Release v0.13.1

Fix NGINX promql and custom metrics checks

.circleci/config.yml

@@ -0,0 +1,38 @@
+version: 2.1
+jobs:
+  e2e-testing:
+    machine: true
+    steps:
+      - checkout
+      - run: test/e2e-kind.sh
+      - run: test/e2e-istio.sh
+      - run: test/e2e-build.sh
+      - run: test/e2e-tests.sh
+
+  e2e-supergloo-testing:
+    machine: true
+    steps:
+      - checkout
+      - run: test/e2e-kind.sh
+      - run: test/e2e-supergloo.sh
+      - run: test/e2e-build.sh supergloo:test.supergloo-system
+      - run: test/e2e-tests.sh canary
+
+workflows:
+  version: 2
+  build-and-test:
+    jobs:
+      - e2e-testing:
+          filters:
+            branches:
+              ignore:
+                - /gh-pages.*/
+                - /docs-.*/
+                - /release-.*/
+      - e2e-supergloo-testing:
+          filters:
+            branches:
+              ignore:
+                - /gh-pages.*/
+                - /docs-.*/
+                - /release-.*/

.codecov.yml

@@ -6,3 +6,6 @@ coverage:
         threshold: 50
         base: auto
     patch: off
+
+comment:
+  require_changes: yes

.github/CODEOWNERS

@@ -0,0 +1 @@
+*   @stefanprodan

.github/main.workflow

@@ -0,0 +1,17 @@
+workflow "Publish Helm charts" {
+  on = "push"
+  resolves = ["helm-push"]
+}
+
+action "helm-lint" {
+  uses = "stefanprodan/gh-actions/helm@master"
+  args = ["lint charts/*"]
+}
+
+action "helm-push" {
+  needs = ["helm-lint"]
+  uses = "stefanprodan/gh-actions/helm-gh-pages@master"
+  args = ["charts/*","https://flagger.app"]
+  secrets = ["GITHUB_TOKEN"]
+}
+

.gitignore

@@ -11,3 +11,7 @@
 # Output of the go coverage tool, specifically when used with LiteIDE
 *.out
 .DS_Store
+
+bin/
+artifacts/gcloud/
+.idea

.goreleaser.yml

@@ -1,7 +1,7 @@
 builds:
   - main: ./cmd/flagger
     binary: flagger
-    ldflags: -s -w -X github.com/stefanprodan/flagger/pkg/version.REVISION={{.Commit}}
+    ldflags: -s -w -X github.com/weaveworks/flagger/pkg/version.REVISION={{.Commit}}
     goos:
       - linux
     goarch:

.travis.yml

@@ -1,8 +1,13 @@
 sudo: required
 language: go
 
+branches:
+  except:
+    - /gh-pages.*/
+    - /docs-.*/
+
 go:
-- 1.11.x
+- 1.12.x
 
 services:
 - docker
@@ -13,26 +18,26 @@ addons:
     - docker-ce
 
 script:
-- set -e
-- make test-fmt
-- make test-codegen
-- go test -race -coverprofile=coverage.txt -covermode=atomic ./pkg/controller/
-- make build
+  - make test-fmt
+  - make test-codegen
+  - go test -race -coverprofile=coverage.txt -covermode=atomic $(go list ./pkg/...)
+  - make build
 
 after_success:
 - if [ -z "$DOCKER_USER" ]; then
     echo "PR build, skipping image push";
   else
-    docker tag stefanprodan/flagger:latest quay.io/stefanprodan/flagger:${TRAVIS_COMMIT};
-    echo $DOCKER_PASS | docker login -u=$DOCKER_USER --password-stdin quay.io;
-    docker push quay.io/stefanprodan/flagger:${TRAVIS_COMMIT};
+    BRANCH_COMMIT=${TRAVIS_BRANCH}-$(echo ${TRAVIS_COMMIT} | head -c7);
+    docker tag weaveworks/flagger:latest weaveworks/flagger:${BRANCH_COMMIT};
+    echo $DOCKER_PASS | docker login -u=$DOCKER_USER --password-stdin;
+    docker push weaveworks/flagger:${BRANCH_COMMIT};
   fi
 - if [ -z "$TRAVIS_TAG" ]; then
     echo "Not a release, skipping image push";
   else
-    docker tag stefanprodan/flagger:latest quay.io/stefanprodan/flagger:${TRAVIS_TAG};
-    echo $DOCKER_PASS | docker login -u=$DOCKER_USER --password-stdin quay.io;
-    docker push quay.io/stefanprodan/flagger:$TRAVIS_TAG;
+    docker tag weaveworks/flagger:latest weaveworks/flagger:${TRAVIS_TAG};
+    echo $DOCKER_PASS | docker login -u=$DOCKER_USER --password-stdin;
+    docker push weaveworks/flagger:$TRAVIS_TAG;
   fi
 - bash <(curl -s https://codecov.io/bash)
 - rm coverage.txt

CHANGELOG.md

@@ -0,0 +1,267 @@
+# Changelog
+
+All notable changes to this project are documented in this file.
+
+## 0.13.1 (2019-04-09) 
+
+Fixes for custom metrics checks and NGINX Prometheus queries 
+
+#### Fixes
+
+- Fix promql queries for custom checks and NGINX [#174](https://github.com/weaveworks/flagger/pull/174)
+
+
+## 0.13.0 (2019-04-08) 
+
+Adds support for [NGINX](https://docs.flagger.app/usage/nginx-progressive-delivery) ingress controller
+
+#### Features
+
+- Add support for nginx ingress controller (weighted traffic and A/B testing) [#170](https://github.com/weaveworks/flagger/pull/170)
+- Add Prometheus add-on to Flagger Helm chart for App Mesh and NGINX [79b3370](https://github.com/weaveworks/flagger/pull/170/commits/79b337089294a92961bc8446fd185b38c50a32df)
+
+#### Fixes
+
+- Fix duplicate hosts Istio error when using wildcards [#162](https://github.com/weaveworks/flagger/pull/162)
+
+## 0.12.0 (2019-04-29) 
+
+Adds support for [SuperGloo](https://docs.flagger.app/install/flagger-install-with-supergloo)
+
+#### Features
+
+- Supergloo support for canary deployment (weighted traffic) [#151](https://github.com/weaveworks/flagger/pull/151)
+
+## 0.11.1 (2019-04-18) 
+
+Move Flagger and the load tester container images to Docker Hub
+
+#### Features
+
+- Add Bash Automated Testing System support to Flagger tester for running acceptance tests as pre-rollout hooks 
+
+## 0.11.0 (2019-04-17) 
+
+Adds pre/post rollout [webhooks](https://docs.flagger.app/how-it-works#webhooks)
+
+#### Features
+
+- Add `pre-rollout` and `post-rollout` webhook types [#147](https://github.com/weaveworks/flagger/pull/147)
+
+#### Improvements 
+
+- Unify App Mesh and Istio builtin metric checks [#146](https://github.com/weaveworks/flagger/pull/146) 
+- Make the pod selector label configurable [#148](https://github.com/weaveworks/flagger/pull/148)
+
+#### Breaking changes
+
+- Set default `mesh` Istio gateway only if no gateway is specified [#141](https://github.com/weaveworks/flagger/pull/141)
+
+## 0.10.0 (2019-03-27) 
+
+Adds support for App Mesh
+
+#### Features
+
+- AWS App Mesh integration
+    [#107](https://github.com/weaveworks/flagger/pull/107)
+    [#123](https://github.com/weaveworks/flagger/pull/123)
+
+#### Improvements 
+
+- Reconcile Kubernetes ClusterIP services [#122](https://github.com/weaveworks/flagger/pull/122) 
+ 
+#### Fixes
+
+- Preserve pod labels on canary promotion [#105](https://github.com/weaveworks/flagger/pull/105)
+- Fix canary status Prometheus metric [#121](https://github.com/weaveworks/flagger/pull/121)
+
+## 0.9.0 (2019-03-11)
+
+Allows A/B testing scenarios where instead of weighted routing, the traffic is split between the 
+primary and canary based on HTTP headers or cookies.
+
+#### Features
+
+- A/B testing - canary with session affinity [#88](https://github.com/weaveworks/flagger/pull/88)
+
+#### Fixes
+
+- Update the analysis interval when the custom resource changes [#91](https://github.com/weaveworks/flagger/pull/91)
+
+## 0.8.0 (2019-03-06)
+
+Adds support for CORS policy and HTTP request headers manipulation
+
+#### Features
+
+- CORS policy support [#83](https://github.com/weaveworks/flagger/pull/83)
+- Allow headers to be appended to HTTP requests [#82](https://github.com/weaveworks/flagger/pull/82)
+
+#### Improvements 
+
+- Refactor the routing management 
+    [#72](https://github.com/weaveworks/flagger/pull/72) 
+    [#80](https://github.com/weaveworks/flagger/pull/80)
+- Fine-grained RBAC [#73](https://github.com/weaveworks/flagger/pull/73)
+- Add option to limit Flagger to a single namespace [#78](https://github.com/weaveworks/flagger/pull/78)
+
+## 0.7.0 (2019-02-28)
+
+Adds support for custom metric checks, HTTP timeouts and HTTP retries
+
+#### Features
+
+- Allow custom promql queries in the canary analysis spec [#60](https://github.com/weaveworks/flagger/pull/60)
+- Add HTTP timeout and retries to canary service spec [#62](https://github.com/weaveworks/flagger/pull/62)
+
+## 0.6.0 (2019-02-25)
+
+Allows for [HTTPMatchRequests](https://istio.io/docs/reference/config/istio.networking.v1alpha3/#HTTPMatchRequest) 
+and [HTTPRewrite](https://istio.io/docs/reference/config/istio.networking.v1alpha3/#HTTPRewrite) 
+to be customized in the service spec of the canary custom resource.
+
+#### Features
+
+- Add HTTP match conditions and URI rewrite to the canary service spec [#55](https://github.com/weaveworks/flagger/pull/55)
+- Update virtual service when the canary service spec changes 
+    [#54](https://github.com/weaveworks/flagger/pull/54)
+    [#51](https://github.com/weaveworks/flagger/pull/51)
+
+#### Improvements 
+
+- Run e2e testing on [Kubernetes Kind](https://github.com/kubernetes-sigs/kind) for canary promotion 
+    [#53](https://github.com/weaveworks/flagger/pull/53)
+
+## 0.5.1 (2019-02-14)
+
+Allows skipping the analysis phase to ship changes directly to production
+
+#### Features
+
+- Add option to skip the canary analysis [#46](https://github.com/weaveworks/flagger/pull/46)
+
+#### Fixes
+
+- Reject deployment if the pod label selector doesn't match `app: <DEPLOYMENT_NAME>` [#43](https://github.com/weaveworks/flagger/pull/43)
+
+## 0.5.0 (2019-01-30)
+
+Track changes in ConfigMaps and Secrets [#37](https://github.com/weaveworks/flagger/pull/37)
+
+#### Features
+
+- Promote configmaps and secrets changes from canary to primary
+- Detect changes in configmaps and/or secrets and (re)start canary analysis
+- Add configs checksum to Canary CRD status
+- Create primary configmaps and secrets at bootstrap
+- Scan canary volumes and containers for configmaps and secrets
+
+#### Fixes
+
+- Copy deployment labels from canary to primary at bootstrap and promotion
+
+## 0.4.1 (2019-01-24)
+
+Load testing webhook [#35](https://github.com/weaveworks/flagger/pull/35)
+
+#### Features
+
+- Add the load tester chart to Flagger Helm repository
+- Implement a load test runner based on [rakyll/hey](https://github.com/rakyll/hey)
+- Log warning when no values are found for Istio metric due to lack of traffic
+
+#### Fixes
+
+- Run wekbooks before the metrics checks to avoid failures when using a load tester
+
+## 0.4.0 (2019-01-18)
+
+Restart canary analysis if revision changes [#31](https://github.com/weaveworks/flagger/pull/31)
+
+#### Breaking changes
+
+- Drop support for Kubernetes 1.10
+
+#### Features
+
+- Detect changes during canary analysis and reset advancement
+- Add status and additional printer columns to CRD
+- Add canary name and namespace to controller structured logs
+
+#### Fixes
+
+- Allow canary name to be different to the target name
+- Check if multiple canaries have the same target and log error
+- Use deep copy when updating Kubernetes objects
+- Skip readiness checks if canary analysis has finished
+
+## 0.3.0 (2019-01-11)
+
+Configurable canary analysis duration [#20](https://github.com/weaveworks/flagger/pull/20)
+
+#### Breaking changes
+
+- Helm chart: flag `controlLoopInterval` has been removed
+
+#### Features
+
+- CRD: canaries.flagger.app v1alpha3
+- Schedule canary analysis independently based on `canaryAnalysis.interval`
+- Add analysis interval to Canary CRD (defaults to one minute)
+- Make autoscaler (HPA) reference optional
+
+## 0.2.0 (2019-01-04)
+
+Webhooks [#18](https://github.com/weaveworks/flagger/pull/18)
+
+#### Features
+
+- CRD: canaries.flagger.app v1alpha2
+- Implement canary external checks based on webhooks HTTP POST calls
+- Add webhooks to Canary CRD
+- Move docs to gitbook [docs.flagger.app](https://docs.flagger.app)
+
+## 0.1.2 (2018-12-06)
+
+Improve Slack notifications [#14](https://github.com/weaveworks/flagger/pull/14)
+
+#### Features
+
+- Add canary analysis metadata to init and start Slack messages
+- Add rollback reason to failed canary Slack messages
+
+## 0.1.1 (2018-11-28)
+
+Canary progress deadline [#10](https://github.com/weaveworks/flagger/pull/10)
+
+#### Features
+
+- Rollback canary based on the deployment progress deadline check
+- Add progress deadline to Canary CRD (defaults to 10 minutes)
+
+## 0.1.0 (2018-11-25)
+
+First stable release
+
+#### Features
+
+- CRD: canaries.flagger.app v1alpha1
+- Notifications: post canary events to Slack
+- Instrumentation: expose Prometheus metrics for canary status and traffic weight percentage
+- Autoscaling: add HPA reference to CRD and create primary HPA at bootstrap
+- Bootstrap: create primary deployment, ClusterIP services and Istio virtual service based on CRD spec
+
+
+## 0.0.1 (2018-10-07)
+
+Initial semver release
+
+#### Features
+
+- Implement canary rollback based on failed checks threshold
+- Scale up the deployment when canary revision changes
+- Add OpenAPI v3 schema validation to Canary CRD
+- Use CRD status for canary state persistence
+- Add Helm charts for Flagger and Grafana
+- Add canary analysis Grafana dashboard 

Dockerfile

@@ -1,17 +1,17 @@
-FROM golang:1.11
+FROM golang:1.12
 
-RUN mkdir -p /go/src/github.com/stefanprodan/flagger/
+RUN mkdir -p /go/src/github.com/weaveworks/flagger/
 
-WORKDIR /go/src/github.com/stefanprodan/flagger
+WORKDIR /go/src/github.com/weaveworks/flagger
 
 COPY . .
 
 RUN GIT_COMMIT=$(git rev-list -1 HEAD) && \
     CGO_ENABLED=0 GOOS=linux go build -ldflags "-s -w \
-    -X github.com/stefanprodan/flagger/pkg/version.REVISION=${GIT_COMMIT}" \
+    -X github.com/weaveworks/flagger/pkg/version.REVISION=${GIT_COMMIT}" \
     -a -installsuffix cgo -o flagger ./cmd/flagger/*
 
-FROM alpine:3.8
+FROM alpine:3.9
 
 RUN addgroup -S flagger \
     && adduser -S -g flagger flagger \
@@ -19,7 +19,7 @@ RUN addgroup -S flagger \
 
 WORKDIR /home/flagger
 
-COPY --from=0 /go/src/github.com/stefanprodan/flagger/flagger .
+COPY --from=0 /go/src/github.com/weaveworks/flagger/flagger .
 
 RUN chown -R flagger:flagger ./
 

Dockerfile.loadtester

@@ -0,0 +1,30 @@
+FROM golang:1.12 AS builder
+
+RUN mkdir -p /go/src/github.com/weaveworks/flagger/
+
+WORKDIR /go/src/github.com/weaveworks/flagger
+
+COPY . .
+
+RUN go test -race ./pkg/loadtester/
+
+RUN CGO_ENABLED=0 GOOS=linux go build -a -installsuffix cgo -o loadtester ./cmd/loadtester/*
+
+FROM bats/bats:v1.1.0
+
+RUN addgroup -S app \
+    && adduser -S -g app app \
+    && apk --no-cache add ca-certificates curl jq
+
+WORKDIR /home/app
+
+RUN curl -sSLo hey "https://storage.googleapis.com/jblabs/dist/hey_linux_v0.1.2" && \
+chmod +x hey && mv hey /usr/local/bin/hey
+
+COPY --from=builder /go/src/github.com/weaveworks/flagger/loadtester .
+
+RUN chown -R app:app ./
+
+USER app
+
+ENTRYPOINT ["./loadtester"]

Gopkg.toml

@@ -11,31 +11,37 @@ required = [
   name = "go.uber.org/zap"
   version = "v1.9.1"
 
+[[constraint]]
+  name = "gopkg.in/h2non/gock.v1"
+  version = "v1.0.14"
+
 [[override]]
   name = "gopkg.in/yaml.v2"
   version = "v2.2.1"
 
 [[override]]
   name = "k8s.io/api"
-  version = "kubernetes-1.11.0"
+  version = "kubernetes-1.13.1"
 
 [[override]]
   name = "k8s.io/apimachinery"
-  version = "kubernetes-1.11.0"
+  version = "kubernetes-1.13.1"
 
 [[override]]
   name = "k8s.io/code-generator"
-  version = "kubernetes-1.11.0"
+  version = "kubernetes-1.13.1"
 
 [[override]]
   name = "k8s.io/client-go"
-  version = "kubernetes-1.11.0"
+  version = "kubernetes-1.13.1"
 
 [[override]]
-  name = "github.com/json-iterator/go"
-  # This is the commit at which k8s depends on this in 1.11
-  # It seems to be broken at HEAD.
-  revision = "f2b4162afba35581b6d4a50d3b8f34e33c144682"
+  name = "k8s.io/apiextensions-apiserver"
+  version = "kubernetes-1.13.1"
+
+[[override]]
+  name = "k8s.io/apiserver"
+  version = "kubernetes-1.13.1"
 
 [[constraint]]
   name = "github.com/prometheus/client_golang"
@@ -45,13 +51,9 @@ required = [
   name = "github.com/google/go-cmp"
   version = "v0.2.0"
 
-[[constraint]]
-  name = "github.com/knative/pkg"
-  revision = "c15d7c8f2220a7578b33504df6edefa948c845ae"
-
 [[override]]
-  name = "github.com/golang/glog"
-  source = "github.com/istio/glog"
+  name = "k8s.io/klog"
+  source = "github.com/stefanprodan/klog"
 
 [prune]
   go-tests = true
@@ -62,3 +64,11 @@ required = [
   name = "k8s.io/code-generator"
   unused-packages = false
   non-go = false
+
+[[constraint]]
+  name = "github.com/solo-io/supergloo"
+  version = "v0.3.11"
+
+[[constraint]]
+  name = "github.com/solo-io/solo-kit"
+  version = "v0.6.3"

MAINTAINERS

@@ -0,0 +1,5 @@
+The maintainers are generally available in Slack at
+https://weave-community.slack.com/messages/flagger/ (obtain an invitation
+at https://slack.weave.works/).
+
+Stefan Prodan, Weaveworks <stefan@weave.works> (Slack: @stefan Twitter: @stefanprodan)

Makefile

@@ -3,18 +3,33 @@ VERSION?=$(shell grep 'VERSION' pkg/version/version.go | awk '{ print $$4 }' | t
 VERSION_MINOR:=$(shell grep 'VERSION' pkg/version/version.go | awk '{ print $$4 }' | tr -d '"' | rev | cut -d'.' -f2- | rev)
 PATCH:=$(shell grep 'VERSION' pkg/version/version.go | awk '{ print $$4 }' | tr -d '"' | awk -F. '{print $$NF}')
 SOURCE_DIRS = cmd pkg/apis pkg/controller pkg/server pkg/logging pkg/version
+LT_VERSION?=$(shell grep 'VERSION' cmd/loadtester/main.go | awk '{ print $$4 }' | tr -d '"' | head -n1)
+TS=$(shell date +%Y-%m-%d_%H-%M-%S)
+
 run:
 	go run cmd/flagger/* -kubeconfig=$$HOME/.kube/config -log-level=info \
-	-metrics-server=https://prometheus.iowa.weavedx.com \
+	-metrics-server=https://prometheus.istio.weavedx.com \
+	-slack-url=https://hooks.slack.com/services/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 \
+	-slack-channel="devops-alerts"
+
+run-appmesh:
+	go run cmd/flagger/* -kubeconfig=$$HOME/.kube/config -log-level=info -mesh-provider=appmesh \
+	-metrics-server=http://acfc235624ca911e9a94c02c4171f346-1585187926.us-west-2.elb.amazonaws.com:9090 \
+	-slack-url=https://hooks.slack.com/services/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 \
+	-slack-channel="devops-alerts"
+
+run-nginx:
+	go run cmd/flagger/* -kubeconfig=$$HOME/.kube/config -log-level=info -mesh-provider=nginx -namespace=nginx \
+	-metrics-server=http://prometheus-weave.istio.weavedx.com \
 	-slack-url=https://hooks.slack.com/services/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 \
 	-slack-channel="devops-alerts"
 
 build:
-	docker build -t stefanprodan/flagger:$(TAG) . -f Dockerfile
+	docker build -t weaveworks/flagger:$(TAG) . -f Dockerfile
 
 push:
-	docker tag stefanprodan/flagger:$(TAG) quay.io/stefanprodan/flagger:$(VERSION)
-	docker push quay.io/stefanprodan/flagger:$(VERSION)
+	docker tag weaveworks/flagger:$(TAG) weaveworks/flagger:$(VERSION)
+	docker push weaveworks/flagger:$(VERSION)
 
 fmt:
 	gofmt -l -s -w $(SOURCE_DIRS)
@@ -29,9 +44,9 @@ test: test-fmt test-codegen
 	go test ./...
 
 helm-package:
-	cd charts/ && helm package flagger/ && helm package grafana/
+	cd charts/ && helm package ./*
 	mv charts/*.tgz docs/
-	helm repo index docs --url https://stefanprodan.github.io/flagger --merge ./docs/index.yaml
+	helm repo index docs --url https://weaveworks.github.io/flagger --merge ./docs/index.yaml
 
 helm-up:
 	helm upgrade --install flagger ./charts/flagger --namespace=istio-system --set crd.create=false
@@ -44,6 +59,7 @@ version-set:
 	sed -i '' "s/flagger:$$current/flagger:$$next/g" artifacts/flagger/deployment.yaml && \
 	sed -i '' "s/tag: $$current/tag: $$next/g" charts/flagger/values.yaml && \
 	sed -i '' "s/appVersion: $$current/appVersion: $$next/g" charts/flagger/Chart.yaml && \
+	sed -i '' "s/version: $$current/version: $$next/g" charts/flagger/Chart.yaml && \
 	echo "Version $$next set in code, deployment and charts"
 
 version-up:
@@ -77,3 +93,7 @@ reset-test:
 	kubectl delete -f ./artifacts/namespaces
 	kubectl apply -f ./artifacts/namespaces
 	kubectl apply -f ./artifacts/canaries
+
+loadtester-push:
+	docker build -t weaveworks/flagger-loadtester:$(LT_VERSION) . -f Dockerfile.loadtester
+	docker push weaveworks/flagger-loadtester:$(LT_VERSION)

README.md

@@ -1,81 +1,63 @@
 # flagger
 
-[![build](https://travis-ci.org/stefanprodan/flagger.svg?branch=master)](https://travis-ci.org/stefanprodan/flagger)
-[![report](https://goreportcard.com/badge/github.com/stefanprodan/flagger)](https://goreportcard.com/report/github.com/stefanprodan/flagger)
-[![codecov](https://codecov.io/gh/stefanprodan/flagger/branch/master/graph/badge.svg)](https://codecov.io/gh/stefanprodan/flagger)
-[![license](https://img.shields.io/github/license/stefanprodan/flagger.svg)](https://github.com/stefanprodan/flagger/blob/master/LICENSE)
-[![release](https://img.shields.io/github/release/stefanprodan/flagger/all.svg)](https://github.com/stefanprodan/flagger/releases)
+[![build](https://travis-ci.org/weaveworks/flagger.svg?branch=master)](https://travis-ci.org/weaveworks/flagger)
+[![report](https://goreportcard.com/badge/github.com/weaveworks/flagger)](https://goreportcard.com/report/github.com/weaveworks/flagger)
+[![codecov](https://codecov.io/gh/weaveworks/flagger/branch/master/graph/badge.svg)](https://codecov.io/gh/weaveworks/flagger)
+[![license](https://img.shields.io/github/license/weaveworks/flagger.svg)](https://github.com/weaveworks/flagger/blob/master/LICENSE)
+[![release](https://img.shields.io/github/release/weaveworks/flagger/all.svg)](https://github.com/weaveworks/flagger/releases)
 
 Flagger is a Kubernetes operator that automates the promotion of canary deployments
-using Istio routing for traffic shifting and Prometheus metrics for canary analysis. 
-The canary analysis can be extended with webhooks for running integration tests, load tests or any other custom 
-validation.
+using Istio, App Mesh or NGINX routing for traffic shifting and Prometheus metrics for canary analysis.
+The canary analysis can be extended with webhooks for running acceptance tests,
+load tests or any other custom validation.
 
-### Install 
+Flagger implements a control loop that gradually shifts traffic to the canary while measuring key performance
+indicators like HTTP requests success rate, requests average duration and pods health.
+Based on analysis of the KPIs a canary is promoted or aborted, and the analysis result is published to Slack.
 
-Before installing Flagger make sure you have Istio setup up with Prometheus enabled. 
-If you are new to Istio you can follow my [Istio service mesh walk-through](https://github.com/stefanprodan/istio-gke).
+![flagger-overview](https://raw.githubusercontent.com/weaveworks/flagger/master/docs/diagrams/flagger-canary-overview.png)
 
-Deploy Flagger in the `istio-system` namespace using Helm:
+## Documentation
 
-```bash
-# add the Helm repository
-helm repo add flagger https://flagger.app
+Flagger documentation can be found at [docs.flagger.app](https://docs.flagger.app)
 
-# install or upgrade
-helm upgrade -i flagger flagger/flagger \
---namespace=istio-system \
---set metricsServer=http://prometheus.istio-system:9090 \
---set controlLoopInterval=1m
-```
+* Install
+  * [Flagger install on Kubernetes](https://docs.flagger.app/install/flagger-install-on-kubernetes)
+  * [Flagger install on GKE Istio](https://docs.flagger.app/install/flagger-install-on-google-cloud)
+  * [Flagger install on EKS App Mesh](https://docs.flagger.app/install/flagger-install-on-eks-appmesh)
+  * [Flagger install with SuperGloo](https://docs.flagger.app/install/flagger-install-with-supergloo)
+* How it works
+  * [Canary custom resource](https://docs.flagger.app/how-it-works#canary-custom-resource)
+  * [Routing](https://docs.flagger.app/how-it-works#istio-routing)
+  * [Canary deployment stages](https://docs.flagger.app/how-it-works#canary-deployment)
+  * [Canary analysis](https://docs.flagger.app/how-it-works#canary-analysis)
+  * [HTTP metrics](https://docs.flagger.app/how-it-works#http-metrics)
+  * [Custom metrics](https://docs.flagger.app/how-it-works#custom-metrics)
+  * [Webhooks](https://docs.flagger.app/how-it-works#webhooks)
+  * [Load testing](https://docs.flagger.app/how-it-works#load-testing)
+* Usage
+  * [Istio canary deployments](https://docs.flagger.app/usage/progressive-delivery)
+  * [Istio A/B testing](https://docs.flagger.app/usage/ab-testing)
+  * [App Mesh canary deployments](https://docs.flagger.app/usage/appmesh-progressive-delivery)
+  * [NGINX ingress controller canary deployments](https://docs.flagger.app/usage/nginx-progressive-delivery)
+  * [Monitoring](https://docs.flagger.app/usage/monitoring)
+  * [Alerting](https://docs.flagger.app/usage/alerting)
+* Tutorials
+  * [Canary deployments with Helm charts and Weave Flux](https://docs.flagger.app/tutorials/canary-helm-gitops)
 
-Flagger is compatible with Kubernetes >1.10.0 and Istio >1.0.0.
+## Canary CRD
 
-### Usage
+Flagger takes a Kubernetes deployment and optionally a horizontal pod autoscaler (HPA),
+then creates a series of objects (Kubernetes deployments, ClusterIP services and Istio or App Mesh virtual services).
+These objects expose the application on the mesh and drive the canary analysis and promotion.
 
-Flagger takes a Kubernetes deployment and creates a series of objects 
-(Kubernetes [deployments](https://kubernetes.io/docs/concepts/workloads/controllers/deployment/), 
-ClusterIP [services](https://kubernetes.io/docs/concepts/services-networking/service/) and 
-Istio [virtual services](https://istio.io/docs/reference/config/istio.networking.v1alpha3/#VirtualService)) 
-to drive the canary analysis and promotion.
-
-![flagger-overview](https://raw.githubusercontent.com/stefanprodan/flagger/master/docs/diagrams/flagger-canary-overview.png)
-
-Gated canary promotion stages:
-
-* scan for canary deployments
-* check Istio virtual service routes are mapped to primary and canary ClusterIP services
-* check primary and canary deployments status
-    * halt advancement if a rolling update is underway
-    * halt advancement if pods are unhealthy
-* increase canary traffic weight percentage from 0% to 5% (step weight)
-* check canary HTTP request success rate and latency
-    * halt advancement if any metric is under the specified threshold
-    * increment the failed checks counter
-* check if the number of failed checks reached the threshold
-    * route all traffic to primary
-    * scale to zero the canary deployment and mark it as failed
-    * wait for the canary deployment to be updated (revision bump) and start over
-* increase canary traffic weight by 5% (step weight) till it reaches 50% (max weight) 
-    * halt advancement while canary request success rate is under the threshold
-    * halt advancement while canary request duration P99 is over the threshold
-    * halt advancement if the primary or canary deployment becomes unhealthy 
-    * halt advancement while canary deployment is being scaled up/down by HPA
-* promote canary to primary
-    * copy canary deployment spec template over primary
-* wait for primary rolling update to finish
-    * halt advancement if pods are unhealthy
-* route all traffic to primary
-* scale to zero the canary deployment
-* mark rollout as finished
-* wait for the canary deployment to be updated (revision bump) and start over
-
-You can change the canary analysis _max weight_ and the _step weight_ percentage in the Flagger's custom resource.
+Flagger keeps track of ConfigMaps and Secrets referenced by a Kubernetes Deployment and triggers a canary analysis if any of those objects change.
+When promoting a workload in production, both code (container images) and configuration (config maps and secrets) are being synchronised.
 
 For a deployment named _podinfo_, a canary promotion can be defined using Flagger's custom resource:
 
 ```yaml
-apiVersion: flagger.app/v1alpha2
+apiVersion: flagger.app/v1alpha3
 kind: Canary
 metadata:
   name: podinfo
@@ -100,10 +82,34 @@ spec:
     # Istio gateways (optional)
     gateways:
     - public-gateway.istio-system.svc.cluster.local
+    - mesh
     # Istio virtual service host names (optional)
     hosts:
-    - app.iowa.weavedx.com
+    - podinfo.example.com
+    # HTTP match conditions (optional)
+    match:
+      - uri:
+          prefix: /
+    # HTTP rewrite (optional)
+    rewrite:
+      uri: /
+    # Envoy timeout and retry policy (optional)
+    headers:
+      request:
+        add:
+          x-envoy-upstream-rq-timeout-ms: "15000"
+          x-envoy-max-retries: "10"
+          x-envoy-retry-on: "gateway-error,connect-failure,refused-stream"
+    # cross-origin resource sharing policy (optional)
+    corsPolicy:
+      allowOrigin:
+        - example.com
+  # promote the canary without analysing it (default false)
+  skipAnalysis: false
+  # define the canary analysis timing and KPIs
   canaryAnalysis:
+    # schedule interval (default 60s)
+    interval: 1m
     # max number of failed metric checks before rollback
     threshold: 10
     # max traffic percentage routed to canary
@@ -114,319 +120,77 @@ spec:
     stepWeight: 5
     # Istio Prometheus checks
     metrics:
-    - name: istio_requests_total
+    # builtin checks
+    - name: request-success-rate
       # minimum req success rate (non 5xx responses)
       # percentage (0-100)
       threshold: 99
       interval: 1m
-    - name: istio_request_duration_seconds_bucket
+    - name: request-duration
       # maximum req duration P99
       # milliseconds
       threshold: 500
       interval: 30s
+    # custom check
+    - name: "kafka lag"
+      threshold: 100
+      query: |
+        avg_over_time(
+          kafka_consumergroup_lag{
+            consumergroup=~"podinfo-consumer-.*",
+            topic="podinfo"
+          }[1m]
+        )
     # external checks (optional)
     webhooks:
-      - name: integration-tests
-        url: http://podinfo.test:9898/echo
-        timeout: 1m
+      - name: load-test
+        url: http://flagger-loadtester.test/
+        timeout: 5s
         metadata:
-          test: "all"
-          token: "16688eb5e9f289f1991c"
+          cmd: "hey -z 1m -q 10 -c 2 http://podinfo.test:9898/"
 ```
 
-The canary analysis is using the following promql queries:
- 
-_HTTP requests success rate percentage_
+For more details on how the canary analysis and promotion works please [read the docs](https://docs.flagger.app/how-it-works).
 
-```sql
-sum(
-    rate(
-        istio_requests_total{
-          reporter="destination",
-          destination_workload_namespace=~"$namespace",
-          destination_workload=~"$workload",
-          response_code!~"5.*"
-        }[$interval]
-    )
-) 
-/ 
-sum(
-    rate(
-        istio_requests_total{
-          reporter="destination",
-          destination_workload_namespace=~"$namespace",
-          destination_workload=~"$workload"
-        }[$interval]
-    )
-)
-```
+## Features
 
-_HTTP requests milliseconds duration P99_
+| Feature                                      | Istio              | App Mesh           | SuperGloo          | NGINX Ingress      |
+| -------------------------------------------- | ------------------ | ------------------ |------------------  |------------------  |
+| Canary deployments (weighted traffic)        | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: |
+| A/B testing (headers and cookies filters)    | :heavy_check_mark: | :heavy_minus_sign: | :heavy_minus_sign: | :heavy_check_mark: |
+| Load testing                                 | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: |
+| Webhooks (custom acceptance tests)           | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: |
+| Request success rate check (L7 metric)       | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: |
+| Request duration check (L7 metric)           | :heavy_check_mark: | :heavy_minus_sign: | :heavy_check_mark: | :heavy_check_mark: |
+| Custom promql checks                         | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: |
+| Ingress gateway (CORS, retries and timeouts) | :heavy_check_mark: | :heavy_minus_sign: | :heavy_check_mark: | :heavy_check_mark: |
 
-```sql
-histogram_quantile(0.99, 
-  sum(
-    irate(
-      istio_request_duration_seconds_bucket{
-        reporter="destination",
-        destination_workload=~"$workload",
-        destination_workload_namespace=~"$namespace"
-      }[$interval]
-    )
-  ) by (le)
-)
-```
+## Roadmap
 
-The canary analysis can be extended with webhooks. 
-Flagger will call the webhooks (HTTP POST) and determine from the response status code (HTTP 2xx) if the canary is failing or not.
-
-Webhook payload:
-
-```json
-{
-    "name": "podinfo",
-    "namespace": "test", 
-    "metadata": {
-        "test":  "all",
-        "token":  "16688eb5e9f289f1991c"
-    }
-}
-```
-
-### Automated canary analysis, promotions and rollbacks
-
-Create a test namespace with Istio sidecar injection enabled:
-
-```bash
-export REPO=https://raw.githubusercontent.com/stefanprodan/flagger/master
-
-kubectl apply -f ${REPO}/artifacts/namespaces/test.yaml
-```
-
-Create a deployment and a horizontal pod autoscaler:
-
-```bash
-kubectl apply -f ${REPO}/artifacts/canaries/deployment.yaml
-kubectl apply -f ${REPO}/artifacts/canaries/hpa.yaml
-```
-
-Create a canary promotion custom resource (replace the Istio gateway and the internet domain with your own):
-
-```bash
-kubectl apply -f ${REPO}/artifacts/canaries/canary.yaml
-```
-
-After a couple of seconds Flagger will create the canary objects:
-
-```bash
-# applied 
-deployment.apps/podinfo
-horizontalpodautoscaler.autoscaling/podinfo
-canary.flagger.app/podinfo
-# generated 
-deployment.apps/podinfo-primary
-horizontalpodautoscaler.autoscaling/podinfo-primary
-service/podinfo
-service/podinfo-canary
-service/podinfo-primary
-virtualservice.networking.istio.io/podinfo
-```
-
-![flagger-canary-steps](https://raw.githubusercontent.com/stefanprodan/flagger/master/docs/diagrams/flagger-canary-steps.png)
-
-Trigger a canary deployment by updating the container image:
-
-```bash
-kubectl -n test set image deployment/podinfo \
-podinfod=quay.io/stefanprodan/podinfo:1.2.1
-```
-
-Flagger detects that the deployment revision changed and starts a new rollout:
-
-```
-kubectl -n test describe canary/podinfo
-
-Status:
-  Canary Revision:  19871136
-  Failed Checks:    0
-  State:            finished
-Events:
-  Type     Reason  Age   From     Message
-  ----     ------  ----  ----     -------
-  Normal   Synced  3m    flagger  New revision detected podinfo.test
-  Normal   Synced  3m    flagger  Scaling up podinfo.test
-  Warning  Synced  3m    flagger  Waiting for podinfo.test rollout to finish: 0 of 1 updated replicas are available
-  Normal   Synced  3m    flagger  Advance podinfo.test canary weight 5
-  Normal   Synced  3m    flagger  Advance podinfo.test canary weight 10
-  Normal   Synced  3m    flagger  Advance podinfo.test canary weight 15
-  Normal   Synced  2m    flagger  Advance podinfo.test canary weight 20
-  Normal   Synced  2m    flagger  Advance podinfo.test canary weight 25
-  Normal   Synced  1m    flagger  Advance podinfo.test canary weight 30
-  Normal   Synced  1m    flagger  Advance podinfo.test canary weight 35
-  Normal   Synced  55s   flagger  Advance podinfo.test canary weight 40
-  Normal   Synced  45s   flagger  Advance podinfo.test canary weight 45
-  Normal   Synced  35s   flagger  Advance podinfo.test canary weight 50
-  Normal   Synced  25s   flagger  Copying podinfo.test template spec to podinfo-primary.test
-  Warning  Synced  15s   flagger  Waiting for podinfo-primary.test rollout to finish: 1 of 2 updated replicas are available
-  Normal   Synced  5s    flagger  Promotion completed! Scaling down podinfo.test
-```
-
-During the canary analysis you can generate HTTP 500 errors and high latency to test if Flagger pauses the rollout.
-
-Create a tester pod and exec into it:
-
-```bash
-kubectl -n test run tester --image=quay.io/stefanprodan/podinfo:1.2.1 -- ./podinfo --port=9898
-kubectl -n test exec -it tester-xx-xx sh
-```
-
-Generate HTTP 500 errors:
-
-```bash
-watch curl http://podinfo-canary:9898/status/500
-```
-
-Generate latency:
-
-```bash
-watch curl http://podinfo-canary:9898/delay/1
-```
-
-When the number of failed checks reaches the canary analysis threshold, the traffic is routed back to the primary,
-the canary is scaled to zero and the rollout is marked as failed. 
-
-```
-kubectl -n test describe canary/podinfo
-
-Status:
-  Canary Revision:  16695041
-  Failed Checks:    10
-  State:            failed
-Events:
-  Type     Reason  Age   From     Message
-  ----     ------  ----  ----     -------
-  Normal   Synced  3m    flagger  Starting canary deployment for podinfo.test
-  Normal   Synced  3m    flagger  Advance podinfo.test canary weight 5
-  Normal   Synced  3m    flagger  Advance podinfo.test canary weight 10
-  Normal   Synced  3m    flagger  Advance podinfo.test canary weight 15
-  Normal   Synced  3m    flagger  Halt podinfo.test advancement success rate 69.17% < 99%
-  Normal   Synced  2m    flagger  Halt podinfo.test advancement success rate 61.39% < 99%
-  Normal   Synced  2m    flagger  Halt podinfo.test advancement success rate 55.06% < 99%
-  Normal   Synced  2m    flagger  Halt podinfo.test advancement success rate 47.00% < 99%
-  Normal   Synced  2m    flagger  (combined from similar events): Halt podinfo.test advancement success rate 38.08% < 99%
-  Warning  Synced  1m    flagger  Rolling back podinfo.test failed checks threshold reached 10
-  Warning  Synced  1m    flagger  Canary failed! Scaling down podinfo.test
-```
-
-### Monitoring
-
-Flagger comes with a Grafana dashboard made for canary analysis.
-
-Install Grafana with Helm:
-
-```bash
-helm upgrade -i flagger-grafana flagger/grafana \
---namespace=istio-system \
---set url=http://prometheus.istio-system:9090
-```
-
-The dashboard shows the RED and USE metrics for the primary and canary workloads:
-
-![flagger-grafana](https://raw.githubusercontent.com/stefanprodan/flagger/master/docs/screens/grafana-canary-analysis.png)
-
-The canary errors and latency spikes have been recorded as Kubernetes events and logged by Flagger in json format:
-
-```
-kubectl -n istio-system logs deployment/flagger --tail=100 | jq .msg
-
-Starting canary deployment for podinfo.test
-Advance podinfo.test canary weight 5
-Advance podinfo.test canary weight 10
-Advance podinfo.test canary weight 15
-Advance podinfo.test canary weight 20
-Advance podinfo.test canary weight 25
-Advance podinfo.test canary weight 30
-Advance podinfo.test canary weight 35
-Halt podinfo.test advancement success rate 98.69% < 99%
-Advance podinfo.test canary weight 40
-Halt podinfo.test advancement request duration 1.515s > 500ms
-Advance podinfo.test canary weight 45
-Advance podinfo.test canary weight 50
-Copying podinfo.test template spec to podinfo-primary.test
-Halt podinfo-primary.test advancement waiting for rollout to finish: 1 old replicas are pending termination
-Scaling down podinfo.test
-Promotion completed! podinfo.test
-```
-
-Flagger exposes Prometheus metrics that can be used to determine the canary analysis status and the destination weight values:
-
-```bash
-# Canaries total gauge
-flagger_canary_total{namespace="test"} 1
-
-# Canary promotion last known status gauge
-# 0 - running, 1 - successful, 2 - failed
-flagger_canary_status{name="podinfo" namespace="test"} 1
-
-# Canary traffic weight gauge
-flagger_canary_weight{workload="podinfo-primary" namespace="test"} 95
-flagger_canary_weight{workload="podinfo" namespace="test"} 5
-
-# Seconds spent performing canary analysis histogram
-flagger_canary_duration_seconds_bucket{name="podinfo",namespace="test",le="10"} 6
-flagger_canary_duration_seconds_bucket{name="podinfo",namespace="test",le="+Inf"} 6
-flagger_canary_duration_seconds_sum{name="podinfo",namespace="test"} 17.3561329
-flagger_canary_duration_seconds_count{name="podinfo",namespace="test"} 6
-```
-
-### Alerting
-
-Flagger can be configured to send Slack notifications:
-
-```bash
-helm upgrade -i flagger flagger/flagger \
---namespace=istio-system \
---set slack.url=https://hooks.slack.com/services/YOUR/SLACK/WEBHOOK \
---set slack.channel=general \
---set slack.user=flagger
-```
-
-Once configured with a Slack incoming webhook, Flagger will post messages when a canary deployment has been initialized,
-when a new revision has been detected and if the canary analysis failed or succeeded.
-
-![flagger-slack](https://raw.githubusercontent.com/stefanprodan/flagger/master/docs/screens/slack-canary-notifications.png)
-
-A canary deployment will be rolled back if the progress deadline exceeded or if the analysis 
-reached the maximum number of failed checks:
-
-![flagger-slack-errors](https://raw.githubusercontent.com/stefanprodan/flagger/master/docs/screens/slack-canary-failed.png)
-
-Besides Slack, you can use Alertmanager to trigger alerts when a canary deployment failed:
-
-```yaml
-  - alert: canary_rollback
-    expr: flagger_canary_status > 1
-    for: 1m
-    labels:
-      severity: warning
-    annotations:
-      summary: "Canary failed"
-      description: "Workload {{ $labels.name }} namespace {{ $labels.namespace }}"
-```
-
-### Roadmap
-
-* Extend the validation mechanism to support other metrics than HTTP success rate and latency
+* Integrate with other service mesh technologies like Linkerd v2
 * Add support for comparing the canary metrics to the primary ones and do the validation based on the derivation between the two
-* Extend the canary analysis and promotion to other types than Kubernetes deployments such as Flux Helm releases or OpenFaaS functions
 
-### Contributing
+## Contributing
 
 Flagger is Apache 2.0 licensed and accepts contributions via GitHub pull requests.
 
-When submitting bug reports please include as much details as possible: 
+When submitting bug reports please include as much details as possible:
+
 * which Flagger version
 * which Flagger CRD version
 * which Kubernetes/Istio version
 * what configuration (canary, virtual service and workloads definitions)
 * what happened (Flagger, Istio Pilot and Proxy logs)
+
+## Getting Help
+
+If you have any questions about Flagger and progressive delivery:
+
+* Read the Flagger [docs](https://docs.flagger.app).
+* Invite yourself to the [Weave community slack](https://slack.weave.works/)
+  and join the [#flagger](https://weave-community.slack.com/messages/flagger/) channel.
+* Join the [Weave User Group](https://www.meetup.com/pro/Weave/) and get invited to online talks,
+  hands-on training and meetups in your area.
+* File an [issue](https://github.com/weaveworks/flagger/issues/new).
+
+Your feedback is always welcome!

artifacts/ab-testing/canary.yaml

@@ -0,0 +1,62 @@
+apiVersion: flagger.app/v1alpha3
+kind: Canary
+metadata:
+  name: abtest
+  namespace: test
+spec:
+  # deployment reference
+  targetRef:
+    apiVersion: apps/v1
+    kind: Deployment
+    name: abtest
+  # the maximum time in seconds for the canary deployment
+  # to make progress before it is rollback (default 600s)
+  progressDeadlineSeconds: 60
+  # HPA reference (optional)
+  autoscalerRef:
+    apiVersion: autoscaling/v2beta1
+    kind: HorizontalPodAutoscaler
+    name: abtest
+  service:
+    # container port
+    port: 9898
+    # Istio gateways (optional)
+    gateways:
+    - public-gateway.istio-system.svc.cluster.local
+    - mesh
+    # Istio virtual service host names (optional)
+    hosts:
+    - abtest.istio.weavedx.com
+  canaryAnalysis:
+    # schedule interval (default 60s)
+    interval: 10s
+    # max number of failed metric checks before rollback
+    threshold: 10
+    # total number of iterations
+    iterations: 10
+    # canary match condition
+    match:
+      - headers:
+          user-agent:
+            regex: "^(?!.*Chrome)(?=.*\bSafari\b).*$"
+      - headers:
+          cookie:
+            regex: "^(.*?;)?(type=insider)(;.*)?$"
+    metrics:
+    - name: request-success-rate
+      # minimum req success rate (non 5xx responses)
+      # percentage (0-100)
+      threshold: 99
+      interval: 1m
+    - name: request-duration
+      # maximum req duration P99
+      # milliseconds
+      threshold: 500
+      interval: 30s
+    # external checks (optional)
+    webhooks:
+      - name: load-test
+        url: http://flagger-loadtester.test/
+        timeout: 5s
+        metadata:
+          cmd: "hey -z 1m -q 10 -c 2 -H 'Cookie: type=insider' http://podinfo.test:9898/"

artifacts/ab-testing/deployment.yaml

@@ -0,0 +1,67 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: abtest
+  namespace: test
+  labels:
+    app: abtest
+spec:
+  minReadySeconds: 5
+  revisionHistoryLimit: 5
+  progressDeadlineSeconds: 60
+  strategy:
+    rollingUpdate:
+      maxUnavailable: 0
+    type: RollingUpdate
+  selector:
+    matchLabels:
+      app: abtest
+  template:
+    metadata:
+      annotations:
+        prometheus.io/scrape: "true"
+      labels:
+        app: abtest
+    spec:
+      containers:
+      - name: podinfod
+        image: quay.io/stefanprodan/podinfo:1.4.0
+        imagePullPolicy: IfNotPresent
+        ports:
+        - containerPort: 9898
+          name: http
+          protocol: TCP
+        command:
+        - ./podinfo
+        - --port=9898
+        - --level=info
+        - --random-delay=false
+        - --random-error=false
+        env:
+        - name: PODINFO_UI_COLOR
+          value: blue
+        livenessProbe:
+          exec:
+            command:
+            - podcli
+            - check
+            - http
+            - localhost:9898/healthz
+          initialDelaySeconds: 5
+          timeoutSeconds: 5
+        readinessProbe:
+          exec:
+            command:
+            - podcli
+            - check
+            - http
+            - localhost:9898/readyz
+          initialDelaySeconds: 5
+          timeoutSeconds: 5
+        resources:
+          limits:
+            cpu: 2000m
+            memory: 512Mi
+          requests:
+            cpu: 100m
+            memory: 64Mi

artifacts/ab-testing/hpa.yaml

@@ -0,0 +1,19 @@
+apiVersion: autoscaling/v2beta1
+kind: HorizontalPodAutoscaler
+metadata:
+  name: abtest
+  namespace: test
+spec:
+  scaleTargetRef:
+    apiVersion: apps/v1
+    kind: Deployment
+    name: abtest
+  minReplicas: 2
+  maxReplicas: 4
+  metrics:
+  - type: Resource
+    resource:
+      name: cpu
+      # scale up if usage is above
+      # 99% of the requested CPU (100m)
+      targetAverageUtilization: 99

artifacts/appmesh/canary.yaml

@@ -0,0 +1,50 @@
+apiVersion: flagger.app/v1alpha3
+kind: Canary
+metadata:
+  name: podinfo
+  namespace: test
+spec:
+  # deployment reference
+  targetRef:
+    apiVersion: apps/v1
+    kind: Deployment
+    name: podinfo
+  # the maximum time in seconds for the canary deployment
+  # to make progress before it is rollback (default 600s)
+  progressDeadlineSeconds: 60
+  # HPA reference (optional)
+  autoscalerRef:
+    apiVersion: autoscaling/v2beta1
+    kind: HorizontalPodAutoscaler
+    name: podinfo
+  service:
+    # container port
+    port: 9898
+    # App Mesh reference
+    meshName: global
+  # define the canary analysis timing and KPIs
+  canaryAnalysis:
+    # schedule interval (default 60s)
+    interval: 10s
+    # max number of failed metric checks before rollback
+    threshold: 10
+    # max traffic percentage routed to canary
+    # percentage (0-100)
+    maxWeight: 50
+    # canary increment step
+    # percentage (0-100)
+    stepWeight: 5
+    # App Mesh Prometheus checks
+    metrics:
+    - name: request-success-rate
+      # minimum req success rate (non 5xx responses)
+      # percentage (0-100)
+      threshold: 99
+      interval: 1m
+    # external checks (optional)
+    webhooks:
+      - name: load-test
+        url: http://flagger-loadtester.test/
+        timeout: 5s
+        metadata:
+          cmd: "hey -z 1m -q 10 -c 2 http://podinfo.test:9898/"

artifacts/appmesh/deployment.yaml

@@ -0,0 +1,65 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: podinfo
+  namespace: test
+  labels:
+    app: podinfo
+spec:
+  minReadySeconds: 5
+  revisionHistoryLimit: 5
+  progressDeadlineSeconds: 60
+  strategy:
+    rollingUpdate:
+      maxUnavailable: 0
+    type: RollingUpdate
+  selector:
+    matchLabels:
+      app: podinfo
+  template:
+    metadata:
+      annotations:
+        prometheus.io/scrape: "true"
+      labels:
+        app: podinfo
+    spec:
+      containers:
+      - name: podinfod
+        image: quay.io/stefanprodan/podinfo:1.4.0
+        imagePullPolicy: IfNotPresent
+        ports:
+        - containerPort: 9898
+          name: http
+          protocol: TCP
+        command:
+        - ./podinfo
+        - --port=9898
+        - --level=info
+        env:
+        - name: PODINFO_UI_COLOR
+          value: blue
+        livenessProbe:
+          exec:
+            command:
+            - podcli
+            - check
+            - http
+            - localhost:9898/healthz
+          initialDelaySeconds: 5
+          timeoutSeconds: 5
+        readinessProbe:
+          exec:
+            command:
+            - podcli
+            - check
+            - http
+            - localhost:9898/readyz
+          initialDelaySeconds: 5
+          timeoutSeconds: 5
+        resources:
+          limits:
+            cpu: 2000m
+            memory: 512Mi
+          requests:
+            cpu: 100m
+            memory: 64Mi

artifacts/appmesh/global-mesh.yaml

@@ -0,0 +1,6 @@
+apiVersion: appmesh.k8s.aws/v1beta1
+kind: Mesh
+metadata:
+  name: global
+spec:
+  serviceDiscoveryType: dns

artifacts/appmesh/hpa.yaml

@@ -0,0 +1,19 @@
+apiVersion: autoscaling/v2beta1
+kind: HorizontalPodAutoscaler
+metadata:
+  name: podinfo
+  namespace: test
+spec:
+  scaleTargetRef:
+    apiVersion: apps/v1
+    kind: Deployment
+    name: podinfo
+  minReplicas: 2
+  maxReplicas: 4
+  metrics:
+  - type: Resource
+    resource:
+      name: cpu
+      # scale up if usage is above
+      # 99% of the requested CPU (100m)
+      targetAverageUtilization: 99

artifacts/appmesh/ingress.yaml

@@ -0,0 +1,177 @@
+---
+kind: ConfigMap
+apiVersion: v1
+metadata:
+  name: ingress-config
+  namespace: test
+  labels:
+    app: ingress
+data:
+  envoy.yaml: |
+    static_resources:
+      listeners:
+        - address:
+            socket_address:
+              address: 0.0.0.0
+              port_value: 80
+          filter_chains:
+            - filters:
+                - name: envoy.http_connection_manager
+                  config:
+                    access_log:
+                    - name: envoy.file_access_log
+                      config:
+                        path: /dev/stdout
+                    codec_type: auto
+                    stat_prefix: ingress_http
+                    http_filters:
+                      - name: envoy.router
+                        config: {}
+                    route_config:
+                      name: local_route
+                      virtual_hosts:
+                        - name: local_service
+                          domains: ["*"]
+                          routes:
+                            - match:
+                                prefix: "/"
+                              route:
+                                cluster: podinfo
+                                host_rewrite: podinfo.test
+                                timeout: 15s
+                                retry_policy:
+                                  retry_on: "gateway-error,connect-failure,refused-stream"
+                                  num_retries: 10
+                                  per_try_timeout: 5s
+      clusters:
+        - name: podinfo
+          connect_timeout: 0.30s
+          type: strict_dns
+          lb_policy: round_robin
+          http2_protocol_options: {}
+          hosts:
+            - socket_address:
+                address: podinfo.test
+                port_value: 9898
+    admin:
+      access_log_path: /dev/null
+      address:
+        socket_address:
+          address: 0.0.0.0
+          port_value: 9999
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: ingress
+  namespace: test
+  labels:
+    app: ingress
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: ingress
+  strategy:
+    type: RollingUpdate
+    rollingUpdate:
+      maxUnavailable: 0
+  template:
+    metadata:
+      labels:
+        app: ingress
+      annotations:
+        prometheus.io/path: "/stats/prometheus"
+        prometheus.io/port: "9999"
+        prometheus.io/scrape: "true"
+        # dummy port to exclude ingress from mesh traffic
+        # only egress should go over the mesh
+        appmesh.k8s.aws/ports: "444"
+    spec:
+      terminationGracePeriodSeconds: 30
+      containers:
+        - name: ingress
+          image: "envoyproxy/envoy-alpine:d920944aed67425f91fc203774aebce9609e5d9a"
+          securityContext:
+            capabilities:
+              drop:
+                - ALL
+              add:
+                - NET_BIND_SERVICE
+          command:
+            - /usr/bin/dumb-init
+            - --
+          args:
+            - /usr/local/bin/envoy
+            - --base-id 30
+            - --v2-config-only
+            - -l
+            - $loglevel
+            - -c
+            - /config/envoy.yaml
+          ports:
+            - name: admin
+              containerPort: 9999
+              protocol: TCP
+            - name: http
+              containerPort: 80
+              protocol: TCP
+            - name: https
+              containerPort: 443
+              protocol: TCP
+          livenessProbe:
+            initialDelaySeconds: 5
+            tcpSocket:
+              port: admin
+          readinessProbe:
+            initialDelaySeconds: 5
+            tcpSocket:
+              port: admin
+          resources:
+            requests:
+              cpu: 100m
+              memory: 64Mi
+          volumeMounts:
+            - name: config
+              mountPath: /config
+      volumes:
+        - name: config
+          configMap:
+            name: ingress-config
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: ingress
+  namespace: test
+spec:
+  selector:
+    app: ingress
+  ports:
+    - protocol: TCP
+      name: http
+      port: 80
+      targetPort: 80
+    - protocol: TCP
+      name: https
+      port: 443
+      targetPort: 443
+  type: LoadBalancer
+---
+apiVersion: appmesh.k8s.aws/v1beta1
+kind: VirtualNode
+metadata:
+  name: ingress
+  namespace: test
+spec:
+  meshName: global
+  listeners:
+    - portMapping:
+        port: 80
+        protocol: http
+  serviceDiscovery:
+    dns:
+      hostName: ingress.test
+  backends:
+    - virtualService:
+        virtualServiceName: podinfo.test

artifacts/canaries/canary.yaml

@@ -1,4 +1,4 @@
-apiVersion: flagger.app/v1alpha2
+apiVersion: flagger.app/v1alpha3
 kind: Canary
 metadata:
   name: podinfo
@@ -23,10 +23,29 @@ spec:
     # Istio gateways (optional)
     gateways:
     - public-gateway.istio-system.svc.cluster.local
+    - mesh
     # Istio virtual service host names (optional)
     hosts:
-    - app.iowa.weavedx.com
+    - app.istio.weavedx.com
+    # HTTP match conditions (optional)
+    match:
+      - uri:
+          prefix: /
+    # HTTP rewrite (optional)
+    rewrite:
+      uri: /
+    # Envoy timeout and retry policy (optional)
+    headers:
+      request:
+        add:
+          x-envoy-upstream-rq-timeout-ms: "15000"
+          x-envoy-max-retries: "10"
+          x-envoy-retry-on: "gateway-error,connect-failure,refused-stream"
+  # promote the canary without analysing it (default false)
+  skipAnalysis: false
   canaryAnalysis:
+    # schedule interval (default 60s)
+    interval: 10s
     # max number of failed metric checks before rollback
     threshold: 10
     # max traffic percentage routed to canary
@@ -37,21 +56,22 @@ spec:
     stepWeight: 5
     # Istio Prometheus checks
     metrics:
-    - name: istio_requests_total
+    - name: request-success-rate
       # minimum req success rate (non 5xx responses)
       # percentage (0-100)
       threshold: 99
       interval: 1m
-    - name: istio_request_duration_seconds_bucket
+    - name: request-duration
       # maximum req duration P99
       # milliseconds
       threshold: 500
       interval: 30s
     # external checks (optional)
     webhooks:
-      - name: integration-tests
-        url: http://podinfo.test:9898/echo
-        timeout: 1m
+      - name: load-test
+        url: http://flagger-loadtester.test/
+        timeout: 5s
         metadata:
-          test: "all"
-          token: "16688eb5e9f289f1991c"
+          type: cmd
+          cmd: "hey -z 1m -q 10 -c 2 http://podinfo.test:9898/"
+          logCmdOutput: "true"

artifacts/canaries/deployment.yaml

@@ -25,7 +25,7 @@ spec:
     spec:
       containers:
       - name: podinfod
-        image: quay.io/stefanprodan/podinfo:1.3.0
+        image: quay.io/stefanprodan/podinfo:1.4.0
         imagePullPolicy: IfNotPresent
         ports:
         - containerPort: 9898

artifacts/cluster/namespaces/test.yaml

@@ -0,0 +1,6 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: test
+  labels:
+    istio-injection: enabled

artifacts/cluster/releases/test/backend.yaml

@@ -0,0 +1,26 @@
+apiVersion: flux.weave.works/v1beta1
+kind: HelmRelease
+metadata:
+  name: backend
+  namespace: test
+  annotations:
+    flux.weave.works/automated: "true"
+    flux.weave.works/tag.chart-image: regexp:^1.4.*
+spec:
+  releaseName: backend
+  chart:
+    repository: https://flagger.app/
+    name: podinfo
+    version: 2.0.0
+  values:
+    image:
+      repository: quay.io/stefanprodan/podinfo
+      tag: 1.4.0
+      httpServer:
+        timeout: 30s
+      canary:
+        enabled: true
+        istioIngress:
+          enabled: false
+        loadtest:
+          enabled: true

artifacts/cluster/releases/test/frontend.yaml

@@ -0,0 +1,27 @@
+apiVersion: flux.weave.works/v1beta1
+kind: HelmRelease
+metadata:
+  name: frontend
+  namespace: test
+  annotations:
+    flux.weave.works/automated: "true"
+    flux.weave.works/tag.chart-image: semver:~1.4
+spec:
+  releaseName: frontend
+  chart:
+    repository: https://flagger.app/
+    name: podinfo
+    version: 2.0.0
+  values:
+    image:
+      repository: quay.io/stefanprodan/podinfo
+      tag: 1.4.0
+      backend: http://backend-podinfo:9898/echo
+      canary:
+        enabled: true
+        istioIngress:
+          enabled: true
+          gateway: public-gateway.istio-system.svc.cluster.local
+          host: frontend.istio.example.com
+        loadtest:
+          enabled: true

artifacts/cluster/releases/test/loadtester.yaml

@@ -0,0 +1,18 @@
+apiVersion: flux.weave.works/v1beta1
+kind: HelmRelease
+metadata:
+  name: loadtester
+  namespace: test
+  annotations:
+    flux.weave.works/automated: "true"
+    flux.weave.works/tag.chart-image: glob:0.*
+spec:
+  releaseName: flagger-loadtester
+  chart:
+    repository: https://flagger.app/
+    name: loadtester
+    version: 0.1.0
+  values:
+    image:
+      repository: quay.io/stefanprodan/flagger-loadtester
+      tag: 0.1.0

artifacts/configs/canary.yaml

@@ -0,0 +1,59 @@
+apiVersion: flagger.app/v1alpha3
+kind: Canary
+metadata:
+  name: podinfo
+  namespace: test
+spec:
+  # deployment reference
+  targetRef:
+    apiVersion: apps/v1
+    kind: Deployment
+    name: podinfo
+  # the maximum time in seconds for the canary deployment
+  # to make progress before it is rollback (default 600s)
+  progressDeadlineSeconds: 60
+  # HPA reference (optional)
+  autoscalerRef:
+    apiVersion: autoscaling/v2beta1
+    kind: HorizontalPodAutoscaler
+    name: podinfo
+  service:
+    # container port
+    port: 9898
+    # Istio gateways (optional)
+    gateways:
+    - public-gateway.istio-system.svc.cluster.local
+    - mesh
+    # Istio virtual service host names (optional)
+    hosts:
+    - app.iowa.weavedx.com
+  canaryAnalysis:
+    # schedule interval (default 60s)
+    interval: 10s
+    # max number of failed metric checks before rollback
+    threshold: 10
+    # max traffic percentage routed to canary
+    # percentage (0-100)
+    maxWeight: 50
+    # canary increment step
+    # percentage (0-100)
+    stepWeight: 5
+    # Istio Prometheus checks
+    metrics:
+    - name: request-success-rate
+      # minimum req success rate (non 5xx responses)
+      # percentage (0-100)
+      threshold: 99
+      interval: 1m
+    - name: request-duration
+      # maximum req duration P99
+      # milliseconds
+      threshold: 500
+      interval: 30s
+    # external checks (optional)
+    webhooks:
+      - name: load-test
+        url: http://flagger-loadtester.test/
+        timeout: 5s
+        metadata:
+          cmd: "hey -z 1m -q 10 -c 2 http://podinfo.test:9898/"

artifacts/configs/configs.yaml

@@ -0,0 +1,16 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: podinfo-config-env
+  namespace: test
+data:
+  color: blue
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: podinfo-config-vol
+  namespace: test
+data:
+  output: console
+  textmode: "true"

artifacts/configs/deployment.yaml

@@ -0,0 +1,89 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: podinfo
+  namespace: test
+  labels:
+    app: podinfo
+spec:
+  minReadySeconds: 5
+  revisionHistoryLimit: 5
+  progressDeadlineSeconds: 60
+  strategy:
+    rollingUpdate:
+      maxUnavailable: 0
+    type: RollingUpdate
+  selector:
+    matchLabels:
+      app: podinfo
+  template:
+    metadata:
+      annotations:
+        prometheus.io/scrape: "true"
+      labels:
+        app: podinfo
+    spec:
+      containers:
+      - name: podinfod
+        image: quay.io/stefanprodan/podinfo:1.3.0
+        imagePullPolicy: IfNotPresent
+        ports:
+        - containerPort: 9898
+          name: http
+          protocol: TCP
+        command:
+        - ./podinfo
+        - --port=9898
+        - --level=info
+        - --random-delay=false
+        - --random-error=false
+        env:
+        - name: PODINFO_UI_COLOR
+          valueFrom:
+            configMapKeyRef:
+              name: podinfo-config-env
+              key: color
+        - name: SECRET_USER
+          valueFrom:
+            secretKeyRef:
+              name: podinfo-secret-env
+              key: user
+        livenessProbe:
+          exec:
+            command:
+            - podcli
+            - check
+            - http
+            - localhost:9898/healthz
+          initialDelaySeconds: 5
+          timeoutSeconds: 5
+        readinessProbe:
+          exec:
+            command:
+            - podcli
+            - check
+            - http
+            - localhost:9898/readyz
+          initialDelaySeconds: 5
+          timeoutSeconds: 5
+        resources:
+          limits:
+            cpu: 2000m
+            memory: 512Mi
+          requests:
+            cpu: 100m
+            memory: 64Mi
+        volumeMounts:
+          - name: configs
+            mountPath: /etc/podinfo/configs
+            readOnly: true
+          - name: secrets
+            mountPath: /etc/podinfo/secrets
+            readOnly: true
+      volumes:
+        - name: configs
+          configMap:
+            name: podinfo-config-vol
+        - name: secrets
+          secret:
+            secretName: podinfo-secret-vol

artifacts/configs/hpa.yaml

@@ -0,0 +1,19 @@
+apiVersion: autoscaling/v2beta1
+kind: HorizontalPodAutoscaler
+metadata:
+  name: podinfo
+  namespace: test
+spec:
+  scaleTargetRef:
+    apiVersion: apps/v1
+    kind: Deployment
+    name: podinfo
+  minReplicas: 1
+  maxReplicas: 4
+  metrics:
+  - type: Resource
+    resource:
+      name: cpu
+      # scale up if usage is above
+      # 99% of the requested CPU (100m)
+      targetAverageUtilization: 99

artifacts/configs/secrets.yaml

@@ -0,0 +1,16 @@
+apiVersion: v1
+kind: Secret
+metadata:
+  name: podinfo-secret-env
+  namespace: test
+data:
+  password: cGFzc3dvcmQ=
+  user: YWRtaW4=
+---
+apiVersion: v1
+kind: Secret
+metadata:
+  name: podinfo-secret-vol
+  namespace: test
+data:
+  key: cGFzc3dvcmQ=

artifacts/eks/appmesh-prometheus.yaml

@@ -0,0 +1,264 @@
+---
+apiVersion: rbac.authorization.k8s.io/v1beta1
+kind: ClusterRole
+metadata:
+  name: prometheus
+  labels:
+    app: prometheus
+rules:
+  - apiGroups: [""]
+    resources:
+      - nodes
+      - services
+      - endpoints
+      - pods
+      - nodes/proxy
+    verbs: ["get", "list", "watch"]
+  - apiGroups: [""]
+    resources:
+      - configmaps
+    verbs: ["get"]
+  - nonResourceURLs: ["/metrics"]
+    verbs: ["get"]
+---
+apiVersion: rbac.authorization.k8s.io/v1beta1
+kind: ClusterRoleBinding
+metadata:
+  name: prometheus
+  labels:
+    app: prometheus
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: prometheus
+subjects:
+  - kind: ServiceAccount
+    name: prometheus
+    namespace: appmesh-system
+---
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: prometheus
+  namespace: appmesh-system
+  labels:
+    app: prometheus
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: prometheus
+  namespace: appmesh-system
+  labels:
+    app: prometheus
+data:
+  prometheus.yml: |-
+    global:
+      scrape_interval: 5s
+    scrape_configs:
+
+    # Scrape config for AppMesh Envoy sidecar
+    - job_name: 'appmesh-envoy'
+      metrics_path: /stats/prometheus
+      kubernetes_sd_configs:
+      - role: pod
+
+      relabel_configs:
+      - source_labels: [__meta_kubernetes_pod_container_name]
+        action: keep
+        regex: '^envoy$'
+      - source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port]
+        action: replace
+        regex: ([^:]+)(?::\d+)?;(\d+)
+        replacement: ${1}:9901
+        target_label: __address__
+      - action: labelmap
+        regex: __meta_kubernetes_pod_label_(.+)
+      - source_labels: [__meta_kubernetes_namespace]
+        action: replace
+        target_label: kubernetes_namespace
+      - source_labels: [__meta_kubernetes_pod_name]
+        action: replace
+        target_label: kubernetes_pod_name
+
+      # Exclude high cardinality metrics
+      metric_relabel_configs:
+      - source_labels: [ cluster_name ]
+        regex: '(outbound|inbound|prometheus_stats).*'
+        action: drop
+      - source_labels: [ tcp_prefix ]
+        regex: '(outbound|inbound|prometheus_stats).*'
+        action: drop
+      - source_labels: [ listener_address ]
+        regex: '(.+)'
+        action: drop
+      - source_labels: [ http_conn_manager_listener_prefix ]
+        regex: '(.+)'
+        action: drop
+      - source_labels: [ http_conn_manager_prefix ]
+        regex: '(.+)'
+        action: drop
+      - source_labels: [ __name__ ]
+        regex: 'envoy_tls.*'
+        action: drop
+      - source_labels: [ __name__ ]
+        regex: 'envoy_tcp_downstream.*'
+        action: drop
+      - source_labels: [ __name__ ]
+        regex: 'envoy_http_(stats|admin).*'
+        action: drop
+      - source_labels: [ __name__ ]
+        regex: 'envoy_cluster_(lb|retry|bind|internal|max|original).*'
+        action: drop
+
+    # Scrape config for API servers
+    - job_name: 'kubernetes-apiservers'
+      kubernetes_sd_configs:
+      - role: endpoints
+        namespaces:
+          names:
+          - default
+      scheme: https
+      tls_config:
+        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+      bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+      relabel_configs:
+      - source_labels: [__meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
+        action: keep
+        regex: kubernetes;https
+
+    # Scrape config for nodes
+    - job_name: 'kubernetes-nodes'
+      scheme: https
+      tls_config:
+        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+      bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+      kubernetes_sd_configs:
+      - role: node
+      relabel_configs:
+      - action: labelmap
+        regex: __meta_kubernetes_node_label_(.+)
+      - target_label: __address__
+        replacement: kubernetes.default.svc:443
+      - source_labels: [__meta_kubernetes_node_name]
+        regex: (.+)
+        target_label: __metrics_path__
+        replacement: /api/v1/nodes/${1}/proxy/metrics
+
+    # scrape config for cAdvisor
+    - job_name: 'kubernetes-cadvisor'
+      scheme: https
+      tls_config:
+        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+      bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+      kubernetes_sd_configs:
+      - role: node
+      relabel_configs:
+      - action: labelmap
+        regex: __meta_kubernetes_node_label_(.+)
+      - target_label: __address__
+        replacement: kubernetes.default.svc:443
+      - source_labels: [__meta_kubernetes_node_name]
+        regex: (.+)
+        target_label: __metrics_path__
+        replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor
+
+    # scrape config for pods
+    - job_name: kubernetes-pods
+      kubernetes_sd_configs:
+      - role: pod
+      relabel_configs:
+      - action: keep
+        regex: true
+        source_labels:
+        - __meta_kubernetes_pod_annotation_prometheus_io_scrape
+      - source_labels: [ __address__ ]
+        regex: '.*9901.*'
+        action: drop
+      - action: replace
+        regex: (.+)
+        source_labels:
+        - __meta_kubernetes_pod_annotation_prometheus_io_path
+        target_label: __metrics_path__
+      - action: replace
+        regex: ([^:]+)(?::\d+)?;(\d+)
+        replacement: $1:$2
+        source_labels:
+        - __address__
+        - __meta_kubernetes_pod_annotation_prometheus_io_port
+        target_label: __address__
+      - action: labelmap
+        regex: __meta_kubernetes_pod_label_(.+)
+      - action: replace
+        source_labels:
+        - __meta_kubernetes_namespace
+        target_label: kubernetes_namespace
+      - action: replace
+        source_labels:
+        - __meta_kubernetes_pod_name
+        target_label: kubernetes_pod_name
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: prometheus
+  namespace: appmesh-system
+  labels:
+    app: prometheus
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: prometheus
+  template:
+    metadata:
+      labels:
+        app: prometheus
+      annotations:
+        version: "appmesh-v1alpha1"
+    spec:
+      serviceAccountName: prometheus
+      containers:
+        - name: prometheus
+          image: "docker.io/prom/prometheus:v2.7.1"
+          imagePullPolicy: IfNotPresent
+          args:
+            - '--storage.tsdb.retention=6h'
+            - '--config.file=/etc/prometheus/prometheus.yml'
+          ports:
+            - containerPort: 9090
+              name: http
+          livenessProbe:
+            httpGet:
+              path: /-/healthy
+              port: 9090
+          readinessProbe:
+            httpGet:
+              path: /-/ready
+              port: 9090
+          resources:
+            requests:
+              cpu: 10m
+              memory: 128Mi
+          volumeMounts:
+            - name: config-volume
+              mountPath: /etc/prometheus
+      volumes:
+        - name: config-volume
+          configMap:
+            name: prometheus
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: prometheus
+  namespace: appmesh-system
+  labels:
+    name: prometheus
+spec:
+  selector:
+    app: prometheus
+  ports:
+    - name: http
+      protocol: TCP
+      port: 9090

artifacts/flagger/account.yaml

@@ -13,11 +13,56 @@ metadata:
   labels:
     app: flagger
 rules:
-- apiGroups: ['*']
-  resources: ['*']
-  verbs: ['*']
-- nonResourceURLs: ['*']
-  verbs: ['*']
+  - apiGroups:
+      - ""
+    resources:
+      - events
+      - configmaps
+      - secrets
+      - services
+    verbs: ["*"]
+  - apiGroups:
+      - apps
+    resources:
+      - deployments
+    verbs: ["*"]
+  - apiGroups:
+      - autoscaling
+    resources:
+      - horizontalpodautoscalers
+    verbs: ["*"]
+  - apiGroups:
+      - "extensions"
+    resources:
+      - ingresses
+      - ingresses/status
+    verbs: ["*"]
+  - apiGroups:
+      - flagger.app
+    resources:
+      - canaries
+      - canaries/status
+    verbs: ["*"]
+  - apiGroups:
+      - networking.istio.io
+    resources:
+      - virtualservices
+      - virtualservices/status
+    verbs: ["*"]
+  - apiGroups:
+      - appmesh.k8s.aws
+    resources:
+      - meshes
+      - meshes/status
+      - virtualnodes
+      - virtualnodes/status
+      - virtualservices
+      - virtualservices/status
+    verbs: ["*"]
+  - nonResourceURLs:
+      - /version
+    verbs:
+      - get
 ---
 apiVersion: rbac.authorization.k8s.io/v1beta1
 kind: ClusterRoleBinding

artifacts/flagger/crd.yaml

@@ -2,13 +2,18 @@ apiVersion: apiextensions.k8s.io/v1beta1
 kind: CustomResourceDefinition
 metadata:
   name: canaries.flagger.app
+  annotations:
+    helm.sh/resource-policy: keep
 spec:
   group: flagger.app
-  version: v1alpha2
+  version: v1alpha3
   versions:
-    - name: v1alpha2
+    - name: v1alpha3
       served: true
       storage: true
+    - name: v1alpha2
+      served: true
+      storage: false
     - name: v1alpha1
       served: true
       storage: false
@@ -16,15 +21,29 @@ spec:
     plural: canaries
     singular: canary
     kind: Canary
+    categories:
+      - all
   scope: Namespaced
+  subresources:
+    status: {}
+  additionalPrinterColumns:
+    - name: Status
+      type: string
+      JSONPath: .status.phase
+    - name: Weight
+      type: string
+      JSONPath: .status.canaryWeight
+    - name: LastTransitionTime
+      type: string
+      JSONPath: .status.lastTransitionTime
   validation:
     openAPIV3Schema:
       properties:
         spec:
           required:
-          - targetRef
-          - service
-          - canaryAnalysis
+            - targetRef
+            - service
+            - canaryAnalysis
           properties:
             progressDeadlineSeconds:
               type: number
@@ -39,7 +58,21 @@ spec:
                 name:
                   type: string
             autoscalerRef:
-              type: object
+              anyOf:
+                - type: string
+                - type: object
+              required: ['apiVersion', 'kind', 'name']
+              properties:
+                apiVersion:
+                  type: string
+                kind:
+                  type: string
+                name:
+                  type: string
+            ingressRef:
+              anyOf:
+                - type: string
+                - type: object
               required: ['apiVersion', 'kind', 'name']
               properties:
                 apiVersion:
@@ -54,8 +87,21 @@ spec:
               properties:
                 port:
                   type: number
+                portName:
+                  type: string
+                meshName:
+                  type: string
+                timeout:
+                  type: string
+            skipAnalysis:
+              type: boolean
             canaryAnalysis:
               properties:
+                interval:
+                  type: string
+                  pattern: "^[0-9]+(m|s)"
+                iterations:
+                  type: number
                 threshold:
                   type: number
                 maxWeight:
@@ -67,15 +113,17 @@ spec:
                   properties:
                     items:
                       type: object
-                      required: ['name', 'interval', 'threshold']
+                      required: ['name', 'threshold']
                       properties:
                         name:
                           type: string
                         interval:
                           type: string
-                          pattern: "^[0-9]+(m)"
+                          pattern: "^[0-9]+(m|s)"
                         threshold:
                           type: number
+                        query:
+                          type: string
                 webhooks:
                   type: array
                   properties:
@@ -85,9 +133,36 @@ spec:
                       properties:
                         name:
                           type: string
+                        type:
+                          type: string
+                          enum:
+                            - ""
+                            - pre-rollout
+                            - rollout
+                            - post-rollout
                         url:
                           type: string
                           format: url
                         timeout:
                           type: string
-                          pattern: "^[0-9]+(s)"
+                          pattern: "^[0-9]+(m|s)"
+        status:
+          properties:
+            phase:
+              type: string
+              enum:
+                - ""
+                - Initialized
+                - Progressing
+                - Succeeded
+                - Failed
+            canaryWeight:
+              type: number
+            failedChecks:
+              type: number
+            iterations:
+              type: number
+            lastAppliedSpec:
+              type: string
+            lastTransitionTime:
+              type: string

artifacts/flagger/deployment.yaml

@@ -22,8 +22,8 @@ spec:
       serviceAccountName: flagger
       containers:
       - name: flagger
-        image: quay.io/stefanprodan/flagger:0.2.0
-        imagePullPolicy: Always
+        image: weaveworks/flagger:0.13.1
+        imagePullPolicy: IfNotPresent
         ports:
         - name: http
           containerPort: 8080
@@ -31,6 +31,7 @@ spec:
         - ./flagger
         - -log-level=info
         - -control-loop-interval=10s
+        - -mesh-provider=$(MESH_PROVIDER)
         - -metrics-server=http://prometheus.istio-system.svc.cluster.local:9090
         livenessProbe:
           exec:

artifacts/gke/istio-gateway.yaml

@@ -0,0 +1,27 @@
+apiVersion: networking.istio.io/v1alpha3
+kind: Gateway
+metadata:
+  name: public-gateway
+  namespace: istio-system
+spec:
+  selector:
+    istio: ingressgateway
+  servers:
+    - port:
+        number: 80
+        name: http
+        protocol: HTTP
+      hosts:
+        - "*"
+      tls:
+        httpsRedirect: true
+    - port:
+        number: 443
+        name: https
+        protocol: HTTPS
+      hosts:
+        - "*"
+      tls:
+        mode: SIMPLE
+        privateKey: /etc/istio/ingressgateway-certs/tls.key
+        serverCertificate: /etc/istio/ingressgateway-certs/tls.crt

artifacts/gke/istio-prometheus.yaml

@@ -0,0 +1,443 @@
+---
+apiVersion: rbac.authorization.k8s.io/v1beta1
+kind: ClusterRole
+metadata:
+  name: prometheus
+  labels:
+    app: prometheus
+rules:
+  - apiGroups: [""]
+    resources:
+      - nodes
+      - services
+      - endpoints
+      - pods
+      - nodes/proxy
+    verbs: ["get", "list", "watch"]
+  - apiGroups: [""]
+    resources:
+      - configmaps
+    verbs: ["get"]
+  - nonResourceURLs: ["/metrics"]
+    verbs: ["get"]
+---
+apiVersion: rbac.authorization.k8s.io/v1beta1
+kind: ClusterRoleBinding
+metadata:
+  name: prometheus
+  labels:
+    app: prometheus
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: prometheus
+subjects:
+  - kind: ServiceAccount
+    name: prometheus
+    namespace: istio-system
+---
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: prometheus
+  namespace: istio-system
+  labels:
+    app: prometheus
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: prometheus
+  namespace: istio-system
+  labels:
+    app: prometheus
+data:
+  prometheus.yml: |-
+    global:
+      scrape_interval: 15s
+    scrape_configs:
+
+    - job_name: 'istio-mesh'
+      # Override the global default and scrape targets from this job every 5 seconds.
+      scrape_interval: 5s
+
+      kubernetes_sd_configs:
+      - role: endpoints
+        namespaces:
+          names:
+          - istio-system
+
+      relabel_configs:
+      - source_labels: [__meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
+        action: keep
+        regex: istio-telemetry;prometheus
+
+
+    # Scrape config for envoy stats
+    - job_name: 'envoy-stats'
+      metrics_path: /stats/prometheus
+      kubernetes_sd_configs:
+      - role: pod
+
+      relabel_configs:
+      - source_labels: [__meta_kubernetes_pod_container_port_name]
+        action: keep
+        regex: '.*-envoy-prom'
+      - source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port]
+        action: replace
+        regex: ([^:]+)(?::\d+)?;(\d+)
+        replacement: $1:15090
+        target_label: __address__
+      - action: labelmap
+        regex: __meta_kubernetes_pod_label_(.+)
+      - source_labels: [__meta_kubernetes_namespace]
+        action: replace
+        target_label: namespace
+      - source_labels: [__meta_kubernetes_pod_name]
+        action: replace
+        target_label: pod_name
+
+      metric_relabel_configs:
+      # Exclude some of the envoy metrics that have massive cardinality
+      # This list may need to be pruned further moving forward, as informed
+      # by performance and scalability testing.
+      - source_labels: [ cluster_name ]
+        regex: '(outbound|inbound|prometheus_stats).*'
+        action: drop
+      - source_labels: [ tcp_prefix ]
+        regex: '(outbound|inbound|prometheus_stats).*'
+        action: drop
+      - source_labels: [ listener_address ]
+        regex: '(.+)'
+        action: drop
+      - source_labels: [ http_conn_manager_listener_prefix ]
+        regex: '(.+)'
+        action: drop
+      - source_labels: [ http_conn_manager_prefix ]
+        regex: '(.+)'
+        action: drop
+      - source_labels: [ __name__ ]
+        regex: 'envoy_tls.*'
+        action: drop
+      - source_labels: [ __name__ ]
+        regex: 'envoy_tcp_downstream.*'
+        action: drop
+      - source_labels: [ __name__ ]
+        regex: 'envoy_http_(stats|admin).*'
+        action: drop
+      - source_labels: [ __name__ ]
+        regex: 'envoy_cluster_(lb|retry|bind|internal|max|original).*'
+        action: drop
+
+
+    - job_name: 'istio-policy'
+      # Override the global default and scrape targets from this job every 5 seconds.
+      scrape_interval: 5s
+      # metrics_path defaults to '/metrics'
+      # scheme defaults to 'http'.
+
+      kubernetes_sd_configs:
+      - role: endpoints
+        namespaces:
+          names:
+          - istio-system
+
+
+      relabel_configs:
+      - source_labels: [__meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
+        action: keep
+        regex: istio-policy;http-monitoring
+
+    - job_name: 'istio-telemetry'
+      # Override the global default and scrape targets from this job every 5 seconds.
+      scrape_interval: 5s
+      # metrics_path defaults to '/metrics'
+      # scheme defaults to 'http'.
+
+      kubernetes_sd_configs:
+      - role: endpoints
+        namespaces:
+          names:
+          - istio-system
+
+      relabel_configs:
+      - source_labels: [__meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
+        action: keep
+        regex: istio-telemetry;http-monitoring
+
+    - job_name: 'pilot'
+      # Override the global default and scrape targets from this job every 5 seconds.
+      scrape_interval: 5s
+      # metrics_path defaults to '/metrics'
+      # scheme defaults to 'http'.
+
+      kubernetes_sd_configs:
+      - role: endpoints
+        namespaces:
+          names:
+          - istio-system
+
+      relabel_configs:
+      - source_labels: [__meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
+        action: keep
+        regex: istio-pilot;http-monitoring
+
+    - job_name: 'galley'
+      # Override the global default and scrape targets from this job every 5 seconds.
+      scrape_interval: 5s
+      # metrics_path defaults to '/metrics'
+      # scheme defaults to 'http'.
+
+      kubernetes_sd_configs:
+      - role: endpoints
+        namespaces:
+          names:
+          - istio-system
+
+      relabel_configs:
+      - source_labels: [__meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
+        action: keep
+        regex: istio-galley;http-monitoring
+
+    # scrape config for API servers
+    - job_name: 'kubernetes-apiservers'
+      kubernetes_sd_configs:
+      - role: endpoints
+        namespaces:
+          names:
+          - default
+      scheme: https
+      tls_config:
+        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+      bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+      relabel_configs:
+      - source_labels: [__meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
+        action: keep
+        regex: kubernetes;https
+
+    # scrape config for nodes (kubelet)
+    - job_name: 'kubernetes-nodes'
+      scheme: https
+      tls_config:
+        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+      bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+      kubernetes_sd_configs:
+      - role: node
+      relabel_configs:
+      - action: labelmap
+        regex: __meta_kubernetes_node_label_(.+)
+      - target_label: __address__
+        replacement: kubernetes.default.svc:443
+      - source_labels: [__meta_kubernetes_node_name]
+        regex: (.+)
+        target_label: __metrics_path__
+        replacement: /api/v1/nodes/${1}/proxy/metrics
+
+    # Scrape config for Kubelet cAdvisor.
+    #
+    # This is required for Kubernetes 1.7.3 and later, where cAdvisor metrics
+    # (those whose names begin with 'container_') have been removed from the
+    # Kubelet metrics endpoint.  This job scrapes the cAdvisor endpoint to
+    # retrieve those metrics.
+    #
+    # In Kubernetes 1.7.0-1.7.2, these metrics are only exposed on the cAdvisor
+    # HTTP endpoint; use "replacement: /api/v1/nodes/${1}:4194/proxy/metrics"
+    # in that case (and ensure cAdvisor's HTTP server hasn't been disabled with
+    # the --cadvisor-port=0 Kubelet flag).
+    #
+    # This job is not necessary and should be removed in Kubernetes 1.6 and
+    # earlier versions, or it will cause the metrics to be scraped twice.
+    - job_name: 'kubernetes-cadvisor'
+      scheme: https
+      tls_config:
+        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+      bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+      kubernetes_sd_configs:
+      - role: node
+      relabel_configs:
+      - action: labelmap
+        regex: __meta_kubernetes_node_label_(.+)
+      - target_label: __address__
+        replacement: kubernetes.default.svc:443
+      - source_labels: [__meta_kubernetes_node_name]
+        regex: (.+)
+        target_label: __metrics_path__
+        replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor
+
+    # scrape config for service endpoints.
+    - job_name: 'kubernetes-service-endpoints'
+      kubernetes_sd_configs:
+      - role: endpoints
+      relabel_configs:
+      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape]
+        action: keep
+        regex: true
+      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scheme]
+        action: replace
+        target_label: __scheme__
+        regex: (https?)
+      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path]
+        action: replace
+        target_label: __metrics_path__
+        regex: (.+)
+      - source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port]
+        action: replace
+        target_label: __address__
+        regex: ([^:]+)(?::\d+)?;(\d+)
+        replacement: $1:$2
+      - action: labelmap
+        regex: __meta_kubernetes_service_label_(.+)
+      - source_labels: [__meta_kubernetes_namespace]
+        action: replace
+        target_label: kubernetes_namespace
+      - source_labels: [__meta_kubernetes_service_name]
+        action: replace
+        target_label: kubernetes_name
+
+    - job_name: 'kubernetes-pods'
+      kubernetes_sd_configs:
+      - role: pod
+      relabel_configs:  # If first two labels are present, pod should be scraped  by the istio-secure job.
+      - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape]
+        action: keep
+        regex: true
+      - source_labels: [__meta_kubernetes_pod_annotation_sidecar_istio_io_status]
+        action: drop
+        regex: (.+)
+      - source_labels: [__meta_kubernetes_pod_annotation_istio_mtls]
+        action: drop
+        regex: (true)
+      - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_path]
+        action: replace
+        target_label: __metrics_path__
+        regex: (.+)
+      - source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port]
+        action: replace
+        regex: ([^:]+)(?::\d+)?;(\d+)
+        replacement: $1:$2
+        target_label: __address__
+      - action: labelmap
+        regex: __meta_kubernetes_pod_label_(.+)
+      - source_labels: [__meta_kubernetes_namespace]
+        action: replace
+        target_label: namespace
+      - source_labels: [__meta_kubernetes_pod_name]
+        action: replace
+        target_label: pod_name
+
+    - job_name: 'kubernetes-pods-istio-secure'
+      scheme: https
+      tls_config:
+        ca_file: /etc/istio-certs/root-cert.pem
+        cert_file: /etc/istio-certs/cert-chain.pem
+        key_file: /etc/istio-certs/key.pem
+        insecure_skip_verify: true  # prometheus does not support secure naming.
+      kubernetes_sd_configs:
+      - role: pod
+      relabel_configs:
+      - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape]
+        action: keep
+        regex: true
+      # sidecar status annotation is added by sidecar injector and
+      # istio_workload_mtls_ability can be specifically placed on a pod to indicate its ability to receive mtls traffic.
+      - source_labels: [__meta_kubernetes_pod_annotation_sidecar_istio_io_status, __meta_kubernetes_pod_annotation_istio_mtls]
+        action: keep
+        regex: (([^;]+);([^;]*))|(([^;]*);(true))
+      - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_path]
+        action: replace
+        target_label: __metrics_path__
+        regex: (.+)
+      - source_labels: [__address__]  # Only keep address that is host:port
+        action: keep    # otherwise an extra target with ':443' is added for https scheme
+        regex: ([^:]+):(\d+)
+      - source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port]
+        action: replace
+        regex: ([^:]+)(?::\d+)?;(\d+)
+        replacement: $1:$2
+        target_label: __address__
+      - action: labelmap
+        regex: __meta_kubernetes_pod_label_(.+)
+      - source_labels: [__meta_kubernetes_namespace]
+        action: replace
+        target_label: namespace
+      - source_labels: [__meta_kubernetes_pod_name]
+        action: replace
+        target_label: pod_name
+---
+
+# Source: istio/charts/prometheus/templates/service.yaml
+apiVersion: v1
+kind: Service
+metadata:
+  name: prometheus
+  namespace: istio-system
+  annotations:
+    prometheus.io/scrape: 'true'
+  labels:
+    name: prometheus
+spec:
+  selector:
+    app: prometheus
+  ports:
+    - name: http-prometheus
+      protocol: TCP
+      port: 9090
+
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: prometheus
+  namespace: istio-system
+  labels:
+    app: prometheus
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: prometheus
+  template:
+    metadata:
+      labels:
+        app: prometheus
+      annotations:
+        sidecar.istio.io/inject: "false"
+        scheduler.alpha.kubernetes.io/critical-pod: ""
+    spec:
+      serviceAccountName: prometheus
+      containers:
+        - name: prometheus
+          image: "docker.io/prom/prometheus:v2.7.1"
+          imagePullPolicy: IfNotPresent
+          args:
+            - '--storage.tsdb.retention=6h'
+            - '--config.file=/etc/prometheus/prometheus.yml'
+          ports:
+            - containerPort: 9090
+              name: http
+          livenessProbe:
+            httpGet:
+              path: /-/healthy
+              port: 9090
+          readinessProbe:
+            httpGet:
+              path: /-/ready
+              port: 9090
+          resources:
+            requests:
+              cpu: 10m
+
+          volumeMounts:
+            - name: config-volume
+              mountPath: /etc/prometheus
+            - mountPath: /etc/istio-certs
+              name: istio-certs
+      volumes:
+        - name: config-volume
+          configMap:
+            name: prometheus
+        - name: istio-certs
+          secret:
+            defaultMode: 420
+            optional: true
+            secretName: istio.default

artifacts/loadtester/config.yaml

@@ -0,0 +1,19 @@
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: flagger-loadtester-bats
+data:
+  tests: |
+    #!/usr/bin/env bats
+
+    @test "check message" {
+      curl -sS http://${URL} | jq -r .message | {
+        run cut -d $' ' -f1
+        [ $output = "greetings" ]
+      }
+    }
+
+    @test "check headers" {
+      curl -sS http://${URL}/headers | grep X-Request-Id
+    }

artifacts/loadtester/deployment.yaml

@@ -0,0 +1,67 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: flagger-loadtester
+  labels:
+    app: flagger-loadtester
+spec:
+  selector:
+    matchLabels:
+      app: flagger-loadtester
+  template:
+    metadata:
+      labels:
+        app: flagger-loadtester
+      annotations:
+        prometheus.io/scrape: "true"
+    spec:
+      containers:
+        - name: loadtester
+          image: weaveworks/flagger-loadtester:0.3.0
+          imagePullPolicy: IfNotPresent
+          ports:
+            - name: http
+              containerPort: 8080
+          command:
+            - ./loadtester
+            - -port=8080
+            - -log-level=info
+            - -timeout=1h
+          livenessProbe:
+            exec:
+              command:
+                - wget
+                - --quiet
+                - --tries=1
+                - --timeout=4
+                - --spider
+                - http://localhost:8080/healthz
+            timeoutSeconds: 5
+          readinessProbe:
+            exec:
+              command:
+                - wget
+                - --quiet
+                - --tries=1
+                - --timeout=4
+                - --spider
+                - http://localhost:8080/healthz
+            timeoutSeconds: 5
+          resources:
+            limits:
+              memory: "512Mi"
+              cpu: "1000m"
+            requests:
+              memory: "32Mi"
+              cpu: "10m"
+          securityContext:
+            readOnlyRootFilesystem: true
+            runAsUser: 10001
+#          volumeMounts:
+#            - name: tests
+#              mountPath: /bats
+#              readOnly: true
+#      volumes:
+#        - name: tests
+#          configMap:
+#            name: flagger-loadtester-bats

artifacts/loadtester/service.yaml

@@ -0,0 +1,15 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: flagger-loadtester
+  labels:
+    app: flagger-loadtester
+spec:
+  type: ClusterIP
+  selector:
+    app: flagger-loadtester
+  ports:
+    - name: http
+      port: 80
+      protocol: TCP
+      targetPort: http

artifacts/namespaces/test.yaml

@@ -4,3 +4,4 @@ metadata:
   name: test
   labels:
     istio-injection: enabled
+    appmesh.k8s.aws/sidecarInjectorWebhook: enabled

artifacts/nginx/canary.yaml

@@ -0,0 +1,68 @@
+apiVersion: flagger.app/v1alpha3
+kind: Canary
+metadata:
+  name: podinfo
+  namespace: test
+spec:
+  # deployment reference
+  targetRef:
+    apiVersion: apps/v1
+    kind: Deployment
+    name: podinfo
+  # ingress reference
+  ingressRef:
+    apiVersion: extensions/v1beta1
+    kind: Ingress
+    name: podinfo
+  # HPA reference (optional)
+  autoscalerRef:
+    apiVersion: autoscaling/v2beta1
+    kind: HorizontalPodAutoscaler
+    name: podinfo
+  # the maximum time in seconds for the canary deployment
+  # to make progress before it is rollback (default 600s)
+  progressDeadlineSeconds: 60
+  service:
+    # container port
+    port: 9898
+  canaryAnalysis:
+    # schedule interval (default 60s)
+    interval: 10s
+    # max number of failed metric checks before rollback
+    threshold: 10
+    # max traffic percentage routed to canary
+    # percentage (0-100)
+    maxWeight: 50
+    # canary increment step
+    # percentage (0-100)
+    stepWeight: 5
+    # NGINX Prometheus checks
+    metrics:
+    - name: request-success-rate
+      # minimum req success rate (non 5xx responses)
+      # percentage (0-100)
+      threshold: 99
+      interval: 1m
+    - name: "latency"
+      threshold: 0.5
+      interval: 1m
+      query: |
+        histogram_quantile(0.99,
+          sum(
+            rate(
+              http_request_duration_seconds_bucket{
+                kubernetes_namespace="test",
+                kubernetes_pod_name=~"podinfo-[0-9a-zA-Z]+(-[0-9a-zA-Z]+)"
+              }[1m]
+            )
+          ) by (le)
+        )
+    # external checks (optional)
+    webhooks:
+      - name: load-test
+        url: http://flagger-loadtester.test/
+        timeout: 5s
+        metadata:
+          type: cmd
+          cmd: "hey -z 1m -q 10 -c 2 http://app.example.com/"
+          logCmdOutput: "true"

artifacts/nginx/deployment.yaml

@@ -0,0 +1,69 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: podinfo
+  namespace: test
+  labels:
+    app: podinfo
+spec:
+  replicas: 1
+  strategy:
+    rollingUpdate:
+      maxUnavailable: 0
+    type: RollingUpdate
+  selector:
+    matchLabels:
+      app: podinfo
+  template:
+    metadata:
+      annotations:
+        prometheus.io/scrape: "true"
+      labels:
+        app: podinfo
+    spec:
+      containers:
+      - name: podinfod
+        image: quay.io/stefanprodan/podinfo:1.4.0
+        imagePullPolicy: IfNotPresent
+        ports:
+        - containerPort: 9898
+          name: http
+          protocol: TCP
+        command:
+        - ./podinfo
+        - --port=9898
+        - --level=info
+        - --random-delay=false
+        - --random-error=false
+        env:
+        - name: PODINFO_UI_COLOR
+          value: green
+        livenessProbe:
+          exec:
+            command:
+            - podcli
+            - check
+            - http
+            - localhost:9898/healthz
+          failureThreshold: 3
+          periodSeconds: 10
+          successThreshold: 1
+          timeoutSeconds: 2
+        readinessProbe:
+          exec:
+            command:
+            - podcli
+            - check
+            - http
+            - localhost:9898/readyz
+          failureThreshold: 3
+          periodSeconds: 3
+          successThreshold: 1
+          timeoutSeconds: 2
+        resources:
+          limits:
+            cpu: 1000m
+            memory: 256Mi
+          requests:
+            cpu: 100m
+            memory: 16Mi

artifacts/nginx/hpa.yaml

@@ -0,0 +1,19 @@
+apiVersion: autoscaling/v2beta1
+kind: HorizontalPodAutoscaler
+metadata:
+  name: podinfo
+  namespace: test
+spec:
+  scaleTargetRef:
+    apiVersion: apps/v1
+    kind: Deployment
+    name: podinfo
+  minReplicas: 2
+  maxReplicas: 4
+  metrics:
+  - type: Resource
+    resource:
+      name: cpu
+      # scale up if usage is above
+      # 99% of the requested CPU (100m)
+      targetAverageUtilization: 99

artifacts/nginx/ingress.yaml

@@ -0,0 +1,17 @@
+apiVersion: extensions/v1beta1
+kind: Ingress
+metadata:
+  name: podinfo
+  namespace: test
+  labels:
+    app: podinfo
+  annotations:
+    kubernetes.io/ingress.class: "nginx"
+spec:
+  rules:
+    - host: app.exmaple.com
+      http:
+        paths:
+          - backend:
+              serviceName: podinfo
+              servicePort: 9898

artifacts/routing/destination-rule.yaml

@@ -0,0 +1,45 @@
+apiVersion: networking.istio.io/v1alpha3
+kind: VirtualService
+metadata:
+  name: podinfo
+  namespace: test
+spec:
+  gateways:
+    - public-gateway.istio-system.svc.cluster.local
+    - mesh
+  hosts:
+    - podinfo.istio.weavedx.com
+    - podinfo
+  http:
+    - route:
+        - destination:
+            host: podinfo
+            subset: primary
+          weight: 50
+        - destination:
+            host: podinfo
+            subset: canary
+          weight: 50
+---
+apiVersion: networking.istio.io/v1alpha3
+kind: DestinationRule
+metadata:
+  name: podinfo-destination
+  namespace: test
+spec:
+  host: podinfo
+  trafficPolicy:
+    loadBalancer:
+      consistentHash:
+        httpCookie:
+          name: istiouser
+          ttl: 30s
+  subsets:
+    - name: primary
+      labels:
+        app: podinfo
+        role: primary
+    - name: canary
+      labels:
+        app: podinfo
+        role: canary

artifacts/routing/match.yaml

@@ -8,13 +8,17 @@ spec:
   - public-gateway.istio-system.svc.cluster.local
   - mesh
   hosts:
-  - podinfo.iowa.weavedx.com
+  - app.istio.weavedx.com
   - podinfo
   http:
   - match:
     - headers:
         user-agent:
           regex: ^(?!.*Chrome)(?=.*\bSafari\b).*$
+      uri:
+        prefix: "/version/"
+    rewrite:
+      uri: /api/info
     route:
     - destination:
         host: podinfo-primary
@@ -26,7 +30,12 @@ spec:
         port:
           number: 9898
       weight: 100
-  - route:
+  - match:
+      - uri:
+          prefix: "/version/"
+    rewrite:
+      uri: /api/info
+    route:
     - destination:
         host: podinfo-primary
         port:

artifacts/workloads/canary-deployment.yaml

@@ -23,7 +23,7 @@ spec:
     spec:
       containers:
       - name: podinfod
-        image: quay.io/stefanprodan/podinfo:1.2.0
+        image: quay.io/stefanprodan/podinfo:1.4.0
         imagePullPolicy: IfNotPresent
         ports:
         - containerPort: 9898
@@ -67,9 +67,3 @@ spec:
           requests:
             cpu: 100m
             memory: 16Mi
-        volumeMounts:
-        - mountPath: /data
-          name: data
-      volumes:
-      - emptyDir: {}
-        name: data

artifacts/workloads/canary-service.yaml

@@ -1,10 +1,8 @@
 apiVersion: v1
 kind: Service
 metadata:
-  name: podinfo
+  name: podinfo-canary
   namespace: test
-  labels:
-    app: podinfo
 spec:
   type: ClusterIP
   selector:

artifacts/workloads/primary-deployment.yaml

@@ -23,7 +23,7 @@ spec:
     spec:
       containers:
       - name: podinfod
-        image: quay.io/stefanprodan/podinfo:1.1.1
+        image: quay.io/stefanprodan/podinfo:1.4.1
         imagePullPolicy: IfNotPresent
         ports:
         - containerPort: 9898

artifacts/workloads/service.yaml

@@ -0,0 +1,14 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: podinfo
+  namespace: test
+spec:
+  type: ClusterIP
+  selector:
+    app: podinfo-primary
+  ports:
+  - name: http
+    port: 9898
+    protocol: TCP
+    targetPort: http

charts/flagger/Chart.yaml

@@ -1,14 +1,14 @@
 apiVersion: v1
 name: flagger
-version: 0.2.0
-appVersion: 0.2.0
-kubeVersion: ">=1.9.0-0"
+version: 0.13.1
+appVersion: 0.13.1
+kubeVersion: ">=1.11.0-0"
 engine: gotpl
-description: Flagger is a Kubernetes operator that automates the promotion of canary deployments using Istio routing for traffic shifting and Prometheus metrics for canary analysis.
-home: https://flagger.app
-icon: https://raw.githubusercontent.com/stefanprodan/flagger/master/docs/logo/flagger-icon.png
+description: Flagger is a Kubernetes operator that automates the promotion of canary deployments using Istio, App Mesh or NGINX routing for traffic shifting and Prometheus metrics for canary analysis.
+home: https://docs.flagger.app
+icon: https://raw.githubusercontent.com/weaveworks/flagger/master/docs/logo/flagger-icon.png
 sources:
-- https://github.com/stefanprodan/flagger
+- https://github.com/weaveworks/flagger
 maintainers:
 - name: stefanprodan
   url: https://github.com/stefanprodan
@@ -16,4 +16,5 @@ maintainers:
 keywords:
 - canary
 - istio
+- appmesh
 - gitops

charts/flagger/README.md

@@ -1,14 +1,14 @@
 # Flagger
 
-[Flagger](https://flagger.app) is a Kubernetes operator that automates the promotion of canary deployments
-using Istio routing for traffic shifting and Prometheus metrics for canary analysis. 
+[Flagger](https://github.com/weaveworks/flagger) is a Kubernetes operator that automates the promotion of 
+canary deployments using Istio routing for traffic shifting and Prometheus metrics for canary analysis. 
 Flagger implements a control loop that gradually shifts traffic to the canary while measuring key performance indicators
 like HTTP requests success rate, requests average duration and pods health.
 Based on the KPIs analysis a canary is promoted or aborted and the analysis result is published to Slack.
 
 ## Prerequisites
 
-* Kubernetes >= 1.9
+* Kubernetes >= 1.11
 * Istio >= 1.0
 * Prometheus >= 2.6
 
@@ -45,10 +45,9 @@ The following tables lists the configurable parameters of the Flagger chart and
 
 Parameter | Description | Default
 --- | --- | ---
-`image.repository` | image repository | `quay.io/stefanprodan/flagger`
+`image.repository` | image repository | `weaveworks/flagger`
 `image.tag` | image tag | `<VERSION>`
 `image.pullPolicy` | image pull policy | `IfNotPresent`
-`controlLoopInterval` | wait interval between checks | `10s`
 `metricsServer` | Prometheus URL | `http://prometheus.istio-system:9090`
 `slack.url` | Slack incoming webhook | None
 `slack.channel` | Slack channel | None
@@ -68,7 +67,8 @@ Specify each parameter using the `--set key=value[,key=value]` argument to `helm
 ```console
 $ helm upgrade -i flagger flagger/flagger \
   --namespace istio-system \
-  --set controlLoopInterval=1m
+  --set slack.url=https://hooks.slack.com/services/YOUR/SLACK/WEBHOOK \
+  --set slack.channel=general
 ```
 
 Alternatively, a YAML file that specifies the values for the above parameters can be provided while installing the chart. For example,
@@ -80,5 +80,5 @@ $ helm upgrade -i flagger flagger/flagger \
 ```
 
 > **Tip**: You can use the default [values.yaml](values.yaml)
-```
+
 

charts/flagger/templates/crd.yaml

@@ -3,13 +3,18 @@ apiVersion: apiextensions.k8s.io/v1beta1
 kind: CustomResourceDefinition
 metadata:
   name: canaries.flagger.app
+  annotations:
+    helm.sh/resource-policy: keep
 spec:
   group: flagger.app
-  version: v1alpha2
+  version: v1alpha3
   versions:
-    - name: v1alpha2
+    - name: v1alpha3
       served: true
       storage: true
+    - name: v1alpha2
+      served: true
+      storage: false
     - name: v1alpha1
       served: true
       storage: false
@@ -17,7 +22,21 @@ spec:
     plural: canaries
     singular: canary
     kind: Canary
+    categories:
+      - all
   scope: Namespaced
+  subresources:
+    status: {}
+  additionalPrinterColumns:
+    - name: Status
+      type: string
+      JSONPath: .status.phase
+    - name: Weight
+      type: string
+      JSONPath: .status.canaryWeight
+    - name: LastTransitionTime
+      type: string
+      JSONPath: .status.lastTransitionTime
   validation:
     openAPIV3Schema:
       properties:
@@ -40,7 +59,21 @@ spec:
                 name:
                   type: string
             autoscalerRef:
-              type: object
+              anyOf:
+                - type: string
+                - type: object
+              required: ['apiVersion', 'kind', 'name']
+              properties:
+                apiVersion:
+                  type: string
+                kind:
+                  type: string
+                name:
+                  type: string
+            ingressRef:
+              anyOf:
+                - type: string
+                - type: object
               required: ['apiVersion', 'kind', 'name']
               properties:
                 apiVersion:
@@ -55,8 +88,21 @@ spec:
               properties:
                 port:
                   type: number
+                portName:
+                  type: string
+                meshName:
+                  type: string
+                timeout:
+                  type: string
+            skipAnalysis:
+              type: boolean
             canaryAnalysis:
               properties:
+                interval:
+                  type: string
+                  pattern: "^[0-9]+(m|s)"
+                iterations:
+                  type: number
                 threshold:
                   type: number
                 maxWeight:
@@ -68,15 +114,17 @@ spec:
                   properties:
                     items:
                       type: object
-                      required: ['name', 'interval', 'threshold']
+                      required: ['name', 'threshold']
                       properties:
                         name:
                           type: string
                         interval:
                           type: string
-                          pattern: "^[0-9]+(m)"
+                          pattern: "^[0-9]+(m|s)"
                         threshold:
                           type: number
+                        query:
+                          type: string
                 webhooks:
                   type: array
                   properties:
@@ -86,11 +134,37 @@ spec:
                       properties:
                         name:
                           type: string
+                        type:
+                          type: string
+                          enum:
+                            - ""
+                            - pre-rollout
+                            - rollout
+                            - post-rollout
                         url:
                           type: string
                           format: url
                         timeout:
                           type: string
-                          pattern: "^[0-9]+(s)"
-
+                          pattern: "^[0-9]+(m|s)"
+        status:
+          properties:
+            phase:
+              type: string
+              enum:
+                - ""
+                - Initialized
+                - Progressing
+                - Succeeded
+                - Failed
+            canaryWeight:
+              type: number
+            failedChecks:
+              type: number
+            iterations:
+              type: number
+            lastAppliedSpec:
+              type: string
+            lastTransitionTime:
+              type: string
 {{- end }}

charts/flagger/templates/deployment.yaml

@@ -35,8 +35,17 @@ spec:
           command:
           - ./flagger
           - -log-level=info
-          - -control-loop-interval={{ .Values.controlLoopInterval }}
+          {{- if .Values.meshProvider }}
+          - -mesh-provider={{ .Values.meshProvider }}
+          {{- end }}
+          {{- if .Values.prometheus.install }}
+          - -metrics-server=http://{{ template "flagger.fullname" . }}-prometheus:9090
+          {{- else }}
           - -metrics-server={{ .Values.metricsServer }}
+          {{- end }}
+          {{- if .Values.namespace }}
+          - -namespace={{ .Values.namespace }}
+          {{- end }}
           {{- if .Values.slack.url }}
           - -slack-url={{ .Values.slack.url }}
           - -slack-user={{ .Values.slack.user }}

charts/flagger/templates/prometheus.yaml

@@ -0,0 +1,292 @@
+{{- if .Values.prometheus.install }}
+apiVersion: rbac.authorization.k8s.io/v1beta1
+kind: ClusterRole
+metadata:
+  name: {{ template "flagger.fullname" . }}-prometheus
+  labels:
+    helm.sh/chart: {{ template "flagger.chart" . }}
+    app.kubernetes.io/name: {{ template "flagger.name" . }}
+    app.kubernetes.io/managed-by: {{ .Release.Service }}
+    app.kubernetes.io/instance: {{ .Release.Name }}
+rules:
+  - apiGroups: [""]
+    resources:
+      - nodes
+      - services
+      - endpoints
+      - pods
+      - nodes/proxy
+    verbs: ["get", "list", "watch"]
+  - apiGroups: [""]
+    resources:
+      - configmaps
+    verbs: ["get"]
+  - nonResourceURLs: ["/metrics"]
+    verbs: ["get"]
+---
+apiVersion: rbac.authorization.k8s.io/v1beta1
+kind: ClusterRoleBinding
+metadata:
+  name: {{ template "flagger.fullname" . }}-prometheus
+  labels:
+    helm.sh/chart: {{ template "flagger.chart" . }}
+    app.kubernetes.io/name: {{ template "flagger.name" . }}
+    app.kubernetes.io/managed-by: {{ .Release.Service }}
+    app.kubernetes.io/instance: {{ .Release.Name }}
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: {{ template "flagger.fullname" . }}-prometheus
+subjects:
+  - kind: ServiceAccount
+    name: {{ template "flagger.serviceAccountName" . }}-prometheus
+    namespace: {{ .Release.Namespace }}
+---
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: {{ template "flagger.serviceAccountName" . }}-prometheus
+  namespace: {{ .Release.Namespace }}
+  labels:
+    helm.sh/chart: {{ template "flagger.chart" . }}
+    app.kubernetes.io/name: {{ template "flagger.name" . }}
+    app.kubernetes.io/managed-by: {{ .Release.Service }}
+    app.kubernetes.io/instance: {{ .Release.Name }}
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: {{ template "flagger.fullname" . }}-prometheus
+  namespace: {{ .Release.Namespace }}
+  labels:
+    helm.sh/chart: {{ template "flagger.chart" . }}
+    app.kubernetes.io/name: {{ template "flagger.name" . }}
+    app.kubernetes.io/managed-by: {{ .Release.Service }}
+    app.kubernetes.io/instance: {{ .Release.Name }}
+data:
+  prometheus.yml: |-
+    global:
+      scrape_interval: 5s
+    scrape_configs:
+
+    # Scrape config for AppMesh Envoy sidecar
+    - job_name: 'appmesh-envoy'
+      metrics_path: /stats/prometheus
+      kubernetes_sd_configs:
+      - role: pod
+
+      relabel_configs:
+      - source_labels: [__meta_kubernetes_pod_container_name]
+        action: keep
+        regex: '^envoy$'
+      - source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port]
+        action: replace
+        regex: ([^:]+)(?::\d+)?;(\d+)
+        replacement: ${1}:9901
+        target_label: __address__
+      - action: labelmap
+        regex: __meta_kubernetes_pod_label_(.+)
+      - source_labels: [__meta_kubernetes_namespace]
+        action: replace
+        target_label: kubernetes_namespace
+      - source_labels: [__meta_kubernetes_pod_name]
+        action: replace
+        target_label: kubernetes_pod_name
+
+      # Exclude high cardinality metrics
+      metric_relabel_configs:
+      - source_labels: [ cluster_name ]
+        regex: '(outbound|inbound|prometheus_stats).*'
+        action: drop
+      - source_labels: [ tcp_prefix ]
+        regex: '(outbound|inbound|prometheus_stats).*'
+        action: drop
+      - source_labels: [ listener_address ]
+        regex: '(.+)'
+        action: drop
+      - source_labels: [ http_conn_manager_listener_prefix ]
+        regex: '(.+)'
+        action: drop
+      - source_labels: [ http_conn_manager_prefix ]
+        regex: '(.+)'
+        action: drop
+      - source_labels: [ __name__ ]
+        regex: 'envoy_tls.*'
+        action: drop
+      - source_labels: [ __name__ ]
+        regex: 'envoy_tcp_downstream.*'
+        action: drop
+      - source_labels: [ __name__ ]
+        regex: 'envoy_http_(stats|admin).*'
+        action: drop
+      - source_labels: [ __name__ ]
+        regex: 'envoy_cluster_(lb|retry|bind|internal|max|original).*'
+        action: drop
+
+    # Scrape config for API servers
+    - job_name: 'kubernetes-apiservers'
+      kubernetes_sd_configs:
+      - role: endpoints
+        namespaces:
+          names:
+          - default
+      scheme: https
+      tls_config:
+        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+      bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+      relabel_configs:
+      - source_labels: [__meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
+        action: keep
+        regex: kubernetes;https
+
+    # Scrape config for nodes
+    - job_name: 'kubernetes-nodes'
+      scheme: https
+      tls_config:
+        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+      bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+      kubernetes_sd_configs:
+      - role: node
+      relabel_configs:
+      - action: labelmap
+        regex: __meta_kubernetes_node_label_(.+)
+      - target_label: __address__
+        replacement: kubernetes.default.svc:443
+      - source_labels: [__meta_kubernetes_node_name]
+        regex: (.+)
+        target_label: __metrics_path__
+        replacement: /api/v1/nodes/${1}/proxy/metrics
+
+    # scrape config for cAdvisor
+    - job_name: 'kubernetes-cadvisor'
+      scheme: https
+      tls_config:
+        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+      bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+      kubernetes_sd_configs:
+      - role: node
+      relabel_configs:
+      - action: labelmap
+        regex: __meta_kubernetes_node_label_(.+)
+      - target_label: __address__
+        replacement: kubernetes.default.svc:443
+      - source_labels: [__meta_kubernetes_node_name]
+        regex: (.+)
+        target_label: __metrics_path__
+        replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor
+
+    # scrape config for pods
+    - job_name: kubernetes-pods
+      kubernetes_sd_configs:
+      - role: pod
+      relabel_configs:
+      - action: keep
+        regex: true
+        source_labels:
+        - __meta_kubernetes_pod_annotation_prometheus_io_scrape
+      - source_labels: [ __address__ ]
+        regex: '.*9901.*'
+        action: drop
+      - action: replace
+        regex: (.+)
+        source_labels:
+        - __meta_kubernetes_pod_annotation_prometheus_io_path
+        target_label: __metrics_path__
+      - action: replace
+        regex: ([^:]+)(?::\d+)?;(\d+)
+        replacement: $1:$2
+        source_labels:
+        - __address__
+        - __meta_kubernetes_pod_annotation_prometheus_io_port
+        target_label: __address__
+      - action: labelmap
+        regex: __meta_kubernetes_pod_label_(.+)
+      - action: replace
+        source_labels:
+        - __meta_kubernetes_namespace
+        target_label: kubernetes_namespace
+      - action: replace
+        source_labels:
+        - __meta_kubernetes_pod_name
+        target_label: kubernetes_pod_name
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: {{ template "flagger.fullname" . }}-prometheus
+  namespace: {{ .Release.Namespace }}
+  labels:
+    helm.sh/chart: {{ template "flagger.chart" . }}
+    app.kubernetes.io/name: {{ template "flagger.name" . }}
+    app.kubernetes.io/managed-by: {{ .Release.Service }}
+    app.kubernetes.io/instance: {{ .Release.Name }}
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: {{ template "flagger.name" . }}-prometheus
+      app.kubernetes.io/instance: {{ .Release.Name }}
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: {{ template "flagger.name" . }}-prometheus
+        app.kubernetes.io/instance: {{ .Release.Name }}
+      annotations:
+        appmesh.k8s.aws/sidecarInjectorWebhook: disabled
+        sidecar.istio.io/inject: "false"
+    spec:
+      serviceAccountName: {{ template "flagger.serviceAccountName" . }}-prometheus
+      containers:
+        - name: prometheus
+          image: "docker.io/prom/prometheus:v2.7.1"
+          imagePullPolicy: IfNotPresent
+          args:
+            - '--storage.tsdb.retention=6h'
+            - '--config.file=/etc/prometheus/prometheus.yml'
+          ports:
+            - containerPort: 9090
+              name: http
+          livenessProbe:
+            httpGet:
+              path: /-/healthy
+              port: 9090
+          readinessProbe:
+            httpGet:
+              path: /-/ready
+              port: 9090
+          resources:
+            requests:
+              cpu: 10m
+              memory: 128Mi
+          volumeMounts:
+            - name: config-volume
+              mountPath: /etc/prometheus
+            - name: data-volume
+              mountPath: /prometheus/data
+
+      volumes:
+        - name: config-volume
+          configMap:
+            name: {{ template "flagger.fullname" . }}-prometheus
+        - name: data-volume
+          emptyDir: {}
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: {{ template "flagger.fullname" . }}-prometheus
+  namespace: {{ .Release.Namespace }}
+  labels:
+    helm.sh/chart: {{ template "flagger.chart" . }}
+    app.kubernetes.io/name: {{ template "flagger.name" . }}
+    app.kubernetes.io/managed-by: {{ .Release.Service }}
+    app.kubernetes.io/instance: {{ .Release.Name }}
+spec:
+  selector:
+    app.kubernetes.io/name: {{ template "flagger.name" . }}-prometheus
+    app.kubernetes.io/instance: {{ .Release.Name }}
+  ports:
+    - name: http
+      protocol: TCP
+      port: 9090
+{{- end }}

charts/flagger/templates/rbac.yaml

@@ -9,11 +9,56 @@ metadata:
     app.kubernetes.io/managed-by: {{ .Release.Service }}
     app.kubernetes.io/instance: {{ .Release.Name }}
 rules:
-- apiGroups: ['*']
-  resources: ['*']
-  verbs: ['*']
-- nonResourceURLs: ['*']
-  verbs: ['*']
+  - apiGroups:
+      - ""
+    resources:
+      - events
+      - configmaps
+      - secrets
+      - services
+    verbs: ["*"]
+  - apiGroups:
+      - apps
+    resources:
+      - deployments
+    verbs: ["*"]
+  - apiGroups:
+      - autoscaling
+    resources:
+      - horizontalpodautoscalers
+    verbs: ["*"]
+  - apiGroups:
+      - "extensions"
+    resources:
+      - ingresses
+      - ingresses/status
+    verbs: ["*"]
+  - apiGroups:
+      - flagger.app
+    resources:
+      - canaries
+      - canaries/status
+    verbs: ["*"]
+  - apiGroups:
+      - networking.istio.io
+    resources:
+      - virtualservices
+      - virtualservices/status
+    verbs: ["*"]
+  - apiGroups:
+      - appmesh.k8s.aws
+    resources:
+      - meshes
+      - meshes/status
+      - virtualnodes
+      - virtualnodes/status
+      - virtualservices
+      - virtualservices/status
+    verbs: ["*"]
+  - nonResourceURLs:
+      - /version
+    verbs:
+      - get
 ---
 apiVersion: rbac.authorization.k8s.io/v1beta1
 kind: ClusterRoleBinding

charts/flagger/values.yaml

@@ -1,12 +1,17 @@
 # Default values for flagger.
 
 image:
-  repository: quay.io/stefanprodan/flagger
-  tag: 0.2.0
+  repository: weaveworks/flagger
+  tag: 0.13.1
   pullPolicy: IfNotPresent
 
-controlLoopInterval: "10s"
-metricsServer: "http://prometheus.istio-system.svc.cluster.local:9090"
+metricsServer: "http://prometheus:9090"
+
+# accepted values are istio, appmesh, nginx or supergloo:mesh.namespace (defaults to istio)
+meshProvider: ""
+
+# single namespace restriction
+namespace: ""
 
 slack:
   user: flagger
@@ -44,3 +49,7 @@ nodeSelector: {}
 tolerations: []
 
 affinity: {}
+
+prometheus:
+  # to be used with AppMesh or nginx ingress
+  install: false

charts/grafana/Chart.yaml

@@ -1,12 +1,12 @@
 apiVersion: v1
 name: grafana
-version: 0.1.0
-appVersion: 5.4.2
+version: 1.2.0
+appVersion: 5.4.3
 description: Grafana dashboards for monitoring Flagger canary deployments
-icon: https://raw.githubusercontent.com/stefanprodan/flagger/master/docs/logo/flagger-icon.png
+icon: https://raw.githubusercontent.com/weaveworks/flagger/master/docs/logo/flagger-icon.png
 home: https://flagger.app
 sources:
-- https://github.com/stefanprodan/flagger
+- https://github.com/weaveworks/flagger
 maintainers:
 - name: stefanprodan
   url: https://github.com/stefanprodan

charts/grafana/README.md

@@ -2,11 +2,11 @@
 
 Grafana dashboards for monitoring progressive deployments powered by Istio, Prometheus and Flagger.
 
-![flagger-grafana](https://raw.githubusercontent.com/stefanprodan/flagger/master/docs/screens/grafana-canary-analysis.png)
+![flagger-grafana](https://raw.githubusercontent.com/weaveworks/flagger/master/docs/screens/grafana-canary-analysis.png)
 
 ## Prerequisites
 
-* Kubernetes >= 1.9
+* Kubernetes >= 1.11
 * Istio >= 1.0
 * Prometheus >= 2.6
 
@@ -75,5 +75,5 @@ helm install flagger/grafana --name flagger-grafana -f values.yaml
 ```
 
 > **Tip**: You can use the default [values.yaml](values.yaml)
-```
+
 

charts/grafana/dashboards/istio.json

@@ -2,7 +2,6 @@
   "annotations": {
     "list": [
       {
-        "$$hashKey": "object:1587",
         "builtIn": 1,
         "datasource": "-- Grafana --",
         "enable": true,
@@ -16,8 +15,8 @@
   "editable": true,
   "gnetId": null,
   "graphTooltip": 0,
-  "id": null,
-  "iteration": 1534587617141,
+  "id": 1,
+  "iteration": 1549736611069,
   "links": [],
   "panels": [
     {
@@ -179,7 +178,6 @@
       "tableColumn": "",
       "targets": [
         {
-          "$$hashKey": "object:2857",
           "expr": "sum(irate(istio_requests_total{reporter=\"destination\",destination_workload_namespace=~\"$namespace\",destination_workload=~\"$primary\",response_code!~\"5.*\"}[30s])) / sum(irate(istio_requests_total{reporter=\"destination\",destination_workload_namespace=~\"$namespace\",destination_workload=~\"$primary\"}[30s]))",
           "format": "time_series",
           "intervalFactor": 1,
@@ -344,7 +342,6 @@
       "tableColumn": "",
       "targets": [
         {
-          "$$hashKey": "object:2810",
           "expr": "sum(irate(istio_requests_total{reporter=\"destination\",destination_workload_namespace=~\"$namespace\",destination_workload=~\"$canary\",response_code!~\"5.*\"}[30s])) / sum(irate(istio_requests_total{reporter=\"destination\",destination_workload_namespace=~\"$namespace\",destination_workload=~\"$canary\"}[30s]))",
           "format": "time_series",
           "intervalFactor": 1,
@@ -363,7 +360,7 @@
           "value": "null"
         }
       ],
-      "valueName": "avg"
+      "valueName": "current"
     },
     {
       "aliasColors": {},
@@ -432,6 +429,7 @@
       ],
       "thresholds": [],
       "timeFrom": null,
+      "timeRegions": [],
       "timeShift": null,
       "title": "Primary: Request Duration",
       "tooltip": {
@@ -464,7 +462,11 @@
           "min": null,
           "show": false
         }
-      ]
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
     },
     {
       "aliasColors": {},
@@ -533,6 +535,7 @@
       ],
       "thresholds": [],
       "timeFrom": null,
+      "timeRegions": [],
       "timeShift": null,
       "title": "Canary: Request Duration",
       "tooltip": {
@@ -565,7 +568,11 @@
           "min": null,
           "show": false
         }
-      ]
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
     },
     {
       "content": "<div class=\"dashboard-header text-center\">\n<span>USE: $canary.$namespace</span>\n</div>",
@@ -623,7 +630,6 @@
       "steppedLine": false,
       "targets": [
         {
-          "$$hashKey": "object:1685",
           "expr": "sum(rate(container_cpu_usage_seconds_total{cpu=\"total\",namespace=\"$namespace\",pod_name=~\"$primary.*\", container_name!~\"POD|istio-proxy\"}[1m])) by (pod_name)",
           "format": "time_series",
           "hide": false,
@@ -634,6 +640,7 @@
       ],
       "thresholds": [],
       "timeFrom": null,
+      "timeRegions": [],
       "timeShift": null,
       "title": "Primary: CPU Usage by Pod",
       "tooltip": {
@@ -651,7 +658,6 @@
       },
       "yaxes": [
         {
-          "$$hashKey": "object:1845",
           "format": "s",
           "label": "CPU seconds / second",
           "logBase": 1,
@@ -660,7 +666,6 @@
           "show": true
         },
         {
-          "$$hashKey": "object:1846",
           "format": "short",
           "label": null,
           "logBase": 1,
@@ -668,7 +673,11 @@
           "min": null,
           "show": false
         }
-      ]
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
     },
     {
       "aliasColors": {},
@@ -711,7 +720,6 @@
       "steppedLine": false,
       "targets": [
         {
-          "$$hashKey": "object:1685",
           "expr": "sum(rate(container_cpu_usage_seconds_total{cpu=\"total\",namespace=\"$namespace\",pod_name=~\"$canary.*\", pod_name!~\"$primary.*\", container_name!~\"POD|istio-proxy\"}[1m])) by (pod_name)",
           "format": "time_series",
           "hide": false,
@@ -722,6 +730,7 @@
       ],
       "thresholds": [],
       "timeFrom": null,
+      "timeRegions": [],
       "timeShift": null,
       "title": "Canary: CPU Usage by Pod",
       "tooltip": {
@@ -739,7 +748,6 @@
       },
       "yaxes": [
         {
-          "$$hashKey": "object:1845",
           "format": "s",
           "label": "CPU seconds / second",
           "logBase": 1,
@@ -748,7 +756,6 @@
           "show": true
         },
         {
-          "$$hashKey": "object:1846",
           "format": "short",
           "label": null,
           "logBase": 1,
@@ -756,7 +763,11 @@
           "min": null,
           "show": false
         }
-      ]
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
     },
     {
       "aliasColors": {},
@@ -799,7 +810,6 @@
       "steppedLine": false,
       "targets": [
         {
-          "$$hashKey": "object:1685",
           "expr": "sum(container_memory_working_set_bytes{namespace=\"$namespace\",pod_name=~\"$primary.*\", container_name!~\"POD|istio-proxy\"}) by (pod_name)",
           "format": "time_series",
           "hide": false,
@@ -811,6 +821,7 @@
       ],
       "thresholds": [],
       "timeFrom": null,
+      "timeRegions": [],
       "timeShift": null,
       "title": "Primary: Memory Usage by Pod",
       "tooltip": {
@@ -828,7 +839,6 @@
       },
       "yaxes": [
         {
-          "$$hashKey": "object:1845",
           "decimals": null,
           "format": "bytes",
           "label": "",
@@ -838,7 +848,6 @@
           "show": true
         },
         {
-          "$$hashKey": "object:1846",
           "format": "short",
           "label": null,
           "logBase": 1,
@@ -846,7 +855,11 @@
           "min": null,
           "show": false
         }
-      ]
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
     },
     {
       "aliasColors": {},
@@ -889,7 +902,6 @@
       "steppedLine": false,
       "targets": [
         {
-          "$$hashKey": "object:1685",
           "expr": "sum(container_memory_working_set_bytes{namespace=\"$namespace\",pod_name=~\"$canary.*\", pod_name!~\"$primary.*\", container_name!~\"POD|istio-proxy\"}) by (pod_name)",
           "format": "time_series",
           "hide": false,
@@ -901,6 +913,7 @@
       ],
       "thresholds": [],
       "timeFrom": null,
+      "timeRegions": [],
       "timeShift": null,
       "title": "Canary: Memory Usage by Pod",
       "tooltip": {
@@ -918,7 +931,6 @@
       },
       "yaxes": [
         {
-          "$$hashKey": "object:1845",
           "decimals": null,
           "format": "bytes",
           "label": "",
@@ -928,7 +940,6 @@
           "show": true
         },
         {
-          "$$hashKey": "object:1846",
           "format": "short",
           "label": null,
           "logBase": 1,
@@ -936,7 +947,11 @@
           "min": null,
           "show": false
         }
-      ]
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
     },
     {
       "aliasColors": {},
@@ -975,12 +990,10 @@
       "renderer": "flot",
       "seriesOverrides": [
         {
-          "$$hashKey": "object:3641",
           "alias": "received",
           "color": "#f9d9f9"
         },
         {
-          "$$hashKey": "object:3649",
           "alias": "transmited",
           "color": "#f29191"
         }
@@ -990,7 +1003,6 @@
       "steppedLine": false,
       "targets": [
         {
-          "$$hashKey": "object:2598",
           "expr": "sum(rate (container_network_receive_bytes_total{namespace=\"$namespace\",pod_name=~\"$primary.*\"}[1m])) ",
           "format": "time_series",
           "intervalFactor": 1,
@@ -998,7 +1010,6 @@
           "refId": "A"
         },
         {
-          "$$hashKey": "object:3245",
           "expr": "-sum (rate (container_network_transmit_bytes_total{namespace=\"$namespace\",pod_name=~\"$primary.*\"}[1m]))",
           "format": "time_series",
           "intervalFactor": 1,
@@ -1008,6 +1019,7 @@
       ],
       "thresholds": [],
       "timeFrom": null,
+      "timeRegions": [],
       "timeShift": null,
       "title": "Primary: Network I/O",
       "tooltip": {
@@ -1025,7 +1037,6 @@
       },
       "yaxes": [
         {
-          "$$hashKey": "object:1845",
           "decimals": null,
           "format": "Bps",
           "label": "",
@@ -1035,7 +1046,6 @@
           "show": true
         },
         {
-          "$$hashKey": "object:1846",
           "format": "short",
           "label": null,
           "logBase": 1,
@@ -1043,7 +1053,11 @@
           "min": null,
           "show": false
         }
-      ]
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
     },
     {
       "aliasColors": {},
@@ -1082,12 +1096,10 @@
       "renderer": "flot",
       "seriesOverrides": [
         {
-          "$$hashKey": "object:3641",
           "alias": "received",
           "color": "#f9d9f9"
         },
         {
-          "$$hashKey": "object:3649",
           "alias": "transmited",
           "color": "#f29191"
         }
@@ -1097,7 +1109,6 @@
       "steppedLine": false,
       "targets": [
         {
-          "$$hashKey": "object:2598",
           "expr": "sum(rate (container_network_receive_bytes_total{namespace=\"$namespace\",pod_name=~\"$canary.*\",pod_name!~\"$primary.*\"}[1m])) ",
           "format": "time_series",
           "intervalFactor": 1,
@@ -1105,7 +1116,6 @@
           "refId": "A"
         },
         {
-          "$$hashKey": "object:3245",
           "expr": "-sum (rate (container_network_transmit_bytes_total{namespace=\"$namespace\",pod_name=~\"$canary.*\",pod_name!~\"$primary.*\"}[1m]))",
           "format": "time_series",
           "intervalFactor": 1,
@@ -1115,6 +1125,7 @@
       ],
       "thresholds": [],
       "timeFrom": null,
+      "timeRegions": [],
       "timeShift": null,
       "title": "Canary: Network I/O",
       "tooltip": {
@@ -1132,7 +1143,6 @@
       },
       "yaxes": [
         {
-          "$$hashKey": "object:1845",
           "decimals": null,
           "format": "Bps",
           "label": "",
@@ -1142,7 +1152,6 @@
           "show": true
         },
         {
-          "$$hashKey": "object:1846",
           "format": "short",
           "label": null,
           "logBase": 1,
@@ -1150,7 +1159,11 @@
           "min": null,
           "show": false
         }
-      ]
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
     },
     {
       "content": "<div class=\"dashboard-header text-center\">\n<span>IN/OUTBOUND: $canary.$namespace</span>\n</div>",
@@ -1205,7 +1218,6 @@
       "steppedLine": false,
       "targets": [
         {
-          "$$hashKey": "object:1953",
           "expr": "round(sum(irate(istio_requests_total{connection_security_policy=\"mutual_tls\", destination_workload_namespace=~\"$namespace\", destination_workload=~\"$primary\", reporter=\"destination\"}[30s])) by (source_workload, source_workload_namespace, response_code), 0.001)",
           "format": "time_series",
           "hide": false,
@@ -1215,7 +1227,6 @@
           "step": 2
         },
         {
-          "$$hashKey": "object:1954",
           "expr": "round(sum(irate(istio_requests_total{connection_security_policy!=\"mutual_tls\", destination_workload_namespace=~\"$namespace\", destination_workload=~\"$primary\", reporter=\"destination\"}[30s])) by (source_workload, source_workload_namespace, response_code), 0.001)",
           "format": "time_series",
           "hide": false,
@@ -1227,6 +1238,7 @@
       ],
       "thresholds": [],
       "timeFrom": null,
+      "timeRegions": [],
       "timeShift": null,
       "title": "Primary: Incoming Requests by Source And Response Code",
       "tooltip": {
@@ -1246,7 +1258,6 @@
       },
       "yaxes": [
         {
-          "$$hashKey": "object:1999",
           "format": "ops",
           "label": null,
           "logBase": 1,
@@ -1255,7 +1266,6 @@
           "show": true
         },
         {
-          "$$hashKey": "object:2000",
           "format": "short",
           "label": null,
           "logBase": 1,
@@ -1263,7 +1273,11 @@
           "min": null,
           "show": false
         }
-      ]
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
     },
     {
       "aliasColors": {},
@@ -1323,6 +1337,7 @@
       ],
       "thresholds": [],
       "timeFrom": null,
+      "timeRegions": [],
       "timeShift": null,
       "title": "Canary: Incoming Requests by Source And Response Code",
       "tooltip": {
@@ -1357,7 +1372,11 @@
           "min": null,
           "show": false
         }
-      ]
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
     },
     {
       "aliasColors": {},
@@ -1416,6 +1435,7 @@
       ],
       "thresholds": [],
       "timeFrom": null,
+      "timeRegions": [],
       "timeShift": null,
       "title": "Primary: Outgoing Requests by Destination And Response Code",
       "tooltip": {
@@ -1450,7 +1470,11 @@
           "min": null,
           "show": false
         }
-      ]
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
     },
     {
       "aliasColors": {},
@@ -1509,6 +1533,7 @@
       ],
       "thresholds": [],
       "timeFrom": null,
+      "timeRegions": [],
       "timeShift": null,
       "title": "Canary: Outgoing Requests by Destination And Response Code",
       "tooltip": {
@@ -1543,7 +1568,11 @@
           "min": null,
           "show": false
         }
-      ]
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
     }
   ],
   "refresh": "10s",
@@ -1554,11 +1583,9 @@
     "list": [
       {
         "allValue": null,
-        "current": {
-          "text": "demo",
-          "value": "demo"
-        },
+        "current": null,
         "datasource": "prometheus",
+        "definition": "",
         "hide": 0,
         "includeAll": false,
         "label": "Namespace",
@@ -1568,6 +1595,7 @@
         "query": "query_result(sum(istio_requests_total) by (destination_workload_namespace) or sum(istio_tcp_sent_bytes_total) by (destination_workload_namespace))",
         "refresh": 1,
         "regex": "/.*_namespace=\"([^\"]*).*/",
+        "skipUrlSync": false,
         "sort": 0,
         "tagValuesQuery": "",
         "tags": [],
@@ -1577,20 +1605,19 @@
       },
       {
         "allValue": null,
-        "current": {
-          "text": "primary",
-          "value": "primary"
-        },
+        "current": null,
         "datasource": "prometheus",
+        "definition": "",
         "hide": 0,
         "includeAll": false,
         "label": "Primary",
         "multi": false,
         "name": "primary",
         "options": [],
-        "query": "query_result(sum(istio_requests_total{destination_workload_namespace=~\"$namespace\"}) by (destination_service_name))",
+        "query": "query_result(sum(istio_requests_total{destination_workload_namespace=~\"$namespace\"}) by (destination_workload))",
         "refresh": 1,
-        "regex": "/.*destination_service_name=\"([^\"]*).*/",
+        "regex": "/.*destination_workload=\"([^\"]*).*/",
+        "skipUrlSync": false,
         "sort": 1,
         "tagValuesQuery": "",
         "tags": [],
@@ -1600,20 +1627,19 @@
       },
       {
         "allValue": null,
-        "current": {
-          "text": "canary",
-          "value": "canary"
-        },
+        "current": null,
         "datasource": "prometheus",
+        "definition": "",
         "hide": 0,
         "includeAll": false,
         "label": "Canary",
         "multi": false,
         "name": "canary",
         "options": [],
-        "query": "query_result(sum(istio_requests_total{destination_workload_namespace=~\"$namespace\"}) by (destination_service_name))",
+        "query": "query_result(sum(istio_requests_total{destination_workload_namespace=~\"$namespace\"}) by (destination_workload))",
         "refresh": 1,
-        "regex": "/.*destination_service_name=\"([^\"]*).*/",
+        "regex": "/.*destination_workload=\"([^\"]*).*/",
+        "skipUrlSync": false,
         "sort": 1,
         "tagValuesQuery": "",
         "tags": [],
@@ -1653,7 +1679,7 @@
     ]
   },
   "timezone": "",
-  "title": "Canary analysis",
-  "uid": "RdykD7tiz",
-  "version": 2
-}
+  "title": "Istio Canary",
+  "uid": "flagger-istio",
+  "version": 3
+}

charts/grafana/templates/NOTES.txt

@@ -1,15 +1,7 @@
-1. Get the application URL by running these commands:
-{{- if contains "NodePort" .Values.service.type }}
-  export NODE_PORT=$(kubectl get --namespace {{ .Release.Namespace }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ template "grafana.fullname" . }})
-  export NODE_IP=$(kubectl get nodes --namespace {{ .Release.Namespace }} -o jsonpath="{.items[0].status.addresses[0].address}")
-  echo http://$NODE_IP:$NODE_PORT
-{{- else if contains "LoadBalancer" .Values.service.type }}
-     NOTE: It may take a few minutes for the LoadBalancer IP to be available.
-           You can watch the status of by running 'kubectl get svc -w {{ template "grafana.fullname" . }}'
-  export SERVICE_IP=$(kubectl get svc --namespace {{ .Release.Namespace }} {{ template "grafana.fullname" . }} -o jsonpath='{.status.loadBalancer.ingress[0].ip}')
-  echo http://$SERVICE_IP:{{ .Values.service.port }}
-{{- else if contains "ClusterIP" .Values.service.type }}
-  export POD_NAME=$(kubectl get pods --namespace {{ .Release.Namespace }} -l "app={{ template "grafana.name" . }},release={{ .Release.Name }}" -o jsonpath="{.items[0].metadata.name}")
-  echo "Visit http://127.0.0.1:8080 to use your application"
-  kubectl port-forward $POD_NAME 8080:80
-{{- end }}
+1. Run the port forward command:
+
+kubectl -n {{ .Release.Namespace }} port-forward svc/{{ .Release.Name }} 3000:80
+
+2. Navigate to:
+
+http://localhost:3000

charts/grafana/templates/deployment.yaml

@@ -38,12 +38,21 @@ spec:
 #              path: /
 #              port: http
           env:
+          - name: GF_PATHS_PROVISIONING
+            value: /etc/grafana/provisioning/
+          {{- if .Values.password }}
           - name: GF_SECURITY_ADMIN_USER
             value: {{ .Values.user }}
           - name: GF_SECURITY_ADMIN_PASSWORD
             value: {{ .Values.password }}
-          - name: GF_PATHS_PROVISIONING
-            value: /etc/grafana/provisioning/
+          {{- else }}
+          - name: GF_AUTH_BASIC_ENABLED
+            value: "false"
+          - name: GF_AUTH_ANONYMOUS_ENABLED
+            value: "true"
+          - name: GF_AUTH_ANONYMOUS_ORG_ROLE
+            value: Admin
+          {{- end }}
           volumeMounts:
           - name: grafana
             mountPath: /var/lib/grafana

charts/grafana/values.yaml

@@ -6,7 +6,7 @@ replicaCount: 1
 
 image:
   repository: grafana/grafana
-  tag: 5.4.2
+  tag: 5.4.3
   pullPolicy: IfNotPresent
 
 service:
@@ -28,7 +28,7 @@ tolerations: []
 affinity: {}
 
 user: admin
-password: admin
+password:
 
 # Istio Prometheus instance
 url: http://prometheus:9090

charts/loadtester/.helmignore

@@ -0,0 +1,22 @@
+# Patterns to ignore when building packages.
+# This supports shell glob matching, relative path matching, and
+# negation (prefixed with !). Only one pattern per line.
+.DS_Store
+# Common VCS dirs
+.git/
+.gitignore
+.bzr/
+.bzrignore
+.hg/
+.hgignore
+.svn/
+# Common backup files
+*.swp
+*.bak
+*.tmp
+*~
+# Various IDEs
+.project
+.idea/
+*.tmproj
+.vscode/

charts/loadtester/Chart.yaml

@@ -0,0 +1,21 @@
+apiVersion: v1
+name: loadtester
+version: 0.4.0
+appVersion: 0.3.0
+kubeVersion: ">=1.11.0-0"
+engine: gotpl
+description: Flagger's load testing services based on rakyll/hey that generates traffic during canary analysis when configured as a webhook.
+home: https://docs.flagger.app
+icon: https://raw.githubusercontent.com/weaveworks/flagger/master/docs/logo/flagger-icon.png
+sources:
+  - https://github.com/weaveworks/flagger
+maintainers:
+  - name: stefanprodan
+    url: https://github.com/stefanprodan
+    email: stefanprodan@users.noreply.github.com
+keywords:
+  - canary
+  - istio
+  - appmesh
+  - gitops
+  - load testing

charts/loadtester/README.md

@@ -0,0 +1,78 @@
+# Flagger load testing service
+
+[Flagger's](https://github.com/weaveworks/flagger) load testing service is based on 
+[rakyll/hey](https://github.com/rakyll/hey) 
+and can be used to generates traffic during canary analysis when configured as a webhook.
+
+## Prerequisites
+
+* Kubernetes >= 1.11
+* Istio >= 1.0
+
+## Installing the Chart
+
+Add Flagger Helm repository:
+
+```console
+helm repo add flagger https://flagger.app
+```
+
+To install the chart with the release name `flagger-loadtester`:
+
+```console
+helm upgrade -i flagger-loadtester flagger/loadtester
+```
+
+The command deploys Grafana on the Kubernetes cluster in the default namespace.
+
+> **Tip**: Note that the namespace where you deploy the load tester should have the Istio sidecar injection enabled
+
+The [configuration](#configuration) section lists the parameters that can be configured during installation.
+
+## Uninstalling the Chart
+
+To uninstall/delete the `flagger-loadtester` deployment:
+
+```console
+helm delete --purge flagger-loadtester
+```
+
+The command removes all the Kubernetes components associated with the chart and deletes the release.
+
+## Configuration
+
+The following tables lists the configurable parameters of the load tester chart and their default values.
+
+Parameter | Description | Default
+--- | --- | ---
+`image.repository` | Image repository | `quay.io/stefanprodan/flagger-loadtester`
+`image.pullPolicy` | Image pull policy | `IfNotPresent`
+`image.tag` | Image tag | `<VERSION>`
+`replicaCount` | desired number of pods | `1`
+`resources.requests.cpu` | CPU requests | `10m`
+`resources.requests.memory` | memory requests | `64Mi`
+`tolerations` | List of node taints to tolerate | `[]`
+`affinity` | node/pod affinities | `node`
+`nodeSelector` | node labels for pod assignment | `{}`
+`service.type` | type of service | `ClusterIP`
+`service.port` | ClusterIP port | `80`
+`cmd.timeout` | Command execution timeout | `1h`
+`logLevel` | Log level can be debug, info, warning, error or panic | `info`
+`meshName` | AWS App Mesh name | `none`
+`backends` | AWS App Mesh virtual services | `none`
+
+Specify each parameter using the `--set key=value[,key=value]` argument to `helm install`. For example,
+
+```console
+helm install flagger/loadtester --name flagger-loadtester
+```
+
+Alternatively, a YAML file that specifies the values for the above parameters can be provided while installing the chart. For example,
+
+```console
+helm install flagger/loadtester --name flagger-loadtester -f values.yaml
+```
+
+> **Tip**: You can use the default [values.yaml](values.yaml)
+
+

charts/loadtester/templates/NOTES.txt

@@ -0,0 +1 @@
+Flagger's load testing service is available at http://{{ include "loadtester.fullname" . }}.{{ .Release.Namespace }}/

charts/loadtester/templates/_helpers.tpl

@@ -0,0 +1,32 @@
+{{/* vim: set filetype=mustache: */}}
+{{/*
+Expand the name of the chart.
+*/}}
+{{- define "loadtester.name" -}}
+{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" -}}
+{{- end -}}
+
+{{/*
+Create a default fully qualified app name.
+We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec).
+If release name contains chart name it will be used as a full name.
+*/}}
+{{- define "loadtester.fullname" -}}
+{{- if .Values.fullnameOverride -}}
+{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" -}}
+{{- else -}}
+{{- $name := default .Chart.Name .Values.nameOverride -}}
+{{- if contains $name .Release.Name -}}
+{{- .Release.Name | trunc 63 | trimSuffix "-" -}}
+{{- else -}}
+{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" -}}
+{{- end -}}
+{{- end -}}
+{{- end -}}
+
+{{/*
+Create chart name and version as used by the chart label.
+*/}}
+{{- define "loadtester.chart" -}}
+{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" -}}
+{{- end -}}

charts/loadtester/templates/deployment.yaml

@@ -0,0 +1,67 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: {{ include "loadtester.fullname" . }}
+  labels:
+    app.kubernetes.io/name: {{ include "loadtester.name" . }}
+    helm.sh/chart: {{ include "loadtester.chart" . }}
+    app.kubernetes.io/instance: {{ .Release.Name }}
+    app.kubernetes.io/managed-by: {{ .Release.Service }}
+spec:
+  replicas: {{ .Values.replicaCount }}
+  selector:
+    matchLabels:
+      app: {{ include "loadtester.name" . }}
+  template:
+    metadata:
+      labels:
+        app: {{ include "loadtester.name" . }}
+      annotations:
+        appmesh.k8s.aws/ports: "444"
+    spec:
+      containers:
+        - name: {{ .Chart.Name }}
+          image: "{{ .Values.image.repository }}:{{ .Values.image.tag }}"
+          imagePullPolicy: {{ .Values.image.pullPolicy }}
+          ports:
+            - name: http
+              containerPort: 8080
+          command:
+            - ./loadtester
+            - -port=8080
+            - -log-level={{ .Values.logLevel }}
+            - -timeout={{ .Values.cmd.timeout }}
+          livenessProbe:
+            exec:
+              command:
+                - wget
+                - --quiet
+                - --tries=1
+                - --timeout=4
+                - --spider
+                - http://localhost:8080/healthz
+            timeoutSeconds: 5
+          readinessProbe:
+            exec:
+              command:
+                - wget
+                - --quiet
+                - --tries=1
+                - --timeout=4
+                - --spider
+                - http://localhost:8080/healthz
+            timeoutSeconds: 5
+          resources:
+            {{- toYaml .Values.resources | nindent 12 }}
+      {{- with .Values.nodeSelector }}
+      nodeSelector:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+    {{- with .Values.affinity }}
+      affinity:
+        {{- toYaml . | nindent 8 }}
+    {{- end }}
+    {{- with .Values.tolerations }}
+      tolerations:
+        {{- toYaml . | nindent 8 }}
+    {{- end }}

charts/loadtester/templates/service.yaml

@@ -0,0 +1,18 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: {{ include "loadtester.fullname" . }}
+  labels:
+    app.kubernetes.io/name: {{ include "loadtester.name" . }}
+    helm.sh/chart: {{ include "loadtester.chart" . }}
+    app.kubernetes.io/instance: {{ .Release.Name }}
+    app.kubernetes.io/managed-by: {{ .Release.Service }}
+spec:
+  type: {{ .Values.service.type }}
+  ports:
+    - port: {{ .Values.service.port }}
+      targetPort: http
+      protocol: TCP
+      name: http
+  selector:
+    app: {{ include "loadtester.name" . }}

charts/loadtester/templates/virtual-node.yaml

@@ -0,0 +1,27 @@
+{{- if .Values.meshName }}
+apiVersion: appmesh.k8s.aws/v1beta1
+kind: VirtualNode
+metadata:
+  name: {{ include "loadtester.fullname" . }}
+  labels:
+    app.kubernetes.io/name: {{ include "loadtester.name" . }}
+    helm.sh/chart: {{ include "loadtester.chart" . }}
+    app.kubernetes.io/instance: {{ .Release.Name }}
+    app.kubernetes.io/managed-by: {{ .Release.Service }}
+spec:
+  meshName: {{ .Values.meshName }}
+  listeners:
+    - portMapping:
+        port: 444
+        protocol: http
+  serviceDiscovery:
+    dns:
+      hostName: {{ include "loadtester.fullname" . }}.{{ .Release.Namespace }}
+  {{- if .Values.backends }}
+  backends:
+    {{- range .Values.backends }}
+    - virtualService:
+        virtualServiceName: {{ . }}
+    {{- end }}
+  {{- end }}
+{{- end }}

charts/loadtester/values.yaml

@@ -0,0 +1,34 @@
+replicaCount: 1
+
+image:
+  repository: weaveworks/flagger-loadtester
+  tag: 0.3.0
+  pullPolicy: IfNotPresent
+
+logLevel: info
+cmd:
+  timeout: 1h
+
+nameOverride: ""
+fullnameOverride: ""
+
+service:
+  type: ClusterIP
+  port: 80
+
+resources:
+  requests:
+    cpu: 10m
+    memory: 64Mi
+
+nodeSelector: {}
+
+tolerations: []
+
+affinity: {}
+
+# App Mesh virtual node settings
+meshName: ""
+#backends:
+#  - app1.namespace
+#  - app2.namespace

charts/podinfo/.helmignore

@@ -0,0 +1,21 @@
+# Patterns to ignore when building packages.
+# This supports shell glob matching, relative path matching, and
+# negation (prefixed with !). Only one pattern per line.
+.DS_Store
+# Common VCS dirs
+.git/
+.gitignore
+.bzr/
+.bzrignore
+.hg/
+.hgignore
+.svn/
+# Common backup files
+*.swp
+*.bak
+*.tmp
+*~
+# Various IDEs
+.project
+.idea/
+*.tmproj

charts/podinfo/Chart.yaml

@@ -0,0 +1,12 @@
+apiVersion: v1
+version: 2.0.1
+appVersion: 1.4.0
+name: podinfo
+engine: gotpl
+description: Flagger canary deployment demo chart
+home: https://github.com/weaveworks/flagger
+maintainers:
+- email: stefanprodan@users.noreply.github.com
+  name: stefanprodan
+sources:
+- https://github.com/weaveworks/flagger

charts/podinfo/README.md

@@ -0,0 +1,79 @@
+# Podinfo
+
+Podinfo is a tiny web application made with Go 
+that showcases best practices of running canary deployments with Flagger and Istio.
+
+## Installing the Chart
+
+Add Flagger Helm repository:
+
+```console
+helm repo add flagger https://flagger.app
+```
+
+To install the chart with the release name `frontend`:
+
+```console
+helm upgrade -i frontend flagger/podinfo \
+--namespace test \
+--set nameOverride=frontend \
+--set backend=http://backend.test:9898/echo \
+--set canary.enabled=true \
+--set canary.istioIngress.enabled=true \
+--set canary.istioIngress.gateway=public-gateway.istio-system.svc.cluster.local \
+--set canary.istioIngress.host=frontend.istio.example.com
+```
+
+To install the chart as `backend`:
+
+```console
+helm upgrade -i backend flagger/podinfo \
+--namespace test \
+--set nameOverride=backend \
+--set canary.enabled=true 
+```
+
+## Uninstalling the Chart
+
+To uninstall/delete the `frontend` deployment:
+
+```console
+$ helm delete --purge frontend
+```
+
+The command removes all the Kubernetes components associated with the chart and deletes the release.
+
+## Configuration
+
+The following tables lists the configurable parameters of the podinfo chart and their default values.
+
+Parameter | Description | Default
+--- | --- | ---
+`image.repository` | image repository | `quay.io/stefanprodan/podinfo`
+`image.tag` | image tag | `<VERSION>`
+`image.pullPolicy` | image pull policy | `IfNotPresent`
+`hpa.enabled` | enables HPA | `true`
+`hpa.cpu` | target CPU usage per pod | `80`
+`hpa.memory` | target memory usage per pod | `512Mi`
+`hpa.minReplicas` | maximum pod replicas | `2`
+`hpa.maxReplicas` | maximum pod replicas | `4`
+`resources.requests/cpu` | pod CPU request | `1m`
+`resources.requests/memory` | pod memory request | `16Mi`
+`backend` | backend URL | None
+`faults.delay` | random HTTP response delays between 0 and 5 seconds | `false`
+`faults.error` | 1/3 chances of a random HTTP response error | `false`
+
+Specify each parameter using the `--set key=value[,key=value]` argument to `helm install`. For example,
+
+```console
+$ helm install flagger/podinfo --name frontend \
+  --set=image.tag=1.4.1,hpa.enabled=false
+```
+
+Alternatively, a YAML file that specifies the values for the above parameters can be provided while installing the chart. For example,
+
+```console
+$ helm install flagger/podinfo --name frontend -f values.yaml
+```
+
+

charts/podinfo/templates/NOTES.txt

@@ -0,0 +1 @@
+podinfo {{ .Release.Name }} deployed!

charts/podinfo/templates/_helpers.tpl

@@ -0,0 +1,43 @@
+{{/* vim: set filetype=mustache: */}}
+{{/*
+Expand the name of the chart.
+*/}}
+{{- define "podinfo.name" -}}
+{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" -}}
+{{- end -}}
+
+{{/*
+Create a default fully qualified app name.
+We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec).
+If release name contains chart name it will be used as a full name.
+*/}}
+{{- define "podinfo.fullname" -}}
+{{- if .Values.fullnameOverride -}}
+{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" -}}
+{{- else -}}
+{{- $name := default .Chart.Name .Values.nameOverride -}}
+{{- if contains $name .Release.Name -}}
+{{- .Release.Name | trunc 63 | trimSuffix "-" -}}
+{{- else -}}
+{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" -}}
+{{- end -}}
+{{- end -}}
+{{- end -}}
+
+{{/*
+Create chart name and version as used by the chart label.
+*/}}
+{{- define "podinfo.chart" -}}
+{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" -}}
+{{- end -}}
+
+{{/*
+Create chart name suffix.
+*/}}
+{{- define "podinfo.suffix" -}}
+{{- if .Values.canary.enabled -}}
+{{- "-primary" -}}
+{{- else -}}
+{{- "" -}}
+{{- end -}}
+{{- end -}}

charts/podinfo/templates/canary.yaml

@@ -0,0 +1,54 @@
+{{- if .Values.canary.enabled }}
+apiVersion: flagger.app/v1alpha3
+kind: Canary
+metadata:
+  name: {{ template "podinfo.fullname" . }}
+  labels:
+    app: {{ template "podinfo.name" . }}
+    chart: {{ template "podinfo.chart" . }}
+    release: {{ .Release.Name }}
+    heritage: {{ .Release.Service }}
+spec:
+  targetRef:
+    apiVersion: apps/v1
+    kind: Deployment
+    name:  {{ template "podinfo.fullname" . }}
+  progressDeadlineSeconds: 60
+  autoscalerRef:
+    apiVersion: autoscaling/v2beta1
+    kind: HorizontalPodAutoscaler
+    name:  {{ template "podinfo.fullname" . }}
+  service:
+    port: {{ .Values.service.port }}
+    {{- if .Values.canary.istioIngress.enabled }}
+    gateways:
+    -  {{ .Values.canary.istioIngress.gateway }}
+    hosts:
+    - {{ .Values.canary.istioIngress.host }}
+    {{- end }}
+  canaryAnalysis:
+    interval: {{ .Values.canary.analysis.interval }}
+    threshold: {{ .Values.canary.analysis.threshold }}
+    maxWeight: {{ .Values.canary.analysis.maxWeight }}
+    stepWeight: {{ .Values.canary.analysis.stepWeight }}
+    metrics:
+    - name: request-success-rate
+      threshold: {{ .Values.canary.thresholds.successRate }}
+      interval: 1m
+    - name: request-duration
+      threshold: {{ .Values.canary.thresholds.latency }}
+      interval: 1m
+    {{- if .Values.canary.loadtest.enabled }}
+    webhooks:
+      - name: load-test-get
+        url: {{ .Values.canary.loadtest.url }}
+        timeout: 5s
+        metadata:
+          cmd: "hey -z 1m -q 5 -c 2 http://{{ template "podinfo.fullname" . }}.{{ .Release.Namespace }}:{{ .Values.service.port }}"
+      - name: load-test-post
+        url: {{ .Values.canary.loadtest.url }}
+        timeout: 5s
+        metadata:
+          cmd: "hey -z 1m -q 5 -c 2 -m POST -d '{\"test\": true}' http://{{ template "podinfo.fullname" . }}.{{ .Release.Namespace }}:{{ .Values.service.port }}/echo"
+    {{- end }}
+{{- end }}

charts/podinfo/templates/configmap.yaml

@@ -0,0 +1,15 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: {{ template "podinfo.fullname" . }}
+  labels:
+    app: {{ template "podinfo.name" . }}
+    chart: {{ template "podinfo.chart" . }}
+    release: {{ .Release.Name }}
+    heritage: {{ .Release.Service }}
+data:
+  config.yaml: |-
+    # http settings
+    http-client-timeout: 1m
+    http-server-timeout: {{ .Values.httpServer.timeout }}
+    http-server-shutdown-timeout: 5s

charts/podinfo/templates/deployment.yaml

@@ -0,0 +1,93 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: {{ template "podinfo.fullname" . }}
+  labels:
+    app: {{ template "podinfo.name" . }}
+    chart: {{ template "podinfo.chart" . }}
+    release: {{ .Release.Name }}
+    heritage: {{ .Release.Service }}
+spec:
+  strategy:
+    type: RollingUpdate
+    rollingUpdate:
+      maxUnavailable: 1
+  selector:
+    matchLabels:
+      app: {{ template "podinfo.fullname" . }}
+  template:
+    metadata:
+      labels:
+        app: {{ template "podinfo.fullname" . }}
+      annotations:
+        prometheus.io/scrape: 'true'
+    spec:
+      terminationGracePeriodSeconds: 30
+      containers:
+        - name: {{ .Chart.Name }}
+          image: "{{ .Values.image.repository }}:{{ .Values.image.tag }}"
+          imagePullPolicy: {{ .Values.image.pullPolicy }}
+          command:
+            - ./podinfo
+            - --port={{ .Values.service.port }}
+            - --level={{ .Values.logLevel }}
+            - --random-delay={{ .Values.faults.delay }}
+            - --random-error={{ .Values.faults.error }}
+            - --config-path=/podinfo/config
+          env:
+          {{- if .Values.message }}
+          - name: PODINFO_UI_MESSAGE
+            value: {{ .Values.message }}
+          {{- end }}
+          {{- if .Values.backend }}
+          - name: PODINFO_BACKEND_URL
+            value: {{ .Values.backend }}
+          {{- end }}
+          ports:
+            - name: http
+              containerPort: {{ .Values.service.port }}
+              protocol: TCP
+          livenessProbe:
+            exec:
+              command:
+              - podcli
+              - check
+              - http
+              - localhost:{{ .Values.service.port }}/healthz
+            initialDelaySeconds: 5
+            timeoutSeconds: 5
+          readinessProbe:
+            exec:
+              command:
+              - podcli
+              - check
+              - http
+              - localhost:{{ .Values.service.port }}/readyz
+            initialDelaySeconds: 5
+            timeoutSeconds: 5
+          volumeMounts:
+          - name: data
+            mountPath: /data
+          - name: config
+            mountPath: /podinfo/config
+            readOnly: true
+          resources:
+{{ toYaml .Values.resources | indent 12 }}
+    {{- with .Values.nodeSelector }}
+      nodeSelector:
+{{ toYaml . | indent 8 }}
+    {{- end }}
+    {{- with .Values.affinity }}
+      affinity:
+{{ toYaml . | indent 8 }}
+    {{- end }}
+    {{- with .Values.tolerations }}
+      tolerations:
+{{ toYaml . | indent 8 }}
+    {{- end }}
+      volumes:
+      - name: data
+        emptyDir: {}
+      - name: config
+        configMap:
+          name: {{ template "podinfo.fullname" . }}

charts/podinfo/templates/hpa.yaml

@@ -0,0 +1,37 @@
+{{- if .Values.hpa.enabled -}}
+apiVersion: autoscaling/v2beta1
+kind: HorizontalPodAutoscaler
+metadata:
+  name: {{ template "podinfo.fullname" . }}
+  labels:
+    app: {{ template "podinfo.name" . }}
+    chart: {{ template "podinfo.chart" . }}
+    release: {{ .Release.Name }}
+    heritage: {{ .Release.Service }}
+spec:
+  scaleTargetRef:
+    apiVersion: apps/v1beta2
+    kind: Deployment
+    name: {{ template "podinfo.fullname" . }}
+  minReplicas: {{ .Values.hpa.minReplicas }}
+  maxReplicas: {{ .Values.hpa.maxReplicas }}
+  metrics:
+  {{- if .Values.hpa.cpu }}
+  - type: Resource
+    resource:
+      name: cpu
+      targetAverageUtilization: {{ .Values.hpa.cpu }}
+  {{- end }}
+  {{- if .Values.hpa.memory }}
+  - type: Resource
+    resource:
+      name: memory
+      targetAverageValue: {{ .Values.hpa.memory }}
+  {{- end }}
+  {{- if .Values.hpa.requests }}
+  - type: Pod
+      pods:
+        metricName: http_requests
+        targetAverageValue: {{ .Values.hpa.requests }}
+  {{- end }}
+{{- end }}

charts/podinfo/templates/service.yaml

@@ -0,0 +1,20 @@
+{{- if not .Values.canary.enabled }}
+apiVersion: v1
+kind: Service
+metadata:
+  name: {{ template "podinfo.fullname" . }}
+  labels:
+    app: {{ template "podinfo.name" . }}
+    chart: {{ template "podinfo.chart" . }}
+    release: {{ .Release.Name }}
+    heritage: {{ .Release.Service }}
+spec:
+  type: {{ .Values.service.type }}
+  ports:
+    - port: {{ .Values.service.port }}
+      targetPort: http
+      protocol: TCP
+      name: http
+  selector:
+    app: {{ template "podinfo.fullname" . }}
+{{- end }}

charts/podinfo/templates/tests/test-config.yaml

@@ -0,0 +1,22 @@
+{{- $url := printf "%s%s.%s:%v" (include "podinfo.fullname" .) (include "podinfo.suffix" .) .Release.Namespace .Values.service.port -}}
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name:  {{ template "podinfo.fullname" . }}-tests
+  labels:
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    chart: {{ .Chart.Name }}-{{ .Chart.Version }}
+    app: {{ template "podinfo.name" . }}
+data:
+  run.sh: |-
+    @test "HTTP POST /echo" {
+      run curl --retry 3 --connect-timeout 2 -sSX POST -d 'test' {{ $url }}/echo
+      [ $output = "test" ]
+    }
+    @test "HTTP POST /store" {
+      curl --retry 3 --connect-timeout 2 -sSX POST -d 'test' {{ $url }}/store
+    }
+    @test "HTTP GET /" {
+      curl --retry 3 --connect-timeout 2 -sS {{ $url }} | grep hostname
+    }

charts/podinfo/templates/tests/test-pod.yaml

@@ -0,0 +1,43 @@
+apiVersion: v1
+kind: Pod
+metadata:
+  name: {{ template "podinfo.fullname" . }}-tests-{{ randAlphaNum 5 | lower }}
+  annotations:
+    "helm.sh/hook": test-success
+    sidecar.istio.io/inject: "false"
+  labels:
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    chart: {{ .Chart.Name }}-{{ .Chart.Version }}
+    app: {{ template "podinfo.name" . }}
+spec:
+  initContainers:
+    - name: "test-framework"
+      image: "dduportal/bats:0.4.0"
+      command:
+      - "bash"
+      - "-c"
+      - |
+        set -ex
+        # copy bats to tools dir
+        cp -R /usr/local/libexec/ /tools/bats/
+      volumeMounts:
+      - mountPath: /tools
+        name: tools
+  containers:
+    - name: {{ .Release.Name }}-ui-test
+      image: dduportal/bats:0.4.0
+      command: ["/tools/bats/bats", "-t", "/tests/run.sh"]
+      volumeMounts:
+      - mountPath: /tests
+        name: tests
+        readOnly: true
+      - mountPath: /tools
+        name: tools
+  volumes:
+  - name: tests
+    configMap:
+      name: {{ template "podinfo.fullname" . }}-tests
+  - name: tools
+    emptyDir: {}
+  restartPolicy: Never

charts/podinfo/values.yaml

@@ -0,0 +1,73 @@
+# Default values for podinfo.
+image:
+  repository: quay.io/stefanprodan/podinfo
+  tag: 1.4.0
+  pullPolicy: IfNotPresent
+
+service:
+  type: ClusterIP
+  port: 9898
+
+hpa:
+  enabled: true
+  minReplicas: 2
+  maxReplicas: 2
+  cpu: 80
+  memory: 512Mi
+
+canary:
+  enabled: true
+  istioIngress:
+    enabled: false
+    # Istio ingress gateway name
+    gateway: public-gateway.istio-system.svc.cluster.local
+    # external host name eg. podinfo.example.com
+    host:
+  analysis:
+    # schedule interval (default 60s)
+    interval: 15s
+    # max number of failed metric checks before rollback
+    threshold: 10
+    # max traffic percentage routed to canary
+    # percentage (0-100)
+    maxWeight: 50
+    # canary increment step
+    # percentage (0-100)
+    stepWeight: 5
+  thresholds:
+    # minimum req success rate (non 5xx responses)
+    # percentage (0-100)
+    successRate: 99
+    # maximum req duration P99
+    # milliseconds
+    latency: 500
+  loadtest:
+    enabled: false
+    # load tester address
+    url: http://flagger-loadtester.test/
+
+resources:
+  limits:
+  requests:
+    cpu: 100m
+    memory: 32Mi
+
+nodeSelector: {}
+
+tolerations: []
+
+affinity: {}
+
+nameOverride: ""
+fullnameOverride: ""
+
+logLevel: info
+backend: #http://backend-podinfo:9898/echo
+message: #UI greetings
+
+faults:
+  delay: false
+  error: false
+
+httpServer:
+  timeout: 30s

cmd/flagger/main.go

@@ -3,18 +3,21 @@ package main
 import (
 	"flag"
 	"log"
+	"strings"
 	"time"
 
-	_ "github.com/istio/glog"
-	istioclientset "github.com/knative/pkg/client/clientset/versioned"
-	"github.com/knative/pkg/signals"
-	clientset "github.com/stefanprodan/flagger/pkg/client/clientset/versioned"
-	informers "github.com/stefanprodan/flagger/pkg/client/informers/externalversions"
-	"github.com/stefanprodan/flagger/pkg/controller"
-	"github.com/stefanprodan/flagger/pkg/logging"
-	"github.com/stefanprodan/flagger/pkg/notifier"
-	"github.com/stefanprodan/flagger/pkg/server"
-	"github.com/stefanprodan/flagger/pkg/version"
+	_ "github.com/stefanprodan/klog"
+	clientset "github.com/weaveworks/flagger/pkg/client/clientset/versioned"
+	informers "github.com/weaveworks/flagger/pkg/client/informers/externalversions"
+	"github.com/weaveworks/flagger/pkg/controller"
+	"github.com/weaveworks/flagger/pkg/logger"
+	"github.com/weaveworks/flagger/pkg/metrics"
+	"github.com/weaveworks/flagger/pkg/notifier"
+	"github.com/weaveworks/flagger/pkg/router"
+	"github.com/weaveworks/flagger/pkg/server"
+	"github.com/weaveworks/flagger/pkg/signals"
+	"github.com/weaveworks/flagger/pkg/version"
+	"go.uber.org/zap"
 	"k8s.io/client-go/kubernetes"
 	_ "k8s.io/client-go/plugin/pkg/client/auth/gcp"
 	"k8s.io/client-go/tools/cache"
@@ -31,27 +34,43 @@ var (
 	slackURL            string
 	slackUser           string
 	slackChannel        string
+	threadiness         int
+	zapReplaceGlobals   bool
+	zapEncoding         string
+	namespace           string
+	meshProvider        string
+	selectorLabels      string
 )
 
 func init() {
 	flag.StringVar(&kubeconfig, "kubeconfig", "", "Path to a kubeconfig. Only required if out-of-cluster.")
 	flag.StringVar(&masterURL, "master", "", "The address of the Kubernetes API server. Overrides any value in kubeconfig. Only required if out-of-cluster.")
 	flag.StringVar(&metricsServer, "metrics-server", "http://prometheus:9090", "Prometheus URL")
-	flag.DurationVar(&controlLoopInterval, "control-loop-interval", 10*time.Second, "wait interval between rollouts")
+	flag.DurationVar(&controlLoopInterval, "control-loop-interval", 10*time.Second, "Kubernetes API sync interval")
 	flag.StringVar(&logLevel, "log-level", "debug", "Log level can be: debug, info, warning, error.")
 	flag.StringVar(&port, "port", "8080", "Port to listen on.")
 	flag.StringVar(&slackURL, "slack-url", "", "Slack hook URL.")
 	flag.StringVar(&slackUser, "slack-user", "flagger", "Slack user name.")
 	flag.StringVar(&slackChannel, "slack-channel", "", "Slack channel.")
+	flag.IntVar(&threadiness, "threadiness", 2, "Worker concurrency.")
+	flag.BoolVar(&zapReplaceGlobals, "zap-replace-globals", false, "Whether to change the logging level of the global zap logger.")
+	flag.StringVar(&zapEncoding, "zap-encoding", "json", "Zap logger encoding.")
+	flag.StringVar(&namespace, "namespace", "", "Namespace that flagger would watch canary object")
+	flag.StringVar(&meshProvider, "mesh-provider", "istio", "Service mesh provider, can be istio or appmesh")
+	flag.StringVar(&selectorLabels, "selector-labels", "app,name,app.kubernetes.io/name", "List of pod labels that Flagger uses to create pod selectors")
 }
 
 func main() {
 	flag.Parse()
 
-	logger, err := logging.NewLogger(logLevel)
+	logger, err := logger.NewLoggerWithEncoding(logLevel, zapEncoding)
 	if err != nil {
 		log.Fatalf("Error creating logger: %v", err)
 	}
+	if zapReplaceGlobals {
+		zap.ReplaceGlobals(logger.Desugar())
+	}
+
 	defer logger.Sync()
 
 	stopCh := signals.SetupSignalHandler()
@@ -66,7 +85,7 @@ func main() {
 		logger.Fatalf("Error building kubernetes clientset: %v", err)
 	}
 
-	istioClient, err := istioclientset.NewForConfig(cfg)
+	meshClient, err := clientset.NewForConfig(cfg)
 	if err != nil {
 		logger.Fatalf("Error building istio clientset: %v", err)
 	}
@@ -76,19 +95,28 @@ func main() {
 		logger.Fatalf("Error building example clientset: %s", err.Error())
 	}
 
-	flaggerInformerFactory := informers.NewSharedInformerFactory(flaggerClient, time.Second*30)
-	canaryInformer := flaggerInformerFactory.Flagger().V1alpha2().Canaries()
+	flaggerInformerFactory := informers.NewSharedInformerFactoryWithOptions(flaggerClient, time.Second*30, informers.WithNamespace(namespace))
 
-	logger.Infof("Starting flagger version %s revision %s", version.VERSION, version.REVISION)
+	canaryInformer := flaggerInformerFactory.Flagger().V1alpha3().Canaries()
+
+	logger.Infof("Starting flagger version %s revision %s mesh provider %s", version.VERSION, version.REVISION, meshProvider)
 
 	ver, err := kubeClient.Discovery().ServerVersion()
 	if err != nil {
 		logger.Fatalf("Error calling Kubernetes API: %v", err)
 	}
 
-	logger.Infof("Connected to Kubernetes API %s", ver)
+	labels := strings.Split(selectorLabels, ",")
+	if len(labels) < 1 {
+		logger.Fatalf("At least one selector label is required")
+	}
 
-	ok, err := controller.CheckMetricsServer(metricsServer)
+	logger.Infof("Connected to Kubernetes API %s", ver)
+	if namespace != "" {
+		logger.Infof("Watching namespace %s", namespace)
+	}
+
+	ok, err := metrics.CheckMetricsServer(metricsServer)
 	if ok {
 		logger.Infof("Connected to metrics server %s", metricsServer)
 	} else {
@@ -108,15 +136,21 @@ func main() {
 	// start HTTP server
 	go server.ListenAndServe(port, 3*time.Second, logger, stopCh)
 
+	routerFactory := router.NewFactory(cfg, kubeClient, flaggerClient, logger, meshClient)
+
 	c := controller.NewController(
 		kubeClient,
-		istioClient,
+		meshClient,
 		flaggerClient,
 		canaryInformer,
 		controlLoopInterval,
 		metricsServer,
 		logger,
 		slack,
+		routerFactory,
+		meshProvider,
+		version.VERSION,
+		labels,
 	)
 
 	flaggerInformerFactory.Start(stopCh)
@@ -132,7 +166,7 @@ func main() {
 
 	// start controller
 	go func(ctrl *controller.Controller) {
-		if err := ctrl.Run(2, stopCh); err != nil {
+		if err := ctrl.Run(threadiness, stopCh); err != nil {
 			logger.Fatalf("Error running controller: %v", err)
 		}
 	}(c)

cmd/loadtester/main.go

@@ -0,0 +1,51 @@
+package main
+
+import (
+	"flag"
+	"github.com/weaveworks/flagger/pkg/loadtester"
+	"github.com/weaveworks/flagger/pkg/logger"
+	"github.com/weaveworks/flagger/pkg/signals"
+	"go.uber.org/zap"
+	"log"
+	"time"
+)
+
+var VERSION = "0.3.0"
+var (
+	logLevel          string
+	port              string
+	timeout           time.Duration
+	zapReplaceGlobals bool
+	zapEncoding       string
+)
+
+func init() {
+	flag.StringVar(&logLevel, "log-level", "debug", "Log level can be: debug, info, warning, error.")
+	flag.StringVar(&port, "port", "9090", "Port to listen on.")
+	flag.DurationVar(&timeout, "timeout", time.Hour, "Load test exec timeout.")
+	flag.BoolVar(&zapReplaceGlobals, "zap-replace-globals", false, "Whether to change the logging level of the global zap logger.")
+	flag.StringVar(&zapEncoding, "zap-encoding", "json", "Zap logger encoding.")
+}
+
+func main() {
+	flag.Parse()
+
+	logger, err := logger.NewLoggerWithEncoding(logLevel, zapEncoding)
+	if err != nil {
+		log.Fatalf("Error creating logger: %v", err)
+	}
+	if zapReplaceGlobals {
+		zap.ReplaceGlobals(logger.Desugar())
+	}
+
+	defer logger.Sync()
+
+	stopCh := signals.SetupSignalHandler()
+
+	taskRunner := loadtester.NewTaskRunner(logger, timeout)
+
+	go taskRunner.Start(100*time.Millisecond, stopCh)
+
+	logger.Infof("Starting load tester v%s API on port %s", VERSION, port)
+	loadtester.ListenAndServe(port, time.Minute, logger, taskRunner, stopCh)
+}

docs/CNAME

@@ -1 +0,0 @@
-flagger.app

docs/README.md

@@ -1,11 +0,0 @@
-# Flagger
-
-Flagger is a Kubernetes operator that automates the promotion of canary deployments using Istio routing for traffic 
-shifting and Prometheus metrics for canary analysis.
-
-Flagger implements a control loop that gradually shifts traffic to the canary while measuring key performance 
-indicators like HTTP requests success rate, requests average duration and pods health. Based on the KPIs analysis 
-a canary is promoted or aborted and the analysis result is published to Slack.
-
-### For the install instructions and usage examples please see [docs.flagger.app](https://docs.flagger.app)
-

docs/_config.yaml

@@ -1,55 +0,0 @@
-title: Flagger - Istio Progressive Delivery Kubernetes Operator
-
-remote_theme: errordeveloper/simple-project-homepage
-repository: stefanprodan/flagger
-by_weaveworks: true
-
-url: "https://flagger.app"
-baseurl: "/"
-
-twitter:
-  username: "stefanprodan"
-author:
-  twitter: "stefanprodan"
-
-# Set default og:image
-defaults:
-- scope: {path: ""}
-  values: {image: "diagrams/flagger-overview.png"}
-
-# See: https://material.io/guidelines/style/color.html
-# Use color-name-value, like pink-200 or deep-purple-100
-brand_color: "amber-400"
-
-# How article URLs are structured.
-# See: https://jekyllrb.com/docs/permalinks/
-permalink: posts/:title/
-
-# "UA-NNNNNNNN-N"
-google_analytics: ""
-
-# Language. For example, if you write in Japanese, use "ja"
-lang: "en"
-
-# How many posts are visible on the home page without clicking "View More"
-num_posts_visible_initially: 5
-
-# Date format: See http://strftime.net/
-date_format: "%b %-d, %Y"
-
-plugins:
-- jekyll-feed
-- jekyll-readme-index
-- jekyll-seo-tag
-- jekyll-sitemap
-- jemoji
-# # required for local builds with starefossen/github-pages
-# - jekyll-github-metadata
-# - jekyll-mentions
-# - jekyll-redirect-from
-# - jekyll-remote-theme
-
-exclude:
-- CNAME
-- gitbook
-