s6rbMoyhPOpSCFHMZXC/eEb09wTzgpop0KDE/koiUsg==",
"SigningCertUrl": "https://sns.us-west-2.amazonaws.com/SimpleNotificationService-01d088a6f77103d0fe307c0069e40ed6.pem",
"UnsubscribeUrl": "https://sns.us-west-2.amazonaws.com/?Action=Unsubscribe&SubscriptionArn=arn:aws:sns:us-west-2:123456789012:AlertHub:63470449-620d-44ce-971f-ad9582804b13",
"MessageAttributes": {
"Resource": {
"Type": "String",
"Value": "arn:aws:rds:us-west-2:123456789012:cluster-snapshot:rds:projectdb-cluster-2023-08-15-07-03"
},
"EventID": {
"Type": "String",
"Value": "RDS-EVENT-0168"
}
}
}
}
]
}
'''
)
self.send_event(event)
def test_asg(self):
event = json.loads(
r' {"Records": [{"EventSource": "aws:sns", "EventVersion": "1.0", "EventSubscriptionArn": "arn:aws:sns:eu-central-1:123456789012:AlertHub:0e7ce1ba-c3e4-4264-bae1-4eb71c91235a", "Sns": {"Type": "Notification", "MessageId": "10ae86eb-9ddc-5c2f-806c-df6ecb6bde42", "TopicArn": "arn:aws:sns:eu-central-1:123456789012:AlertHub", "Subject": null, "Message": "{\"Origin\":\"AutoScalingGroup\",\"Destination\":\"EC2\",\"Progress\":50,\"AccountId\":\"123456789012\",\"Description\":\"Terminating EC2 instance: i-023ca42b188ffd91d\",\"RequestId\":\"1764cac3-224b-46bf-8bed-407a5b868e63\",\"EndTime\":\"2023-05-15T08:51:16.195Z\",\"AutoScalingGroupARN\":\"arn:aws:autoscaling:us-west-2:123456789012:autoScalingGroup:4a4fb6e3-22b4-487b-8335-3904f02ff9fd:autoScalingGroupName/powerbi\",\"ActivityId\":\"1764cac3-224b-46bf-8bed-407a5b868e63\",\"StartTime\":\"2023-05-15T08:50:14.145Z\",\"Service\":\"AWS Auto Scaling\",\"Time\":\"2023-05-15T08:51:16.195Z\",\"EC2InstanceId\":\"i-023ca42b188ffd91d\",\"StatusCode\":\"InProgress\",\"StatusMessage\":\"\",\"Details\":{\"Subnet ID\":\"subnet-fe2d6189\",\"Availability Zone\":\"us-west-2a\"},\"AutoScalingGroupName\":\"powerbi\",\"Cause\":\"At 2023-05-15T08:50:03Z the scheduled action end executed. Setting min size from 1 to 0. Setting desired capacity from 1 to 0. At 2023-05-15T08:50:03Z a scheduled action update of AutoScalingGroup constraints to min: 0, max: 1, desired: 0 changing the desired capacity from 1 to 0. At 2023-05-15T08:50:13Z an instance was taken out of service in response to a difference between desired and actual capacity, shrinking the capacity from 1 to 0. At 2023-05-15T08:50:14Z instance i-023ca42b188ffd91d was selected for termination.\",\"Event\":\"autoscaling:EC2_INSTANCE_TERMINATE\"}" }}]}'
)
self.send_event(event)