Merge pull request #159 from weaveworks/release-v0.12.0

Prepare release v0.12.0

.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

.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
@@ -13,27 +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 "$DOCKER_USER" ]; then
     echo "PR build, skipping image push";
   else
     BRANCH_COMMIT=${TRAVIS_BRANCH}-$(echo ${TRAVIS_COMMIT} | head -c7);
-    docker tag stefanprodan/flagger:latest quay.io/stefanprodan/flagger:${BRANCH_COMMIT};
-    echo $DOCKER_PASS | docker login -u=$DOCKER_USER --password-stdin quay.io;
-    docker push quay.io/stefanprodan/flagger:${BRANCH_COMMIT};
+    docker tag weaveworks/flagger:latest weaveworks/flagger:${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 +1,245 @@
+# Changelog
+
+All notable changes to this project are documented in this file.
+
+## 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

@@ -1,24 +1,8 @@
-FROM golang:1.11 AS hey-builder
+FROM golang:1.12 AS builder
 
-RUN mkdir -p /go/src/github.com/rakyll/hey/
+RUN mkdir -p /go/src/github.com/weaveworks/flagger/
 
-WORKDIR /go/src/github.com/rakyll/hey
-
-ADD https://github.com/rakyll/hey/archive/v0.1.1.tar.gz .
-
-RUN tar xzf v0.1.1.tar.gz --strip 1
-
-RUN go get ./...
-
-RUN CGO_ENABLED=0 GOOS=linux GOARCH=amd64 \
-  go install -ldflags '-w -extldflags "-static"' \
-  /go/src/github.com/rakyll/hey
-
-FROM golang:1.11 AS builder
-
-RUN mkdir -p /go/src/github.com/stefanprodan/flagger/
-
-WORKDIR /go/src/github.com/stefanprodan/flagger
+WORKDIR /go/src/github.com/weaveworks/flagger
 
 COPY . .
 
@@ -26,16 +10,18 @@ RUN go test -race ./pkg/loadtester/
 
 RUN CGO_ENABLED=0 GOOS=linux go build -a -installsuffix cgo -o loadtester ./cmd/loadtester/*
 
-FROM alpine:3.8
+FROM bats/bats:v1.1.0
 
 RUN addgroup -S app \
     && adduser -S -g app app \
-    && apk --no-cache add ca-certificates curl
+    && apk --no-cache add ca-certificates curl jq
 
 WORKDIR /home/app
 
-COPY --from=hey-builder /go/bin/hey /usr/local/bin/hey
-COPY --from=builder /go/src/github.com/stefanprodan/flagger/loadtester .
+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 ./
 

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

@@ -4,19 +4,26 @@ VERSION_MINOR:=$(shell grep 'VERSION' pkg/version/version.go | awk '{ print $$4
 PATCH:=$(shell grep 'VERSION' pkg/version/version.go | awk '{ print $$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"
 
 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)
@@ -31,9 +38,9 @@ test: test-fmt test-codegen
 	go test ./...
 
 helm-package:
-	cd charts/ && helm package flagger/ && helm package grafana/ && helm package loadtester/
+	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
@@ -82,5 +89,5 @@ reset-test:
 	kubectl apply -f ./artifacts/canaries
 
 loadtester-push:
-	docker build -t quay.io/stefanprodan/flagger-loadtester:$(LT_VERSION) . -f Dockerfile.loadtester
-	docker push quay.io/stefanprodan/flagger-loadtester:$(LT_VERSION)
+	docker build -t weaveworks/flagger-loadtester:$(LT_VERSION) . -f Dockerfile.loadtester
+	docker push weaveworks/flagger-loadtester:$(LT_VERSION)

README.md

@@ -1,79 +1,58 @@
 # 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, 
+using Istio or App Mesh 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 
-```
+* 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)
+  * [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 >1.11.0 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 keeps track of ConfigMaps and Secrets referenced by a Kubernetes Deployment and triggers a canary analysis if any of those objects change. 
+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.
 
-![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)
-* call webhooks and check results
-* 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 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 ConfigMaps and Secrets from 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 and start over
-
 For a deployment named _podinfo_, a canary promotion can be defined using Flagger's custom resource:
 
 ```yaml
@@ -102,9 +81,31 @@ spec:
     # Istio gateways (optional)
     gateways:
     - public-gateway.istio-system.svc.cluster.local
+    - mesh
     # Istio virtual service host names (optional)
     hosts:
     - 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
@@ -118,16 +119,27 @@ 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: load-test
@@ -137,322 +149,47 @@ spec:
           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          |
+| -------------------------------------------- | ------------------ | ------------------ |------------------  |
+| Canary deployments (weighted traffic)        | :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: |
+| Load testing                                 | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: |
+| Webhooks (custom acceptance tests)           | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: |
+| Request success rate check (Envoy metric)    | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: |
+| Request duration check (Envoy metric)        | :heavy_check_mark: | :heavy_minus_sign: | :heavy_check_mark: |
+| Custom promql checks                         | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: |
+| Ingress gateway (CORS, retries and timeouts) | :heavy_check_mark: | :heavy_minus_sign: | :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
-```
-
-Deploy the load testing service to generate traffic during the canary analysis:
-
-```bash
-kubectl -n test apply -f ${REPO}/artifacts/loadtester/deployment.yaml
-kubectl -n test apply -f ${REPO}/artifacts/loadtester/service.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:1.4.0
-```
-
-**Note** that Flagger tracks changes in the deployment `PodSpec` but also in `ConfigMaps` and `Secrets` 
-that are referenced in the pod's volumes and containers environment variables.
-
-Flagger detects that the deployment revision changed and starts a new canary analysis:
-
-```
-kubectl -n test describe canary/podinfo
-
-Status:
-  Canary Weight:         0
-  Failed Checks:         0
-  Last Transition Time:  2019-01-16T13:47:16Z
-  Phase:                 Succeeded
-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
-```
-
-You can monitor all canaries with:
-
-```bash
-watch kubectl get canaries --all-namespaces
-
-NAMESPACE   NAME      STATUS        WEIGHT   LASTTRANSITIONTIME
-test        podinfo   Progressing   5        2019-01-16T14:05:07Z
-```
-
-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 Weight:         0
-  Failed Checks:         10
-  Last Transition Time:  2019-01-16T13:47:16Z
-  Phase:                 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
-```
-
-**Note** that if you apply new changes to the deployment during the canary analysis, Flagger will restart the analysis.
-
-### 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

@@ -23,9 +23,26 @@ 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
@@ -39,12 +56,12 @@ 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
@@ -55,4 +72,6 @@ spec:
         url: http://flagger-loadtester.test/
         timeout: 5s
         metadata:
+          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

@@ -23,6 +23,7 @@ spec:
     # Istio gateways (optional)
     gateways:
     - public-gateway.istio-system.svc.cluster.local
+    - mesh
     # Istio virtual service host names (optional)
     hosts:
     - app.iowa.weavedx.com
@@ -39,12 +40,12 @@ 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

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 +13,50 @@ 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:
+      - 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

@@ -2,6 +2,8 @@ apiVersion: apiextensions.k8s.io/v1beta1
 kind: CustomResourceDefinition
 metadata:
   name: canaries.flagger.app
+  annotations:
+    helm.sh/resource-policy: keep
 spec:
   group: flagger.app
   version: v1alpha3
@@ -39,9 +41,9 @@ spec:
       properties:
         spec:
           required:
-          - targetRef
-          - service
-          - canaryAnalysis
+            - targetRef
+            - service
+            - canaryAnalysis
           properties:
             progressDeadlineSeconds:
               type: number
@@ -73,11 +75,21 @@ 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:
@@ -89,7 +101,7 @@ spec:
                   properties:
                     items:
                       type: object
-                      required: ['name', 'interval', 'threshold']
+                      required: ['name', 'threshold']
                       properties:
                         name:
                           type: string
@@ -98,6 +110,8 @@ spec:
                           pattern: "^[0-9]+(m|s)"
                         threshold:
                           type: number
+                        query:
+                          type: string
                 webhooks:
                   type: array
                   properties:
@@ -107,9 +121,36 @@ 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]+(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:0.5.0
-        imagePullPolicy: Always
+        image: weaveworks/flagger:0.12.0
+        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

@@ -17,7 +17,7 @@ spec:
     spec:
       containers:
         - name: loadtester
-          image: quay.io/stefanprodan/flagger-loadtester:0.1.0
+          image: weaveworks/flagger-loadtester:0.3.0
           imagePullPolicy: IfNotPresent
           ports:
             - name: http
@@ -27,7 +27,6 @@ spec:
             - -port=8080
             - -log-level=info
             - -timeout=1h
-            - -log-cmd-output=true
           livenessProbe:
             exec:
               command:
@@ -58,3 +57,11 @@ spec:
           securityContext:
             readOnlyRootFilesystem: true
             runAsUser: 10001
+#          volumeMounts:
+#            - name: tests
+#              mountPath: /bats
+#              readOnly: true
+#      volumes:
+#        - name: tests
+#          configMap:
+#            name: flagger-loadtester-bats

artifacts/namespaces/test.yaml

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

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: 0.5.0
-appVersion: 0.5.0
+version: 0.12.0
+appVersion: 0.12.0
 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://docs.flagger.app
-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
 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

@@ -1,6 +1,6 @@
 # Flagger
 
-[Flagger](https://github.com/stefanprodan/flagger) is a Kubernetes operator that automates the promotion of 
+[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.

charts/flagger/templates/crd.yaml

@@ -3,6 +3,8 @@ apiVersion: apiextensions.k8s.io/v1beta1
 kind: CustomResourceDefinition
 metadata:
   name: canaries.flagger.app
+  annotations:
+    helm.sh/resource-policy: keep
 spec:
   group: flagger.app
   version: v1alpha3
@@ -74,11 +76,21 @@ 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:
@@ -90,7 +102,7 @@ spec:
                   properties:
                     items:
                       type: object
-                      required: ['name', 'interval', 'threshold']
+                      required: ['name', 'threshold']
                       properties:
                         name:
                           type: string
@@ -99,6 +111,8 @@ spec:
                           pattern: "^[0-9]+(m|s)"
                         threshold:
                           type: number
+                        query:
+                          type: string
                 webhooks:
                   type: array
                   properties:
@@ -108,10 +122,37 @@ 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]+(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

@@ -35,7 +35,13 @@ spec:
           command:
           - ./flagger
           - -log-level=info
+          {{- if .Values.meshProvider }}
+          - -mesh-provider={{ .Values.meshProvider }}
+          {{- end }}
           - -metrics-server={{ .Values.metricsServer }}
+          {{- if .Values.namespace }}
+          - -namespace={{ .Values.namespace }}
+          {{- end }}
           {{- if .Values.slack.url }}
           - -slack-url={{ .Values.slack.url }}
           - -slack-user={{ .Values.slack.user }}

charts/flagger/templates/rbac.yaml

@@ -9,11 +9,50 @@ 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:
+      - 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

@@ -1,11 +1,17 @@
 # Default values for flagger.
 
 image:
-  repository: quay.io/stefanprodan/flagger
-  tag: 0.5.0
+  repository: weaveworks/flagger
+  tag: 0.12.0
   pullPolicy: IfNotPresent
 
-metricsServer: "http://prometheus.istio-system.svc.cluster.local:9090"
+metricsServer: "http://prometheus:9090"
+
+# accepted values are istio or appmesh (defaults to istio)
+meshProvider: ""
+
+# single namespace restriction
+namespace: ""
 
 slack:
   user: flagger

charts/grafana/Chart.yaml

@@ -1,12 +1,12 @@
 apiVersion: v1
 name: grafana
-version: 0.1.0
-appVersion: 5.4.2
+version: 1.1.0
+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

@@ -2,7 +2,7 @@
 
 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
 

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": [],
@@ -1577,11 +1605,9 @@
       },
       {
         "allValue": null,
-        "current": {
-          "text": "primary",
-          "value": "primary"
-        },
+        "current": null,
         "datasource": "prometheus",
+        "definition": "",
         "hide": 0,
         "includeAll": false,
         "label": "Primary",
@@ -1591,6 +1617,7 @@
         "query": "query_result(sum(istio_requests_total{destination_workload_namespace=~\"$namespace\"}) by (destination_service_name))",
         "refresh": 1,
         "regex": "/.*destination_service_name=\"([^\"]*).*/",
+        "skipUrlSync": false,
         "sort": 1,
         "tagValuesQuery": "",
         "tags": [],
@@ -1600,11 +1627,9 @@
       },
       {
         "allValue": null,
-        "current": {
-          "text": "canary",
-          "value": "canary"
-        },
+        "current": null,
         "datasource": "prometheus",
+        "definition": "",
         "hide": 0,
         "includeAll": false,
         "label": "Canary",
@@ -1614,6 +1639,7 @@
         "query": "query_result(sum(istio_requests_total{destination_workload_namespace=~\"$namespace\"}) by (destination_service_name))",
         "refresh": 1,
         "regex": "/.*destination_service_name=\"([^\"]*).*/",
+        "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/Chart.yaml

@@ -1,14 +1,14 @@
 apiVersion: v1
 name: loadtester
-version: 0.1.0
-appVersion: 0.1.0
+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/stefanprodan/flagger/master/docs/logo/flagger-icon.png
+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
@@ -16,5 +16,6 @@ maintainers:
 keywords:
   - canary
   - istio
+  - appmesh
   - gitops
   - load testing

charts/loadtester/README.md

@@ -1,6 +1,6 @@
 # Flagger load testing service
 
-[Flagger's](https://github.com/stefanprodan/flagger) load testing service is based on 
+[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.
 
@@ -56,15 +56,15 @@ Parameter | Description | Default
 `nodeSelector` | node labels for pod assignment | `{}`
 `service.type` | type of service | `ClusterIP`
 `service.port` | ClusterIP port | `80`
-`cmd.logOutput` | Log the command output to stderr | `true`
 `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 \
---set cmd.logOutput=false
+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,

charts/loadtester/templates/deployment.yaml

@@ -16,6 +16,8 @@ spec:
     metadata:
       labels:
         app: {{ include "loadtester.name" . }}
+      annotations:
+        appmesh.k8s.aws/ports: "444"
     spec:
       containers:
         - name: {{ .Chart.Name }}
@@ -29,7 +31,6 @@ spec:
             - -port=8080
             - -log-level={{ .Values.logLevel }}
             - -timeout={{ .Values.cmd.timeout }}
-            - -log-cmd-output={{ .Values.cmd.logOutput }}
           livenessProbe:
             exec:
               command:

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

@@ -1,13 +1,12 @@
 replicaCount: 1
 
 image:
-  repository: quay.io/stefanprodan/flagger-loadtester
-  tag: 0.1.0
+  repository: weaveworks/flagger-loadtester
+  tag: 0.3.0
   pullPolicy: IfNotPresent
 
 logLevel: info
 cmd:
-  logOutput: true
   timeout: 1h
 
 nameOverride: ""
@@ -27,3 +26,9 @@ 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"
@@ -31,6 +34,12 @@ var (
 	slackURL            string
 	slackUser           string
 	slackChannel        string
+	threadiness         int
+	zapReplaceGlobals   bool
+	zapEncoding         string
+	namespace           string
+	meshProvider        string
+	selectorLabels      string
 )
 
 func init() {
@@ -43,15 +52,25 @@ func init() {
 	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)
 	}
@@ -76,7 +95,8 @@ func main() {
 		logger.Fatalf("Error building example clientset: %s", err.Error())
 	}
 
-	flaggerInformerFactory := informers.NewSharedInformerFactory(flaggerClient, time.Second*30)
+	flaggerInformerFactory := informers.NewSharedInformerFactoryWithOptions(flaggerClient, time.Second*30, informers.WithNamespace(namespace))
+
 	canaryInformer := flaggerInformerFactory.Flagger().V1alpha3().Canaries()
 
 	logger.Infof("Starting flagger version %s revision %s", version.VERSION, version.REVISION)
@@ -86,9 +106,17 @@ func main() {
 		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

@@ -2,40 +2,47 @@ package main
 
 import (
 	"flag"
-	"github.com/knative/pkg/signals"
-	"github.com/stefanprodan/flagger/pkg/loadtester"
-	"github.com/stefanprodan/flagger/pkg/logging"
+	"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 = "0.1.0"
+var VERSION = "0.3.0"
 var (
-	logLevel     string
-	port         string
-	timeout      time.Duration
-	logCmdOutput bool
+	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, "Command exec timeout.")
-	flag.BoolVar(&logCmdOutput, "log-cmd-output", true, "Log command output to stderr")
+	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 := 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()
 
-	taskRunner := loadtester.NewTaskRunner(logger, timeout, logCmdOutput)
+	taskRunner := loadtester.NewTaskRunner(logger, timeout)
 
 	go taskRunner.Start(100*time.Millisecond, stopCh)
 

docs/gitbook/README.md

@@ -1,21 +1,21 @@
 ---
-description: Flagger is an Istio progressive delivery Kubernetes operator
+description: Flagger is a progressive delivery Kubernetes operator
 ---
 
 # Introduction
 
-[Flagger](https://github.com/stefanprodan/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.
+[Flagger](https://github.com/weaveworks/flagger) is a **Kubernetes** operator that automates the promotion of canary 
+deployments using **Istio** or **App Mesh** routing for traffic shifting and **Prometheus** metrics for canary analysis.
+The canary analysis can be extended with webhooks for running 
+system integration/acceptance tests, load tests, or any other custom validation.
 
 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**.
+Based on analysis of the **KPIs** a canary is promoted or aborted, and the analysis result is published to **Slack**.
 
-![Flagger overview diagram](https://raw.githubusercontent.com/stefanprodan/flagger/master/docs/diagrams/flagger-canary-overview.png)
+![Flagger overview diagram](https://raw.githubusercontent.com/weaveworks/flagger/master/docs/diagrams/flagger-canary-overview.png)
 
-Flagger can be configured with Kubernetes custom resources \(canaries.flagger.app kind\) and is compatible with 
+Flagger can be configured with Kubernetes custom resources and is compatible with 
 any CI/CD solutions made for Kubernetes. Since Flagger is declarative and reacts to Kubernetes events, 
 it can be used in **GitOps** pipelines together with Weave Flux or JenkinsX.
 

docs/gitbook/SUMMARY.md

@@ -5,13 +5,20 @@
 
 ## Install
 
-* [Install Flagger](install/install-flagger.md)
-* [Install Grafana](install/install-grafana.md)
-* [Install Istio](install/install-istio.md)
+* [Flagger Install on Kubernetes](install/flagger-install-on-kubernetes.md)
+* [Flagger Install on GKE Istio](install/flagger-install-on-google-cloud.md)
+* [Flagger Install on EKS App Mesh](install/flagger-install-on-eks-appmesh.md)
+* [Flagger Install with SuperGloo](install/flagger-install-with-supergloo.md)
 
 ## Usage
 
-* [Canary Deployments](usage/progressive-delivery.md)
+* [Istio Canary Deployments](usage/progressive-delivery.md)
+* [Istio A/B Testing](usage/ab-testing.md)
+* [App Mesh Canary Deployments](usage/appmesh-progressive-delivery.md)
 * [Monitoring](usage/monitoring.md)
 * [Alerting](usage/alerting.md)
 
+## Tutorials
+
+* [Canaries with Helm charts and GitOps](tutorials/canary-helm-gitops.md)
+* [Zero downtime deployments](tutorials/zero-downtime-deployments.md)

docs/gitbook/faq.md

@@ -0,0 +1,21 @@
+# Frequently asked questions
+
+**Can Flagger be part of my integration tests?**
+> Yes, Flagger supports webhooks to do integration testing.
+
+**What if I only want to target beta testers?**
+> That's a feature in Flagger, not in App Mesh. It's on the App Mesh roadmap.
+
+**When do I use A/B testing when Canary?**
+> One advantage of using A/B testing is that each version remains separated and routes aren't mixed.
+>
+> Using a Canary deployment can lead to behaviour like this one observed by a
+> user:
+>
+> [..] during a canary deployment of our nodejs app, the version that is being served <50% traffic reports mime type mismatch errors in the browser (js as "text/html")
+> When the deployment Passes/ Fails (doesn't really matter) the version that stays alive works as expected. If anyone has any tips or direction I would greatly appreciate it. Even if its as simple as I'm looking in the wrong place. Thanks in advance!
+>
+> The issue was that we were not maintaining session affinity while serving files for our frontend. Which resulted in any redirects or refreshes occasionally returning a mismatched app.*.js file (generated from vue)
+>
+> Read up on [A/B testing](https://docs.flagger.app/usage/ab-testing).
+

docs/gitbook/how-it-works.md

@@ -1,10 +1,10 @@
 # How it works
 
-[Flagger](https://github.com/stefanprodan/flagger) takes a Kubernetes deployment and optionally 
+[Flagger](https://github.com/weaveworks/flagger) takes a Kubernetes deployment and optionally 
 a horizontal pod autoscaler \(HPA\) and creates a series of objects 
-\(Kubernetes deployments, ClusterIP services and Istio virtual services\) to drive the canary analysis and promotion. 
+\(Kubernetes deployments, ClusterIP services and Istio or App Mesh virtual services\) to drive the canary analysis and promotion. 
 
-![Flagger Canary Process](https://raw.githubusercontent.com/stefanprodan/flagger/master/docs/diagrams/flagger-canary-hpa.png)
+![Flagger Canary Process](https://raw.githubusercontent.com/weaveworks/flagger/master/docs/diagrams/flagger-canary-hpa.png)
 
 ### Canary Custom Resource
 
@@ -33,12 +33,18 @@ spec:
   service:
     # container port
     port: 9898
+    # service port name (optional, will default to "http")
+    portName: http-podinfo
     # Istio gateways (optional)
     gateways:
     - public-gateway.istio-system.svc.cluster.local
+    - mesh
     # Istio virtual service host names (optional)
     hosts:
     - podinfo.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
@@ -50,14 +56,14 @@ spec:
     # canary increment step
     # percentage (0-100)
     stepWeight: 5
-    # Istio Prometheus checks
+    # 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
@@ -90,12 +96,167 @@ spec:
         app: podinfo
 ```
 
+Besides `app` Flagger supports `name` and `app.kubernetes.io/name` selectors. If you use a different 
+convention you can specify your label with the `-selector-labels` flag.
+
 The target deployment should expose a TCP port that will be used by Flagger to create the ClusterIP Service and 
 the Istio Virtual Service. The container port from the target deployment should match the `service.port` value.
 
-### Canary Deployment
+### Istio routing
 
-![Flagger Canary Stages](https://raw.githubusercontent.com/stefanprodan/flagger/master/docs/diagrams/flagger-canary-steps.png)
+Flagger creates an Istio Virtual Service based on the Canary service spec. The service configuration lets you expose 
+an app inside or outside the mesh.
+You can also define HTTP match conditions, URI rewrite rules, CORS policies, timeout and retries.
+
+The following spec exposes the `frontend` workload inside the mesh on `frontend.test.svc.cluster.local:9898` 
+and outside the mesh on `frontend.example.com`. You'll have to specify an Istio ingress gateway for external hosts.
+
+```yaml
+apiVersion: flagger.app/v1alpha3
+kind: Canary
+metadata:
+  name: frontend
+  namespace: test
+spec:
+  service:
+    # container port
+    port: 9898
+    # service port name (optional, will default to "http")
+    portName: http-frontend
+    # Istio gateways (optional)
+    gateways:
+    - public-gateway.istio-system.svc.cluster.local
+    - mesh
+    # Istio virtual service host names (optional)
+    hosts:
+    - frontend.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
+      allowMethods:
+        - GET
+      allowCredentials: false
+      allowHeaders:
+        - x-some-header
+      maxAge: 24h
+```
+
+For the above spec Flagger will generate the following virtual service:
+
+```yaml
+apiVersion: networking.istio.io/v1alpha3
+kind: VirtualService
+metadata:
+  name: frontend
+  namespace: test
+  ownerReferences:
+    - apiVersion: flagger.app/v1alpha3
+      blockOwnerDeletion: true
+      controller: true
+      kind: Canary
+      name: podinfo
+      uid: 3a4a40dd-3875-11e9-8e1d-42010a9c0fd1
+spec:
+  gateways:
+    - public-gateway.istio-system.svc.cluster.local
+    - mesh
+  hosts:
+    - frontend.example.com
+    - frontend
+  http:
+  - appendHeaders:
+      x-envoy-max-retries: "10"
+      x-envoy-retry-on: gateway-error,connect-failure,refused-stream
+      x-envoy-upstream-rq-timeout-ms: "15000"
+    corsPolicy:
+      allowHeaders:
+      - x-some-header
+      allowMethods:
+      - GET
+      allowOrigin:
+      - example.com
+      maxAge: 24h
+    match:
+    - uri:
+        prefix: /
+    rewrite:
+      uri: /
+    route:
+    - destination:
+        host: podinfo-primary
+        port:
+          number: 9898
+      weight: 100
+    - destination:
+        host: podinfo-canary
+        port:
+          number: 9898
+      weight: 0
+```
+
+Flagger keeps in sync the virtual service with the canary service spec. Any direct modification to the virtual 
+service spec will be overwritten.
+
+To expose a workload inside the mesh on `http://backend.test.svc.cluster.local:9898`,
+the service spec can contain only the container port:
+
+```yaml
+apiVersion: flagger.app/v1alpha3
+kind: Canary
+metadata:
+  name: backend
+  namespace: test
+spec:
+  service:
+    port: 9898
+```
+
+Based on the above spec, Flagger will create several ClusterIP services like:
+
+```yaml
+apiVersion: v1
+kind: Service
+metadata:
+  name: backend-primary
+  ownerReferences:
+  - apiVersion: flagger.app/v1alpha3
+    blockOwnerDeletion: true
+    controller: true
+    kind: Canary
+    name: backend
+    uid: 2ca1a9c7-2ef6-11e9-bd01-42010a9c0145
+spec:
+  type: ClusterIP
+  ports:
+  - name: http
+    port: 9898
+    protocol: TCP
+    targetPort: 9898
+  selector:
+    app: backend-primary
+```
+
+Flagger works for user facing apps exposed outside the cluster via an ingress gateway
+and for backend HTTP APIs that are accessible only from inside the mesh.
+
+### Canary Stages
+
+![Flagger Canary Stages](https://raw.githubusercontent.com/weaveworks/flagger/master/docs/diagrams/flagger-canary-steps.png)
 
 A canary deployment is triggered by changes in any of the following objects:
 
@@ -110,16 +271,22 @@ Gated canary promotion stages:
 * check primary and canary deployments status
     * halt advancement if a rolling update is underway
     * halt advancement if pods are unhealthy
+* call pre-rollout webhooks are check results
+    * halt advancement if any hook returned a non HTTP 2xx result
+    * increment the failed checks counter
 * increase canary traffic weight percentage from 0% to 5% (step weight)
-* call webhooks and check results
+* call rollout webhooks and check results
 * 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
+    * call post-rollout webhooks
+    * post the analysis result to Slack
     * wait for the canary deployment to be updated and start over
 * increase canary traffic weight by 5% (step weight) till it reaches 50% (max weight) 
+    * halt advancement if any webhook call fails
     * 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 
@@ -132,6 +299,8 @@ Gated canary promotion stages:
 * route all traffic to primary
 * scale to zero the canary deployment
 * mark rollout as finished
+* call post-rollout webhooks
+* post the analysis result to Slack
 * wait for the canary deployment to be updated and start over
 
 ### Canary Analysis
@@ -152,6 +321,9 @@ Spec:
     # canary increment step
     # percentage (0-100)
     stepWeight: 2
+  # deploy straight to production without
+  # the metrics and webhook checks
+  skipAnalysis: false
 ```
 
 The above analysis, if it succeeds, will run for 25 minutes while validating the HTTP metrics and webhooks every minute.
@@ -167,6 +339,54 @@ And the time it takes for a canary to be rollback when the metrics or webhook ch
 interval * threshold 
 ```
 
+In emergency cases, you may want to skip the analysis phase and ship changes directly to production. 
+At any time you can set the `spec.skipAnalysis: true`. 
+When skip analysis is enabled, Flagger checks if the canary deployment is healthy and 
+promotes it without analysing it. If an analysis is underway, Flagger cancels it and runs the promotion.
+
+### A/B Testing
+
+Besides weighted routing, Flagger can be configured to route traffic to the canary based on HTTP match conditions.
+In an A/B testing scenario, you'll be using HTTP headers or cookies to target a certain segment of your users.
+This is particularly useful for frontend applications that require session affinity.
+
+You can enable A/B testing by specifying the HTTP match conditions and the number of iterations:
+
+```yaml
+  canaryAnalysis:
+    # schedule interval (default 60s)
+    interval: 1m
+    # total number of iterations
+    iterations: 10
+    # max number of failed iterations before rollback
+    threshold: 2
+    # canary match condition
+    match:
+      - headers:
+          user-agent:
+            regex: "^(?!.*Chrome).*Safari.*"
+      - headers:
+          cookie:
+            regex: "^(.*?;)?(user=test)(;.*)?$"
+```
+
+If Flagger finds a HTTP match condition, it will ignore the `maxWeight` and `stepWeight` settings.
+
+The above configuration will run an analysis for ten minutes targeting the Safari users and those that have a test cookie.
+You can determine the minimum time that it takes to validate and promote a canary deployment using this formula:
+
+```
+interval * iterations
+```
+
+And the time it takes for a canary to be rollback when the metrics or webhook checks are failing:
+
+```
+interval * threshold 
+```
+
+Make sure that the analysis threshold is lower than the number of iterations.
+
 ### HTTP Metrics
 
 The canary analysis is using the following Prometheus queries:
@@ -178,14 +398,14 @@ Spec:
 ```yaml
   canaryAnalysis:
     metrics:
-    - name: istio_requests_total
+    - name: request-success-rate
       # minimum req success rate (non 5xx responses)
       # percentage (0-100)
       threshold: 99
       interval: 1m
 ```
 
-Query:
+Istio query:
 
 ```javascript
 sum(
@@ -210,6 +430,29 @@ sum(
 )
 ```
 
+App Mesh query:
+
+```javascript
+sum(
+    rate(
+        envoy_cluster_upstream_rq{
+          kubernetes_namespace="$namespace",
+          kubernetes_pod_name=~"$workload",
+          response_code!~"5.*"
+        }[$interval]
+    )
+) 
+/ 
+sum(
+    rate(
+        envoy_cluster_upstream_rq{
+          kubernetes_namespace="$namespace",
+          kubernetes_pod_name=~"$workload"
+        }[$interval]
+    )
+)
+```
+
 **HTTP requests milliseconds duration P99**
 
 Spec:
@@ -217,14 +460,14 @@ Spec:
 ```yaml
   canaryAnalysis:
     metrics:
-    - name: istio_request_duration_seconds_bucket
+    - name: request-duration
       # maximum req duration P99
       # milliseconds
       threshold: 500
       interval: 1m
 ```
 
-Query:
+Istio query:
 
 ```javascript
 histogram_quantile(0.99, 
@@ -240,40 +483,145 @@ histogram_quantile(0.99,
 )
 ```
 
+App Mesh query:
+
+```javascript
+histogram_quantile(0.99, 
+  sum(
+    irate(
+      envoy_cluster_upstream_rq_time_bucket{
+        kubernetes_pod_name=~"$workload",
+        kubernetes_namespace=~"$namespace"
+      }[$interval]
+    )
+  ) by (le)
+)
+```
+
 > **Note** that the metric interval should be lower or equal to the control loop interval.
 
+### Custom Metrics
+
+The canary analysis can be extended with custom Prometheus queries. 
+
+```yaml
+  canaryAnalysis:
+    threshold: 1
+    maxWeight: 50
+    stepWeight: 5
+    metrics:
+    - name: "404s percentage"
+      threshold: 5
+      query: |
+        100 - sum(
+            rate(
+                istio_requests_total{
+                  reporter="destination",
+                  destination_workload_namespace="test",
+                  destination_workload="podinfo",
+                  response_code!="404"
+                }[1m]
+            )
+        )
+        /
+        sum(
+            rate(
+                istio_requests_total{
+                  reporter="destination",
+                  destination_workload_namespace="test",
+                  destination_workload="podinfo"
+                }[1m]
+            )
+        ) * 100
+```
+
+The above configuration validates the canary by checking
+if the HTTP 404 req/sec percentage is below 5 percent of the total traffic.
+If the 404s rate reaches the 5% threshold, then the canary fails.
+
+```yaml
+  canaryAnalysis:
+    threshold: 1
+    maxWeight: 50
+    stepWeight: 5
+    metrics:
+    - name: "rpc error rate"
+      threshold: 5
+      query: |
+        100 - (sum
+            rate(
+                grpc_server_handled_total{
+                  grpc_service="my.TestService",
+                  grpc_code!="OK"
+                }[1m]
+            )
+        )
+        /
+        sum(
+            rate(
+                grpc_server_started_total{
+                  grpc_service="my.TestService"
+                }[1m]
+            )
+        ) * 100
+```
+
+The above configuration validates the canary by checking if the percentage of
+non-OK GRPC req/sec is below 5 percent of the total requests. If the non-OK
+rate reaches the 5% threshold, then the canary fails.
+
+When specifying a query, Flagger will run the promql query and convert the result to float64. 
+Then it compares the query result value with the metric threshold value.
+
 ### Webhooks
 
-The canary analysis can be extended with webhooks. 
-Flagger will call each webhook URL and determine from the response status code (HTTP 2xx) if the canary is failing or not.
+The canary analysis can be extended with webhooks. Flagger will call each webhook URL and
+determine from the response status code (HTTP 2xx) if the canary is failing or not.
+
+There are three types of hooks:
+* Pre-rollout hooks are executed before routing traffic to canary. 
+The canary advancement is paused if a pre-rollout hook fails and if the number of failures reach the 
+threshold the canary will be rollback.
+* Rollout hooks are executed during the analysis on each iteration before the metric checks. 
+If a rollout hook call fails the canary advancement is paused and eventfully rolled back.
+* Post-rollout hooks are executed after the canary has been promoted or rolled back. 
+If a post rollout hook fails the error is logged.
 
 Spec:
 
 ```yaml
   canaryAnalysis:
     webhooks:
-      - name: integration-tests
-        url: http://podinfo.test:9898/echo
-        timeout: 30s
-        metadata:
-          test: "all"
-          token: "16688eb5e9f289f1991c"
-      - name: load-tests
-        url: http://podinfo.test:9898/echo
+      - name: "smoke test"
+        type: pre-rollout
+        url: http://migration-check.db/query
         timeout: 30s
         metadata:
           key1: "val1"
           key2: "val2"
+      - name: "load test"
+        type: rollout
+        url: http://flagger-loadtester.test/
+        timeout: 15s
+        metadata:
+          cmd: "hey -z 1m -q 5 -c 2 http://podinfo-canary.test:9898/"
+      - name: "notify"
+        type: post-rollout
+        url: http://telegram.bot:8080/
+        timeout: 5s
+        metadata:
+          some: "message"
 ```
 
-> **Note** that the sum of all webhooks timeouts should be lower than the control loop interval. 
+> **Note** that the sum of all rollout webhooks timeouts should be lower than the analysis interval. 
 
 Webhook payload (HTTP POST):
 
 ```json
 {
     "name": "podinfo",
-    "namespace": "test", 
+    "namespace": "test",
+    "phase": "Progressing", 
     "metadata": {
         "test":  "all",
         "token":  "16688eb5e9f289f1991c"
@@ -298,12 +646,12 @@ Flagger metric checks will fail with "no values found for metric istio_requests_
 Flagger comes with a load testing service based on [rakyll/hey](https://github.com/rakyll/hey) 
 that generates traffic during analysis when configured as a webhook.
 
-![Flagger Load Testing Webhook](https://raw.githubusercontent.com/stefanprodan/flagger/master/docs/diagrams/flagger-load-testing.png)
+![Flagger Load Testing Webhook](https://raw.githubusercontent.com/weaveworks/flagger/master/docs/diagrams/flagger-load-testing.png)
 
 First you need to deploy the load test runner in a namespace with Istio sidecar injection enabled:
 
 ```bash
-export REPO=https://raw.githubusercontent.com/stefanprodan/flagger/master
+export REPO=https://raw.githubusercontent.com/weaveworks/flagger/master
 
 kubectl -n test apply -f ${REPO}/artifacts/loadtester/deployment.yaml
 kubectl -n test apply -f ${REPO}/artifacts/loadtester/service.yaml
@@ -315,8 +663,7 @@ Or by using Helm:
 helm repo add flagger https://flagger.app
 
 helm upgrade -i flagger-loadtester flagger/loadtester \
---namepace=test \
---set cmd.logOutput=true \
+--namespace=test \
 --set cmd.timeout=1h
 ```
 
@@ -330,11 +677,13 @@ webhooks:
     url: http://flagger-loadtester.test/
     timeout: 5s
     metadata:
+      type: cmd
       cmd: "hey -z 1m -q 10 -c 2 http://podinfo.test:9898/"
   - name: load-test-post
     url: http://flagger-loadtester.test/
     timeout: 5s
     metadata:
+      type: cmd
       cmd: "hey -z 1m -q 10 -c 2 -m POST -d '{test: 2}' http://podinfo.test:9898/echo"
 ```
 
@@ -351,6 +700,7 @@ webhooks:
     url: http://flagger-loadtester.test/
     timeout: 5s
     metadata:
+      type: cmd
       cmd: "hey -z 1m -q 10 -c 2 -h2 https://podinfo.example.com/"
 ```
 
@@ -363,3 +713,32 @@ FROM quay.io/stefanprodan/flagger-loadtester:<VER>
 RUN curl -Lo /usr/local/bin/my-cli https://github.com/user/repo/releases/download/ver/my-cli \
     && chmod +x /usr/local/bin/my-cli
 ```
+
+### Load Testing Delegation
+
+The load tester can also forward testing tasks to external tools, by now [nGrinder](https://github.com/naver/ngrinder)
+is supported.
+
+To use this feature, add a load test task of type 'ngrinder' to the canary analysis spec:
+
+```yaml
+webhooks:
+  - name: load-test-post
+    url: http://flagger-loadtester.test/
+    timeout: 5s
+    metadata:
+      # type of this load test task, cmd or ngrinder
+      type: ngrinder
+      # base url of your nGrinder controller server
+      server: http://ngrinder-server:port
+      # id of the test to clone from, the test must have been defined.
+      clone: 100
+      # user name and base64 encoded password to authenticate against the nGrinder server
+      username: admin
+      passwd: YWRtaW4=
+      # the interval between between nGrinder test status polling, default to 1s
+      pollInterval: 5s
+```
+When the canary analysis starts, the load tester will initiate a [clone_and_start request](https://github.com/naver/ngrinder/wiki/REST-API-PerfTest)
+to the nGrinder server and start a new performance test. the load tester will periodically poll the nGrinder server
+for the status of the test, and prevent duplicate requests from being sent in subsequent analysis loops.

docs/gitbook/install/flagger-install-on-eks-appmesh.md

@@ -0,0 +1,188 @@
+# Flagger install on AWS
+
+This guide walks you through setting up Flagger and AWS App Mesh on EKS.
+
+### App Mesh
+
+The App Mesh integration with EKS is made out of the following components:
+
+* Kubernetes custom resources
+    * `mesh.appmesh.k8s.aws` defines a logical boundary for network traffic between the services 
+    * `virtualnode.appmesh.k8s.aws` defines a logical pointer to a Kubernetes workload
+    * `virtualservice.appmesh.k8s.aws` defines the routing rules for a workload inside the mesh
+* CRD controller - keeps the custom resources in sync with the App Mesh control plane
+* Admission controller - injects the Envoy sidecar and assigns Kubernetes pods to App Mesh virtual nodes
+* Metrics server - Prometheus instance that collects and stores Envoy's metrics
+
+Prerequisites:
+
+* jq
+* homebrew
+* openssl
+* kubectl
+* AWS CLI (default region us-west-2)
+
+### Create a Kubernetes cluster
+
+In order to create an EKS cluster you can use [eksctl](https://eksctl.io).
+Eksctl is an open source command-line utility made by Weaveworks in collaboration with Amazon, 
+it’s a Kubernetes-native tool written in Go.
+
+On MacOS you can install eksctl with Homebrew:
+
+```bash
+brew tap weaveworks/tap
+brew install weaveworks/tap/eksctl
+```
+
+Create an EKS cluster:
+
+```bash
+eksctl create cluster --name=appmesh \
+--region=us-west-2 \
+--appmesh-access
+```
+
+The above command will create a two nodes cluster with App Mesh
+[IAM policy](https://docs.aws.amazon.com/app-mesh/latest/userguide/MESH_IAM_user_policies.html)
+attached to the EKS node instance role.
+
+Verify the install with:
+
+```bash
+kubectl get nodes
+```
+
+### Install Helm
+
+Install the [Helm](https://docs.helm.sh/using_helm/#installing-helm) command-line tool:
+
+```text
+brew install kubernetes-helm
+```
+
+Create a service account and a cluster role binding for Tiller:
+
+```bash
+kubectl -n kube-system create sa tiller
+
+kubectl create clusterrolebinding tiller-cluster-rule \
+--clusterrole=cluster-admin \
+--serviceaccount=kube-system:tiller 
+```
+
+Deploy Tiller in the `kube-system` namespace:
+
+```bash
+helm init --service-account tiller
+```
+
+You should consider using SSL between Helm and Tiller, for more information on securing your Helm 
+installation see [docs.helm.sh](https://docs.helm.sh/using_helm/#securing-your-helm-installation).
+
+### Enable horizontal pod auto-scaling
+
+Install the Horizontal Pod Autoscaler (HPA) metrics provider:
+
+```bash
+helm upgrade -i metrics-server stable/metrics-server \
+--namespace kube-system
+```
+
+After a minute, the metrics API should report CPU and memory usage for pods.
+You can very the metrics API with:
+
+```bash
+kubectl -n kube-system top pods
+```
+
+### Install the App Mesh components
+
+Run the App Mesh installer:
+
+```bash
+curl -fsSL https://git.io/get-app-mesh-eks.sh | bash -
+```
+
+The installer does the following:
+
+* creates the `appmesh-system` namespace
+* generates a certificate signed by Kubernetes CA
+* registers the App Mesh mutating webhook
+* deploys the App Mesh webhook in `appmesh-system` namespace
+* deploys the App Mesh CRDs
+* deploys the App Mesh controller in `appmesh-system` namespace
+* creates a mesh called `global`
+
+Verify that the global mesh is active:
+
+```bash
+kubectl describe mesh
+
+Status:
+  Mesh Condition:
+    Status:                True
+    Type:                  MeshActive
+```
+
+### Install Prometheus
+
+In order to collect the App Mesh metrics that Flagger needs to run the canary analysis, 
+you'll need to setup a Prometheus instance to scrape the Envoy sidecars.
+
+Deploy Prometheus in the `appmesh-system` namespace:
+
+```bash
+REPO=https://raw.githubusercontent.com/weaveworks/flagger/master
+
+kubectl apply -f ${REPO}/artifacts/eks/appmesh-prometheus.yaml
+```
+
+### Install Flagger and Grafana
+
+Add Flagger Helm repository:
+
+```bash
+helm repo add flagger https://flagger.app
+```
+
+Deploy Flagger in the _**appmesh-system**_ namespace:
+
+```bash
+helm upgrade -i flagger flagger/flagger \
+--namespace=appmesh-system \
+--set meshProvider=appmesh \
+--set metricsServer=http://prometheus.appmesh-system:9090
+```
+
+You can install Flagger in any namespace as long as it can talk to the Istio Prometheus service on port 9090.
+
+You can enable **Slack** notifications with:
+
+```bash
+helm upgrade -i flagger flagger/flagger \
+--namespace=appmesh-system \
+--set meshProvider=appmesh \
+--set metricsServer=http://prometheus.appmesh:9090 \
+--set slack.url=https://hooks.slack.com/services/YOUR/SLACK/WEBHOOK \
+--set slack.channel=general \
+--set slack.user=flagger
+```
+
+Flagger comes with a Grafana dashboard made for monitoring the canary analysis.
+Deploy Grafana in the _**appmesh-system**_ namespace:
+
+```bash
+helm upgrade -i flagger-grafana flagger/grafana \
+--namespace=appmesh-system \
+--set url=http://prometheus.appmesh-system:9090
+```
+
+You can access Grafana using port forwarding:
+
+```bash
+kubectl -n appmesh-system port-forward svc/flagger-grafana 3000:80
+```
+
+Now that you have Flagger running you can try the
+[App Mesh canary deployments tutorial](https://docs.flagger.app/usage/appmesh-progressive-delivery).

docs/gitbook/install/flagger-install-on-google-cloud.md

@@ -1,16 +1,15 @@
-# Install Istio
+# Flagger install on Google Cloud
 
-This guide walks you through setting up Istio with Jaeger, Prometheus, Grafana and 
-Let’s Encrypt TLS for ingress gateway on Google Kubernetes Engine.
+This guide walks you through setting up Flagger and Istio on Google Kubernetes Engine.
 
-![Istio GKE diagram](https://raw.githubusercontent.com/stefanprodan/istio-gke/master/docs/screens/istio-gcp-overview.png)
+![GKE Cluster Overview](https://raw.githubusercontent.com/weaveworks/flagger/master/docs/diagrams/flagger-gke-istio.png)
 
 ### Prerequisites
 
 You will be creating a cluster on Google’s Kubernetes Engine \(GKE\), 
 if you don’t have an account you can sign up [here](https://cloud.google.com/free/) for free credits.
 
-Login into GCP, create a project and enable billing for it.
+Login into Google Cloud, create a project and enable billing for it.
 
 Install the [gcloud](https://cloud.google.com/sdk/) command line utility and configure your project with `gcloud init`.
 
@@ -23,8 +22,8 @@ gcloud config set project PROJECT_ID
 Set the default compute region and zone:
 
 ```text
-gcloud config set compute/region europe-west3
-gcloud config set compute/zone europe-west3-a
+gcloud config set compute/region us-central1
+gcloud config set compute/zone us-central1-a
 ```
 
 Enable the Kubernetes and Cloud DNS services for your project:
@@ -34,46 +33,42 @@ gcloud services enable container.googleapis.com
 gcloud services enable dns.googleapis.com
 ```
 
-Install the `kubectl` command-line tool:
+Install the kubectl command-line tool:
 
 ```text
 gcloud components install kubectl
 ```
 
-Install the `helm` command-line tool:
-
-```text
-brew install kubernetes-helm
-```
-
 ### GKE cluster setup
 
-Create a cluster with three nodes using the latest Kubernetes version:
+Create a cluster with the Istio add-on:
 
 ```bash
-k8s_version=$(gcloud container get-server-config --format=json \
-| jq -r '.validNodeVersions[0]')
+K8S_VERSION=$(gcloud container get-server-config --format=json \
+| jq -r '.validMasterVersions[0]')
 
-gcloud container clusters create istio \
---cluster-version=${k8s_version} \
---zone=europe-west3-a \
---num-nodes=3 \
+gcloud beta container clusters create istio \
+--cluster-version=${K8S_VERSION} \
+--zone=us-central1-a \
+--num-nodes=2 \
 --machine-type=n1-highcpu-4 \
 --preemptible \
 --no-enable-cloud-logging \
+--no-enable-cloud-monitoring \
 --disk-size=30 \
 --enable-autorepair \
---scopes=gke-default,compute-rw,storage-rw
+--addons=HorizontalPodAutoscaling,Istio \
+--istio-config=auth=MTLS_PERMISSIVE
 ```
 
-The above command will create a default node pool consisting of `n1-highcpu-4` \(vCPU: 4, RAM 3.60GB, DISK: 30GB\) 
+The above command will create a default node pool consisting of two `n1-highcpu-4` \(vCPU: 4, RAM 3.60GB, DISK: 30GB\) 
 preemptible VMs. Preemptible VMs are up to 80% cheaper than regular instances and are terminated and replaced 
 after a maximum of 24 hours.
 
 Set up credentials for `kubectl`:
 
 ```bash
-gcloud container clusters get-credentials istio -z=europe-west3-a
+gcloud container clusters get-credentials istio
 ```
 
 Create a cluster admin role binding:
@@ -87,9 +82,11 @@ kubectl create clusterrolebinding "cluster-admin-$(whoami)" \
 Validate your setup with:
 
 ```bash
-kubectl get nodes -o wide
+kubectl -n istio-system get svc
 ```
 
+In a couple of seconds GCP should allocate an external IP to the `istio-ingressgateway` service. 
+
 ### Cloud DNS setup
 
 You will need an internet domain and access to the registrar to change the name servers to Google Cloud DNS.
@@ -116,34 +113,30 @@ Wait for the name servers to change \(replace `example.com` with your domain\):
 watch dig +short NS example.com
 ```
 
-Create a static IP address named `istio-gateway-ip` in the same region as your GKE cluster:
+Create a static IP address named `istio-gateway` using the Istio ingress IP:
 
 ```bash
-gcloud compute addresses create istio-gateway-ip --region europe-west3
+export GATEWAY_IP=$(kubectl -n istio-system get svc/istio-ingressgateway -ojson \
+| jq -r .status.loadBalancer.ingress[0].ip)
+
+gcloud compute addresses create istio-gateway --addresses ${GATEWAY_IP} --region us-central1
 ```
 
-Find the static IP address:
-
-```bash
-gcloud compute addresses describe istio-gateway-ip --region europe-west3
-```
-
-Create the following DNS records \(replace `example.com` with your domain and set your Istio Gateway IP\):
+Create the following DNS records \(replace `example.com` with your domain\):
 
 ```bash
 DOMAIN="example.com"
-GATEWAYIP="35.198.98.90"
 
 gcloud dns record-sets transaction start --zone=istio
 
 gcloud dns record-sets transaction add --zone=istio \
---name="${DOMAIN}" --ttl=300 --type=A ${GATEWAYIP}
+--name="${DOMAIN}" --ttl=300 --type=A ${GATEWAY_IP}
 
 gcloud dns record-sets transaction add --zone=istio \
---name="www.${DOMAIN}" --ttl=300 --type=A ${GATEWAYIP}
+--name="www.${DOMAIN}" --ttl=300 --type=A ${GATEWAY_IP}
 
 gcloud dns record-sets transaction add --zone=istio \
---name="*.${DOMAIN}" --ttl=300 --type=A ${GATEWAYIP}
+--name="*.${DOMAIN}" --ttl=300 --type=A ${GATEWAY_IP}
 
 gcloud dns record-sets transaction execute --zone istio
 ```
@@ -154,31 +147,22 @@ Verify that the wildcard DNS is working \(replace `example.com` with your domain
 watch host test.example.com
 ```
 
-### Install Istio with Helm
+### Install Helm
 
-Download the latest Istio release:
+Install the [Helm](https://docs.helm.sh/using_helm/#installing-helm) command-line tool:
 
-```bash
-curl -L https://git.io/getLatestIstio | sh -
-```
-
-Navigate to `istio-x.x.x` dir and copy the Istio CLI in your bin:
-
-```bash
-cd istio-x.x.x/
-sudo cp ./bin/istioctl /usr/local/bin/istioctl
-```
-
-Apply the Istio CRDs:
-
-```bash
-kubectl apply -f ./install/kubernetes/helm/istio/templates/crds.yaml
+```text
+brew install kubernetes-helm
 ```
 
 Create a service account and a cluster role binding for Tiller:
 
 ```bash
-kubectl apply -f ./install/kubernetes/helm/helm-service-account.yaml
+kubectl -n kube-system create sa tiller
+
+kubectl create clusterrolebinding tiller-cluster-rule \
+--clusterrole=cluster-admin \
+--serviceaccount=kube-system:tiller 
 ```
 
 Deploy Tiller in the `kube-system` namespace:
@@ -187,125 +171,53 @@ Deploy Tiller in the `kube-system` namespace:
 helm init --service-account tiller
 ```
 
-Find the GKE IP ranges:
+You should consider using SSL between Helm and Tiller, for more information on securing your Helm 
+installation see [docs.helm.sh](https://docs.helm.sh/using_helm/#securing-your-helm-installation).
+
+### Install cert-manager
+
+Jetstack's [cert-manager](https://github.com/jetstack/cert-manager) 
+is a Kubernetes operator that automatically creates and manages TLS certs issued by Let’s Encrypt.
+
+You'll be using cert-manager to provision a wildcard certificate for the Istio ingress gateway. 
+
+Install cert-manager's CRDs:
 
 ```bash
-gcloud container clusters describe istio --zone=europe-west3-a \
-| grep -e clusterIpv4Cidr -e servicesIpv4Cidr
+CERT_REPO=https://raw.githubusercontent.com/jetstack/cert-manager
+
+kubectl apply -f ${CERT_REPO}/release-0.7/deploy/manifests/00-crds.yaml
 ```
 
-You'll be using the IP ranges to allow unrestricted egress traffic for services running inside the service mesh.
-
-Configure Istio with Prometheus, Jaeger, and cert-manager:
-
-```yaml
-global:
-  nodePort: false
-  proxy:
-    # replace with your GKE IP ranges
-    includeIPRanges: "10.28.0.0/14,10.7.240.0/20"
-
-sidecarInjectorWebhook:
-  enabled: true
-  enableNamespacesByDefault: false
-
-gateways:
-  enabled: true
-  istio-ingressgateway:
-    replicaCount: 2
-    autoscaleMin: 2
-    autoscaleMax: 3
-    # replace with your Istio Gateway IP
-    loadBalancerIP: "35.198.98.90"
-    type: LoadBalancer
-
-pilot:
-  enabled: true
-  replicaCount: 1
-  autoscaleMin: 1
-  autoscaleMax: 1
-  resources:
-    requests:
-      cpu: 500m
-      memory: 1024Mi
-
-grafana:
-  enabled: true
-  security:
-    enabled: true
-    adminUser: admin
-    # change the password
-    adminPassword: admin
-
-prometheus:
-  enabled: true
-
-servicegraph:
-  enabled: true
-
-tracing:
-  enabled: true
-  jaeger:
-    tag: 1.7
-
-certmanager:
-  enabled: true
-```
-
-Save the above file as `my-istio.yaml` and install Istio with Helm:
+Create the cert-manager namespace and disable resource validation:
 
 ```bash
-helm upgrade --install istio ./install/kubernetes/helm/istio \
---namespace=istio-system \
--f ./my-istio.yaml
+kubectl create namespace cert-manager
+
+kubectl label namespace cert-manager certmanager.k8s.io/disable-validation=true
 ```
 
-Verify that Istio workloads are running:
+Install cert-manager with Helm:
 
-```text
-kubectl -n istio-system get pods
+```bash
+helm repo add jetstack https://charts.jetstack.io && \
+helm repo update && \
+helm upgrade -i cert-manager \
+--namespace cert-manager \
+--version v0.7.0 \
+jetstack/cert-manager
 ```
 
-### Configure Istio Gateway with LE TLS
+### Istio Gateway TLS setup
 
-![Istio Let's Encrypt diagram](https://raw.githubusercontent.com/stefanprodan/istio-gke/master/docs/screens/istio-cert-manager-gcp.png)
+![Istio Let's Encrypt](https://raw.githubusercontent.com/weaveworks/flagger/master/docs/diagrams/istio-cert-manager-gke.png)
 
-Create a Istio Gateway in istio-system namespace with HTTPS redirect:
+Create a generic Istio Gateway to expose services outside the mesh on HTTPS:
 
-```yaml
-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
-```
+```bash
+REPO=https://raw.githubusercontent.com/weaveworks/flagger/master
 
-Save the above resource as istio-gateway.yaml and then apply it:
-
-```text
-kubectl apply -f ./istio-gateway.yaml
+kubectl apply -f ${REPO}/artifacts/gke/istio-gateway.yaml
 ```
 
 Create a service account with Cloud DNS admin role \(replace `my-gcp-project` with your project ID\):
@@ -374,7 +286,7 @@ metadata:
   name: istio-gateway
   namespace: istio-system
 spec:
-  secretname: istio-ingressgateway-certs
+  secretName: istio-ingressgateway-certs
   issuerRef:
     name: letsencrypt-prod
   commonName: "*.example.com"
@@ -387,37 +299,76 @@ spec:
       - "example.com"
 ```
 
-Save the above resource as of-cert.yaml and then apply it:
+Save the above resource as istio-gateway-cert.yaml and then apply it:
 
 ```text
-kubectl apply -f ./of-cert.yaml
+kubectl apply -f ./istio-gateway-cert.yaml
 ```
 
 In a couple of seconds cert-manager should fetch a wildcard certificate from letsencrypt.org:
 
 ```text
-kubectl -n istio-system logs deployment/certmanager -f
+kubectl -n istio-system describe certificate istio-gateway
 
-Certificate issued successfully
-Certificate istio-system/istio-gateway scheduled for renewal in 1438 hours
+Events:
+  Type    Reason         Age    From          Message
+  ----    ------         ----   ----          -------
+  Normal  CertIssued     1m52s  cert-manager  Certificate issued successfully
 ```
 
 Recreate Istio ingress gateway pods:
 
 ```bash
-kubectl -n istio-system delete pods -l istio=ingressgateway
+kubectl -n istio-system get pods -l istio=ingressgateway
 ```
 
 Note that Istio gateway doesn't reload the certificates from the TLS secret on cert-manager renewal. 
 Since the GKE cluster is made out of preemptible VMs the gateway pods will be replaced once every 24h, 
-if your not using preemptible nodes then you need to manually kill the gateway pods every two months 
+if your not using preemptible nodes then you need to manually delete the gateway pods every two months 
 before the certificate expires.
 
-### Expose services outside the service mesh
+### Install Prometheus
 
-In order to expose services via the Istio Gateway you have to create a Virtual Service attached to Istio Gateway.
+The GKE Istio add-on does not include a Prometheus instance that scrapes the Istio telemetry service. 
+Because Flagger uses the Istio HTTP metrics to run the canary analysis you have to deploy the following 
+Prometheus configuration that's similar to the one that comes with the official Istio Helm chart.
 
-Create a virtual service in `istio-system` namespace for Grafana \(replace `example.com` with your domain\):
+```bash
+REPO=https://raw.githubusercontent.com/weaveworks/flagger/master
+
+kubectl apply -f ${REPO}/artifacts/gke/istio-prometheus.yaml
+```
+
+### Install Flagger and Grafana
+
+Add Flagger Helm repository:
+
+```bash
+helm repo add flagger https://flagger.app
+```
+
+Deploy Flagger in the `istio-system` namespace with Slack notifications enabled:
+
+```bash
+helm upgrade -i flagger flagger/flagger \
+--namespace=istio-system \
+--set metricsServer=http://prometheus.istio-system:9090 \
+--set slack.url=https://hooks.slack.com/services/YOUR/SLACK/WEBHOOK \
+--set slack.channel=general \
+--set slack.user=flagger
+```
+
+Deploy Grafana in the `istio-system` namespace:
+
+```bash
+helm upgrade -i flagger-grafana flagger/grafana \
+--namespace=istio-system \
+--set url=http://prometheus.istio-system:9090 \
+--set user=admin \
+--set password=replace-me
+```
+
+Expose Grafana through the public gateway by creating a virtual service \(replace `example.com` with your domain\):
 
 ```yaml
 apiVersion: networking.istio.io/v1alpha3
@@ -433,8 +384,7 @@ spec:
   http:
   - route:
     - destination:
-        host: grafana
-    timeout: 30s
+        host: flagger-grafana
 ```
 
 Save the above resource as grafana-virtual-service.yaml and then apply it:
@@ -444,17 +394,3 @@ kubectl apply -f ./grafana-virtual-service.yaml
 ```
 
 Navigate to `http://grafana.example.com` in your browser and you should be redirected to the HTTPS version.
-
-Check that HTTP2 is enabled:
-
-```bash
-curl -I --http2 https://grafana.example.com
-
-HTTP/2 200 
-content-type: text/html; charset=UTF-8
-x-envoy-upstream-service-time: 3
-server: envoy
-```
-
-
-

docs/gitbook/install/flagger-install-on-kubernetes.md

@@ -0,0 +1,145 @@
+# Flagger install on Kubernetes
+
+This guide walks you through setting up Flagger on a Kubernetes cluster.
+
+### Prerequisites
+
+Flagger requires a Kubernetes cluster **v1.11** or newer with the following admission controllers enabled:
+
+* MutatingAdmissionWebhook
+* ValidatingAdmissionWebhook 
+
+Flagger depends on [Istio](https://istio.io/docs/setup/kubernetes/quick-start/) **v1.0.3** or newer 
+with traffic management, telemetry and Prometheus enabled. 
+
+A minimal Istio installation should contain the following services:
+
+* istio-pilot
+* istio-ingressgateway
+* istio-sidecar-injector
+* istio-telemetry
+* prometheus
+
+### Install Flagger
+
+Add Flagger Helm repository:
+
+```bash
+helm repo add flagger https://flagger.app
+```
+
+Deploy Flagger in the _**istio-system**_ namespace:
+
+```bash
+helm upgrade -i flagger flagger/flagger \
+--namespace=istio-system \
+--set metricsServer=http://prometheus.istio-system:9090
+```
+
+You can install Flagger in any namespace as long as it can talk to the Istio Prometheus service on port 9090.
+
+Enable **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
+```
+
+If you don't have Tiller you can use the helm template command and apply the generated yaml with kubectl:
+
+```bash
+# generate
+helm fetch --untar --untardir . flagger/flagger &&
+helm template flagger \
+--name flagger \
+--namespace=istio-system \
+--set metricsServer=http://prometheus.istio-system:9090 \
+> $HOME/flagger.yaml
+
+# apply
+kubectl apply -f $HOME/flagger.yaml
+```
+
+To uninstall the Flagger release with Helm run:
+
+```text
+helm delete --purge flagger
+```
+
+The command removes all the Kubernetes components associated with the chart and deletes the release.
+
+> **Note** that on uninstall the Canary CRD will not be removed. 
+Deleting the CRD will make Kubernetes remove all the objects owned by Flagger like Istio virtual services, 
+Kubernetes deployments and ClusterIP services.
+
+If you want to remove all the objects created by Flagger you have delete the Canary CRD with kubectl:
+
+```text
+kubectl delete crd canaries.flagger.app
+```
+
+### Install Grafana
+
+Flagger comes with a Grafana dashboard made for monitoring the canary analysis.
+
+Deploy Grafana in the _**istio-system**_ namespace:
+
+```bash
+helm upgrade -i flagger-grafana flagger/grafana \
+--namespace=istio-system \
+--set url=http://prometheus.istio-system:9090 \
+--set user=admin \
+--set password=change-me
+```
+
+Or use helm template command and apply the generated yaml with kubectl:
+
+```bash
+# generate
+helm fetch --untar --untardir . flagger/grafana &&
+helm template grafana \
+--name flagger-grafana \
+--namespace=istio-system \
+> $HOME/flagger-grafana.yaml
+
+# apply
+kubectl apply -f $HOME/flagger-grafana.yaml
+```
+
+You can access Grafana using port forwarding:
+
+```bash
+kubectl -n istio-system port-forward svc/flagger-grafana 3000:80
+```
+
+###  Install Load Tester
+
+Flagger comes with an optional load testing service that generates traffic 
+during canary analysis when configured as a webhook.
+
+Deploy the load test runner with Helm:
+
+```bash
+helm upgrade -i flagger-loadtester flagger/loadtester \
+--namespace=test \
+--set cmd.timeout=1h
+```
+
+Deploy with kubectl:
+
+```bash
+helm fetch --untar --untardir . flagger/loadtester &&
+helm template loadtester \
+--name flagger-loadtester \
+--namespace=test
+> $HOME/flagger-loadtester.yaml
+
+# apply
+kubectl apply -f $HOME/flagger-loadtester.yaml
+```
+
+> **Note** that the load tester should be deployed in a namespace with Istio sidecar injection enabled.
+

docs/gitbook/install/flagger-install-with-supergloo.md

@@ -0,0 +1,135 @@
+# Flagger install on Kubernetes with SuperGloo
+
+This guide walks you through setting up Flagger on a Kubernetes cluster using [SuperGloo](https://github.com/solo-io/supergloo).
+
+SuperGloo by [Solo.io](https://solo.io) is an opinionated abstraction layer that will simplify the installation, management, and operation of your service mesh. 
+It supports running multiple ingress with multiple mesh (Istio, App Mesh, Consul Connect and Linkerd 2) in the same cluster. 
+
+### Prerequisites
+
+Flagger requires a Kubernetes cluster **v1.11** or newer with the following admission controllers enabled:
+
+* MutatingAdmissionWebhook
+* ValidatingAdmissionWebhook 
+
+### Install Istio with SuperGloo
+
+Download SuperGloo CLI and add it to your path:
+
+```bash
+curl -sL https://run.solo.io/supergloo/install | sh
+export PATH=$HOME/.supergloo/bin:$PATH
+```
+
+Deploy the SuperGloo controller in the `supergloo-system` namespace:
+
+```bash
+supergloo init
+```
+
+Create the `istio-system` namespace and install Istio with traffic management, telemetry and Prometheus enabled:
+
+```bash
+ISTIO_VER="1.0.6"
+
+kubectl create ns istio-system
+
+supergloo install istio --name istio \
+--namespace=supergloo-system \
+--auto-inject=true \
+--installation-namespace=istio-system \
+--mtls=false \
+--prometheus=true \
+--version ${ISTIO_VER}
+```
+
+Create a cluster role binding so that Flagger can manipulate SuperGloo custom resources:
+
+```bash
+kubectl create clusterrolebinding flagger-supergloo \
+--clusterrole=mesh-discovery \
+--serviceaccount=istio-system:flagger
+```
+
+Wait for the Istio control plane to become available:
+
+```bash
+kubectl -n istio-system rollout status deployment/istio-sidecar-injector
+kubectl -n istio-system rollout status deployment/prometheus
+```
+
+### Install Flagger
+
+Add Flagger Helm repository:
+
+```bash
+helm repo add flagger https://flagger.app
+```
+
+Deploy Flagger in the _**istio-system**_ namespace and set the service mesh provider to SuperGloo:
+
+```bash
+helm upgrade -i flagger flagger/flagger \
+--namespace=istio-system \
+--set metricsServer=http://prometheus.istio-system:9090 \
+--set meshProvider=supergloo:istio.supergloo-system
+```
+
+When using SuperGloo the mesh provider format is `supergloo:<MESH-NAME>.<SUPERGLOO-NAMESPACE>`.
+
+Optionally you can enable **Slack** notifications:
+
+```bash
+helm upgrade -i flagger flagger/flagger \
+--reuse-values \
+--namespace=istio-system \
+--set slack.url=https://hooks.slack.com/services/YOUR/SLACK/WEBHOOK \
+--set slack.channel=general \
+--set slack.user=flagger
+```
+
+### Install Grafana
+
+Flagger comes with a Grafana dashboard made for monitoring the canary analysis.
+
+Deploy Grafana in the _**istio-system**_ namespace:
+
+```bash
+helm upgrade -i flagger-grafana flagger/grafana \
+--namespace=istio-system \
+--set url=http://prometheus.istio-system:9090
+```
+
+You can access Grafana using port forwarding:
+
+```bash
+kubectl -n istio-system port-forward svc/flagger-grafana 3000:80
+```
+
+###  Install Load Tester
+
+Flagger comes with an optional load testing service that generates traffic 
+during canary analysis when configured as a webhook.
+
+Deploy the load test runner with Helm:
+
+```bash
+helm upgrade -i flagger-loadtester flagger/loadtester \
+--namespace=test \
+--set cmd.timeout=1h
+```
+
+Deploy with kubectl:
+
+```bash
+helm fetch --untar --untardir . flagger/loadtester &&
+helm template loadtester \
+--name flagger-loadtester \
+--namespace=test
+> $HOME/flagger-loadtester.yaml
+
+# apply
+kubectl apply -f $HOME/flagger-loadtester.yaml
+```
+
+> **Note** that the load tester should be deployed in a namespace with Istio sidecar injection enabled.

docs/gitbook/install/install-flagger.md

@@ -1,75 +0,0 @@
-# Install Flagger
-
-Before installing Flagger make sure you have [Istio](https://istio.io) running with Prometheus enabled. 
-If you are new to Istio you can follow this GKE guide 
-[Istio service mesh walk-through](https://docs.flagger.app/install/install-istio).
-
-**Prerequisites**
-
-* Kubernetes >= 1.11
-* Istio >= 1.0
-* Prometheus >= 2.6
-
-### Install with Helm and Tiller
-
-Add Flagger Helm repository:
-
-```bash
-helm repo add flagger https://flagger.app
-```
-
-Deploy Flagger in the _**istio-system**_ namespace:
-
-```bash
-helm upgrade -i flagger flagger/flagger \
---namespace=istio-system \
---set metricsServer=http://prometheus.istio-system:9090
-```
-
-Enable **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
-```
-
-### Install with kubectl
-
-If you don't have Tiller you can use the helm template command and apply the generated yaml with kubectl:
-
-```bash
-# generate
-helm template flagger/flagger \
---name flagger \
---namespace=istio-system \
---set metricsServer=http://prometheus.istio-system:9090 \
---set controlLoopInterval=1m > $HOME/flagger.yaml
-
-# apply
-kubectl apply -f $HOME/flagger.yaml
-```
-
-###  Uninstall
-
-To uninstall/delete the flagger release with Helm run:
-
-```text
-helm delete --purge flagger
-```
-
-The command removes all the Kubernetes components associated with the chart and deletes the release.
-
-> **Note** that on uninstall the Canary CRD will not be removed. 
-Deleting the CRD will make Kubernetes remove all the objects owned by Flagger like Istio virtual services, 
-Kubernetes deployments and ClusterIP services.
-
-
-If you want to remove all the objects created by Flagger you have delete the Canary CRD with kubectl:
-
-```text
-kubectl delete crd canaries.flagger.app
-```
-

docs/gitbook/install/install-grafana.md

@@ -1,48 +0,0 @@
-# Install Grafana
-
-Flagger comes with a Grafana dashboard made for monitoring the canary analysis.
-
-### Install with Helm and Tiller
-
-Add Flagger Helm repository:
-
-```bash
-helm repo add flagger https://flagger.app
-```
-
-Deploy Grafana in the _**istio-system**_ namespace:
-
-```bash
-helm upgrade -i flagger-grafana flagger/grafana \
---namespace=istio-system \
---set url=http://prometheus:9090 \
---set user=admin \
---set password=admin
-```
-
-### Install with kubectl
-
-If you don't have Tiller you can use the helm template command and apply the generated yaml with kubectl:
-
-```bash
-# generate
-helm template flagger/grafana \
---name flagger-grafana \
---namespace=istio-system \
---set user=admin \
---set password=admin > $HOME/flagger-grafana.yaml
-
-# apply
-kubectl apply -f $HOME/flagger-grafana.yaml
-```
-
-###  Uninstall
-
-To uninstall/delete the Grafana release with Helm run:
-
-```text
-helm delete --purge flagger-grafana
-```
-
-The command removes all the Kubernetes components associated with the chart and deletes the release.
-

docs/gitbook/tutorials/canary-helm-gitops.md

@@ -0,0 +1,353 @@
+# Canary Deployments with Helm Charts and GitOps
+
+This guide shows you how to package a web app into a Helm chart, trigger canary deployments on Helm upgrade
+and automate the chart release process with Weave Flux.
+
+### Packaging
+
+You'll be using the [podinfo](https://github.com/stefanprodan/k8s-podinfo) chart. 
+This chart packages a web app made with Go, it's configuration, a horizontal pod autoscaler (HPA) 
+and the canary configuration file.
+
+```
+├── Chart.yaml
+├── README.md
+├── templates
+│   ├── NOTES.txt
+│   ├── _helpers.tpl
+│   ├── canary.yaml
+│   ├── configmap.yaml
+│   ├── deployment.yaml
+│   └── hpa.yaml
+└── values.yaml
+```
+
+You can find the chart source [here](https://github.com/stefanprodan/flagger/tree/master/charts/podinfo).
+
+### Install 
+
+Create a test namespace with Istio sidecar injection enabled:
+
+```bash
+export REPO=https://raw.githubusercontent.com/weaveworks/flagger/master
+
+kubectl apply -f ${REPO}/artifacts/namespaces/test.yaml
+```
+
+Add Flagger Helm repository:
+
+```bash
+helm repo add flagger https://flagger.app
+```
+
+Install podinfo with the release name `frontend` (replace `example.com` with your own domain):
+
+```bash
+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
+```
+
+Flagger takes a Kubernetes deployment and a horizontal pod autoscaler (HPA), 
+then creates a series of objects (Kubernetes deployments, ClusterIP services and Istio virtual services). 
+These objects expose the application on the mesh and drive the canary analysis and promotion.
+
+```bash
+# generated by Helm 
+configmap/frontend
+deployment.apps/frontend
+horizontalpodautoscaler.autoscaling/frontend
+canary.flagger.app/frontend
+
+# generated by Flagger
+configmap/frontend-primary
+deployment.apps/frontend-primary
+horizontalpodautoscaler.autoscaling/frontend-primary
+service/frontend
+service/frontend-canary
+service/frontend-primary
+virtualservice.networking.istio.io/frontend
+```
+
+When the `frontend-primary` deployment comes online, 
+Flagger will route all traffic to the primary pods and scale to zero the `frontend` deployment.
+
+Open your browser and navigate to the frontend URL:
+
+![Podinfo Frontend](https://raw.githubusercontent.com/weaveworks/flagger/master/docs/screens/demo-frontend.png)
+
+Now let's install the `backend` release without exposing it outside the mesh:
+
+```bash
+helm upgrade -i backend flagger/podinfo \
+--namespace test \
+--set nameOverride=backend \
+--set canary.enabled=true \
+--set canary.istioIngress.enabled=false
+```
+
+Check if Flagger has successfully deployed the canaries: 
+
+```
+kubectl -n test get canaries
+
+NAME       STATUS        WEIGHT   LASTTRANSITIONTIME
+backend    Initialized   0        2019-02-12T18:53:18Z
+frontend   Initialized   0        2019-02-12T17:50:50Z
+```
+
+Click on the ping button in the `frontend` UI to trigger a HTTP POST request 
+that will reach the `backend` app:
+
+![Jaeger Tracing](https://raw.githubusercontent.com/weaveworks/flagger/master/docs/screens/demo-frontend-jaeger.png)
+
+We'll use the `/echo` endpoint (same as the one the ping button calls) 
+to generate load on both apps during a canary deployment.
+
+### Upgrade
+
+First let's install a load testing service that will generate traffic during analysis:
+
+```bash
+helm upgrade -i flagger-loadtester flagger/loadtester \
+--namespace=test
+```
+
+Enable the load tester and deploy a new `frontend` version:
+
+```bash
+helm upgrade -i frontend flagger/podinfo/ \
+--namespace test \
+--reuse-values \
+--set canary.loadtest.enabled=true \
+--set image.tag=1.4.1
+```
+
+Flagger detects that the deployment revision changed and starts the canary analysis along with the load test:
+
+```
+kubectl -n istio-system logs deployment/flagger -f | jq .msg
+
+New revision detected! Scaling up frontend.test
+Halt advancement frontend.test waiting for rollout to finish: 0 of 2 updated replicas are available
+Starting canary analysis for frontend.test
+Advance frontend.test canary weight 5
+Advance frontend.test canary weight 10
+Advance frontend.test canary weight 15
+Advance frontend.test canary weight 20
+Advance frontend.test canary weight 25
+Advance frontend.test canary weight 30
+Advance frontend.test canary weight 35
+Advance frontend.test canary weight 40
+Advance frontend.test canary weight 45
+Advance frontend.test canary weight 50
+Copying frontend.test template spec to frontend-primary.test
+Halt advancement frontend-primary.test waiting for rollout to finish: 1 old replicas are pending termination
+Promotion completed! Scaling down frontend.test
+```
+
+You can monitor the canary deployment with Grafana. Open the Flagger dashboard, 
+select `test` from the namespace dropdown, `frontend-primary` from the primary dropdown and `frontend` from the
+canary dropdown.
+
+![Flagger Grafana Dashboard](https://raw.githubusercontent.com/weaveworks/flagger/master/docs/screens/demo-frontend-dashboard.png)
+
+Now trigger a canary deployment for the `backend` app, but this time you'll change a value in the configmap:
+
+```bash
+helm upgrade -i backend flagger/podinfo/ \
+--namespace test \
+--reuse-values \
+--set canary.loadtest.enabled=true \
+--set httpServer.timeout=25s
+```
+
+Generate HTTP 500 errors:
+
+```bash
+kubectl -n test exec -it flagger-loadtester-xxx-yyy sh
+
+watch curl http://backend-canary:9898/status/500 
+```
+
+Generate latency:
+
+```bash
+kubectl -n test exec -it flagger-loadtester-xxx-yyy sh
+
+watch curl http://backend-canary:9898/delay/1 
+```
+
+Flagger detects the config map change and starts a canary analysis. Flagger will pause the advancement 
+when the HTTP success rate drops under 99% or when the average request duration in the last minute is over 500ms:
+
+```
+kubectl -n test describe canary backend
+
+Events:
+
+ConfigMap backend has changed
+New revision detected! Scaling up backend.test
+Starting canary analysis for backend.test
+Advance backend.test canary weight 5
+Advance backend.test canary weight 10
+Advance backend.test canary weight 15
+Advance backend.test canary weight 20
+Advance backend.test canary weight 25
+Advance backend.test canary weight 30
+Advance backend.test canary weight 35
+Halt backend.test advancement success rate 62.50% < 99%
+Halt backend.test advancement success rate 88.24% < 99%
+Advance backend.test canary weight 40
+Advance backend.test canary weight 45
+Halt backend.test advancement request duration 2.415s > 500ms
+Halt backend.test advancement request duration 2.42s > 500ms
+Advance backend.test canary weight 50
+ConfigMap backend-primary synced
+Copying backend.test template spec to backend-primary.test
+Promotion completed! Scaling down backend.test
+```
+
+![Flagger Grafana Dashboard](https://raw.githubusercontent.com/weaveworks/flagger/master/docs/screens/demo-backend-dashboard.png)
+
+If 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.
+
+```bash
+kubectl -n test get canary
+
+NAME       STATUS        WEIGHT   LASTTRANSITIONTIME
+backend    Succeeded     0        2019-02-12T19:33:11Z
+frontend   Failed        0        2019-02-12T19:47:20Z
+```
+
+If you've enabled the Slack notifications, you'll receive an alert with the reason why the `backend` promotion failed.
+
+### GitOps automation
+
+Instead of using Helm CLI from a CI tool to perform the install and upgrade, 
+you could use a Git based approach. GitOps is a way to do Continuous Delivery, 
+it works by using Git as a source of truth for declarative infrastructure and workloads.
+In the [GitOps model](https://www.weave.works/technologies/gitops/), 
+any change to production must be committed in source control
+prior to being applied on the cluster. This way rollback and audit logs are provided by Git.
+
+![Helm GitOps Canary Deployment](https://raw.githubusercontent.com/weaveworks/flagger/master/docs/diagrams/flagger-flux-gitops.png)
+
+In order to apply the GitOps pipeline model to Flagger canary deployments you'll need 
+a Git repository with your workloads definitions in YAML format, 
+a container registry where your CI system pushes immutable images and 
+an operator that synchronizes the Git repo with the cluster state.
+
+Create a git repository with the following content:
+
+```
+├── namespaces
+│   └── test.yaml
+└── releases
+    └── test
+        ├── backend.yaml
+        ├── frontend.yaml
+        └── loadtester.yaml
+``` 
+
+You can find the git source [here](https://github.com/stefanprodan/flagger/tree/master/artifacts/cluster).
+
+Define the `frontend` release using Flux `HelmRelease` custom resource:
+
+```yaml
+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://stefanprodan.github.io/flagger/
+    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
+```
+
+In the `chart` section I've defined the release source by specifying the Helm repository (hosted on GitHub Pages), chart name and version.
+In the `values` section I've overwritten the defaults set in values.yaml.
+
+With the `flux.weave.works` annotations I instruct Flux to automate this release. 
+When an image tag in the sem ver range of `1.4.0 - 1.4.99` is pushed to Quay, 
+Flux will upgrade the Helm release and from there Flagger will pick up the change and start a canary deployment.
+
+Install [Weave Flux](https://github.com/weaveworks/flux) and its Helm Operator by specifying your Git repo URL:
+
+```bash
+helm repo add weaveworks https://weaveworks.github.io/flux
+
+helm install --name flux \
+--set helmOperator.create=true \
+--set git.url=git@github.com:<USERNAME>/<REPOSITORY> \
+--namespace flux \
+weaveworks/flux
+```
+
+At startup Flux generates a SSH key and logs the public key. Find the SSH public key with:
+
+```bash
+kubectl -n flux logs deployment/flux | grep identity.pub | cut -d '"' -f2
+```
+
+In order to sync your cluster state with Git you need to copy the public key and create a 
+deploy key with write access on your GitHub repository.
+
+Open GitHub, navigate to your fork, go to _Setting > Deploy keys_ click on _Add deploy key_, 
+check _Allow write access_, paste the Flux public key and click _Add key_.
+
+After a couple of seconds Flux will apply the Kubernetes resources from Git and Flagger will
+launch the `frontend` and `backend` apps. 
+
+A CI/CD pipeline for the `frontend` release could look like this:
+
+* cut a release from the master branch of the podinfo code repo with the git tag `1.4.1`
+* CI builds the image and pushes the `podinfo:1.4.1` image to the container registry
+* Flux scans the registry and updates the Helm release `image.tag` to `1.4.1`
+* Flux commits and push the change to the cluster repo
+* Flux applies the updated Helm release on the cluster
+* Flux Helm Operator picks up the change and calls Tiller to upgrade the release
+* Flagger detects a revision change and scales up the `frontend` deployment
+* Flagger starts the load test and runs the canary analysis 
+* Based on the analysis result the canary deployment is promoted to production or rolled back
+* Flagger sends a Slack notification with the canary result
+
+If the canary fails, fix the bug, do another patch release eg `1.4.2` and the whole process will run again.
+
+A canary deployment can fail due to any of the following reasons:
+
+* the container image can't be downloaded 
+* the deployment replica set is stuck for more then ten minutes (eg. due to a container crash loop)
+* the webooks (acceptance tests, load tests, etc) are returning a non 2xx response
+* the HTTP success rate (non 5xx responses) metric drops under the threshold
+* the HTTP average duration metric goes over the threshold
+* the Istio telemetry service is unable to collect traffic metrics
+* the metrics server (Prometheus) can't be reached
+
+If you want to find out more about managing Helm releases with Flux here is an in-depth guide 
+[github.com/stefanprodan/gitops-helm](https://github.com/stefanprodan/gitops-helm).

docs/gitbook/tutorials/zero-downtime-deployments.md

@@ -0,0 +1,206 @@
+# Zero downtime deployments
+
+This is a list of things you should consider when dealing with a high traffic production environment if you want to
+minimise the impact of rolling updates and downscaling.
+
+### Deployment strategy
+
+Limit the number of unavailable pods during a rolling update:
+
+```yaml
+apiVersion: apps/v1
+kind: Deployment
+spec:
+  progressDeadlineSeconds: 120
+  strategy:
+    type: RollingUpdate
+    rollingUpdate:
+      maxUnavailable: 0
+```
+
+The default progress deadline for a deployment is ten minutes.
+You should consider adjusting this value to make the deployment process fail faster.
+
+### Liveness health check
+
+You application should expose a HTTP endpoint that Kubernetes can call to determine if 
+your app transitioned to a broken state from which it can't recover and needs to be restarted.
+
+```yaml
+readinessProbe:
+  exec:
+    command:
+    - wget
+    - --quiet
+    - --tries=1
+    - --timeout=4
+    - --spider
+    - http://localhost:8080/healthz
+  timeoutSeconds: 5
+  initialDelaySeconds: 5
+```
+
+If you've enabled mTLS, you'll have to use `exec` for liveness and readiness checks since 
+kubelet is not part of the service mesh and doesn't have access to the TLS cert.
+
+### Readiness health check
+
+You application should expose a HTTP endpoint that Kubernetes can call to determine if 
+your app is ready to receive traffic.
+
+```yaml
+livenessProbe:
+  exec:
+    command:
+    - wget
+    - --quiet
+    - --tries=1
+    - --timeout=4
+    - --spider
+    - http://localhost:8080/readyz
+  timeoutSeconds: 5
+  initialDelaySeconds: 5
+  periodSeconds: 5
+```
+
+If your app depends on external services, you should check if those services are available before allowing Kubernetes
+to route traffic to an app instance. Keep in mind that the Envoy sidecar can have a slower startup than your app.
+This means that on application start you should retry for at least a couple of seconds any external connection.
+
+### Graceful shutdown
+
+Before a pod gets terminated, Kubernetes sends a `SIGTERM` signal to every container and waits for period of 
+time (30s by default) for all containers to exit gracefully. If your app doesn't handle the `SIGTERM` signal or if it 
+doesn't exit within the grace period, Kubernetes will kill the container and any inflight requests that your app is 
+processing will fail.
+
+```yaml
+apiVersion: apps/v1
+kind: Deployment
+spec:
+  template:
+    spec:
+      terminationGracePeriodSeconds: 60
+      containers:
+      - name: app
+        lifecycle:
+          preStop:
+            exec:
+              command:
+              - sleep
+              - "10"
+```
+
+Your app container should have a `preStop` hook that delays the container shutdown.
+This will allow the service mesh to drain the traffic and remove this pod from all other Envoy sidecars before your app 
+becomes unavailable.
+
+### Delay Envoy shutdown
+
+Even if your app reacts to `SIGTERM` and tries to complete the inflight requests before shutdown, that 
+doesn't mean that the response will make it back to the caller. If the Envoy sidecar shuts down before your app, then 
+the caller will receive a 503 error.
+
+To mitigate this issue you can add a `preStop` hook to the Istio proxy and wait for the main app to exist before Envoy exists.
+
+```bash
+#!/bin/bash
+set -e
+if ! pidof envoy &>/dev/null; then
+  exit 0
+fi
+
+if ! pidof pilot-agent &>/dev/null; then
+  exit 0
+fi
+
+while [ $(netstat -plunt | grep tcp | grep -v envoy | wc -l | xargs) -ne 0 ]; do
+  sleep 1;
+done
+
+exit 0
+```
+
+You'll have to build your own Envoy docker image with the above script and
+modify the Istio injection webhook with the `preStop` directive. 
+
+Thanks to Stono for his excellent [tips](https://github.com/istio/istio/issues/12183) on minimising 503s. 
+
+### Resource requests and limits
+
+Setting CPU and memory requests/limits for all workloads is a mandatory step if you're running a production system.
+Without limits your nodes could run out of memory or become unresponsive due to CPU exhausting.
+Without CPU and memory requests,
+the Kubernetes scheduler will not be able to make decisions about which nodes to place pods on.
+
+```yaml
+apiVersion: apps/v1
+kind: Deployment
+spec:
+  template:
+    spec:
+      containers:
+      - name: app
+        resources:
+          limits:
+            cpu: 1000m
+            memory: 1Gi
+          requests:
+            cpu: 100m
+            memory: 128Mi
+```
+
+Note that without resource requests the horizontal pod autoscaler can't determine when to scale your app.
+
+### Autoscaling
+
+A production environment should be able to handle traffic bursts without impacting the quality of service.
+This can be achieved with Kubernetes autoscaling capabilities.
+Autoscaling in Kubernetes has two dimensions: the Cluster Autoscaler that deals with node scaling operations and
+the Horizontal Pod Autoscaler that automatically scales the number of pods in a deployment.
+
+```yaml
+apiVersion: autoscaling/v2beta1
+kind: HorizontalPodAutoscaler
+spec:
+  scaleTargetRef:
+    apiVersion: apps/v1
+    kind: Deployment
+    name: app
+  minReplicas: 2
+  maxReplicas: 4
+  metrics:
+  - type: Resource
+    resource:
+      name: cpu
+      targetAverageValue: 900m
+  - type: Resource
+    resource:
+      name: memory
+      targetAverageValue: 768Mi
+```
+
+The above HPA ensures your app will be scaled up before the pods reach the CPU or memory limits.
+
+### Ingress retries
+
+To minimise the impact of downscaling operations you can make use of Envoy retry capabilities.
+
+```yaml
+apiVersion: flagger.app/v1alpha3
+kind: Canary
+spec:
+  service:
+    port: 9898
+    gateways:
+    - public-gateway.istio-system.svc.cluster.local
+    hosts:
+    - app.example.com
+    appendHeaders:
+      x-envoy-upstream-rq-timeout-ms: "15000"
+      x-envoy-max-retries: "10"
+      x-envoy-retry-on: "gateway-error,connect-failure,refused-stream"
+```
+
+When the HPA scales down your app, your users could run into 503 errors.
+The above configuration will make Envoy retry the HTTP requests that failed due to gateway errors.

docs/gitbook/usage/ab-testing.md

@@ -0,0 +1,214 @@
+# Istio A/B Testing 
+
+This guide shows you how to automate A/B testing with Istio and Flagger.
+
+Besides weighted routing, Flagger can be configured to route traffic to the canary based on HTTP match conditions.
+In an A/B testing scenario, you'll be using HTTP headers or cookies to target a certain segment of your users.
+This is particularly useful for frontend applications that require session affinity.
+
+![Flagger A/B Testing Stages](https://raw.githubusercontent.com/weaveworks/flagger/master/docs/diagrams/flagger-abtest-steps.png)
+
+### Bootstrap
+
+Create a test namespace with Istio sidecar injection enabled:
+
+```bash
+export REPO=https://raw.githubusercontent.com/weaveworks/flagger/master
+
+kubectl apply -f ${REPO}/artifacts/namespaces/test.yaml
+```
+
+Create a deployment and a horizontal pod autoscaler:
+
+```bash
+kubectl apply -f ${REPO}/artifacts/ab-testing/deployment.yaml
+kubectl apply -f ${REPO}/artifacts/ab-testing/hpa.yaml
+```
+
+Deploy the load testing service to generate traffic during the canary analysis:
+
+```bash
+kubectl -n test apply -f ${REPO}/artifacts/loadtester/deployment.yaml
+kubectl -n test apply -f ${REPO}/artifacts/loadtester/service.yaml
+```
+
+Create a canary custom resource (replace example.com with your own domain):
+
+```yaml
+apiVersion: flagger.app/v1alpha3
+kind: Canary
+metadata:
+  name: abtest
+  namespace: test
+spec:
+  # deployment reference
+  targetRef:
+    apiVersion: apps/v1
+    kind: Deployment
+    name: abtest
+  # the maximum time in seconds for the canary deployment
+  # to make progress before it is rollback (default 600s)
+  progressDeadlineSeconds: 60
+  # HPA reference (optional)
+  autoscalerRef:
+    apiVersion: autoscaling/v2beta1
+    kind: HorizontalPodAutoscaler
+    name: abtest
+  service:
+    # container port
+    port: 9898
+    # Istio gateways (optional)
+    gateways:
+    - public-gateway.istio-system.svc.cluster.local
+    - mesh
+    # Istio virtual service host names (optional)
+    hosts:
+    - app.example.com
+  canaryAnalysis:
+    # schedule interval (default 60s)
+    interval: 1m
+    # total number of iterations
+    iterations: 10
+    # max number of failed iterations before rollback
+    threshold: 2
+    # canary match condition
+    match:
+      - headers:
+          user-agent:
+            regex: "^(?!.*Chrome).*Safari.*"
+      - headers:
+          cookie:
+            regex: "^(.*?;)?(type=insider)(;.*)?$"
+    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
+    # generate traffic during analysis
+    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/"
+```
+
+The above configuration will run an analysis for ten minutes targeting Safari users and those that have an insider cookie.
+
+Save the above resource as podinfo-abtest.yaml and then apply it:
+
+```bash
+kubectl apply -f ./podinfo-abtest.yaml
+```
+
+After a couple of seconds Flagger will create the canary objects:
+
+```bash
+# applied 
+deployment.apps/abtest
+horizontalpodautoscaler.autoscaling/abtest
+canary.flagger.app/abtest
+
+# generated 
+deployment.apps/abtest-primary
+horizontalpodautoscaler.autoscaling/abtest-primary
+service/abtest
+service/abtest-canary
+service/abtest-primary
+virtualservice.networking.istio.io/abtest
+```
+
+### Automated canary promotion
+
+Trigger a canary deployment by updating the container image:
+
+```bash
+kubectl -n test set image deployment/abtest \
+podinfod=quay.io/stefanprodan/podinfo:1.4.1
+```
+
+Flagger detects that the deployment revision changed and starts a new rollout:
+
+```text
+kubectl -n test describe canary/abtest
+
+Status:
+  Failed Checks:         0
+  Phase:                 Succeeded
+Events:
+  Type     Reason  Age   From     Message
+  ----     ------  ----  ----     -------
+  Normal   Synced  3m    flagger  New revision detected abtest.test
+  Normal   Synced  3m    flagger  Scaling up abtest.test
+  Warning  Synced  3m    flagger  Waiting for abtest.test rollout to finish: 0 of 1 updated replicas are available
+  Normal   Synced  3m    flagger  Advance abtest.test canary iteration 1/10
+  Normal   Synced  3m    flagger  Advance abtest.test canary iteration 2/10
+  Normal   Synced  3m    flagger  Advance abtest.test canary iteration 3/10
+  Normal   Synced  2m    flagger  Advance abtest.test canary iteration 4/10
+  Normal   Synced  2m    flagger  Advance abtest.test canary iteration 5/10
+  Normal   Synced  1m    flagger  Advance abtest.test canary iteration 6/10
+  Normal   Synced  1m    flagger  Advance abtest.test canary iteration 7/10
+  Normal   Synced  55s   flagger  Advance abtest.test canary iteration 8/10
+  Normal   Synced  45s   flagger  Advance abtest.test canary iteration 9/10
+  Normal   Synced  35s   flagger  Advance abtest.test canary iteration 10/10
+  Normal   Synced  25s   flagger  Copying abtest.test template spec to abtest-primary.test
+  Warning  Synced  15s   flagger  Waiting for abtest-primary.test rollout to finish: 1 of 2 updated replicas are available
+  Normal   Synced  5s    flagger  Promotion completed! Scaling down abtest.test
+```
+
+**Note** that if you apply new changes to the deployment during the canary analysis, Flagger will restart the analysis.
+
+You can monitor all canaries with:
+
+```bash
+watch kubectl get canaries --all-namespaces
+
+NAMESPACE   NAME      STATUS        WEIGHT   LASTTRANSITIONTIME
+test        abtest    Progressing   100      2019-03-16T14:05:07Z
+prod        frontend  Succeeded     0        2019-03-15T16:15:07Z
+prod        backend   Failed        0        2019-03-14T17:05:07Z
+```
+
+### Automated rollback
+
+During the canary analysis you can generate HTTP 500 errors and high latency to test Flagger's rollback.
+
+Generate HTTP 500 errors:
+
+```bash
+watch curl -b 'type=insider' http://app.example.com/status/500
+```
+
+Generate latency:
+
+```bash
+watch curl -b 'type=insider' http://app.example.com/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.
+
+```text
+kubectl -n test describe canary/abtest
+
+Status:
+  Failed Checks:         2
+  Phase:                 Failed
+Events:
+  Type     Reason  Age   From     Message
+  ----     ------  ----  ----     -------
+  Normal   Synced  3m    flagger  Starting canary deployment for abtest.test
+  Normal   Synced  3m    flagger  Advance abtest.test canary iteration 1/10
+  Normal   Synced  3m    flagger  Advance abtest.test canary iteration 2/10
+  Normal   Synced  3m    flagger  Advance abtest.test canary iteration 3/10
+  Normal   Synced  3m    flagger  Halt abtest.test advancement success rate 69.17% < 99%
+  Normal   Synced  2m    flagger  Halt abtest.test advancement success rate 61.39% < 99%
+  Warning  Synced  2m    flagger  Rolling back abtest.test failed checks threshold reached 2
+  Warning  Synced  1m    flagger  Canary failed! Scaling down abtest.test
+```

docs/gitbook/usage/alerting.md

@@ -15,12 +15,12 @@ helm upgrade -i flagger flagger/flagger \
 Once configured with a Slack incoming **webhook**, Flagger will post messages when a canary deployment 
 has been initialised, 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)
+![Slack Notifications](https://raw.githubusercontent.com/weaveworks/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)
+![Slack Notifications](https://raw.githubusercontent.com/weaveworks/flagger/master/docs/screens/slack-canary-failed.png)
 
 ### Prometheus Alert Manager
 

docs/gitbook/usage/appmesh-progressive-delivery.md

@@ -0,0 +1,286 @@
+# App Mesh Canary Deployments
+
+This guide shows you how to use App Mesh and Flagger to automate canary deployments. 
+You'll need an EKS cluster configured with App Mesh, you can find the install guide 
+[here](https://docs.flagger.app/install/flagger-install-on-eks-appmesh).
+
+### Bootstrap
+
+Flagger takes a Kubernetes deployment and optionally a horizontal pod autoscaler (HPA), 
+then creates a series of objects (Kubernetes deployments, ClusterIP services, App Mesh virtual nodes and services). 
+These objects expose the application on the mesh and drive the canary analysis and promotion.
+The only App Mesh object you need to create by yourself is the mesh resource.
+
+Create a mesh called `global`:
+
+```bash
+export REPO=https://raw.githubusercontent.com/weaveworks/flagger/master
+
+kubectl apply -f ${REPO}/artifacts/appmesh/global-mesh.yaml
+```
+
+Create a test namespace with App Mesh sidecar injection enabled:
+
+```bash
+kubectl apply -f ${REPO}/artifacts/namespaces/test.yaml
+```
+
+Create a deployment and a horizontal pod autoscaler:
+
+```bash
+kubectl apply -f ${REPO}/artifacts/appmesh/deployment.yaml
+kubectl apply -f ${REPO}/artifacts/appmesh/hpa.yaml
+```
+
+Deploy the load testing service to generate traffic during the canary analysis:
+
+```bash
+helm upgrade -i flagger-loadtester flagger/loadtester \
+--namespace=test \
+--set meshName=global.appmesh-system \
+--set "backends[0]=podinfo.test"
+```
+
+Create a canary custom resource:
+
+```yaml
+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.appmesh-system
+    # App Mesh egress (optional) 
+    backends:
+      - backend.test
+  # 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/"
+```
+
+Save the above resource as podinfo-canary.yaml and then apply it:
+
+```bash
+kubectl apply -f ./podinfo-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 Kubernetes objects
+deployment.apps/podinfo-primary
+horizontalpodautoscaler.autoscaling/podinfo-primary
+service/podinfo
+service/podinfo-canary
+service/podinfo-primary
+
+# generated App Mesh objects
+virtualnode.appmesh.k8s.aws/podinfo
+virtualnode.appmesh.k8s.aws/podinfo-canary
+virtualnode.appmesh.k8s.aws/podinfo-primary
+virtualservice.appmesh.k8s.aws/podinfo.test
+```
+
+The App Mesh specific settings are:
+
+```yaml
+  service:
+    port: 9898
+    meshName: global.appmesh-system
+    backends:
+      - backend1.test
+      - backend2.test
+```
+
+App Mesh blocks all egress traffic by default. If your application needs to call another service, you have to create an
+App Mesh virtual service for it and add the virtual service name to the backend list.
+
+### Setup App Mesh ingress (optional)
+
+In order to expose the podinfo app outside the mesh you'll be using an Envoy ingress and an AWS classic load balancer.
+The ingress binds to an internet domain and forwards the calls into the mesh through the App Mesh sidecar.
+If podinfo becomes unavailable due to a HPA downscaling or a node restart,
+the ingress will retry the calls for a short period of time.
+
+Deploy the ingress and the AWS ELB service:
+
+```bash
+kubectl apply -f ${REPO}/artifacts/appmesh/ingress.yaml
+```
+
+Find the ingress public address:
+
+```bash
+kubectl -n test describe svc/ingress | grep Ingress
+
+LoadBalancer Ingress:     yyy-xx.us-west-2.elb.amazonaws.com
+```
+
+Wait for the ELB to become active:
+
+```bash
+ watch curl -sS ${INGRESS_URL}
+```
+
+Open your browser and navigate to the ingress address to access podinfo UI.
+
+### Automated canary promotion
+
+Trigger a canary deployment by updating the container image:
+
+```bash
+kubectl -n test set image deployment/podinfo \
+podinfod=quay.io/stefanprodan/podinfo:1.4.1
+```
+
+Flagger detects that the deployment revision changed and starts a new rollout:
+
+```text
+kubectl -n test describe canary/podinfo
+
+Status:
+  Canary Weight:         0
+  Failed Checks:         0
+  Phase:                 Succeeded
+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
+```
+
+**Note** that if you apply new changes to the deployment during the canary analysis, Flagger will restart the analysis.
+
+During the analysis the canary’s progress can be monitored with Grafana. The App Mesh dashboard URL is 
+http://localhost:3000/d/flagger-appmesh/appmesh-canary?refresh=10s&orgId=1&var-namespace=test&var-primary=podinfo-primary&var-canary=podinfo
+
+![App Mesh Canary Dashboard](https://raw.githubusercontent.com/weaveworks/flagger/master/docs/screens/flagger-grafana-appmesh.png)
+
+You can monitor all canaries with:
+
+```bash
+watch kubectl get canaries --all-namespaces
+
+NAMESPACE   NAME      STATUS        WEIGHT   LASTTRANSITIONTIME
+test        podinfo   Progressing   15       2019-03-16T14:05:07Z
+prod        frontend  Succeeded     0        2019-03-15T16:15:07Z
+prod        backend   Failed        0        2019-03-14T17:05:07Z
+```
+
+If you’ve enabled the Slack notifications, you should receive the following messages:
+
+![Flagger Slack Notifications](https://raw.githubusercontent.com/weaveworks/flagger/master/docs/screens/slack-canary-notifications.png)
+
+### Automated rollback
+
+During the canary analysis you can generate HTTP 500 errors to test if Flagger pauses the rollout.
+
+Trigger a canary deployment:
+
+```bash
+kubectl -n test set image deployment/podinfo \
+podinfod=quay.io/stefanprodan/podinfo:1.4.2
+```
+
+Exec into the load tester pod with:
+
+```bash
+kubectl -n test exec -it flagger-loadtester-xx-xx sh
+```
+
+Generate HTTP 500 errors:
+
+```bash
+hey -z 1m -c 5 -q 5 http://podinfo.test:9898/status/500
+```
+
+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.
+
+```text
+kubectl -n test describe canary/podinfo
+
+Status:
+  Canary Weight:         0
+  Failed Checks:         10
+  Phase:                 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
+```
+
+If you’ve enabled the Slack notifications, you’ll receive a message if the progress deadline is exceeded, 
+or if the analysis reached the maximum number of failed checks:
+
+![Flagger Slack Notifications](https://raw.githubusercontent.com/weaveworks/flagger/master/docs/screens/slack-canary-failed.png)

docs/gitbook/usage/monitoring.md

@@ -6,15 +6,13 @@ Flagger comes with a Grafana dashboard made for canary analysis. Install Grafana
 
 ```bash
 helm upgrade -i flagger-grafana flagger/grafana \
---namespace=istio-system \
---set url=http://prometheus:9090 \
---set user=admin \
---set password=admin
+--namespace=istio-system \ # or appmesh-system
+--set url=http://prometheus:9090
 ```
 
 The dashboard shows the RED and USE metrics for the primary and canary workloads:
 
-![canary dashboard](https://raw.githubusercontent.com/stefanprodan/flagger/master/docs/screens/grafana-canary-analysis.png)
+![Canary Dashboard](https://raw.githubusercontent.com/weaveworks/flagger/master/docs/screens/grafana-canary-analysis.png)
 
 ### Logging
 
@@ -48,6 +46,9 @@ Flagger exposes Prometheus metrics that can be used to determine the canary anal
 the destination weight values:
 
 ```bash
+# Flagger version and mesh provider gauge
+flagger_info{version="0.10.0", mesh_provider="istio"} 1
+
 # Canaries total gauge
 flagger_canary_total{namespace="test"} 1