Merge pull request #35 from stefanprodan/gh-actions

Publish charts with GitHub Actions

.codecov.yml

@@ -0,0 +1,8 @@
+coverage:
+  status:
+    project:
+      default:
+        target: auto
+        threshold: 50
+        base: auto
+    patch: off

.gitbook.yaml

@@ -0,0 +1 @@
+root: ./docs/gitbook

.github/main.workflow

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

.travis.yml

@@ -2,7 +2,7 @@ sudo: required
 language: go
 
 go:
-- 1.10.x
+- 1.11.x
 
 services:
 - docker
@@ -14,25 +14,29 @@ addons:
 
 script:
 - set -e
-- make test
+- make test-fmt
+- make test-codegen
+- go test -race -coverprofile=coverage.txt -covermode=atomic ./pkg/controller/
 - make build
 
 after_success:
 - if [ -z "$DOCKER_USER" ]; then
-    echo "PR build, skipping Docker Hub push";
+    echo "PR build, skipping image push";
   else
-    docker tag stefanprodan/flagger:latest stefanprodan/flagger:${TRAVIS_COMMIT};
-    echo $DOCKER_PASS | docker login -u=$DOCKER_USER --password-stdin;
-    docker push stefanprodan/flagger:${TRAVIS_COMMIT};
+    BRANCH_COMMIT=${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:${BRANCH_COMMIT};
   fi
 - if [ -z "$TRAVIS_TAG" ]; then
-    echo "Not a release, skipping Docker Hub push";
+    echo "Not a release, skipping image push";
   else
-    docker tag stefanprodan/flagger:latest stefanprodan/flagger:$TRAVIS_TAG;
-    echo $DOCKER_PASS | docker login -u=$DOCKER_USER --password-stdin;
-    docker push stefanprodan/flagger:latest;
-    docker push stefanprodan/flagger:$TRAVIS_TAG;
+    docker tag stefanprodan/flagger:latest quay.io/stefanprodan/flagger:${TRAVIS_TAG};
+    echo $DOCKER_PASS | docker login -u=$DOCKER_USER --password-stdin quay.io;
+    docker push quay.io/stefanprodan/flagger:$TRAVIS_TAG;
   fi
+- bash <(curl -s https://codecov.io/bash)
+- rm coverage.txt
 
 deploy:
 - provider: script

CONTRIBUTING.md

@@ -0,0 +1,72 @@
+# How to Contribute
+
+Flagger is [Apache 2.0 licensed](LICENSE) and accepts contributions via GitHub
+pull requests. This document outlines some of the conventions on development
+workflow, commit message formatting, contact points and other resources to make
+it easier to get your contribution accepted.
+
+We gratefully welcome improvements to documentation as well as to code.
+
+## Certificate of Origin
+
+By contributing to this project you agree to the Developer Certificate of
+Origin (DCO). This document was created by the Linux Kernel community and is a
+simple statement that you, as a contributor, have the legal right to make the
+contribution.
+
+## Chat
+
+The project uses Slack: To join the conversation, simply join the
+[Weave community](https://slack.weave.works/) Slack workspace.
+
+## Getting Started
+
+- Fork the repository on GitHub
+- If you want to contribute as a developer, continue reading this document for further instructions
+- If you have questions, concerns, get stuck or need a hand, let us know
+  on the Slack channel. We are happy to help and look forward to having
+  you part of the team. No matter in which capacity.
+- Play with the project, submit bugs, submit pull requests!
+
+## Contribution workflow
+
+This is a rough outline of how to prepare a contribution:
+
+- Create a topic branch from where you want to base your work (usually branched from master).
+- Make commits of logical units.
+- Make sure your commit messages are in the proper format (see below).
+- Push your changes to a topic branch in your fork of the repository.
+- If you changed code:
+  - add automated tests to cover your changes
+- Submit a pull request to the original repository.
+
+## Acceptance policy
+
+These things will make a PR more likely to be accepted:
+
+- a well-described requirement
+- new code and tests follow the conventions in old code and tests
+- a good commit message (see below)
+- All code must abide [Go Code Review Comments](https://github.com/golang/go/wiki/CodeReviewComments)
+- Names should abide [What's in a name](https://talks.golang.org/2014/names.slide#1)
+- Code must build on both Linux and Darwin, via plain `go build`
+- Code should have appropriate test coverage and tests should be written
+  to work with `go test`
+
+In general, we will merge a PR once one maintainer has endorsed it.
+For substantial changes, more people may become involved, and you might
+get asked to resubmit the PR or divide the changes into more than one PR.
+
+### Format of the Commit Message
+
+For Flux we prefer the following rules for good commit messages:
+
+- Limit the subject to 50 characters and write as the continuation
+  of the sentence "If applied, this commit will ..."
+- Explain what and why in the body, if more than a trivial change;
+  wrap it at 72 characters.
+
+The [following article](https://chris.beams.io/posts/git-commit/#seven-rules)
+has some more helpful advice on documenting your work.
+
+This doc is adapted from the [Weaveworks Flux](https://github.com/weaveworks/flux/blob/master/CONTRIBUTING.md)

Dockerfile

@@ -1,4 +1,4 @@
-FROM golang:1.10
+FROM golang:1.11
 
 RUN mkdir -p /go/src/github.com/stefanprodan/flagger/
 
@@ -13,17 +13,17 @@ RUN GIT_COMMIT=$(git rev-list -1 HEAD) && \
 
 FROM alpine:3.8
 
-RUN addgroup -S app \
-    && adduser -S -g app app \
+RUN addgroup -S flagger \
+    && adduser -S -g flagger flagger \
     && apk --no-cache add ca-certificates
 
-WORKDIR /home/app
+WORKDIR /home/flagger
 
 COPY --from=0 /go/src/github.com/stefanprodan/flagger/flagger .
 
-RUN chown -R app:app ./
+RUN chown -R flagger:flagger ./
 
-USER app
+USER flagger
 
 ENTRYPOINT ["./flagger"]
 

Dockerfile.loadtester

@@ -0,0 +1,44 @@
+FROM golang:1.11 AS hey-builder
+
+RUN mkdir -p /go/src/github.com/rakyll/hey/
+
+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
+
+COPY . .
+
+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
+
+RUN addgroup -S app \
+    && adduser -S -g app app \
+    && apk --no-cache add ca-certificates curl
+
+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 chown -R app:app ./
+
+USER app
+
+ENTRYPOINT ["./loadtester"]

Gopkg.lock

@@ -25,14 +25,6 @@
   revision = "8991bc29aa16c548c550c7ff78260e27b9ab7c73"
   version = "v1.1.1"
 
-[[projects]]
-  digest = "1:ade392a843b2035effb4b4a2efa2c3bab3eb29b992e98bacf9c898b0ecb54e45"
-  name = "github.com/fatih/color"
-  packages = ["."]
-  pruneopts = "NUT"
-  revision = "5b77d2a35fb0ede96d138fc9a99f5c9b6aef11b4"
-  version = "v1.7.0"
-
 [[projects]]
   digest = "1:81466b4218bf6adddac2572a30ac733a9255919bc2f470b4827a317bd4ee1756"
   name = "github.com/ghodss/yaml"
@@ -92,10 +84,11 @@
   revision = "4030bb1f1f0c35b30ca7009e9ebd06849dd45306"
 
 [[projects]]
-  digest = "1:2e3c336fc7fde5c984d2841455a658a6d626450b1754a854b3b32e7a8f49a07a"
+  digest = "1:d2754cafcab0d22c13541618a8029a70a8959eb3525ff201fe971637e2274cd0"
   name = "github.com/google/go-cmp"
   packages = [
     "cmp",
+    "cmp/cmpopts",
     "cmp/internal/diff",
     "cmp/internal/function",
     "cmp/internal/value",
@@ -170,7 +163,7 @@
   revision = "f2b4162afba35581b6d4a50d3b8f34e33c144682"
 
 [[projects]]
-  digest = "1:555e31114bd0e89c6340c47ab73162e8c8d873e4d88914310923566f487bfcd5"
+  digest = "1:03a74b0d86021c8269b52b7c908eb9bb3852ff590b363dad0a807cf58cec2f89"
   name = "github.com/knative/pkg"
   packages = [
     "apis",
@@ -182,31 +175,19 @@
     "apis/istio/common/v1alpha1",
     "apis/istio/v1alpha3",
     "client/clientset/versioned",
+    "client/clientset/versioned/fake",
     "client/clientset/versioned/scheme",
     "client/clientset/versioned/typed/authentication/v1alpha1",
+    "client/clientset/versioned/typed/authentication/v1alpha1/fake",
     "client/clientset/versioned/typed/duck/v1alpha1",
+    "client/clientset/versioned/typed/duck/v1alpha1/fake",
     "client/clientset/versioned/typed/istio/v1alpha3",
+    "client/clientset/versioned/typed/istio/v1alpha3/fake",
     "signals",
   ]
   pruneopts = "NUT"
   revision = "c15d7c8f2220a7578b33504df6edefa948c845ae"
 
-[[projects]]
-  digest = "1:08c231ec84231a7e23d67e4b58f975e1423695a32467a362ee55a803f9de8061"
-  name = "github.com/mattn/go-colorable"
-  packages = ["."]
-  pruneopts = "NUT"
-  revision = "167de6bfdfba052fa6b2d3664c8f5272e23c9072"
-  version = "v0.0.9"
-
-[[projects]]
-  digest = "1:bffa444ca07c69c599ae5876bc18b25bfd5fa85b297ca10a25594d284a7e9c5d"
-  name = "github.com/mattn/go-isatty"
-  packages = ["."]
-  pruneopts = "NUT"
-  revision = "6ca4dbf54d38eea1a992b3c722a76a5d1c4cb25c"
-  version = "v0.0.4"
-
 [[projects]]
   digest = "1:5985ef4caf91ece5d54817c11ea25f182697534f8ae6521eadcd628c142ac4b6"
   name = "github.com/matttproud/golang_protobuf_extensions"
@@ -547,42 +528,72 @@
   version = "kubernetes-1.11.0"
 
 [[projects]]
-  digest = "1:29e55bcff61dd3d1f768724450a3933ea76e6277684796eb7c315154f41db902"
+  digest = "1:c7d6cf5e28c377ab4000b94b6b9ff562c4b13e7e8b948ad943f133c5104be011"
   name = "k8s.io/client-go"
   packages = [
     "discovery",
     "discovery/fake",
     "kubernetes",
+    "kubernetes/fake",
     "kubernetes/scheme",
     "kubernetes/typed/admissionregistration/v1alpha1",
+    "kubernetes/typed/admissionregistration/v1alpha1/fake",
     "kubernetes/typed/admissionregistration/v1beta1",
+    "kubernetes/typed/admissionregistration/v1beta1/fake",
     "kubernetes/typed/apps/v1",
+    "kubernetes/typed/apps/v1/fake",
     "kubernetes/typed/apps/v1beta1",
+    "kubernetes/typed/apps/v1beta1/fake",
     "kubernetes/typed/apps/v1beta2",
+    "kubernetes/typed/apps/v1beta2/fake",
     "kubernetes/typed/authentication/v1",
+    "kubernetes/typed/authentication/v1/fake",
     "kubernetes/typed/authentication/v1beta1",
+    "kubernetes/typed/authentication/v1beta1/fake",
     "kubernetes/typed/authorization/v1",
+    "kubernetes/typed/authorization/v1/fake",
     "kubernetes/typed/authorization/v1beta1",
+    "kubernetes/typed/authorization/v1beta1/fake",
     "kubernetes/typed/autoscaling/v1",
+    "kubernetes/typed/autoscaling/v1/fake",
     "kubernetes/typed/autoscaling/v2beta1",
+    "kubernetes/typed/autoscaling/v2beta1/fake",
     "kubernetes/typed/batch/v1",
+    "kubernetes/typed/batch/v1/fake",
     "kubernetes/typed/batch/v1beta1",
+    "kubernetes/typed/batch/v1beta1/fake",
     "kubernetes/typed/batch/v2alpha1",
+    "kubernetes/typed/batch/v2alpha1/fake",
     "kubernetes/typed/certificates/v1beta1",
+    "kubernetes/typed/certificates/v1beta1/fake",
     "kubernetes/typed/core/v1",
+    "kubernetes/typed/core/v1/fake",
     "kubernetes/typed/events/v1beta1",
+    "kubernetes/typed/events/v1beta1/fake",
     "kubernetes/typed/extensions/v1beta1",
+    "kubernetes/typed/extensions/v1beta1/fake",
     "kubernetes/typed/networking/v1",
+    "kubernetes/typed/networking/v1/fake",
     "kubernetes/typed/policy/v1beta1",
+    "kubernetes/typed/policy/v1beta1/fake",
     "kubernetes/typed/rbac/v1",
+    "kubernetes/typed/rbac/v1/fake",
     "kubernetes/typed/rbac/v1alpha1",
+    "kubernetes/typed/rbac/v1alpha1/fake",
     "kubernetes/typed/rbac/v1beta1",
+    "kubernetes/typed/rbac/v1beta1/fake",
     "kubernetes/typed/scheduling/v1alpha1",
+    "kubernetes/typed/scheduling/v1alpha1/fake",
     "kubernetes/typed/scheduling/v1beta1",
+    "kubernetes/typed/scheduling/v1beta1/fake",
     "kubernetes/typed/settings/v1alpha1",
+    "kubernetes/typed/settings/v1alpha1/fake",
     "kubernetes/typed/storage/v1",
+    "kubernetes/typed/storage/v1/fake",
     "kubernetes/typed/storage/v1alpha1",
+    "kubernetes/typed/storage/v1alpha1/fake",
     "kubernetes/typed/storage/v1beta1",
+    "kubernetes/typed/storage/v1beta1/fake",
     "pkg/apis/clientauthentication",
     "pkg/apis/clientauthentication/v1alpha1",
     "pkg/apis/clientauthentication/v1beta1",
@@ -675,24 +686,29 @@
   analyzer-name = "dep"
   analyzer-version = 1
   input-imports = [
-    "github.com/fatih/color",
     "github.com/google/go-cmp/cmp",
+    "github.com/google/go-cmp/cmp/cmpopts",
     "github.com/istio/glog",
     "github.com/knative/pkg/apis/istio/v1alpha3",
     "github.com/knative/pkg/client/clientset/versioned",
+    "github.com/knative/pkg/client/clientset/versioned/fake",
     "github.com/knative/pkg/signals",
     "github.com/prometheus/client_golang/prometheus/promhttp",
     "go.uber.org/zap",
     "go.uber.org/zap/zapcore",
     "k8s.io/api/apps/v1",
+    "k8s.io/api/autoscaling/v1",
+    "k8s.io/api/autoscaling/v2beta1",
     "k8s.io/api/core/v1",
     "k8s.io/apimachinery/pkg/api/errors",
+    "k8s.io/apimachinery/pkg/api/resource",
     "k8s.io/apimachinery/pkg/apis/meta/v1",
     "k8s.io/apimachinery/pkg/labels",
     "k8s.io/apimachinery/pkg/runtime",
     "k8s.io/apimachinery/pkg/runtime/schema",
     "k8s.io/apimachinery/pkg/runtime/serializer",
     "k8s.io/apimachinery/pkg/types",
+    "k8s.io/apimachinery/pkg/util/intstr",
     "k8s.io/apimachinery/pkg/util/runtime",
     "k8s.io/apimachinery/pkg/util/sets/types",
     "k8s.io/apimachinery/pkg/util/wait",
@@ -700,6 +716,7 @@
     "k8s.io/client-go/discovery",
     "k8s.io/client-go/discovery/fake",
     "k8s.io/client-go/kubernetes",
+    "k8s.io/client-go/kubernetes/fake",
     "k8s.io/client-go/kubernetes/scheme",
     "k8s.io/client-go/kubernetes/typed/core/v1",
     "k8s.io/client-go/plugin/pkg/client/auth/gcp",

LICENSE

@@ -186,7 +186,7 @@
       same "printed page" as the copyright notice for easier
       identification within third-party archives.
 
-   Copyright [yyyy] [name of copyright owner]
+   Copyright 2018 Weaveworks. All rights reserved.
 
    Licensed under the Apache License, Version 2.0 (the "License");
    you may not use this file except in compliance with the License.

Makefile

@@ -3,14 +3,20 @@ VERSION?=$(shell grep 'VERSION' pkg/version/version.go | awk '{ print $$4 }' | t
 VERSION_MINOR:=$(shell grep 'VERSION' pkg/version/version.go | awk '{ print $$4 }' | tr -d '"' | rev | cut -d'.' -f2- | rev)
 PATCH:=$(shell grep 'VERSION' pkg/version/version.go | awk '{ print $$4 }' | tr -d '"' | awk -F. '{print $$NF}')
 SOURCE_DIRS = cmd pkg/apis pkg/controller pkg/server pkg/logging pkg/version
+LT_VERSION?=$(shell grep 'VERSION' cmd/loadtester/main.go | awk '{ print $$4 }' | tr -d '"' | head -n1)
+
 run:
-	go run cmd/flagger/* -kubeconfig=$$HOME/.kube/config -log-level=info -metrics-server=https://prometheus.istio.weavedx.com
+	go run cmd/flagger/* -kubeconfig=$$HOME/.kube/config -log-level=info \
+	-metrics-server=https://prometheus.iowa.weavedx.com \
+	-slack-url=https://hooks.slack.com/services/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 \
+	-slack-channel="devops-alerts"
 
 build:
 	docker build -t stefanprodan/flagger:$(TAG) . -f Dockerfile
 
 push:
-	docker push stefanprodan/flagger:$(TAG)
+	docker tag stefanprodan/flagger:$(TAG) quay.io/stefanprodan/flagger:$(VERSION)
+	docker push quay.io/stefanprodan/flagger:$(VERSION)
 
 fmt:
 	gofmt -l -s -w $(SOURCE_DIRS)
@@ -25,12 +31,13 @@ test: test-fmt test-codegen
 	go test ./...
 
 helm-package:
-	cd charts/ && helm package flagger/ && helm package podinfo-flagger/ && helm package grafana/
+	cd charts/ && helm package flagger/ && helm package grafana/ && helm package loadtester/
 	mv charts/*.tgz docs/
 	helm repo index docs --url https://stefanprodan.github.io/flagger --merge ./docs/index.yaml
 
 helm-up:
 	helm upgrade --install flagger ./charts/flagger --namespace=istio-system --set crd.create=false
+	helm upgrade --install flagger-grafana ./charts/grafana --namespace=istio-system
 
 version-set:
 	@next="$(TAG)" && \
@@ -52,10 +59,10 @@ version-up:
 
 dev-up: version-up
 	@echo "Starting build/push/deploy pipeline for $(VERSION)"
-	docker build -t stefanprodan/flagger:$(VERSION) . -f Dockerfile
-	docker push stefanprodan/flagger:$(VERSION)
+	docker build -t quay.io/stefanprodan/flagger:$(VERSION) . -f Dockerfile
+	docker push quay.io/stefanprodan/flagger:$(VERSION)
 	kubectl apply -f ./artifacts/flagger/crd.yaml
-	helm upgrade --install flagger ./charts/flagger --namespace=istio-system --set crd.create=false
+	helm upgrade -i flagger ./charts/flagger --namespace=istio-system --set crd.create=false
 
 release:
 	git tag $(VERSION)
@@ -68,3 +75,11 @@ release-set: fmt version-set helm-package
 	git tag $(VERSION)
 	git push origin $(VERSION)
 
+reset-test:
+	kubectl delete -f ./artifacts/namespaces
+	kubectl apply -f ./artifacts/namespaces
+	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)

README.md

@@ -2,13 +2,14 @@
 
 [![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)
 
 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 project is currently in experimental phase and it is expected that breaking changes 
-to the API will be made in the upcoming releases.
+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.
 
 ### Install 
 
@@ -19,50 +20,50 @@ Deploy Flagger in the `istio-system` namespace using Helm:
 
 ```bash
 # add the Helm repository
-helm repo add flagger https://stefanprodan.github.io/flagger
+helm repo add flagger https://flagger.app
 
 # install or upgrade
 helm upgrade -i flagger flagger/flagger \
 --namespace=istio-system \
---set metricsServer=http://prometheus.istio-system:9090 \
---set controlLoopInterval=1m
+--set metricsServer=http://prometheus.istio-system:9090 
 ```
 
-Flagger is compatible with Kubernetes >1.10.0 and Istio >1.0.0.
+Flagger is compatible with Kubernetes >1.11.0 and Istio >1.0.0.
 
 ### Usage
 
-Flagger requires two Kubernetes [deployments](https://kubernetes.io/docs/concepts/workloads/controllers/deployment/): 
-one for the version you want to upgrade called _primary_ and one for the _canary_.
-Each deployment must have a corresponding ClusterIP [service](https://kubernetes.io/docs/concepts/services-networking/service/) 
-that exposes a port named http or https. These services are used as destinations in a Istio [virtual service](https://istio.io/docs/reference/config/istio.networking.v1alpha3/#VirtualService).
+Flagger takes a Kubernetes deployment and creates a series of objects 
+(Kubernetes [deployments](https://kubernetes.io/docs/concepts/workloads/controllers/deployment/), 
+ClusterIP [services](https://kubernetes.io/docs/concepts/services-networking/service/) and 
+Istio [virtual services](https://istio.io/docs/reference/config/istio.networking.v1alpha3/#VirtualService)) 
+to drive the canary analysis and promotion.
 
-![flagger-overview](https://raw.githubusercontent.com/stefanprodan/flagger/master/docs/diagrams/flagger-overview.png)
+![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 rollout if a rolling update is underway
-    * halt rollout if pods are unhealthy
+    * halt advancement if a rolling update is underway
+    * halt advancement if pods are unhealthy
 * increase canary traffic weight percentage from 0% to 5% (step weight)
 * check canary HTTP request success rate and latency
-    * halt rollout if any metric is under the specified threshold
+    * halt advancement if any metric is under the specified threshold
     * increment the failed checks counter
 * check if the number of failed checks reached the threshold
     * route all traffic to primary
     * scale to zero the canary deployment and mark it as failed
     * wait for the canary deployment to be updated (revision bump) and start over
 * increase canary traffic weight by 5% (step weight) till it reaches 50% (max weight) 
-    * halt rollout while canary request success rate is under the threshold
-    * halt rollout while canary request duration P99 is over the threshold
-    * halt rollout if the primary or canary deployment becomes unhealthy 
-    * halt rollout while canary deployment is being scaled up/down by HPA
+    * halt advancement while canary request success rate is under the threshold
+    * halt advancement while canary request duration P99 is over the threshold
+    * halt advancement if the primary or canary deployment becomes unhealthy 
+    * halt advancement while canary deployment is being scaled up/down by HPA
 * promote canary to primary
     * copy canary deployment spec template over primary
 * wait for primary rolling update to finish
-    * halt rollout if pods are unhealthy
+    * halt advancement if pods are unhealthy
 * route all traffic to primary
 * scale to zero the canary deployment
 * mark rollout as finished
@@ -70,69 +71,41 @@ Gated canary promotion stages:
 
 You can change the canary analysis _max weight_ and the _step weight_ percentage in the Flagger's custom resource.
 
-Assuming the primary deployment is named _podinfo_ and the canary one _podinfo-canary_, Flagger will require 
-a virtual service configured with weight-based routing:
+For a deployment named _podinfo_, a canary promotion can be defined using Flagger's custom resource:
 
 ```yaml
-apiVersion: networking.istio.io/v1alpha3
-kind: VirtualService
-metadata:
-  name: podinfo
-spec:
-  hosts:
-  - podinfo
-  http:
-  - route:
-    - destination:
-        host: podinfo
-        port:
-          number: 9898
-      weight: 100
-    - destination:
-        host: podinfo-canary
-        port:
-          number: 9898
-      weight: 0
-```
-
-Primary and canary services should expose a port named http:
-
-```yaml
-apiVersion: v1
-kind: Service
-metadata:
-  name: podinfo-canary
-spec:
-  type: ClusterIP
-  selector:
-    app: podinfo-canary
-  ports:
-  - name: http
-    port: 9898
-    targetPort: 9898
-```
-
-Based on the two deployments, services and virtual service, a canary promotion can be defined using Flagger's custom resource:
-
-```yaml
-apiVersion: flagger.app/v1beta1
+apiVersion: flagger.app/v1alpha3
 kind: Canary
 metadata:
   name: podinfo
   namespace: test
 spec:
-  targetKind: Deployment
-  virtualService:
+  # deployment reference
+  targetRef:
+    apiVersion: apps/v1
+    kind: Deployment
     name: podinfo
-  primary:
+  # 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
-    host: podinfo
-  canary:
-    name: podinfo-canary
-    host: podinfo-canary
+  service:
+    # container port
+    port: 9898
+    # Istio gateways (optional)
+    gateways:
+    - public-gateway.istio-system.svc.cluster.local
+    # Istio virtual service host names (optional)
+    hosts:
+    - podinfo.example.com
   canaryAnalysis:
-    # max number of failed checks
-    # before rolling back the canary
+    # schedule interval (default 60s)
+    interval: 1m
+    # max number of failed metric checks before rollback
     threshold: 10
     # max traffic percentage routed to canary
     # percentage (0-100)
@@ -140,6 +113,7 @@ spec:
     # canary increment step
     # percentage (0-100)
     stepWeight: 5
+    # Istio Prometheus checks
     metrics:
     - name: istio_requests_total
       # minimum req success rate (non 5xx responses)
@@ -150,7 +124,14 @@ spec:
       # maximum req duration P99
       # milliseconds
       threshold: 500
-      interval: 1m
+      interval: 30s
+    # external checks (optional)
+    webhooks:
+      - name: load-test
+        url: http://flagger-loadtester.test/
+        timeout: 5s
+        metadata:
+          cmd: "hey -z 1m -q 10 -c 2 http://podinfo.test:9898/"
 ```
 
 The canary analysis is using the following promql queries:
@@ -196,9 +177,23 @@ histogram_quantile(0.99,
 )
 ```
 
-### Automated canary analysis, promotions and rollbacks
+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.
 
-![flagger-canary](https://raw.githubusercontent.com/stefanprodan/flagger/master/docs/diagrams/flagger-canary-hpa.png)
+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:
 
@@ -208,66 +203,89 @@ export REPO=https://raw.githubusercontent.com/stefanprodan/flagger/master
 kubectl apply -f ${REPO}/artifacts/namespaces/test.yaml
 ```
 
-Create the primary deployment, service and hpa:
+Create a deployment and a horizontal pod autoscaler:
 
 ```bash
-kubectl apply -f ${REPO}/artifacts/workloads/primary-deployment.yaml
-kubectl apply -f ${REPO}/artifacts/workloads/primary-service.yaml
-kubectl apply -f ${REPO}/artifacts/workloads/primary-hpa.yaml
+kubectl apply -f ${REPO}/artifacts/canaries/deployment.yaml
+kubectl apply -f ${REPO}/artifacts/canaries/hpa.yaml
 ```
 
-Create the canary deployment, service and hpa:
+Deploy the load testing service to generate traffic during the canary analysis:
 
 ```bash
-kubectl apply -f ${REPO}/artifacts/workloads/canary-deployment.yaml
-kubectl apply -f ${REPO}/artifacts/workloads/canary-service.yaml
-kubectl apply -f ${REPO}/artifacts/workloads/canary-hpa.yaml
+kubectl -n test apply -f ${REPO}/artifacts/loadtester/deployment.yaml
+kubectl -n test apply -f ${REPO}/artifacts/loadtester/service.yaml
 ```
 
-Create a virtual service (replace the Istio gateway and the internet domain with your own):
+Create a canary promotion custom resource (replace the Istio gateway and the internet domain with your own):
 
 ```bash
-kubectl apply -f ${REPO}/artifacts/workloads/virtual-service.yaml
+kubectl apply -f ${REPO}/artifacts/canaries/canary.yaml
 ```
 
-Create a canary promotion custom resource:
+After a couple of seconds Flagger will create the canary objects:
 
 ```bash
-kubectl apply -f ${REPO}/artifacts/rollouts/podinfo.yaml
+# 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
 ```
 
-Canary promotion output:
+![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
+```
+
+Flagger detects that the deployment revision changed and starts a new canary analysis:
 
 ```
 kubectl -n test describe canary/podinfo
 
 Status:
-  Canary Revision:  16271121
-  Failed Checks:    6
-  State:            finished
+  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  Starting canary deployment for podinfo.test
+  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
-  Warning  Synced  3m    flagger  Halt podinfo.test advancement request duration 2.525s > 500ms
-  Warning  Synced  3m    flagger  Halt podinfo.test advancement request duration 1.567s > 500ms
-  Warning  Synced  3m    flagger  Halt podinfo.test advancement request duration 823ms > 500ms
   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
-  Warning  Synced  1m    flagger  Halt podinfo.test advancement success rate 82.33% < 99%
-  Warning  Synced  1m    flagger  Halt podinfo.test advancement success rate 87.22% < 99%
-  Warning  Synced  1m    flagger  Halt podinfo.test advancement success rate 94.74% < 99%
   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-canary.test template spec to podinfo.test
-  Warning  Synced  15s   flagger  Waiting for podinfo.test rollout to finish: 1 of 2 updated replicas are available
-  Normal   Synced  5s    flagger  Promotion completed! Scaling down podinfo-canary.test
+  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.
@@ -298,9 +316,10 @@ the canary is scaled to zero and the rollout is marked as failed.
 kubectl -n test describe canary/podinfo
 
 Status:
-  Canary Revision:  16695041
-  Failed Checks:    10
-  State:            failed
+  Canary Weight:         0
+  Failed Checks:         10
+  Last Transition Time:  2019-01-16T13:47:16Z
+  Phase:                 Failed
 Events:
   Type     Reason  Age   From     Message
   ----     ------  ----  ----     -------
@@ -313,45 +332,8 @@ Events:
   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-canary.test failed checks threshold reached 10
-  Warning  Synced  1m    flagger  Canary failed! Scaling down podinfo-canary.test
-```
-
-Trigger a new canary deployment by updating the canary image:
-
-```bash
-kubectl -n test set image deployment/podinfo-canary \
-podinfod=quay.io/stefanprodan/podinfo:1.2.1
-```
-
-Steer detects that the canary revision changed and starts a new rollout:
-
-```
-kubectl -n test describe canary/podinfo
-
-Status:
-  Canary Revision:  19871136
-  Failed Checks:    0
-  State:            finished
-Events:
-  Type     Reason  Age   From     Message
-  ----     ------  ----  ----     -------
-  Normal   Synced  3m    flagger  New revision detected podinfo-canary.test old 17211012 new 17246876
-  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-canary.test template spec to podinfo.test
-  Warning  Synced  15s   flagger  Waiting for podinfo.test rollout to finish: 1 of 2 updated replicas are available
-  Normal   Synced  5s    flagger  Promotion completed! Scaling down podinfo-canary.test
+  Warning  Synced  1m    flagger  Rolling back podinfo.test failed checks threshold reached 10
+  Warning  Synced  1m    flagger  Canary failed! Scaling down podinfo.test
 ```
 
 ### Monitoring
@@ -388,18 +370,73 @@ 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-canary.test template spec to podinfo-primary.test
-Scaling down podinfo-canary.test
-Promotion completed! podinfo-canary.test revision 81289
+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 canary analysis and promotion to other types than Kubernetes deployments such as Flux Helm releases or OpenFaaS functions
 * Extend the validation mechanism to support other metrics than HTTP success rate and latency
 * Add support for comparing the canary metrics to the primary ones and do the validation based on the derivation between the two
-* Alerting: Trigger Alertmanager on successful or failed promotions (Prometheus instrumentation of the canary analysis)  
-* Reporting: publish canary analysis results to Slack/Jira/etc
+* Extend the canary analysis and promotion to other types than Kubernetes deployments such as Flux Helm releases or OpenFaaS functions
 
 ### Contributing
 

artifacts/canaries/canary.yaml

@@ -0,0 +1,58 @@
+apiVersion: flagger.app/v1alpha3
+kind: Canary
+metadata:
+  name: podinfo
+  namespace: test
+spec:
+  # deployment reference
+  targetRef:
+    apiVersion: apps/v1
+    kind: Deployment
+    name: podinfo
+  # the maximum time in seconds for the canary deployment
+  # to make progress before it is rollback (default 600s)
+  progressDeadlineSeconds: 60
+  # HPA reference (optional)
+  autoscalerRef:
+    apiVersion: autoscaling/v2beta1
+    kind: HorizontalPodAutoscaler
+    name: podinfo
+  service:
+    # container port
+    port: 9898
+    # Istio gateways (optional)
+    gateways:
+    - public-gateway.istio-system.svc.cluster.local
+    # Istio virtual service host names (optional)
+    hosts:
+    - app.iowa.weavedx.com
+  canaryAnalysis:
+    # schedule interval (default 60s)
+    interval: 10s
+    # max number of failed metric checks before rollback
+    threshold: 10
+    # max traffic percentage routed to canary
+    # percentage (0-100)
+    maxWeight: 50
+    # canary increment step
+    # percentage (0-100)
+    stepWeight: 5
+    # Istio Prometheus checks
+    metrics:
+    - name: istio_requests_total
+      # minimum req success rate (non 5xx responses)
+      # percentage (0-100)
+      threshold: 99
+      interval: 1m
+    - name: istio_request_duration_seconds_bucket
+      # maximum req duration P99
+      # milliseconds
+      threshold: 500
+      interval: 30s
+    # external checks (optional)
+    webhooks:
+      - name: load-test
+        url: http://flagger-loadtester.test/
+        timeout: 5s
+        metadata:
+          cmd: "hey -z 1m -q 10 -c 2 http://podinfo.test:9898/"

artifacts/canaries/deployment.yaml

@@ -0,0 +1,67 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: podinfo
+  namespace: test
+  labels:
+    app: podinfo
+spec:
+  minReadySeconds: 5
+  revisionHistoryLimit: 5
+  progressDeadlineSeconds: 60
+  strategy:
+    rollingUpdate:
+      maxUnavailable: 0
+    type: RollingUpdate
+  selector:
+    matchLabels:
+      app: podinfo
+  template:
+    metadata:
+      annotations:
+        prometheus.io/scrape: "true"
+      labels:
+        app: podinfo
+    spec:
+      containers:
+      - name: podinfod
+        image: quay.io/stefanprodan/podinfo:1.3.0
+        imagePullPolicy: IfNotPresent
+        ports:
+        - containerPort: 9898
+          name: http
+          protocol: TCP
+        command:
+        - ./podinfo
+        - --port=9898
+        - --level=info
+        - --random-delay=false
+        - --random-error=false
+        env:
+        - name: PODINFO_UI_COLOR
+          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/canaries/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/flagger/crd.yaml

@@ -4,47 +4,80 @@ metadata:
   name: canaries.flagger.app
 spec:
   group: flagger.app
-  version: v1beta1
+  version: v1alpha3
   versions:
-    - name: v1beta1
+    - name: v1alpha3
       served: true
       storage: true
+    - name: v1alpha2
+      served: true
+      storage: false
+    - name: v1alpha1
+      served: true
+      storage: false
   names:
     plural: canaries
     singular: canary
     kind: Canary
+    categories:
+      - all
   scope: Namespaced
+  subresources:
+    status: {}
+  additionalPrinterColumns:
+    - name: Status
+      type: string
+      JSONPath: .status.phase
+    - name: Weight
+      type: string
+      JSONPath: .status.canaryWeight
+    - name: LastTransitionTime
+      type: string
+      JSONPath: .status.lastTransitionTime
   validation:
     openAPIV3Schema:
       properties:
         spec:
           required:
-            - targetKind
-            - virtualService
-            - primary
-            - canary
-            - canaryAnalysis
+          - targetRef
+          - service
+          - canaryAnalysis
           properties:
-            targetKind:
-              type: string
-            virtualService:
+            progressDeadlineSeconds:
+              type: number
+            targetRef:
+              type: object
+              required: ['apiVersion', 'kind', 'name']
               properties:
+                apiVersion:
+                  type: string
+                kind:
+                  type: string
                 name:
                   type: string
-            primary:
+            autoscalerRef:
+              anyOf:
+                - type: string
+                - type: object
+              required: ['apiVersion', 'kind', 'name']
               properties:
+                apiVersion:
+                  type: string
+                kind:
+                  type: string
                 name:
                   type: string
-                host:
-                  type: string
-            canary:
+            service:
+              type: object
+              required: ['port']
               properties:
-                name:
-                  type: string
-                host:
-                  type: string
+                port:
+                  type: number
             canaryAnalysis:
               properties:
+                interval:
+                  type: string
+                  pattern: "^[0-9]+(m|s)"
                 threshold:
                   type: number
                 maxWeight:
@@ -56,12 +89,27 @@ spec:
                   properties:
                     items:
                       type: object
+                      required: ['name', 'interval', 'threshold']
                       properties:
                         name:
                           type: string
                         interval:
                           type: string
-                          pattern: "^[0-9]+(m)"
+                          pattern: "^[0-9]+(m|s)"
                         threshold:
                           type: number
-
+                webhooks:
+                  type: array
+                  properties:
+                    items:
+                      type: object
+                      required: ['name', 'url', 'timeout']
+                      properties:
+                        name:
+                          type: string
+                        url:
+                          type: string
+                          format: url
+                        timeout:
+                          type: string
+                          pattern: "^[0-9]+(m|s)"

artifacts/flagger/deployment.yaml

@@ -22,7 +22,7 @@ spec:
       serviceAccountName: flagger
       containers:
       - name: flagger
-        image: stefanprodan/flagger:0.0.1
+        image: quay.io/stefanprodan/flagger:0.4.1
         imagePullPolicy: Always
         ports:
         - name: http
@@ -41,6 +41,7 @@ spec:
             - --timeout=2
             - --spider
             - http://localhost:8080/healthz
+          timeoutSeconds: 5
         readinessProbe:
           exec:
             command:
@@ -50,6 +51,7 @@ spec:
             - --timeout=2
             - --spider
             - http://localhost:8080/healthz
+          timeoutSeconds: 5
         resources:
           limits:
             memory: "512Mi"

artifacts/loadtester/deployment.yaml

@@ -0,0 +1,60 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: flagger-loadtester
+  labels:
+    app: flagger-loadtester
+spec:
+  selector:
+    matchLabels:
+      app: flagger-loadtester
+  template:
+    metadata:
+      labels:
+        app: flagger-loadtester
+      annotations:
+        prometheus.io/scrape: "true"
+    spec:
+      containers:
+        - name: loadtester
+          image: quay.io/stefanprodan/flagger-loadtester:0.1.0
+          imagePullPolicy: IfNotPresent
+          ports:
+            - name: http
+              containerPort: 8080
+          command:
+            - ./loadtester
+            - -port=8080
+            - -log-level=info
+            - -timeout=1h
+            - -log-cmd-output=true
+          livenessProbe:
+            exec:
+              command:
+                - wget
+                - --quiet
+                - --tries=1
+                - --timeout=4
+                - --spider
+                - http://localhost:8080/healthz
+            timeoutSeconds: 5
+          readinessProbe:
+            exec:
+              command:
+                - wget
+                - --quiet
+                - --tries=1
+                - --timeout=4
+                - --spider
+                - http://localhost:8080/healthz
+            timeoutSeconds: 5
+          resources:
+            limits:
+              memory: "512Mi"
+              cpu: "1000m"
+            requests:
+              memory: "32Mi"
+              cpu: "10m"
+          securityContext:
+            readOnlyRootFilesystem: true
+            runAsUser: 10001

artifacts/loadtester/service.yaml

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

artifacts/rollouts/podinfo.yaml

@@ -1,42 +0,0 @@
-# monitor events:  watch "kubectl -n test describe rollout/podinfo | sed -n 35,1000p"
-# run tester: kubectl run -n test tester --image=quay.io/stefanprodan/podinfo:1.2.1 -- ./podinfo --port=9898
-# generate latency: watch curl http://podinfo-canary:9898/delay/1
-# generate errors: watch curl http://podinfo-canary:9898/status/500
-# run load test: kubectl run -n test -it --rm --restart=Never hey --image=stefanprodan/loadtest -- sh
-# generate load: hey -z 2m -h2 -m POST -d '{test: 1}' -c 10 -q 5 http://podinfo:9898/api/echo
-apiVersion: flagger.app/v1beta1
-kind: Canary
-metadata:
-  name: podinfo
-  namespace: test
-spec:
-  targetKind: Deployment
-  virtualService:
-    name: podinfo
-  primary:
-    name: podinfo
-    host: podinfo
-  canary:
-    name: podinfo-canary
-    host: podinfo-canary
-  canaryAnalysis:
-    # max number of failed metric checks
-    # before rolling back the canary
-    threshold: 5
-    # max traffic percentage routed to canary
-    # percentage (0-100)
-    maxWeight: 50
-    # canary increment step
-    # percentage (0-100)
-    stepWeight: 10
-    metrics:
-    - name: istio_requests_total
-      # minimum req success rate (non 5xx responses)
-      # percentage (0-100)
-      threshold: 99
-      interval: 1m
-    - name: istio_request_duration_seconds_bucket
-      # maximum req duration P99
-      # milliseconds
-      threshold: 500
-      interval: 30s

artifacts/rollouts/podinfoc.yaml

@@ -1,36 +0,0 @@
-apiVersion: flagger.app/v1beta1
-kind: Canary
-metadata:
-  name: podinfoc
-  namespace: test
-spec:
-  targetKind: Deployment
-  virtualService:
-    name: podinfoc
-  primary:
-    name: podinfoc-primary
-    host: podinfoc-primary
-  canary:
-    name: podinfoc-canary
-    host: podinfoc-canary
-  canaryAnalysis:
-    # max number of failed metric checks
-    # before rolling back the canary
-    threshold: 10
-    # max traffic percentage routed to canary
-    # percentage (0-100)
-    maxWeight: 50
-    # canary increment step
-    # percentage (0-100)
-    stepWeight: 10
-    metrics:
-    - name: istio_requests_total
-      # minimum req success rate (non 5xx responses)
-      # percentage (0-100)
-      threshold: 99
-      interval: 1m
-    - name: istio_request_duration_seconds_bucket
-      # maximum req duration P99
-      # milliseconds
-      threshold: 500
-      interval: 30s

artifacts/routing/match.yaml

@@ -0,0 +1,34 @@
+apiVersion: networking.istio.io/v1alpha3
+kind: VirtualService
+metadata:
+  name: podinfo
+  namespace: test
+spec:
+  gateways:
+  - public-gateway.istio-system.svc.cluster.local
+  - mesh
+  hosts:
+  - podinfo.iowa.weavedx.com
+  - podinfo
+  http:
+  - match:
+    - headers:
+        user-agent:
+          regex: ^(?!.*Chrome)(?=.*\bSafari\b).*$
+    route:
+    - destination:
+        host: podinfo-primary
+        port:
+          number: 9898
+      weight: 0
+    - destination:
+        host: podinfo
+        port:
+          number: 9898
+      weight: 100
+  - route:
+    - destination:
+        host: podinfo-primary
+        port:
+          number: 9898
+      weight: 100

artifacts/routing/mirror.yaml

@@ -0,0 +1,25 @@
+apiVersion: networking.istio.io/v1alpha3
+kind: VirtualService
+metadata:
+  name: podinfo
+  namespace: test
+  labels:
+    app: podinfo
+spec:
+  gateways:
+  - public-gateway.istio-system.svc.cluster.local
+  - mesh
+  hosts:
+  - podinfo.iowa.weavedx.com
+  - podinfo
+  http:
+  - route:
+    - destination:
+        host: podinfo-primary
+        port:
+          number: 9898
+      weight: 100
+    mirror:
+      host: podinfo
+      port:
+        number: 9898

artifacts/routing/weight.yaml

@@ -0,0 +1,26 @@
+apiVersion: networking.istio.io/v1alpha3
+kind: VirtualService
+metadata:
+  name: podinfo
+  namespace: test
+  labels:
+    app: podinfo
+spec:
+  gateways:
+  - public-gateway.istio-system.svc.cluster.local
+  - mesh
+  hosts:
+  - podinfo.iowa.weavedx.com
+  - podinfo
+  http:
+  - route:
+    - destination:
+        host: podinfo-primary
+        port:
+          number: 9898
+      weight: 100
+    - destination:
+        host: podinfo
+        port:
+          number: 9898
+      weight: 0

artifacts/workloads/canary-deployment.yaml

@@ -1,10 +1,10 @@
 apiVersion: apps/v1
 kind: Deployment
 metadata:
-  name: podinfo-canary
+  name: podinfo
   namespace: test
   labels:
-    app: podinfo-canary
+    app: podinfo
 spec:
   replicas: 1
   strategy:
@@ -13,13 +13,13 @@ spec:
     type: RollingUpdate
   selector:
     matchLabels:
-      app: podinfo-canary
+      app: podinfo
   template:
     metadata:
       annotations:
         prometheus.io/scrape: "true"
       labels:
-        app: podinfo-canary
+        app: podinfo
     spec:
       containers:
       - name: podinfod

artifacts/workloads/canary-hpa.yaml

@@ -1,13 +1,13 @@
 apiVersion: autoscaling/v2beta1
 kind: HorizontalPodAutoscaler
 metadata:
-  name: podinfo-canary
+  name: podinfo
   namespace: test
 spec:
   scaleTargetRef:
     apiVersion: apps/v1
     kind: Deployment
-    name: podinfo-canary
+    name: podinfo
   minReplicas: 2
   maxReplicas: 3
   metrics:

artifacts/workloads/canary-service.yaml

@@ -1,14 +1,14 @@
 apiVersion: v1
 kind: Service
 metadata:
-  name: podinfo-canary
+  name: podinfo
   namespace: test
   labels:
-    app: podinfo-canary
+    app: podinfo
 spec:
   type: ClusterIP
   selector:
-    app: podinfo-canary
+    app: podinfo
   ports:
   - name: http
     port: 9898

artifacts/workloads/primary-deployment.yaml

@@ -1,10 +1,10 @@
 apiVersion: apps/v1
 kind: Deployment
 metadata:
-  name: podinfo
+  name: podinfo-primary
   namespace: test
   labels:
-    app: podinfo
+    app: podinfo-primary
 spec:
   replicas: 1
   strategy:
@@ -13,13 +13,13 @@ spec:
     type: RollingUpdate
   selector:
     matchLabels:
-      app: podinfo
+      app: podinfo-primary
   template:
     metadata:
       annotations:
         prometheus.io/scrape: "true"
       labels:
-        app: podinfo
+        app: podinfo-primary
     spec:
       containers:
       - name: podinfod

artifacts/workloads/primary-hpa.yaml

@@ -1,13 +1,13 @@
 apiVersion: autoscaling/v2beta1
 kind: HorizontalPodAutoscaler
 metadata:
-  name: podinfo
+  name: podinfo-primary
   namespace: test
 spec:
   scaleTargetRef:
     apiVersion: apps/v1
     kind: Deployment
-    name: podinfo
+    name: podinfo-primary
   minReplicas: 2
   maxReplicas: 4
   metrics:

artifacts/workloads/primary-service.yaml

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

artifacts/workloads/virtual-service.yaml

@@ -8,18 +8,19 @@ metadata:
 spec:
   gateways:
   - public-gateway.istio-system.svc.cluster.local
+  - mesh
   hosts:
-  - app.istio.weavedx.com
+  - podinfo.istio.weavedx.com
   - podinfo
   http:
   - route:
     - destination:
-        host: podinfo
+        host: podinfo-primary
         port:
           number: 9898
       weight: 100
     - destination:
-        host: podinfo-canary
+        host: podinfo
         port:
           number: 9898
       weight: 0

charts/flagger/Chart.yaml

@@ -1,6 +1,19 @@
 apiVersion: v1
 name: flagger
-version: 0.0.1
-appVersion: 0.0.1
+version: 0.4.1
+appVersion: 0.4.1
+kubeVersion: ">=1.11.0-0"
+engine: gotpl
 description: Flagger is a Kubernetes operator that automates the promotion of canary deployments using Istio routing for traffic shifting and Prometheus metrics for canary analysis.
-home: https://github.com/stefanprodan/flagger
+home: https://docs.flagger.app
+icon: https://raw.githubusercontent.com/stefanprodan/flagger/master/docs/logo/flagger-icon.png
+sources:
+- https://github.com/stefanprodan/flagger
+maintainers:
+- name: stefanprodan
+  url: https://github.com/stefanprodan
+  email: stefanprodan@users.noreply.github.com
+keywords:
+- canary
+- istio
+- gitops

charts/flagger/README.md

@@ -1,14 +1,29 @@
 # Flagger
 
-Flagger is a Kubernetes operator that automates the promotion of canary deployments
-using Istio routing for traffic shifting and Prometheus metrics for canary analysis.
+[Flagger](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. 
+Flagger implements a control loop that gradually shifts traffic to the canary while measuring key performance indicators
+like HTTP requests success rate, requests average duration and pods health.
+Based on the KPIs analysis a canary is promoted or aborted and the analysis result is published to Slack.
+
+## Prerequisites
+
+* Kubernetes >= 1.11
+* Istio >= 1.0
+* Prometheus >= 2.6
 
 ## Installing the Chart
 
+Add Flagger Helm repository:
+
+```console
+helm repo add flagger https://flagger.app
+```
+
 To install the chart with the release name `flagger`:
 
 ```console
-$ helm upgrade --install flagger ./charts/flagger --namespace=istio-system
+$ helm install --name flagger --namespace istio-system flagger/flagger
 ```
 
 The command deploys Flagger on the Kubernetes cluster in the istio-system namespace.
@@ -30,9 +45,15 @@ The following tables lists the configurable parameters of the Flagger chart and
 
 Parameter | Description | Default
 --- | --- | ---
-`image.repository` | image repository | `stefanprodan/flagger`
+`image.repository` | image repository | `quay.io/stefanprodan/flagger`
 `image.tag` | image tag | `<VERSION>`
 `image.pullPolicy` | image pull policy | `IfNotPresent`
+`metricsServer` | Prometheus URL | `http://prometheus.istio-system:9090`
+`slack.url` | Slack incoming webhook | None
+`slack.channel` | Slack channel | None
+`slack.user` | Slack username | `flagger`
+`rbac.create` | if `true`, create and use RBAC resources | `true`
+`crd.create` | if `true`, create Flagger's CRDs | `true`
 `resources.requests/cpu` | pod CPU request | `10m`
 `resources.requests/memory` | pod memory request | `32Mi`
 `resources.limits/cpu` | pod CPU limit | `1000m`
@@ -44,19 +65,20 @@ Parameter | Description | Default
 Specify each parameter using the `--set key=value[,key=value]` argument to `helm upgrade`. For example,
 
 ```console
-$ helm upgrade --install flagger ./charts/flagger \
-  --namespace=istio-system \
-  --set=image.tag=0.0.2
+$ helm upgrade -i flagger flagger/flagger \
+  --namespace istio-system \
+  --set slack.url=https://hooks.slack.com/services/YOUR/SLACK/WEBHOOK \
+  --set slack.channel=general
 ```
 
 Alternatively, a YAML file that specifies the values for the above parameters can be provided while installing the chart. For example,
 
 ```console
-$ helm upgrade --install flagger ./charts/flagger \
-  --namespace=istio-system \
+$ helm upgrade -i flagger flagger/flagger \
+  --namespace istio-system \
   -f values.yaml
 ```
 
 > **Tip**: You can use the default [values.yaml](values.yaml)
-```
+
 

charts/flagger/templates/_helpers.tpl

@@ -1,4 +1,10 @@
-{{/* vim: set filetype=mustache: */}}
+{{/*
+Create chart name and version as used by the chart label.
+*/}}
+{{- define "flagger.chart" -}}
+{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" -}}
+{{- end -}}
+
 {{/*
 Expand the name of the chart.
 */}}
@@ -25,8 +31,12 @@ If release name contains chart name it will be used as a full name.
 {{- end -}}
 
 {{/*
-Create chart name and version as used by the chart label.
+Create the name of the service account to use
 */}}
-{{- define "flagger.chart" -}}
-{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" -}}
+{{- define "flagger.serviceAccountName" -}}
+{{- if .Values.serviceAccount.create -}}
+    {{ default (include "flagger.fullname" .) .Values.serviceAccount.name }}
+{{- else -}}
+    {{ default "default" .Values.serviceAccount.name }}
 {{- end -}}
+{{- end -}}

charts/flagger/templates/account.yaml

@@ -1,9 +1,11 @@
+{{- if .Values.serviceAccount.create }}
 apiVersion: v1
 kind: ServiceAccount
 metadata:
-  name: {{ template "flagger.name" . }}
+  name: {{ template "flagger.serviceAccountName" . }}
   labels:
-    app: {{ template "flagger.name" . }}
-    chart: {{ template "flagger.chart" . }}
-    release: {{ .Release.Name }}
-    heritage: {{ .Release.Service }}
+    helm.sh/chart: {{ template "flagger.chart" . }}
+    app.kubernetes.io/name: {{ template "flagger.name" . }}
+    app.kubernetes.io/managed-by: {{ .Release.Service }}
+    app.kubernetes.io/instance: {{ .Release.Name }}
+{{- end }}

charts/flagger/templates/crd.yaml

@@ -5,47 +5,80 @@ metadata:
   name: canaries.flagger.app
 spec:
   group: flagger.app
-  version: v1beta1
+  version: v1alpha3
   versions:
-    - name: v1beta1
+    - name: v1alpha3
       served: true
       storage: true
+    - name: v1alpha2
+      served: true
+      storage: false
+    - name: v1alpha1
+      served: true
+      storage: false
   names:
     plural: canaries
     singular: canary
     kind: Canary
+    categories:
+      - all
   scope: Namespaced
+  subresources:
+    status: {}
+  additionalPrinterColumns:
+    - name: Status
+      type: string
+      JSONPath: .status.phase
+    - name: Weight
+      type: string
+      JSONPath: .status.canaryWeight
+    - name: LastTransitionTime
+      type: string
+      JSONPath: .status.lastTransitionTime
   validation:
     openAPIV3Schema:
       properties:
         spec:
           required:
-            - targetKind
-            - virtualService
-            - primary
-            - canary
+            - targetRef
+            - service
             - canaryAnalysis
           properties:
-            targetKind:
-              type: string
-            virtualService:
+            progressDeadlineSeconds:
+              type: number
+            targetRef:
+              type: object
+              required: ['apiVersion', 'kind', 'name']
               properties:
+                apiVersion:
+                  type: string
+                kind:
+                  type: string
                 name:
                   type: string
-            primary:
+            autoscalerRef:
+              anyOf:
+                - type: string
+                - type: object
+              required: ['apiVersion', 'kind', 'name']
               properties:
+                apiVersion:
+                  type: string
+                kind:
+                  type: string
                 name:
                   type: string
-                host:
-                  type: string
-            canary:
+            service:
+              type: object
+              required: ['port']
               properties:
-                name:
-                  type: string
-                host:
-                  type: string
+                port:
+                  type: number
             canaryAnalysis:
               properties:
+                interval:
+                  type: string
+                  pattern: "^[0-9]+(m|s)"
                 threshold:
                   type: number
                 maxWeight:
@@ -57,12 +90,28 @@ spec:
                   properties:
                     items:
                       type: object
+                      required: ['name', 'interval', 'threshold']
                       properties:
                         name:
                           type: string
                         interval:
                           type: string
-                          pattern: "^[0-9]+(m)"
+                          pattern: "^[0-9]+(m|s)"
                         threshold:
                           type: number
+                webhooks:
+                  type: array
+                  properties:
+                    items:
+                      type: object
+                      required: ['name', 'url', 'timeout']
+                      properties:
+                        name:
+                          type: string
+                        url:
+                          type: string
+                          format: url
+                        timeout:
+                          type: string
+                          pattern: "^[0-9]+(m|s)"
 {{- end }}

charts/flagger/templates/deployment.yaml

@@ -3,25 +3,25 @@ kind: Deployment
 metadata:
   name: {{ include "flagger.fullname" . }}
   labels:
-    app: {{ include "flagger.name" . }}
-    chart: {{ include "flagger.chart" . }}
-    release: {{ .Release.Name }}
-    heritage: {{ .Release.Service }}
+    helm.sh/chart: {{ template "flagger.chart" . }}
+    app.kubernetes.io/name: {{ template "flagger.name" . }}
+    app.kubernetes.io/managed-by: {{ .Release.Service }}
+    app.kubernetes.io/instance: {{ .Release.Name }}
 spec:
   replicas: 1
   strategy:
     type: Recreate
   selector:
     matchLabels:
-      app: {{ include "flagger.name" . }}
-      release: {{ .Release.Name }}
+      app.kubernetes.io/name: {{ template "flagger.name" . }}
+      app.kubernetes.io/instance: {{ .Release.Name }}
   template:
     metadata:
       labels:
-        app: {{ include "flagger.name" . }}
-        release: {{ .Release.Name }}
+        app.kubernetes.io/name: {{ template "flagger.name" . }}
+        app.kubernetes.io/instance: {{ .Release.Name }}
     spec:
-      serviceAccountName: flagger
+      serviceAccountName: {{ template "flagger.serviceAccountName" . }}
       containers:
         - name: flagger
           securityContext:
@@ -35,26 +35,32 @@ spec:
           command:
           - ./flagger
           - -log-level=info
-          - -control-loop-interval={{ .Values.controlLoopInterval }}
           - -metrics-server={{ .Values.metricsServer }}
+          {{- if .Values.slack.url }}
+          - -slack-url={{ .Values.slack.url }}
+          - -slack-user={{ .Values.slack.user }}
+          - -slack-channel={{ .Values.slack.channel }}
+          {{- end }}
           livenessProbe:
             exec:
               command:
               - wget
               - --quiet
               - --tries=1
-              - --timeout=2
+              - --timeout=4
               - --spider
               - http://localhost:8080/healthz
+            timeoutSeconds: 5
           readinessProbe:
             exec:
               command:
               - wget
               - --quiet
               - --tries=1
-              - --timeout=2
+              - --timeout=4
               - --spider
               - http://localhost:8080/healthz
+            timeoutSeconds: 5
           resources:
 {{ toYaml .Values.resources | indent 12 }}
     {{- with .Values.nodeSelector }}

charts/flagger/templates/rbac.yaml

@@ -4,10 +4,10 @@ kind: ClusterRole
 metadata:
   name: {{ template "flagger.fullname" . }}
   labels:
-    app: {{ template "flagger.name" . }}
-    chart: {{ template "flagger.chart" . }}
-    release: {{ .Release.Name }}
-    heritage: {{ .Release.Service }}
+    helm.sh/chart: {{ template "flagger.chart" . }}
+    app.kubernetes.io/name: {{ template "flagger.name" . }}
+    app.kubernetes.io/managed-by: {{ .Release.Service }}
+    app.kubernetes.io/instance: {{ .Release.Name }}
 rules:
 - apiGroups: ['*']
   resources: ['*']
@@ -20,16 +20,16 @@ kind: ClusterRoleBinding
 metadata:
   name: {{ template "flagger.fullname" . }}
   labels:
-    app: {{ template "flagger.name" . }}
-    chart: {{ template "flagger.chart" . }}
-    release: {{ .Release.Name }}
-    heritage: {{ .Release.Service }}
+    helm.sh/chart: {{ template "flagger.chart" . }}
+    app.kubernetes.io/name: {{ template "flagger.name" . }}
+    app.kubernetes.io/managed-by: {{ .Release.Service }}
+    app.kubernetes.io/instance: {{ .Release.Name }}
 roleRef:
   apiGroup: rbac.authorization.k8s.io
   kind: ClusterRole
   name: {{ template "flagger.fullname" . }}
 subjects:
-- name: {{ template "flagger.name" . }}
-  namespace: {{ .Release.Namespace | quote }}
+- name: {{ template "flagger.serviceAccountName" . }}
+  namespace: {{ .Release.Namespace }}
   kind: ServiceAccount
 {{- end }}

charts/flagger/values.yaml

@@ -1,17 +1,30 @@
 # Default values for flagger.
 
 image:
-  repository: stefanprodan/flagger
-  tag: 0.0.1
+  repository: quay.io/stefanprodan/flagger
+  tag: 0.4.1
   pullPolicy: IfNotPresent
 
-controlLoopInterval: "10s"
 metricsServer: "http://prometheus.istio-system.svc.cluster.local:9090"
 
-crd:
+slack:
+  user: flagger
+  channel:
+  # incoming webhook https://api.slack.com/incoming-webhooks
+  url:
+
+serviceAccount:
+  # serviceAccount.create: Whether to create a service account or not
   create: true
+  # serviceAccount.name: The name of the service account to create or use
+  name: ""
 
 rbac:
+  # rbac.create: `true` if rbac resources should be created
+  create: true
+
+crd:
+  # crd.create: `true` if custom resource definitions should be created
   create: true
 
 nameOverride: ""

charts/grafana/Chart.yaml

@@ -1,6 +1,13 @@
 apiVersion: v1
 name: grafana
-version: 5.2.4
-appVersion: 5.2.0
-description: A Helm chart for monitoring progressive deployments powered by Istio and Flagger
-home: https://github.com/stefanprodan/flagger
+version: 0.1.0
+appVersion: 5.4.2
+description: Grafana dashboards for monitoring Flagger canary deployments
+icon: https://raw.githubusercontent.com/stefanprodan/flagger/master/docs/logo/flagger-icon.png
+home: https://flagger.app
+sources:
+- https://github.com/stefanprodan/flagger
+maintainers:
+- name: stefanprodan
+  url: https://github.com/stefanprodan
+  email: stefanprodan@users.noreply.github.com

charts/grafana/README.md

@@ -1,16 +1,31 @@
-# Weave Cloud Grafana
+# Flagger Grafana
 
-Grafana v5 with Kubernetes dashboards and Prometheus and Weave Cloud data sources.
+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)
+
+## Prerequisites
+
+* Kubernetes >= 1.11
+* Istio >= 1.0
+* Prometheus >= 2.6
 
 ## Installing the Chart
 
-To install the chart with the release name `my-release`:
+Add Flagger Helm repository:
 
 ```console
-$ helm install stable/grafana --name my-release \
-    --set service.type=NodePort \
-    --set token=WEAVE-TOKEN \
-    --set password=admin
+helm repo add flagger https://flagger.app
+```
+
+To install the chart with the release name `flagger-grafana`:
+
+```console
+helm upgrade -i flagger-grafana flagger/grafana \
+--namespace=istio-system \
+--set url=http://prometheus:9090 \
+--set user=admin \
+--set password=admin
 ```
 
 The command deploys Grafana on the Kubernetes cluster in the default namespace.
@@ -18,10 +33,10 @@ The [configuration](#configuration) section lists the parameters that can be con
 
 ## Uninstalling the Chart
 
-To uninstall/delete the `my-release` deployment:
+To uninstall/delete the `flagger-grafana` deployment:
 
 ```console
-$ helm delete --purge my-release
+helm delete --purge flagger-grafana
 ```
 
 The command removes all the Kubernetes components associated with the chart and deletes the release.
@@ -34,32 +49,31 @@ Parameter | Description | Default
 --- | --- | ---
 `image.repository` | Image repository | `grafana/grafana`
 `image.pullPolicy` | Image pull policy | `IfNotPresent`
-`image.tag` | Image tag | `5.0.1`
+`image.tag` | Image tag | `<VERSION>`
 `replicaCount` | desired number of pods | `1`
 `resources` | pod resources | `none`
 `tolerations` | List of node taints to tolerate | `[]`
 `affinity` | node/pod affinities | `node`
 `nodeSelector` | node labels for pod assignment | `{}`
-`service.type` | type of service | `LoadBalancer`
-`url` | Prometheus URL, used when Weave token is empty | `http://prometheus:9090`
+`service.type` | type of service | `ClusterIP`
+`url` | Prometheus URL, used when Weave Cloud token is empty | `http://prometheus:9090`
 `token` | Weave Cloud token | `none`
 `user` | Grafana admin username | `admin`
-`password` | Grafana admin password | `none`
+`password` | Grafana admin password | `admin`
 
 Specify each parameter using the `--set key=value[,key=value]` argument to `helm install`. For example,
 
 ```console
-$ helm install stable/grafana --name my-release \
-  --set=token=WEAVE-TOKEN \
-  --set password=admin
+helm install flagger/grafana --name flagger-grafana \
+--set token=WEAVE-CLOUD-TOKEN
 ```
 
 Alternatively, a YAML file that specifies the values for the above parameters can be provided while installing the chart. For example,
 
 ```console
-$ helm install stable/grafana --name my-release -f values.yaml
+helm install flagger/grafana --name flagger-grafana -f values.yaml
 ```
 
 > **Tip**: You can use the default [values.yaml](values.yaml)
-```
+
 

charts/grafana/dashboards/canary.json

@@ -21,7 +21,7 @@
   "links": [],
   "panels": [
     {
-      "content": "<div class=\"dashboard-header text-center\">\n<span>RED: $primary.$namespace</span>\n</div>",
+      "content": "<div class=\"dashboard-header text-center\">\n<span>RED: $canary.$namespace</span>\n</div>",
       "gridPos": {
         "h": 3,
         "w": 24,
@@ -568,7 +568,7 @@
       ]
     },
     {
-      "content": "<div class=\"dashboard-header text-center\">\n<span>USE: $primary.$namespace</span>\n</div>",
+      "content": "<div class=\"dashboard-header text-center\">\n<span>USE: $canary.$namespace</span>\n</div>",
       "gridPos": {
         "h": 3,
         "w": 24,
@@ -712,7 +712,7 @@
       "targets": [
         {
           "$$hashKey": "object:1685",
-          "expr": "sum(rate(container_cpu_usage_seconds_total{cpu=\"total\",namespace=\"$namespace\",pod_name=~\"$canary.*\", container_name!~\"POD|istio-proxy\"}[1m])) by (pod_name)",
+          "expr": "sum(rate(container_cpu_usage_seconds_total{cpu=\"total\",namespace=\"$namespace\",pod_name=~\"$canary.*\", pod_name!~\"$primary.*\", container_name!~\"POD|istio-proxy\"}[1m])) by (pod_name)",
           "format": "time_series",
           "hide": false,
           "intervalFactor": 1,
@@ -890,7 +890,7 @@
       "targets": [
         {
           "$$hashKey": "object:1685",
-          "expr": "sum(container_memory_working_set_bytes{namespace=\"$namespace\",pod_name=~\"$canary.*\", container_name!~\"POD|istio-proxy\"}) by (pod_name)",
+          "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,
           "interval": "",
@@ -1098,7 +1098,7 @@
       "targets": [
         {
           "$$hashKey": "object:2598",
-          "expr": "sum(rate (container_network_receive_bytes_total{namespace=\"$namespace\",pod_name=~\"$canary.*\"}[1m])) ",
+          "expr": "sum(rate (container_network_receive_bytes_total{namespace=\"$namespace\",pod_name=~\"$canary.*\",pod_name!~\"$primary.*\"}[1m])) ",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "received",
@@ -1106,7 +1106,7 @@
         },
         {
           "$$hashKey": "object:3245",
-          "expr": "-sum (rate (container_network_transmit_bytes_total{namespace=\"$namespace\",pod_name=~\"$canary.*\"}[1m]))",
+          "expr": "-sum (rate (container_network_transmit_bytes_total{namespace=\"$namespace\",pod_name=~\"$canary.*\",pod_name!~\"$primary.*\"}[1m]))",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "transmited",
@@ -1153,7 +1153,7 @@
       ]
     },
     {
-      "content": "<div class=\"dashboard-header text-center\">\n<span>IN/OUTBOUND: $primary.$namespace</span>\n</div>",
+      "content": "<div class=\"dashboard-header text-center\">\n<span>IN/OUTBOUND: $canary.$namespace</span>\n</div>",
       "gridPos": {
         "h": 3,
         "w": 24,
@@ -1653,7 +1653,7 @@
     ]
   },
   "timezone": "",
-  "title": "Flagger",
+  "title": "Canary analysis",
   "uid": "RdykD7tiz",
   "version": 2
 }

charts/grafana/values.yaml

@@ -6,7 +6,7 @@ replicaCount: 1
 
 image:
   repository: grafana/grafana
-  tag: 5.2.4
+  tag: 5.4.2
   pullPolicy: IfNotPresent
 
 service:

charts/loadtester/.helmignore

@@ -19,3 +19,4 @@
 .project
 .idea/
 *.tmproj
+.vscode/

charts/loadtester/Chart.yaml

@@ -0,0 +1,20 @@
+apiVersion: v1
+name: loadtester
+version: 0.1.0
+appVersion: 0.1.0
+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
+sources:
+  - https://github.com/stefanprodan/flagger
+maintainers:
+  - name: stefanprodan
+    url: https://github.com/stefanprodan
+    email: stefanprodan@users.noreply.github.com
+keywords:
+  - canary
+  - istio
+  - gitops
+  - load testing

charts/loadtester/README.md

@@ -0,0 +1,78 @@
+# Flagger load testing service
+
+[Flagger's](https://github.com/stefanprodan/flagger) load testing service is based on 
+[rakyll/hey](https://github.com/rakyll/hey) 
+and can be used to generates traffic during canary analysis when configured as a webhook.
+
+## Prerequisites
+
+* Kubernetes >= 1.11
+* Istio >= 1.0
+
+## Installing the Chart
+
+Add Flagger Helm repository:
+
+```console
+helm repo add flagger https://flagger.app
+```
+
+To install the chart with the release name `flagger-loadtester`:
+
+```console
+helm upgrade -i flagger-loadtester flagger/loadtester
+```
+
+The command deploys Grafana on the Kubernetes cluster in the default namespace.
+
+> **Tip**: Note that the namespace where you deploy the load tester should have the Istio sidecar injection enabled
+
+The [configuration](#configuration) section lists the parameters that can be configured during installation.
+
+## Uninstalling the Chart
+
+To uninstall/delete the `flagger-loadtester` deployment:
+
+```console
+helm delete --purge flagger-loadtester
+```
+
+The command removes all the Kubernetes components associated with the chart and deletes the release.
+
+## Configuration
+
+The following tables lists the configurable parameters of the load tester chart and their default values.
+
+Parameter | Description | Default
+--- | --- | ---
+`image.repository` | Image repository | `quay.io/stefanprodan/flagger-loadtester`
+`image.pullPolicy` | Image pull policy | `IfNotPresent`
+`image.tag` | Image tag | `<VERSION>`
+`replicaCount` | desired number of pods | `1`
+`resources.requests.cpu` | CPU requests | `10m`
+`resources.requests.memory` | memory requests | `64Mi`
+`tolerations` | List of node taints to tolerate | `[]`
+`affinity` | node/pod affinities | `node`
+`nodeSelector` | node labels for pod assignment | `{}`
+`service.type` | type of service | `ClusterIP`
+`service.port` | ClusterIP port | `80`
+`cmd.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`
+
+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
+```
+
+Alternatively, a YAML file that specifies the values for the above parameters can be provided while installing the chart. For example,
+
+```console
+helm install flagger/loadtester --name flagger-loadtester -f values.yaml
+```
+
+> **Tip**: You can use the default [values.yaml](values.yaml)
+
+

charts/loadtester/templates/NOTES.txt

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

charts/loadtester/templates/_helpers.tpl

@@ -2,35 +2,31 @@
 {{/*
 Expand the name of the chart.
 */}}
-{{- define "podinfo-flagger.name" -}}
+{{- define "loadtester.name" -}}
 {{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" -}}
 {{- end -}}
 
 {{/*
 Create a default fully qualified app name.
 We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec).
-The release name is used as a full name.
+If release name contains chart name it will be used as a full name.
 */}}
-{{- define "podinfo-flagger.fullname" -}}
+{{- define "loadtester.fullname" -}}
 {{- if .Values.fullnameOverride -}}
 {{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" -}}
 {{- else -}}
+{{- $name := default .Chart.Name .Values.nameOverride -}}
+{{- if contains $name .Release.Name -}}
 {{- .Release.Name | trunc 63 | trimSuffix "-" -}}
+{{- else -}}
+{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" -}}
 {{- end -}}
 {{- end -}}
-
-{{- define "podinfo-flagger.primary" -}}
-{{- printf "%s-%s" .Release.Name "primary" | trunc 63 | trimSuffix "-" -}}
-{{- end -}}
-
-{{- define "podinfo-flagger.canary" -}}
-{{- printf "%s-%s" .Release.Name "canary" | trunc 63 | trimSuffix "-" -}}
 {{- end -}}
 
 {{/*
 Create chart name and version as used by the chart label.
 */}}
-{{- define "podinfo-flagger.chart" -}}
+{{- define "loadtester.chart" -}}
 {{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" -}}
 {{- end -}}
-

charts/loadtester/templates/deployment.yaml

@@ -0,0 +1,66 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: {{ include "loadtester.fullname" . }}
+  labels:
+    app.kubernetes.io/name: {{ include "loadtester.name" . }}
+    helm.sh/chart: {{ include "loadtester.chart" . }}
+    app.kubernetes.io/instance: {{ .Release.Name }}
+    app.kubernetes.io/managed-by: {{ .Release.Service }}
+spec:
+  replicas: {{ .Values.replicaCount }}
+  selector:
+    matchLabels:
+      app: {{ include "loadtester.name" . }}
+  template:
+    metadata:
+      labels:
+        app: {{ include "loadtester.name" . }}
+    spec:
+      containers:
+        - name: {{ .Chart.Name }}
+          image: "{{ .Values.image.repository }}:{{ .Values.image.tag }}"
+          imagePullPolicy: {{ .Values.image.pullPolicy }}
+          ports:
+            - name: http
+              containerPort: 8080
+          command:
+            - ./loadtester
+            - -port=8080
+            - -log-level={{ .Values.logLevel }}
+            - -timeout={{ .Values.cmd.timeout }}
+            - -log-cmd-output={{ .Values.cmd.logOutput }}
+          livenessProbe:
+            exec:
+              command:
+                - wget
+                - --quiet
+                - --tries=1
+                - --timeout=4
+                - --spider
+                - http://localhost:8080/healthz
+            timeoutSeconds: 5
+          readinessProbe:
+            exec:
+              command:
+                - wget
+                - --quiet
+                - --tries=1
+                - --timeout=4
+                - --spider
+                - http://localhost:8080/healthz
+            timeoutSeconds: 5
+          resources:
+            {{- toYaml .Values.resources | nindent 12 }}
+      {{- with .Values.nodeSelector }}
+      nodeSelector:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+    {{- with .Values.affinity }}
+      affinity:
+        {{- toYaml . | nindent 8 }}
+    {{- end }}
+    {{- with .Values.tolerations }}
+      tolerations:
+        {{- toYaml . | nindent 8 }}
+    {{- end }}

charts/loadtester/templates/service.yaml

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

charts/loadtester/values.yaml

@@ -0,0 +1,29 @@
+replicaCount: 1
+
+image:
+  repository: quay.io/stefanprodan/flagger-loadtester
+  tag: 0.1.0
+  pullPolicy: IfNotPresent
+
+logLevel: info
+cmd:
+  logOutput: true
+  timeout: 1h
+
+nameOverride: ""
+fullnameOverride: ""
+
+service:
+  type: ClusterIP
+  port: 80
+
+resources:
+  requests:
+    cpu: 10m
+    memory: 64Mi
+
+nodeSelector: {}
+
+tolerations: []
+
+affinity: {}

charts/podinfo-flagger/Chart.yaml

@@ -1,12 +0,0 @@
-apiVersion: v1
-version: 2.0.0
-appVersion: 1.2.1
-engine: gotpl
-name: podinfo-flagger
-description: Podinfo Helm chart for Flagger progressive delivery
-home: https://github.com/stefanprodan/k8s-podinfo
-maintainers:
-- email: stefanprodan@users.noreply.github.com
-  name: stefanprodan
-sources:
-- https://github.com/stefanprodan/flagger

charts/podinfo-flagger/README.md

@@ -1,56 +0,0 @@
-# Podinfo Istio
-
-Podinfo is a tiny web application made with Go 
-that showcases best practices of running microservices in Kubernetes.
-
-## Installing the Chart
-
-Create an Istio enabled namespace:
-
-```console
-kubectl create namespace test
-kubectl label namespace test istio-injection=enabled
-```
-
-Create an Istio Gateway in the `istio-system` namespace named `public-gateway`:
-
-```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
-```
-
-Create the `frontend` release by specifying the external domain name:
-
-```console
-helm upgrade frontend -i ./charts/podinfo-flagger \
-  --namespace=test \
-  --set gateway.enabled=true \
-  --set gateway.host=podinfo.example.com 
-```
-
-

charts/podinfo-flagger/templates/NOTES.txt

@@ -1 +0,0 @@
- {{ template "podinfo-flagger.fullname" . }} has been deployed successfully!

charts/podinfo-flagger/templates/canary-deployment.yaml

@@ -1,63 +0,0 @@
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: {{ template "podinfo-flagger.canary" . }}
-  labels:
-    app: {{ template "podinfo-flagger.fullname" . }}
-    chart: {{ template "podinfo-flagger.chart" . }}
-    release: {{ .Release.Name }}
-    heritage: {{ .Release.Service }}
-spec:
-  strategy:
-    type: RollingUpdate
-    rollingUpdate:
-      maxUnavailable: 0
-  selector:
-    matchLabels:
-      app: {{ template "podinfo-flagger.canary" . }}
-  template:
-    metadata:
-      labels:
-        app: {{ template "podinfo-flagger.canary" . }}
-      annotations:
-        prometheus.io/scrape: "true"
-    spec:
-      terminationGracePeriodSeconds: 30
-      containers:
-        - name: podinfod
-          image: "{{ .Values.image.repository }}:{{ .Values.image.tag }}"
-          imagePullPolicy: {{ .Values.imagePullPolicy }}
-          command:
-            - ./podinfo
-            - --port={{ .Values.containerPort }}
-            - --level={{ .Values.logLevel }}
-          env:
-          - name: PODINFO_UI_COLOR
-            value: green
-          ports:
-            - name: http
-              containerPort: {{ .Values.containerPort }}
-              protocol: TCP
-          livenessProbe:
-            exec:
-              command:
-              - podcli
-              - check
-              - http
-              - localhost:{{ .Values.containerPort }}/healthz
-          readinessProbe:
-            exec:
-              command:
-              - podcli
-              - check
-              - http
-              - localhost:{{ .Values.containerPort }}/readyz
-            periodSeconds: 3
-          volumeMounts:
-          - name: data
-            mountPath: /data
-          resources:
-{{ toYaml .Values.resources | indent 12 }}
-      volumes:
-      - name: data
-        emptyDir: {}

charts/podinfo-flagger/templates/canary-hpa.yaml

@@ -1,21 +0,0 @@
-apiVersion: autoscaling/v2beta1
-kind: HorizontalPodAutoscaler
-metadata:
-  name: {{ template "podinfo-flagger.canary" . }}
-  labels:
-    app: {{ template "podinfo-flagger.fullname" . }}
-    chart: {{ template "podinfo-flagger.chart" . }}
-    release: {{ .Release.Name }}
-    heritage: {{ .Release.Service }}
-spec:
-  scaleTargetRef:
-    apiVersion: apps/v1
-    kind: Deployment
-    name: {{ template "podinfo-flagger.canary" . }}
-  minReplicas: {{ .Values.hpa.minReplicas }}
-  maxReplicas: {{ .Values.hpa.maxReplicas }}
-  metrics:
-  - type: Resource
-    resource:
-      name: cpu
-      targetAverageUtilization: {{ .Values.hpa.targetAverageUtilization }}

charts/podinfo-flagger/templates/canary-service.yaml

@@ -1,18 +0,0 @@
-apiVersion: v1
-kind: Service
-metadata:
-  name: {{ template "podinfo-flagger.canary" . }}
-  labels:
-    app: {{ template "podinfo-flagger.fullname" . }}
-    chart: {{ template "podinfo-flagger.chart" . }}
-    release: {{ .Release.Name }}
-    heritage: {{ .Release.Service }}
-spec:
-  type: ClusterIP
-  ports:
-    - port: {{ .Values.containerPort }}
-      targetPort: http
-      protocol: TCP
-      name: http
-  selector:
-    app: {{ template "podinfo-flagger.canary" . }}

charts/podinfo-flagger/templates/primary-deployment.yaml

@@ -1,63 +0,0 @@
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: {{ template "podinfo-flagger.primary" . }}
-  labels:
-    app: {{ template "podinfo-flagger.fullname" . }}
-    chart: {{ template "podinfo-flagger.chart" . }}
-    release: {{ .Release.Name }}
-    heritage: {{ .Release.Service }}
-spec:
-  strategy:
-    type: RollingUpdate
-    rollingUpdate:
-      maxUnavailable: 0
-  selector:
-    matchLabels:
-      app: {{ template "podinfo-flagger.primary" . }}
-  template:
-    metadata:
-      labels:
-        app: {{ template "podinfo-flagger.primary" . }}
-      annotations:
-        prometheus.io/scrape: "true"
-    spec:
-      terminationGracePeriodSeconds: 30
-      containers:
-        - name: podinfod
-          image: "quay.io/stefanprodan/podinfo:1.1.1"
-          imagePullPolicy: {{ .Values.imagePullPolicy }}
-          command:
-            - ./podinfo
-            - --port={{ .Values.containerPort }}
-            - --level={{ .Values.logLevel }}
-          env:
-          - name: PODINFO_UI_COLOR
-            value: blue
-          ports:
-            - name: http
-              containerPort: {{ .Values.containerPort }}
-              protocol: TCP
-          livenessProbe:
-            exec:
-              command:
-              - podcli
-              - check
-              - http
-              - localhost:{{ .Values.containerPort }}/healthz
-          readinessProbe:
-            exec:
-              command:
-              - podcli
-              - check
-              - http
-              - localhost:{{ .Values.containerPort }}/readyz
-            periodSeconds: 3
-          volumeMounts:
-          - name: data
-            mountPath: /data
-          resources:
-{{ toYaml .Values.resources | indent 12 }}
-      volumes:
-      - name: data
-        emptyDir: {}

charts/podinfo-flagger/templates/primary-hpa.yaml

@@ -1,21 +0,0 @@
-apiVersion: autoscaling/v2beta1
-kind: HorizontalPodAutoscaler
-metadata:
-  name: {{ template "podinfo-flagger.primary" . }}
-  labels:
-    app: {{ template "podinfo-flagger.fullname" . }}
-    chart: {{ template "podinfo-flagger.chart" . }}
-    release: {{ .Release.Name }}
-    heritage: {{ .Release.Service }}
-spec:
-  scaleTargetRef:
-    apiVersion: apps/v1
-    kind: Deployment
-    name: {{ template "podinfo-flagger.primary" . }}
-  minReplicas: {{ .Values.hpa.minReplicas }}
-  maxReplicas: {{ .Values.hpa.maxReplicas }}
-  metrics:
-  - type: Resource
-    resource:
-      name: cpu
-      targetAverageUtilization: {{ .Values.hpa.targetAverageUtilization }}

charts/podinfo-flagger/templates/primary-service.yaml

@@ -1,18 +0,0 @@
-apiVersion: v1
-kind: Service
-metadata:
-  name: {{ template "podinfo-flagger.primary" . }}
-  labels:
-    app: {{ template "podinfo-flagger.fullname" . }}
-    chart: {{ template "podinfo-flagger.chart" . }}
-    release: {{ .Release.Name }}
-    heritage: {{ .Release.Service }}
-spec:
-  type: ClusterIP
-  ports:
-  - port: {{ .Values.containerPort }}
-    targetPort: http
-    protocol: TCP
-    name: http
-  selector:
-    app: {{ template "podinfo-flagger.primary" . }}

charts/podinfo-flagger/templates/virtual-service.yaml

@@ -1,30 +0,0 @@
-apiVersion: networking.istio.io/v1alpha3
-kind: VirtualService
-metadata:
-  name: {{ template "podinfo-flagger.fullname" . }}
-  labels:
-    app: {{ template "podinfo-flagger.fullname" . }}
-    chart: {{ template "podinfo-flagger.chart" . }}
-    release: {{ .Release.Name }}
-    heritage: {{ .Release.Service }}
-spec:
-  hosts:
-    - {{ template "podinfo-flagger.fullname" . }}
-{{- if .Values.gateway.enabled }}
-    - {{ .Values.gateway.host }}
-  gateways:
-  - {{ .Values.gateway.name }}
-{{- end }}
-  http:
-  - route:
-    - destination:
-        host: {{ template "podinfo-flagger.primary" . }}
-        port:
-          number: {{ .Values.containerPort }}
-      weight: 100
-    - destination:
-        host: {{ template "podinfo-flagger.canary" . }}
-        port:
-          number: {{ .Values.containerPort }}
-      weight: 0
-    timeout: {{ .Values.timeout }}

charts/podinfo-flagger/values.yaml

@@ -1,30 +0,0 @@
-# Default values for podinfo-flagger.
-
-image:
-  repository: quay.io/stefanprodan/podinfo
-  tag: "1.2.0"
-
-# enable the gateway when exposing the service outside the cluster
-gateway:
-  enabled: false
-  name: public-gateway.istio-system.svc.cluster.local
-  # external domain name
-  host:
-
-hpa:
-  minReplicas: 2
-  maxReplicas: 4
-  targetAverageUtilization: 99
-
-timeout: 30s
-logLevel: info
-containerPort: 9898
-imagePullPolicy: IfNotPresent
-
-resources:
-  limits:
-    cpu: 2000m
-    memory: 512Mi
-  requests:
-    cpu: 100m
-    memory: 64Mi

cmd/flagger/main.go

@@ -6,12 +6,13 @@ import (
 	"time"
 
 	_ "github.com/istio/glog"
-	sharedclientset "github.com/knative/pkg/client/clientset/versioned"
+	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"
 	"k8s.io/client-go/kubernetes"
@@ -27,15 +28,21 @@ var (
 	controlLoopInterval time.Duration
 	logLevel            string
 	port                string
+	slackURL            string
+	slackUser           string
+	slackChannel        string
 )
 
 func init() {
 	flag.StringVar(&kubeconfig, "kubeconfig", "", "Path to a kubeconfig. Only required if out-of-cluster.")
 	flag.StringVar(&masterURL, "master", "", "The address of the Kubernetes API server. Overrides any value in kubeconfig. Only required if out-of-cluster.")
 	flag.StringVar(&metricsServer, "metrics-server", "http://prometheus:9090", "Prometheus URL")
-	flag.DurationVar(&controlLoopInterval, "control-loop-interval", 10*time.Second, "wait interval between rollouts")
+	flag.DurationVar(&controlLoopInterval, "control-loop-interval", 10*time.Second, "Kubernetes API sync interval")
 	flag.StringVar(&logLevel, "log-level", "debug", "Log level can be: debug, info, warning, error.")
 	flag.StringVar(&port, "port", "8080", "Port to listen on.")
+	flag.StringVar(&slackURL, "slack-url", "", "Slack hook URL.")
+	flag.StringVar(&slackUser, "slack-user", "flagger", "Slack user name.")
+	flag.StringVar(&slackChannel, "slack-channel", "", "Slack channel.")
 }
 
 func main() {
@@ -59,18 +66,18 @@ func main() {
 		logger.Fatalf("Error building kubernetes clientset: %v", err)
 	}
 
-	sharedClient, err := sharedclientset.NewForConfig(cfg)
+	istioClient, err := istioclientset.NewForConfig(cfg)
 	if err != nil {
-		logger.Fatalf("Error building shared clientset: %v", err)
+		logger.Fatalf("Error building istio clientset: %v", err)
 	}
 
-	rolloutClient, err := clientset.NewForConfig(cfg)
+	flaggerClient, err := clientset.NewForConfig(cfg)
 	if err != nil {
 		logger.Fatalf("Error building example clientset: %s", err.Error())
 	}
 
-	rolloutInformerFactory := informers.NewSharedInformerFactory(rolloutClient, time.Second*30)
-	rolloutInformer := rolloutInformerFactory.Flagger().V1beta1().Canaries()
+	flaggerInformerFactory := informers.NewSharedInformerFactory(flaggerClient, time.Second*30)
+	canaryInformer := flaggerInformerFactory.Flagger().V1alpha3().Canaries()
 
 	logger.Infof("Starting flagger version %s revision %s", version.VERSION, version.REVISION)
 
@@ -88,24 +95,35 @@ func main() {
 		logger.Errorf("Metrics server %s unreachable %v", metricsServer, err)
 	}
 
+	var slack *notifier.Slack
+	if slackURL != "" {
+		slack, err = notifier.NewSlack(slackURL, slackUser, slackChannel)
+		if err != nil {
+			logger.Errorf("Notifier %v", err)
+		} else {
+			logger.Infof("Slack notifications enabled for channel %s", slack.Channel)
+		}
+	}
+
 	// start HTTP server
 	go server.ListenAndServe(port, 3*time.Second, logger, stopCh)
 
 	c := controller.NewController(
 		kubeClient,
-		sharedClient,
-		rolloutClient,
-		rolloutInformer,
+		istioClient,
+		flaggerClient,
+		canaryInformer,
 		controlLoopInterval,
 		metricsServer,
 		logger,
+		slack,
 	)
 
-	rolloutInformerFactory.Start(stopCh)
+	flaggerInformerFactory.Start(stopCh)
 
 	logger.Info("Waiting for informer caches to sync")
 	for _, synced := range []cache.InformerSynced{
-		rolloutInformer.Informer().HasSynced,
+		canaryInformer.Informer().HasSynced,
 	} {
 		if ok := cache.WaitForCacheSync(stopCh, synced); !ok {
 			logger.Fatalf("Failed to wait for cache sync")

cmd/loadtester/main.go

@@ -0,0 +1,44 @@
+package main
+
+import (
+	"flag"
+	"github.com/knative/pkg/signals"
+	"github.com/stefanprodan/flagger/pkg/loadtester"
+	"github.com/stefanprodan/flagger/pkg/logging"
+	"log"
+	"time"
+)
+
+var VERSION = "0.1.0"
+var (
+	logLevel     string
+	port         string
+	timeout      time.Duration
+	logCmdOutput bool
+)
+
+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")
+}
+
+func main() {
+	flag.Parse()
+
+	logger, err := logging.NewLogger(logLevel)
+	if err != nil {
+		log.Fatalf("Error creating logger: %v", err)
+	}
+	defer logger.Sync()
+
+	stopCh := signals.SetupSignalHandler()
+
+	taskRunner := loadtester.NewTaskRunner(logger, timeout, logCmdOutput)
+
+	go taskRunner.Start(100*time.Millisecond, stopCh)
+
+	logger.Infof("Starting load tester v%s API on port %s", VERSION, port)
+	loadtester.ListenAndServe(port, time.Minute, logger, taskRunner, stopCh)
+}

code-of-conduct.md

@@ -0,0 +1,73 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+In the interest of fostering an open and welcoming environment, we as
+contributors and maintainers pledge to making participation in our project and
+our community a harassment-free experience for everyone, regardless of age, body
+size, disability, ethnicity, gender identity and expression, level of experience,
+education, socio-economic status, nationality, personal appearance, race,
+religion, or sexual identity and orientation.
+
+## Our Standards
+
+Examples of behavior that contributes to creating a positive environment
+include:
+
+* Using welcoming and inclusive language
+* Being respectful of differing viewpoints and experiences
+* Gracefully accepting constructive criticism
+* Focusing on what is best for the community
+* Showing empathy towards other community members
+
+Examples of unacceptable behavior by participants include:
+
+* The use of sexualized language or imagery and unwelcome sexual attention or
+  advances
+* Trolling, insulting/derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or electronic
+  address, without explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Our Responsibilities
+
+Project maintainers are responsible for clarifying the standards of acceptable
+behavior and are expected to take appropriate and fair corrective action in
+response to any instances of unacceptable behavior.
+
+Project maintainers have the right and responsibility to remove, edit, or
+reject comments, commits, code, wiki edits, issues, and other contributions
+that are not aligned to this Code of Conduct, or to ban temporarily or
+permanently any contributor for other behaviors that they deem inappropriate,
+threatening, offensive, or harmful.
+
+## Scope
+
+This Code of Conduct applies both within project spaces and in public spaces
+when an individual is representing the project or its community. Examples of
+representing a project or community include using an official project e-mail
+address, posting via an official social media account, or acting as an appointed
+representative at an online or offline event. Representation of a project may be
+further defined and clarified by project maintainers.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior
+may be reported by contacting stefan.prodan(at)gmail.com. 
+All complaints will be reviewed and investigated and will result in a response that is deemed
+necessary and appropriate to the circumstances. The project team is
+obligated to maintain confidentiality with regard to the reporter of
+an incident. Further details of specific enforcement policies may be
+posted separately.
+
+Project maintainers who do not follow or enforce the Code of Conduct in good
+faith may face temporary or permanent repercussions as determined by other
+members of the project's leadership.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant](https://www.contributor-covenant.org), version 1.4,
+available at https://www.contributor-covenant.org/version/1/4/code-of-conduct.html
+

docs/CNAME

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

docs/README.md

@@ -1,413 +0,0 @@
-# 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)
-[![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)
-
-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 project is currently in experimental phase and it is expected that breaking changes 
-to the API will be made in the upcoming releases.
-
-### Install 
-
-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).
-
-Deploy Flagger in the `istio-system` namespace using Helm:
-
-```bash
-# add the Helm repository
-helm repo add flagger https://stefanprodan.github.io/flagger
-
-# install or upgrade
-helm upgrade -i flagger flagger/flagger \
---namespace=istio-system \
---set metricsServer=http://prometheus.istio-system:9090 \
---set controlLoopInterval=1m
-```
-
-Flagger is compatible with Kubernetes >1.10.0 and Istio >1.0.0.
-
-### Usage
-
-Flagger requires two Kubernetes [deployments](https://kubernetes.io/docs/concepts/workloads/controllers/deployment/): 
-one for the version you want to upgrade called _primary_ and one for the _canary_.
-Each deployment must have a corresponding ClusterIP [service](https://kubernetes.io/docs/concepts/services-networking/service/) 
-that exposes a port named http or https. These services are used as destinations in a Istio [virtual service](https://istio.io/docs/reference/config/istio.networking.v1alpha3/#VirtualService).
-
-![flagger-overview](https://raw.githubusercontent.com/stefanprodan/flagger/master/docs/diagrams/flagger-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 rollout if a rolling update is underway
-    * halt rollout if pods are unhealthy
-* increase canary traffic weight percentage from 0% to 5% (step weight)
-* check canary HTTP request success rate and latency
-    * halt rollout if any metric is under the specified threshold
-    * increment the failed checks counter
-* check if the number of failed checks reached the threshold
-    * route all traffic to primary
-    * scale to zero the canary deployment and mark it as failed
-    * wait for the canary deployment to be updated (revision bump) and start over
-* increase canary traffic weight by 5% (step weight) till it reaches 50% (max weight) 
-    * halt rollout while canary request success rate is under the threshold
-    * halt rollout while canary request duration P99 is over the threshold
-    * halt rollout if the primary or canary deployment becomes unhealthy 
-    * halt rollout while canary deployment is being scaled up/down by HPA
-* promote canary to primary
-    * copy canary deployment spec template over primary
-* wait for primary rolling update to finish
-    * halt rollout if pods are unhealthy
-* route all traffic to primary
-* scale to zero the canary deployment
-* mark rollout as finished
-* wait for the canary deployment to be updated (revision bump) and start over
-
-You can change the canary analysis _max weight_ and the _step weight_ percentage in the Flagger's custom resource.
-
-Assuming the primary deployment is named _podinfo_ and the canary one _podinfo-canary_, Flagger will require 
-a virtual service configured with weight-based routing:
-
-```yaml
-apiVersion: networking.istio.io/v1alpha3
-kind: VirtualService
-metadata:
-  name: podinfo
-spec:
-  hosts:
-  - podinfo
-  http:
-  - route:
-    - destination:
-        host: podinfo
-        port:
-          number: 9898
-      weight: 100
-    - destination:
-        host: podinfo-canary
-        port:
-          number: 9898
-      weight: 0
-```
-
-Primary and canary services should expose a port named http:
-
-```yaml
-apiVersion: v1
-kind: Service
-metadata:
-  name: podinfo-canary
-spec:
-  type: ClusterIP
-  selector:
-    app: podinfo-canary
-  ports:
-  - name: http
-    port: 9898
-    targetPort: 9898
-```
-
-Based on the two deployments, services and virtual service, a canary promotion can be defined using Flagger's custom resource:
-
-```yaml
-apiVersion: flagger.app/v1beta1
-kind: Canary
-metadata:
-  name: podinfo
-  namespace: test
-spec:
-  targetKind: Deployment
-  virtualService:
-    name: podinfo
-  primary:
-    name: podinfo
-    host: podinfo
-  canary:
-    name: podinfo-canary
-    host: podinfo-canary
-  canaryAnalysis:
-    # max number of failed checks
-    # before rolling back the canary
-    threshold: 10
-    # max traffic percentage routed to canary
-    # percentage (0-100)
-    maxWeight: 50
-    # canary increment step
-    # percentage (0-100)
-    stepWeight: 5
-    metrics:
-    - name: istio_requests_total
-      # minimum req success rate (non 5xx responses)
-      # percentage (0-100)
-      threshold: 99
-      interval: 1m
-    - name: istio_request_duration_seconds_bucket
-      # maximum req duration P99
-      # milliseconds
-      threshold: 500
-      interval: 1m
-```
-
-The canary analysis is using the following promql queries:
- 
-_HTTP requests success rate percentage_
-
-```promql
-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]
-    )
-)
-```
-
-_HTTP requests milliseconds duration P99_
-
-```promql
-histogram_quantile(0.99, 
-  sum(
-    irate(
-      istio_request_duration_seconds_bucket{
-        reporter="destination",
-        destination_workload=~"$workload",
-        destination_workload_namespace=~"$namespace"
-      }[$interval]
-    )
-  ) by (le)
-)
-```
-
-### Automated canary analysis, promotions and rollbacks
-
-![flagger-canary](https://raw.githubusercontent.com/stefanprodan/flagger/master/docs/diagrams/flagger-canary-hpa.png)
-
-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 the primary deployment, service and hpa:
-
-```bash
-kubectl apply -f ${REPO}/artifacts/workloads/primary-deployment.yaml
-kubectl apply -f ${REPO}/artifacts/workloads/primary-service.yaml
-kubectl apply -f ${REPO}/artifacts/workloads/primary-hpa.yaml
-```
-
-Create the canary deployment, service and hpa:
-
-```bash
-kubectl apply -f ${REPO}/artifacts/workloads/canary-deployment.yaml
-kubectl apply -f ${REPO}/artifacts/workloads/canary-service.yaml
-kubectl apply -f ${REPO}/artifacts/workloads/canary-hpa.yaml
-```
-
-Create a virtual service (replace the Istio gateway and the internet domain with your own):
-
-```bash
-kubectl apply -f ${REPO}/artifacts/workloads/virtual-service.yaml
-```
-
-Create a canary promotion custom resource:
-
-```bash
-kubectl apply -f ${REPO}/artifacts/rollouts/podinfo.yaml
-```
-
-Canary promotion output:
-
-```
-kubectl -n test describe canary/podinfo
-
-Status:
-  Canary Revision:  16271121
-  Failed Checks:    6
-  State:            finished
-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
-  Warning  Synced  3m    flagger  Halt podinfo.test advancement request duration 2.525s > 500ms
-  Warning  Synced  3m    flagger  Halt podinfo.test advancement request duration 1.567s > 500ms
-  Warning  Synced  3m    flagger  Halt podinfo.test advancement request duration 823ms > 500ms
-  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
-  Warning  Synced  1m    flagger  Halt podinfo.test advancement success rate 82.33% < 99%
-  Warning  Synced  1m    flagger  Halt podinfo.test advancement success rate 87.22% < 99%
-  Warning  Synced  1m    flagger  Halt podinfo.test advancement success rate 94.74% < 99%
-  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-canary.test template spec to podinfo.test
-  Warning  Synced  15s   flagger  Waiting for podinfo.test rollout to finish: 1 of 2 updated replicas are available
-  Normal   Synced  5s    flagger  Promotion completed! Scaling down podinfo-canary.test
-```
-
-During the canary analysis you can generate HTTP 500 errors and high latency to test if Flagger pauses the rollout.
-
-Create a tester pod and exec into it:
-
-```bash
-kubectl -n test run tester --image=quay.io/stefanprodan/podinfo:1.2.1 -- ./podinfo --port=9898
-kubectl -n test exec -it tester-xx-xx sh
-```
-
-Generate HTTP 500 errors:
-
-```bash
-watch curl http://podinfo-canary:9898/status/500
-```
-
-Generate latency:
-
-```bash
-watch curl http://podinfo-canary:9898/delay/1
-```
-
-When the number of failed checks reaches the canary analysis threshold, the traffic is routed back to the primary,
-the canary is scaled to zero and the rollout is marked as failed. 
-
-```
-kubectl -n test describe canary/podinfo
-
-Status:
-  Canary Revision:  16695041
-  Failed Checks:    10
-  State:            failed
-Events:
-  Type     Reason  Age   From     Message
-  ----     ------  ----  ----     -------
-  Normal   Synced  3m    flagger  Starting canary deployment for podinfo.test
-  Normal   Synced  3m    flagger  Advance podinfo.test canary weight 5
-  Normal   Synced  3m    flagger  Advance podinfo.test canary weight 10
-  Normal   Synced  3m    flagger  Advance podinfo.test canary weight 15
-  Normal   Synced  3m    flagger  Halt podinfo.test advancement success rate 69.17% < 99%
-  Normal   Synced  2m    flagger  Halt podinfo.test advancement success rate 61.39% < 99%
-  Normal   Synced  2m    flagger  Halt podinfo.test advancement success rate 55.06% < 99%
-  Normal   Synced  2m    flagger  Halt podinfo.test advancement success rate 47.00% < 99%
-  Normal   Synced  2m    flagger  (combined from similar events): Halt podinfo.test advancement success rate 38.08% < 99%
-  Warning  Synced  1m    flagger  Rolling back podinfo-canary.test failed checks threshold reached 10
-  Warning  Synced  1m    flagger  Canary failed! Scaling down podinfo-canary.test
-```
-
-Trigger a new canary deployment by updating the canary image:
-
-```bash
-kubectl -n test set image deployment/podinfo-canary \
-podinfod=quay.io/stefanprodan/podinfo:1.2.1
-```
-
-Steer detects that the canary revision changed and starts a new rollout:
-
-```
-kubectl -n test describe canary/podinfo
-
-Status:
-  Canary Revision:  19871136
-  Failed Checks:    0
-  State:            finished
-Events:
-  Type     Reason  Age   From     Message
-  ----     ------  ----  ----     -------
-  Normal   Synced  3m    flagger  New revision detected podinfo-canary.test old 17211012 new 17246876
-  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-canary.test template spec to podinfo.test
-  Warning  Synced  15s   flagger  Waiting for podinfo.test rollout to finish: 1 of 2 updated replicas are available
-  Normal   Synced  5s    flagger  Promotion completed! Scaling down podinfo-canary.test
-```
-
-### Monitoring
-
-Flagger comes with a Grafana dashboard made for canary analysis.
-
-Install Grafana with Helm:
-
-```bash
-helm upgrade -i flagger-grafana flagger/grafana \
---namespace=istio-system \
---set url=http://prometheus.istio-system:9090
-```
-
-The dashboard shows the RED and USE metrics for the primary and canary workloads:
-
-![flagger-grafana](https://raw.githubusercontent.com/stefanprodan/flagger/master/docs/screens/grafana-canary-analysis.png)
-
-The canary errors and latency spikes have been recorded as Kubernetes events and logged by Flagger in json format:
-
-```
-kubectl -n istio-system logs deployment/flagger --tail=100 | jq .msg
-
-Starting canary deployment for podinfo.test
-Advance podinfo.test canary weight 5
-Advance podinfo.test canary weight 10
-Advance podinfo.test canary weight 15
-Advance podinfo.test canary weight 20
-Advance podinfo.test canary weight 25
-Advance podinfo.test canary weight 30
-Advance podinfo.test canary weight 35
-Halt podinfo.test advancement success rate 98.69% < 99%
-Advance podinfo.test canary weight 40
-Halt podinfo.test advancement request duration 1.515s > 500ms
-Advance podinfo.test canary weight 45
-Advance podinfo.test canary weight 50
-Copying podinfo-canary.test template spec to podinfo-primary.test
-Scaling down podinfo-canary.test
-Promotion completed! podinfo-canary.test revision 81289
-```
-
-### Roadmap
-
-* Extend the canary analysis and promotion to other types than Kubernetes deployments such as Flux Helm releases or OpenFaaS functions
-* Extend the validation mechanism to support other metrics than HTTP success rate and latency
-* Add support for comparing the canary metrics to the primary ones and do the validation based on the derivation between the two
-* Alerting: Trigger Alertmanager on successful or failed promotions (Prometheus instrumentation of the canary analysis)  
-* Reporting: publish canary analysis results to Slack/Jira/etc
-
-### 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: 
-* 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)

docs/_config.yaml

@@ -1,64 +0,0 @@
-title: Flagger - Istio Progressive Delivery Kubernetes Operator
-
-remote_theme: errordeveloper/simple-project-homepage
-repository: stefanprodan/flagger
-by_weaveworks: true
-
-url: "https://stefanprodan.github.io/flagger"
-baseurl: "/"
-
-twitter:
-  username: "stefanprodan"
-author:
-  twitter: "stefanprodan"
-
-# Set default og:image
-defaults:
-- scope: {path: ""}
-  values: {image: "logo/logo-flagger.png"}
-
-# See: https://material.io/guidelines/style/color.html
-# Use color-name-value, like pink-200 or deep-purple-100
-brand_color: "amber-400"
-
-# How article URLs are structured.
-# See: https://jekyllrb.com/docs/permalinks/
-permalink: posts/:title/
-
-# "UA-NNNNNNNN-N"
-google_analytics: ""
-
-# Language. For example, if you write in Japanese, use "ja"
-lang: "en"
-
-# How many posts are visible on the home page without clicking "View More"
-num_posts_visible_initially: 5
-
-# Date format: See http://strftime.net/
-date_format: "%b %-d, %Y"
-
-plugins:
-- jekyll-feed
-- jekyll-readme-index
-- jekyll-seo-tag
-- jekyll-sitemap
-- jemoji
-# # required for local builds with starefossen/github-pages
-# - jekyll-github-metadata
-# - jekyll-mentions
-# - jekyll-redirect-from
-# - jekyll-remote-theme
-
-exclude:
-- CNAME
-- Dockerfile
-- Gopkg.lock
-- Gopkg.toml
-- LICENSE
-- Makefile
-- add-model.sh
-- build
-- cmd
-- pkg
-- tag_release.sh
-- vendor

docs/gitbook/README.md

@@ -0,0 +1,23 @@
+---
+description: Flagger is an Istio 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 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**.
+
+![Flagger overview diagram](https://raw.githubusercontent.com/stefanprodan/flagger/master/docs/diagrams/flagger-canary-overview.png)
+
+Flagger can be configured with Kubernetes custom resources \(canaries.flagger.app kind\) 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.
+
+This project is sponsored by [Weaveworks](https://www.weave.works/)
+

docs/gitbook/SUMMARY.md

@@ -0,0 +1,17 @@
+# Table of contents
+
+* [Introduction](README.md)
+* [How it works](how-it-works.md)
+
+## Install
+
+* [Install Flagger](install/install-flagger.md)
+* [Install Grafana](install/install-grafana.md)
+* [Install Istio](install/install-istio.md)
+
+## Usage
+
+* [Canary Deployments](usage/progressive-delivery.md)
+* [Monitoring](usage/monitoring.md)
+* [Alerting](usage/alerting.md)
+

docs/gitbook/how-it-works.md

@@ -0,0 +1,361 @@
+# How it works
+
+[Flagger](https://github.com/stefanprodan/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. 
+
+![Flagger Canary Process](https://raw.githubusercontent.com/stefanprodan/flagger/master/docs/diagrams/flagger-canary-hpa.png)
+
+### Canary Custom Resource
+
+For a deployment named _podinfo_, a canary promotion can be defined using Flagger's 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
+    # Istio gateways (optional)
+    gateways:
+    - public-gateway.istio-system.svc.cluster.local
+    # Istio virtual service host names (optional)
+    hosts:
+    - podinfo.example.com
+  canaryAnalysis:
+    # schedule interval (default 60s)
+    interval: 1m
+    # max number of failed metric checks before rollback
+    threshold: 10
+    # max traffic percentage routed to canary
+    # percentage (0-100)
+    maxWeight: 50
+    # canary increment step
+    # percentage (0-100)
+    stepWeight: 5
+    # Istio Prometheus checks
+    metrics:
+    - name: istio_requests_total
+      # minimum req success rate (non 5xx responses)
+      # percentage (0-100)
+      threshold: 99
+      interval: 1m
+    - name: istio_request_duration_seconds_bucket
+      # maximum req duration P99
+      # milliseconds
+      threshold: 500
+      interval: 30s
+    # external checks (optional)
+    webhooks:
+      - name: integration-tests
+        url: http://podinfo.test:9898/echo
+        timeout: 1m
+        # key-value pairs (optional)
+        metadata:
+          test: "all"
+          token: "16688eb5e9f289f1991c"
+```
+
+**Note** that the target deployment must have a single label selector in the format `app: <DEPLOYMENT-NAME>`:
+
+```yaml
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: podinfo
+spec:
+  selector:
+    matchLabels:
+      app: podinfo
+  template:
+    metadata:
+      labels:
+        app: podinfo
+```
+
+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
+
+![Flagger Canary Stages](https://raw.githubusercontent.com/stefanprodan/flagger/master/docs/diagrams/flagger-canary-steps.png)
+
+Gated canary promotion stages:
+
+* scan for canary deployments
+* creates the primary deployment if needed
+* check Istio virtual service routes are mapped to primary and canary ClusterIP services
+* check primary and canary deployments status
+  * halt advancement if a rolling update is underway
+  * halt advancement if pods are unhealthy
+* increase canary traffic weight percentage from 0% to 5% \(step weight\)
+* check canary HTTP request success rate and latency
+  * halt advancement if any metric is under the specified threshold
+  * increment the failed checks counter
+* check if the number of failed checks reached the threshold
+  * route all traffic to primary
+  * scale to zero the canary deployment and mark it as failed
+  * wait for the canary deployment to be updated \(revision bump\) and start over
+* increase canary traffic weight by 5% \(step weight\) till it reaches 50% \(max weight\)
+  * halt advancement if the primary or canary deployment becomes unhealthy
+  * halt advancement while canary deployment is being scaled up/down by HPA
+  * halt advancement if any of the webhook calls are failing
+  * halt advancement while canary request success rate is under the threshold
+  * halt advancement while canary request duration P99 is over the threshold
+* promote canary to primary
+  * copy canary deployment spec template over primary
+* wait for primary rolling update to finish
+  * halt advancement if pods are unhealthy
+* route all traffic to primary
+* scale to zero the canary deployment
+* mark the canary deployment as finished
+* wait for the canary deployment to be updated \(revision bump\) and start over
+
+You can change the canary analysis _max weight_ and the _step weight_ percentage in the Flagger's custom resource.
+
+### Canary Analysis
+
+The canary analysis runs periodically until it reaches the maximum traffic weight or the failed checks threshold. 
+
+Spec:
+
+```yaml
+  canaryAnalysis:
+    # schedule interval (default 60s)
+    interval: 1m
+    # 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: 2
+```
+
+The above analysis, if it succeeds, will run for 25 minutes while validating the HTTP metrics and webhooks every minute.
+You can determine the minimum time that it takes to validate and promote a canary deployment using this formula:
+
+```
+interval * (maxWeight / stepWeight)
+```
+
+And the time it takes for a canary to be rollback when the metrics or webhook checks are failing:
+
+```
+interval * threshold 
+```
+
+### HTTP Metrics
+
+The canary analysis is using the following Prometheus queries:
+
+**HTTP requests success rate percentage**
+
+Spec:
+
+```yaml
+  canaryAnalysis:
+    metrics:
+    - name: istio_requests_total
+      # minimum req success rate (non 5xx responses)
+      # percentage (0-100)
+      threshold: 99
+      interval: 1m
+```
+
+Query:
+
+```javascript
+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]
+    )
+)
+```
+
+**HTTP requests milliseconds duration P99**
+
+Spec:
+
+```yaml
+  canaryAnalysis:
+    metrics:
+    - name: istio_request_duration_seconds_bucket
+      # maximum req duration P99
+      # milliseconds
+      threshold: 500
+      interval: 1m
+```
+
+Query:
+
+```javascript
+histogram_quantile(0.99, 
+  sum(
+    irate(
+      istio_request_duration_seconds_bucket{
+        reporter="destination",
+        destination_workload=~"$workload",
+        destination_workload_namespace=~"$namespace"
+      }[$interval]
+    )
+  ) by (le)
+)
+```
+
+> **Note** that the metric interval should be lower or equal to the control loop interval.
+
+### 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.
+
+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
+        timeout: 30s
+        metadata:
+          key1: "val1"
+          key2: "val2"
+```
+
+> **Note** that the sum of all webhooks timeouts should be lower than the control loop interval. 
+
+Webhook payload (HTTP POST):
+
+```json
+{
+    "name": "podinfo",
+    "namespace": "test", 
+    "metadata": {
+        "test":  "all",
+        "token":  "16688eb5e9f289f1991c"
+    }
+}
+```
+
+Response status codes:
+
+* 200-202 - advance canary by increasing the traffic weight
+* timeout or non-2xx - halt advancement and increment failed checks
+
+On a non-2xx response Flagger will include the response body (if any) in the failed checks log and Kubernetes events.
+
+### Load Testing
+
+For workloads that are not receiving constant traffic Flagger can be configured with a webhook, 
+that when called, will start a load test for the target workload.
+If the target workload doesn't receive any traffic during the canary analysis, 
+Flagger metric checks will fail with "no values found for metric istio_requests_total".
+
+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)
+
+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
+
+kubectl -n test apply -f ${REPO}/artifacts/loadtester/deployment.yaml
+kubectl -n test apply -f ${REPO}/artifacts/loadtester/service.yaml
+```
+
+Or by using Helm:
+
+```bash
+helm repo add flagger https://flagger.app
+
+helm upgrade -i flagger-loadtester flagger/loadtester \
+--namepace=test \
+--set cmd.logOutput=true \
+--set cmd.timeout=1h
+```
+
+When deployed the load tester API will be available at `http://flagger-loadtester.test/`. 
+
+Now you can add webhooks to the canary analysis spec:
+
+```yaml
+webhooks:
+  - name: load-test-get
+    url: http://flagger-loadtester.test/
+    timeout: 5s
+    metadata:
+      cmd: "hey -z 1m -q 10 -c 2 http://podinfo.test:9898/"
+  - name: load-test-post
+    url: http://flagger-loadtester.test/
+    timeout: 5s
+    metadata:
+      cmd: "hey -z 1m -q 10 -c 2 -m POST -d '{test: 2}' http://podinfo.test:9898/echo"
+```
+
+When the canary analysis starts, Flagger will call the webhooks and the load tester will run the `hey` commands 
+in the background, if they are not already running. This will ensure that during the 
+analysis, the `podinfo.test` virtual service will receive a steady steam of GET and POST requests.
+
+If your workload is exposed outside the mesh with the Istio Gateway and TLS you can point `hey` to the 
+public URL and use HTTP2.
+
+```yaml
+webhooks:
+  - name: load-test-get
+    url: http://flagger-loadtester.test/
+    timeout: 5s
+    metadata:
+      cmd: "hey -z 1m -q 10 -c 2 -h2 https://podinfo.example.com/"
+```
+
+The load tester can run arbitrary commands as long as the binary is present in the container image.
+For example if you you want to replace `hey` with another CLI, you can create your own Docker image:
+
+```dockerfile
+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
+```

docs/gitbook/install/install-flagger.md

@@ -0,0 +1,75 @@
+# 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

@@ -0,0 +1,48 @@
+# 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/install/install-istio.md

@@ -0,0 +1,460 @@
+# Install Istio
+
+This guide walks you through setting up Istio with Jaeger, Prometheus, Grafana and 
+Let’s Encrypt TLS for ingress gateway on Google Kubernetes Engine.
+
+![Istio GKE diagram](https://raw.githubusercontent.com/stefanprodan/istio-gke/master/docs/screens/istio-gcp-overview.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.
+
+Install the [gcloud](https://cloud.google.com/sdk/) command line utility and configure your project with `gcloud init`.
+
+Set the default project \(replace `PROJECT_ID` with your own project\):
+
+```text
+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
+```
+
+Enable the Kubernetes and Cloud DNS services for your project:
+
+```text
+gcloud services enable container.googleapis.com
+gcloud services enable dns.googleapis.com
+```
+
+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:
+
+```bash
+k8s_version=$(gcloud container get-server-config --format=json \
+| jq -r '.validNodeVersions[0]')
+
+gcloud container clusters create istio \
+--cluster-version=${k8s_version} \
+--zone=europe-west3-a \
+--num-nodes=3 \
+--machine-type=n1-highcpu-4 \
+--preemptible \
+--no-enable-cloud-logging \
+--disk-size=30 \
+--enable-autorepair \
+--scopes=gke-default,compute-rw,storage-rw
+```
+
+The above command will create a default node pool consisting of `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
+```
+
+Create a cluster admin role binding:
+
+```bash
+kubectl create clusterrolebinding "cluster-admin-$(whoami)" \
+--clusterrole=cluster-admin \
+--user="$(gcloud config get-value core/account)"
+```
+
+Validate your setup with:
+
+```bash
+kubectl get nodes -o wide
+```
+
+### Cloud DNS setup
+
+You will need an internet domain and access to the registrar to change the name servers to Google Cloud DNS.
+
+Create a managed zone named `istio` in Cloud DNS \(replace `example.com` with your domain\):
+
+```bash
+gcloud dns managed-zones create \
+--dns-name="example.com." \
+--description="Istio zone" "istio"
+```
+
+Look up your zone's name servers:
+
+```bash
+gcloud dns managed-zones describe istio
+```
+
+Update your registrar's name server records with the records returned by the above command.
+
+Wait for the name servers to change \(replace `example.com` with your domain\):
+
+```bash
+watch dig +short NS example.com
+```
+
+Create a static IP address named `istio-gateway-ip` in the same region as your GKE cluster:
+
+```bash
+gcloud compute addresses create istio-gateway-ip --region europe-west3
+```
+
+Find the static IP address:
+
+```bash
+gcloud compute addresses describe istio-gateway-ip --region europe-west3
+```
+
+Create the following DNS records \(replace `example.com` with your domain and set your Istio Gateway IP\):
+
+```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 ${GATEWAYIP}
+
+gcloud dns record-sets transaction add --zone=istio \
+--name="www.${DOMAIN}" --ttl=300 --type=A ${GATEWAYIP}
+
+gcloud dns record-sets transaction add --zone=istio \
+--name="*.${DOMAIN}" --ttl=300 --type=A ${GATEWAYIP}
+
+gcloud dns record-sets transaction execute --zone istio
+```
+
+Verify that the wildcard DNS is working \(replace `example.com` with your domain\):
+
+```bash
+watch host test.example.com
+```
+
+### Install Istio with Helm
+
+Download the latest Istio release:
+
+```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
+```
+
+Create a service account and a cluster role binding for Tiller:
+
+```bash
+kubectl apply -f ./install/kubernetes/helm/helm-service-account.yaml
+```
+
+Deploy Tiller in the `kube-system` namespace:
+
+```bash
+helm init --service-account tiller
+```
+
+Find the GKE IP ranges:
+
+```bash
+gcloud container clusters describe istio --zone=europe-west3-a \
+| grep -e clusterIpv4Cidr -e servicesIpv4Cidr
+```
+
+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:
+
+```bash
+helm upgrade --install istio ./install/kubernetes/helm/istio \
+--namespace=istio-system \
+-f ./my-istio.yaml
+```
+
+Verify that Istio workloads are running:
+
+```text
+kubectl -n istio-system get pods
+```
+
+### Configure Istio Gateway with LE TLS
+
+![Istio Let's Encrypt diagram](https://raw.githubusercontent.com/stefanprodan/istio-gke/master/docs/screens/istio-cert-manager-gcp.png)
+
+Create a Istio Gateway in istio-system namespace with HTTPS redirect:
+
+```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
+```
+
+Save the above resource as istio-gateway.yaml and then apply it:
+
+```text
+kubectl apply -f ./istio-gateway.yaml
+```
+
+Create a service account with Cloud DNS admin role \(replace `my-gcp-project` with your project ID\):
+
+```bash
+GCP_PROJECT=my-gcp-project
+
+gcloud iam service-accounts create dns-admin \
+--display-name=dns-admin \
+--project=${GCP_PROJECT}
+
+gcloud iam service-accounts keys create ./gcp-dns-admin.json \
+--iam-account=dns-admin@${GCP_PROJECT}.iam.gserviceaccount.com \
+--project=${GCP_PROJECT}
+
+gcloud projects add-iam-policy-binding ${GCP_PROJECT} \
+--member=serviceAccount:dns-admin@${GCP_PROJECT}.iam.gserviceaccount.com \
+--role=roles/dns.admin
+```
+
+Create a Kubernetes secret with the GCP Cloud DNS admin key:
+
+```bash
+kubectl create secret generic cert-manager-credentials \
+--from-file=./gcp-dns-admin.json \
+--namespace=istio-system
+```
+
+Create a letsencrypt issuer for CloudDNS \(replace `email@example.com` with a valid email address and 
+`my-gcp-project`with your project ID\):
+
+```yaml
+apiVersion: certmanager.k8s.io/v1alpha1
+kind: Issuer
+metadata:
+  name: letsencrypt-prod
+  namespace: istio-system
+spec:
+  acme:
+    server: https://acme-v02.api.letsencrypt.org/directory
+    email: email@example.com
+    privateKeySecretRef:
+      name: letsencrypt-prod
+    dns01:
+      providers:
+      - name: cloud-dns
+        clouddns:
+          serviceAccountSecretRef:
+            name: cert-manager-credentials
+            key: gcp-dns-admin.json
+          project: my-gcp-project
+```
+
+Save the above resource as letsencrypt-issuer.yaml and then apply it:
+
+```text
+kubectl apply -f ./letsencrypt-issuer.yaml
+```
+
+Create a wildcard certificate \(replace `example.com` with your domain\):
+
+```yaml
+apiVersion: certmanager.k8s.io/v1alpha1
+kind: Certificate
+metadata:
+  name: istio-gateway
+  namespace: istio-system
+spec:
+  secretname: istio-ingressgateway-certs
+  issuerRef:
+    name: letsencrypt-prod
+  commonName: "*.example.com"
+  acme:
+    config:
+    - dns01:
+        provider: cloud-dns
+      domains:
+      - "*.example.com"
+      - "example.com"
+```
+
+Save the above resource as of-cert.yaml and then apply it:
+
+```text
+kubectl apply -f ./of-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
+
+Certificate issued successfully
+Certificate istio-system/istio-gateway scheduled for renewal in 1438 hours
+```
+
+Recreate Istio ingress gateway pods:
+
+```bash
+kubectl -n istio-system delete 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 
+before the certificate expires.
+
+### Expose services outside the service mesh
+
+In order to expose services via the Istio Gateway you have to create a Virtual Service attached to Istio Gateway.
+
+Create a virtual service in `istio-system` namespace for Grafana \(replace `example.com` with your domain\):
+
+```yaml
+apiVersion: networking.istio.io/v1alpha3
+kind: VirtualService
+metadata:
+  name: grafana
+  namespace: istio-system
+spec:
+  hosts:
+  - "grafana.example.com"
+  gateways:
+  - public-gateway.istio-system.svc.cluster.local
+  http:
+  - route:
+    - destination:
+        host: grafana
+    timeout: 30s
+```
+
+Save the above resource as grafana-virtual-service.yaml and then apply it:
+
+```bash
+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/usage/alerting.md

@@ -0,0 +1,39 @@
+# Alerting
+
+### Slack
+
+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 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)
+
+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)
+
+### Prometheus Alert Manager
+
+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 }}"
+```
+

docs/gitbook/usage/monitoring.md

@@ -0,0 +1,69 @@
+# Monitoring
+
+### Grafana
+
+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:9090 \
+--set user=admin \
+--set password=admin
+```
+
+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)
+
+### Logging
+
+The canary errors and latency spikes have been recorded as Kubernetes events and logged by Flagger in json format:
+
+```text
+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
+```
+
+### Metrics
+
+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
+```
+
+

docs/gitbook/usage/progressive-delivery.md

@@ -0,0 +1,208 @@
+# Canary Deployments
+
+This guide shows you how to use Istio and Flagger to automate canary deployments.
+
+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 custom resource \(replace example.com with your own domain\):
+
+```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
+    # Istio gateways (optional)
+    gateways:
+    - public-gateway.istio-system.svc.cluster.local
+    # Istio virtual service host names (optional)
+    hosts:
+    - app.example.com
+  canaryAnalysis:
+    # schedule interval (default 60s)
+    interval: 1m
+    # max number of failed metric checks before rollback
+    threshold: 5
+    # max traffic percentage routed to canary
+    # percentage (0-100)
+    maxWeight: 50
+    # canary increment step
+    # percentage (0-100)
+    stepWeight: 10
+    metrics:
+    - name: istio_requests_total
+      # minimum req success rate (non 5xx responses)
+      # percentage (0-100)
+      threshold: 99
+      interval: 1m
+    - name: istio_request_duration_seconds_bucket
+      # 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 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 
+deployment.apps/podinfo-primary
+horizontalpodautoscaler.autoscaling/podinfo-primary
+service/podinfo
+service/podinfo-canary
+service/podinfo-primary
+virtualservice.networking.istio.io/podinfo
+```
+
+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
+```
+
+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
+```
+
+You can monitor all canaries with:
+
+```bash
+watch kubectl get canaries --all-namespaces
+
+NAMESPACE   NAME      STATUS        WEIGHT   LASTTRANSITIONTIME
+test        podinfo   Progressing   15       2019-01-16T14:05:07Z
+prod        frontend  Succeeded     0        2019-01-15T16:15:07Z
+prod        backend   Failed        0        2019-01-14T17:05:07Z
+```
+
+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.
+
+```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
+```
+

docs/index.yaml

@@ -1,61 +0,0 @@
-apiVersion: v1
-entries:
-  flagger:
-  - apiVersion: v1
-    appVersion: 0.0.1
-    created: 2018-10-07T13:00:10.107115+03:00
-    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.
-    digest: ddf0eda9975979bdfc26f10c7b3c15f4a31ebe0484be3285fbaec99b893871be
-    home: https://github.com/stefanprodan/flagger
-    name: flagger
-    urls:
-    - https://stefanprodan.github.io/flagger/flagger-0.0.1.tgz
-    version: 0.0.1
-  grafana:
-  - apiVersion: v1
-    appVersion: 5.2.0
-    created: 2018-10-07T13:00:10.10763+03:00
-    description: A Helm chart for monitoring progressive deployments powered by Istio
-      and Flagger
-    digest: 1e19e9010d2939e19d0f8465287676b185f4772f5df5a75092a8fce0b4a50e5e
-    home: https://github.com/stefanprodan/flagger
-    name: grafana
-    urls:
-    - https://stefanprodan.github.io/flagger/grafana-5.2.4.tgz
-    version: 5.2.4
-  podinfo-flagger:
-  - apiVersion: v1
-    appVersion: 1.2.1
-    created: 2018-10-07T13:00:10.108001+03:00
-    description: Podinfo Helm chart for Flagger progressive delivery
-    digest: 35ce41d10df123a785ba359491668a143c5918ce6d3d24f5b545ca2cb9134d91
-    engine: gotpl
-    home: https://github.com/stefanprodan/k8s-podinfo
-    maintainers:
-    - email: stefanprodan@users.noreply.github.com
-      name: stefanprodan
-    name: podinfo-flagger
-    sources:
-    - https://github.com/stefanprodan/flagger
-    urls:
-    - https://stefanprodan.github.io/flagger/podinfo-flagger-2.0.0.tgz
-    version: 2.0.0
-  - apiVersion: v1
-    appVersion: 1.2.1
-    created: 2018-10-04T14:48:57.586403+03:00
-    description: Podinfo Helm chart for Flagger progressive delivery
-    digest: f559f387aa45005be085af207b8b4c91776e489fcb6ca7e60f20913ecd21184e
-    engine: gotpl
-    home: https://github.com/stefanprodan/k8s-podinfo
-    maintainers:
-    - email: stefanprodan@users.noreply.github.com
-      name: stefanprodan
-    name: podinfo-flagger
-    sources:
-    - https://github.com/stefanprodan/flagger
-    urls:
-    - https://stefanprodan.github.io/flagger/podinfo-flagger-1.2.1.tgz
-    version: 1.2.1
-generated: 2018-10-07T13:00:10.106238+03:00

docs/logo/icon.svg

@@ -1,20 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<svg width="512px" height="534px" viewBox="0 0 512 534" version="1.1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
-    <!-- Generator: Sketch 51.2 (57519) - http://www.bohemiancoding.com/sketch -->
-    <title>istio-refresh</title>
-    <desc>Created with Sketch.</desc>
-    <defs></defs>
-    <g id="Page-1" stroke="none" stroke-width="1" fill="none" fill-rule="evenodd">
-        <g id="Logo" transform="translate(-82.000000, -67.000000)" fill-rule="nonzero">
-            <g id="istio-refresh">
-                <polygon id="hull" fill="#466BB0" points="467.486761 456 322.182535 499.591268 235 456"></polygon>
-                <polygon id="mainsail" fill="#466BB0" points="322.182535 426.834648 322.182535 267 235 441.365071"></polygon>
-                <polygon id="headsail" fill="#466BB0" points="466.773803 441.608451 336 151 336 427.078028"></polygon>
-                <g id="arrows" transform="translate(338.000000, 338.000000) rotate(-24.000000) translate(-338.000000, -338.000000) translate(82.000000, 82.000000)">
-                    <path d="M256.000042,0 C114.772094,0 0.00128552135,114.771366 0.00128552135,256 C-0.0639978677,260.61614 2.36127785,264.909841 6.34842716,267.236963 C10.3355765,269.564084 15.2668702,269.564084 19.2540195,267.236963 C23.2411688,264.909841 25.6664445,260.61614 25.6011612,256 C25.6011612,128.607834 128.608494,25.6 256.000042,25.6 C335.938457,25.6 406.118967,66.3034496 447.449109,128 L413.301505,128 C408.685388,127.934716 404.391707,130.360004 402.064597,134.347172 C399.737487,138.334341 399.737487,143.265659 402.064597,147.252828 C404.391707,151.239996 408.685388,153.665284 413.301505,153.6 L470.549003,153.6 L486.398923,153.6 L486.398923,70.7176471 C486.446301,67.257803 485.091067,63.9261384 482.642017,61.4817859 C480.192966,59.0374333 476.858715,57.6886086 473.398986,57.7426467 C466.339613,57.8529965 460.702373,63.6580397 460.799047,70.7176471 L460.799047,102.525005 C414.068394,40.3001766 339.69529,0 256.000042,0 Z" id="Shape" fill="#35A2EE"></path>
-                    <path d="M498.998861,243.024998 C491.939488,243.135348 486.302248,248.940392 486.398923,256 C486.398923,383.392166 383.391589,486.4 256.000042,486.4 C176.054933,486.4 105.870698,445.69303 64.5509751,384 L92.9338727,384.024998 C97.54999,384.090282 101.843671,381.664995 104.170781,377.677826 C106.497891,373.690657 106.497891,368.75934 104.170781,364.772171 C101.843671,360.785002 97.54999,358.359715 92.9338727,358.424998 L44.1010713,358.4 C42.4667939,358.077951 40.7853733,358.077951 39.151096,358.4 L25.6011612,358.4 L25.6011612,432.243137 C25.5358778,436.859277 27.9611535,441.152979 31.9483028,443.4801 C35.9354521,445.807221 40.8667458,445.807221 44.8538951,443.4801 C48.8410445,441.152979 51.2663202,436.859277 51.2010368,432.243137 L51.2010368,409.424998 C97.9168162,471.668595 172.282881,512 256.000042,512 C397.227989,512 511.998798,397.228634 511.998798,256 C512.046177,252.540156 510.690943,249.208491 508.241893,246.764138 C505.792842,244.319785 502.458591,242.97096 498.998861,243.024998 Z" id="Path" fill="#1DCBA2"></path>
-                </g>
-            </g>
-        </g>
-    </g>
-</svg>

hack/update-codegen.sh

@@ -23,6 +23,6 @@ CODEGEN_PKG=${CODEGEN_PKG:-$(cd ${SCRIPT_ROOT}; ls -d -1 ./vendor/k8s.io/code-ge
 
 ${CODEGEN_PKG}/generate-groups.sh "deepcopy,client,informer,lister" \
   github.com/stefanprodan/flagger/pkg/client github.com/stefanprodan/flagger/pkg/apis \
-  flagger:v1beta1 \
+  flagger:v1alpha3 \
   --go-header-file ${SCRIPT_ROOT}/hack/boilerplate.go.txt
 

pkg/apis/flagger/v1alpha3/doc.go

@@ -16,6 +16,6 @@ limitations under the License.
 
 // +k8s:deepcopy-gen=package
 
-// Package v1beta1 is the v1beta1 version of the API.
+// Package v1alpha3 is the v1alpha3 version of the API.
 // +groupName=flagger.app
-package v1beta1
+package v1alpha3

pkg/apis/flagger/v1alpha3/register.go

@@ -14,7 +14,7 @@ See the License for the specific language governing permissions and
 limitations under the License.
 */
 
-package v1beta1
+package v1alpha3
 
 import (
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
@@ -25,7 +25,7 @@ import (
 )
 
 // SchemeGroupVersion is group version used to register these objects
-var SchemeGroupVersion = schema.GroupVersion{Group: rollout.GroupName, Version: "v1beta1"}
+var SchemeGroupVersion = schema.GroupVersion{Group: rollout.GroupName, Version: "v1alpha3"}
 
 // Kind takes an unqualified kind and returns back a Group qualified GroupKind
 func Kind(kind string) schema.GroupKind {

pkg/apis/flagger/v1alpha3/types.go

@@ -0,0 +1,163 @@
+/*
+Copyright 2018 The Flagger Authors.
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+*/
+
+package v1alpha3
+
+import (
+	hpav1 "k8s.io/api/autoscaling/v1"
+	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
+	"time"
+)
+
+const (
+	CanaryKind              = "Canary"
+	ProgressDeadlineSeconds = 600
+	AnalysisInterval        = 60 * time.Second
+)
+
+// +genclient
+// +k8s:deepcopy-gen:interfaces=k8s.io/apimachinery/pkg/runtime.Object
+
+// Canary is a specification for a Canary resource
+type Canary struct {
+	metav1.TypeMeta   `json:",inline"`
+	metav1.ObjectMeta `json:"metadata,omitempty"`
+
+	Spec   CanarySpec   `json:"spec"`
+	Status CanaryStatus `json:"status"`
+}
+
+// CanarySpec is the spec for a Canary resource
+type CanarySpec struct {
+	// reference to target resource
+	TargetRef hpav1.CrossVersionObjectReference `json:"targetRef"`
+
+	// reference to autoscaling resource
+	// +optional
+	AutoscalerRef *hpav1.CrossVersionObjectReference `json:"autoscalerRef,omitempty"`
+
+	// virtual service spec
+	Service CanaryService `json:"service"`
+
+	// metrics and thresholds
+	CanaryAnalysis CanaryAnalysis `json:"canaryAnalysis"`
+
+	// the maximum time in seconds for a canary deployment to make progress
+	// before it is considered to be failed. Defaults to ten minutes.
+	ProgressDeadlineSeconds *int32 `json:"progressDeadlineSeconds,omitempty"`
+}
+
+// +k8s:deepcopy-gen:interfaces=k8s.io/apimachinery/pkg/runtime.Object
+
+// CanaryList is a list of Canary resources
+type CanaryList struct {
+	metav1.TypeMeta `json:",inline"`
+	metav1.ListMeta `json:"metadata"`
+
+	Items []Canary `json:"items"`
+}
+
+// CanaryPhase is a label for the condition of a canary at the current time
+type CanaryPhase string
+
+const (
+	// CanaryInitialized means the primary deployment, hpa and ClusterIP services
+	// have been created along with the Istio virtual service
+	CanaryInitialized CanaryPhase = "Initialized"
+	// CanaryProgressing means the canary analysis is underway
+	CanaryProgressing CanaryPhase = "Progressing"
+	// CanarySucceeded means the canary analysis has been successful
+	// and the canary deployment has been promoted
+	CanarySucceeded CanaryPhase = "Succeeded"
+	// CanaryFailed means the canary analysis failed
+	// and the canary deployment has been scaled to zero
+	CanaryFailed CanaryPhase = "Failed"
+)
+
+// CanaryStatus is used for state persistence (read-only)
+type CanaryStatus struct {
+	Phase        CanaryPhase `json:"phase"`
+	FailedChecks int         `json:"failedChecks"`
+	CanaryWeight int         `json:"canaryWeight"`
+	// +optional
+	LastAppliedSpec string `json:"lastAppliedSpec,omitempty"`
+	// +optional
+	LastTransitionTime metav1.Time `json:"lastTransitionTime,omitempty"`
+}
+
+// CanaryService is used to create ClusterIP services
+// and Istio Virtual Service
+type CanaryService struct {
+	Port     int32    `json:"port"`
+	Gateways []string `json:"gateways"`
+	Hosts    []string `json:"hosts"`
+}
+
+// CanaryAnalysis is used to describe how the analysis should be done
+type CanaryAnalysis struct {
+	Interval   string          `json:"interval"`
+	Threshold  int             `json:"threshold"`
+	MaxWeight  int             `json:"maxWeight"`
+	StepWeight int             `json:"stepWeight"`
+	Metrics    []CanaryMetric  `json:"metrics"`
+	Webhooks   []CanaryWebhook `json:"webhooks,omitempty"`
+}
+
+// CanaryMetric holds the reference to Istio metrics used for canary analysis
+type CanaryMetric struct {
+	Name      string `json:"name"`
+	Interval  string `json:"interval"`
+	Threshold int    `json:"threshold"`
+}
+
+// CanaryWebhook holds the reference to external checks used for canary analysis
+type CanaryWebhook struct {
+	Name    string `json:"name"`
+	URL     string `json:"url"`
+	Timeout string `json:"timeout"`
+	// +optional
+	Metadata *map[string]string `json:"metadata,omitempty"`
+}
+
+// CanaryWebhookPayload holds the deployment info and metadata sent to webhooks
+type CanaryWebhookPayload struct {
+	Name      string            `json:"name"`
+	Namespace string            `json:"namespace"`
+	Metadata  map[string]string `json:"metadata,omitempty"`
+}
+
+// GetProgressDeadlineSeconds returns the progress deadline (default 600s)
+func (c *Canary) GetProgressDeadlineSeconds() int {
+	if c.Spec.ProgressDeadlineSeconds != nil {
+		return int(*c.Spec.ProgressDeadlineSeconds)
+	}
+
+	return ProgressDeadlineSeconds
+}
+
+// GetAnalysisInterval returns the canary analysis interval (default 60s)
+func (c *Canary) GetAnalysisInterval() time.Duration {
+	if c.Spec.CanaryAnalysis.Interval == "" {
+		return AnalysisInterval
+	}
+
+	interval, err := time.ParseDuration(c.Spec.CanaryAnalysis.Interval)
+	if err != nil {
+		return AnalysisInterval
+	}
+
+	return interval
+}

pkg/apis/flagger/v1alpha3/zz_generated.deepcopy.go

@@ -18,9 +18,10 @@ limitations under the License.
 
 // Code generated by deepcopy-gen. DO NOT EDIT.
 
-package v1beta1
+package v1alpha3
 
 import (
+	v1 "k8s.io/api/autoscaling/v1"
 	runtime "k8s.io/apimachinery/pkg/runtime"
 )
 
@@ -30,7 +31,7 @@ func (in *Canary) DeepCopyInto(out *Canary) {
 	out.TypeMeta = in.TypeMeta
 	in.ObjectMeta.DeepCopyInto(&out.ObjectMeta)
 	in.Spec.DeepCopyInto(&out.Spec)
-	out.Status = in.Status
+	in.Status.DeepCopyInto(&out.Status)
 	return
 }
 
@@ -57,9 +58,16 @@ func (in *CanaryAnalysis) DeepCopyInto(out *CanaryAnalysis) {
 	*out = *in
 	if in.Metrics != nil {
 		in, out := &in.Metrics, &out.Metrics
-		*out = make([]Metric, len(*in))
+		*out = make([]CanaryMetric, len(*in))
 		copy(*out, *in)
 	}
+	if in.Webhooks != nil {
+		in, out := &in.Webhooks, &out.Webhooks
+		*out = make([]CanaryWebhook, len(*in))
+		for i := range *in {
+			(*in)[i].DeepCopyInto(&(*out)[i])
+		}
+	}
 	return
 }
 
@@ -106,13 +114,64 @@ func (in *CanaryList) DeepCopyObject() runtime.Object {
 	return nil
 }
 
+// DeepCopyInto is an autogenerated deepcopy function, copying the receiver, writing into out. in must be non-nil.
+func (in *CanaryMetric) DeepCopyInto(out *CanaryMetric) {
+	*out = *in
+	return
+}
+
+// DeepCopy is an autogenerated deepcopy function, copying the receiver, creating a new CanaryMetric.
+func (in *CanaryMetric) DeepCopy() *CanaryMetric {
+	if in == nil {
+		return nil
+	}
+	out := new(CanaryMetric)
+	in.DeepCopyInto(out)
+	return out
+}
+
+// DeepCopyInto is an autogenerated deepcopy function, copying the receiver, writing into out. in must be non-nil.
+func (in *CanaryService) DeepCopyInto(out *CanaryService) {
+	*out = *in
+	if in.Gateways != nil {
+		in, out := &in.Gateways, &out.Gateways
+		*out = make([]string, len(*in))
+		copy(*out, *in)
+	}
+	if in.Hosts != nil {
+		in, out := &in.Hosts, &out.Hosts
+		*out = make([]string, len(*in))
+		copy(*out, *in)
+	}
+	return
+}
+
+// DeepCopy is an autogenerated deepcopy function, copying the receiver, creating a new CanaryService.
+func (in *CanaryService) DeepCopy() *CanaryService {
+	if in == nil {
+		return nil
+	}
+	out := new(CanaryService)
+	in.DeepCopyInto(out)
+	return out
+}
+
 // DeepCopyInto is an autogenerated deepcopy function, copying the receiver, writing into out. in must be non-nil.
 func (in *CanarySpec) DeepCopyInto(out *CanarySpec) {
 	*out = *in
-	out.Primary = in.Primary
-	out.Canary = in.Canary
+	out.TargetRef = in.TargetRef
+	if in.AutoscalerRef != nil {
+		in, out := &in.AutoscalerRef, &out.AutoscalerRef
+		*out = new(v1.CrossVersionObjectReference)
+		**out = **in
+	}
+	in.Service.DeepCopyInto(&out.Service)
 	in.CanaryAnalysis.DeepCopyInto(&out.CanaryAnalysis)
-	out.VirtualService = in.VirtualService
+	if in.ProgressDeadlineSeconds != nil {
+		in, out := &in.ProgressDeadlineSeconds, &out.ProgressDeadlineSeconds
+		*out = new(int32)
+		**out = **in
+	}
 	return
 }
 
@@ -129,6 +188,7 @@ func (in *CanarySpec) DeepCopy() *CanarySpec {
 // DeepCopyInto is an autogenerated deepcopy function, copying the receiver, writing into out. in must be non-nil.
 func (in *CanaryStatus) DeepCopyInto(out *CanaryStatus) {
 	*out = *in
+	in.LastTransitionTime.DeepCopyInto(&out.LastTransitionTime)
 	return
 }
 
@@ -143,49 +203,51 @@ func (in *CanaryStatus) DeepCopy() *CanaryStatus {
 }
 
 // DeepCopyInto is an autogenerated deepcopy function, copying the receiver, writing into out. in must be non-nil.
-func (in *Metric) DeepCopyInto(out *Metric) {
+func (in *CanaryWebhook) DeepCopyInto(out *CanaryWebhook) {
 	*out = *in
+	if in.Metadata != nil {
+		in, out := &in.Metadata, &out.Metadata
+		*out = new(map[string]string)
+		if **in != nil {
+			in, out := *in, *out
+			*out = make(map[string]string, len(*in))
+			for key, val := range *in {
+				(*out)[key] = val
+			}
+		}
+	}
 	return
 }
 
-// DeepCopy is an autogenerated deepcopy function, copying the receiver, creating a new Metric.
-func (in *Metric) DeepCopy() *Metric {
+// DeepCopy is an autogenerated deepcopy function, copying the receiver, creating a new CanaryWebhook.
+func (in *CanaryWebhook) DeepCopy() *CanaryWebhook {
 	if in == nil {
 		return nil
 	}
-	out := new(Metric)
+	out := new(CanaryWebhook)
 	in.DeepCopyInto(out)
 	return out
 }
 
 // DeepCopyInto is an autogenerated deepcopy function, copying the receiver, writing into out. in must be non-nil.
-func (in *Target) DeepCopyInto(out *Target) {
+func (in *CanaryWebhookPayload) DeepCopyInto(out *CanaryWebhookPayload) {
 	*out = *in
+	if in.Metadata != nil {
+		in, out := &in.Metadata, &out.Metadata
+		*out = make(map[string]string, len(*in))
+		for key, val := range *in {
+			(*out)[key] = val
+		}
+	}
 	return
 }
 
-// DeepCopy is an autogenerated deepcopy function, copying the receiver, creating a new Target.
-func (in *Target) DeepCopy() *Target {
+// DeepCopy is an autogenerated deepcopy function, copying the receiver, creating a new CanaryWebhookPayload.
+func (in *CanaryWebhookPayload) DeepCopy() *CanaryWebhookPayload {
 	if in == nil {
 		return nil
 	}
-	out := new(Target)
-	in.DeepCopyInto(out)
-	return out
-}
-
-// DeepCopyInto is an autogenerated deepcopy function, copying the receiver, writing into out. in must be non-nil.
-func (in *VirtualService) DeepCopyInto(out *VirtualService) {
-	*out = *in
-	return
-}
-
-// DeepCopy is an autogenerated deepcopy function, copying the receiver, creating a new VirtualService.
-func (in *VirtualService) DeepCopy() *VirtualService {
-	if in == nil {
-		return nil
-	}
-	out := new(VirtualService)
+	out := new(CanaryWebhookPayload)
 	in.DeepCopyInto(out)
 	return out
 }

pkg/apis/flagger/v1beta1/types.go

@@ -1,81 +0,0 @@
-/*
-Copyright 2018 The Flagger Authors.
-
-Licensed under the Apache License, Version 2.0 (the "License");
-you may not use this file except in compliance with the License.
-You may obtain a copy of the License at
-
-    http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software
-distributed under the License is distributed on an "AS IS" BASIS,
-WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-See the License for the specific language governing permissions and
-limitations under the License.
-*/
-
-package v1beta1
-
-import (
-	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
-)
-
-// +genclient
-// +k8s:deepcopy-gen:interfaces=k8s.io/apimachinery/pkg/runtime.Object
-
-// Canary is a specification for a Canary resource
-type Canary struct {
-	metav1.TypeMeta   `json:",inline"`
-	metav1.ObjectMeta `json:"metadata,omitempty"`
-
-	Spec   CanarySpec   `json:"spec"`
-	Status CanaryStatus `json:"status"`
-}
-
-// CanarySpec is the spec for a Canary resource
-type CanarySpec struct {
-	TargetKind     string         `json:"targetKind"`
-	Primary        Target         `json:"primary"`
-	Canary         Target         `json:"canary"`
-	CanaryAnalysis CanaryAnalysis `json:"canaryAnalysis"`
-	VirtualService VirtualService `json:"virtualService"`
-}
-
-type Target struct {
-	Name string `json:"name"`
-	Host string `json:"host"`
-}
-
-type VirtualService struct {
-	Name string `json:"name"`
-}
-
-type CanaryAnalysis struct {
-	Threshold  int      `json:"threshold"`
-	MaxWeight  int      `json:"maxWeight"`
-	StepWeight int      `json:"stepWeight"`
-	Metrics    []Metric `json:"metrics"`
-}
-
-type Metric struct {
-	Name      string `json:"name"`
-	Interval  string `json:"interval"`
-	Threshold int    `json:"threshold"`
-}
-
-// CanaryStatus is the status for a Canary resource
-type CanaryStatus struct {
-	State          string `json:"state"`
-	CanaryRevision string `json:"canaryRevision"`
-	FailedChecks   int    `json:"failedChecks"`
-}
-
-// +k8s:deepcopy-gen:interfaces=k8s.io/apimachinery/pkg/runtime.Object
-
-// CanaryList is a list of Canary resources
-type CanaryList struct {
-	metav1.TypeMeta `json:",inline"`
-	metav1.ListMeta `json:"metadata"`
-
-	Items []Canary `json:"items"`
-}

pkg/client/clientset/versioned/clientset.go

@@ -19,7 +19,7 @@ limitations under the License.
 package versioned
 
 import (
-	flaggerv1beta1 "github.com/stefanprodan/flagger/pkg/client/clientset/versioned/typed/flagger/v1beta1"
+	flaggerv1alpha3 "github.com/stefanprodan/flagger/pkg/client/clientset/versioned/typed/flagger/v1alpha3"
 	discovery "k8s.io/client-go/discovery"
 	rest "k8s.io/client-go/rest"
 	flowcontrol "k8s.io/client-go/util/flowcontrol"
@@ -27,27 +27,27 @@ import (
 
 type Interface interface {
 	Discovery() discovery.DiscoveryInterface
-	FlaggerV1beta1() flaggerv1beta1.FlaggerV1beta1Interface
+	FlaggerV1alpha3() flaggerv1alpha3.FlaggerV1alpha3Interface
 	// Deprecated: please explicitly pick a version if possible.
-	Flagger() flaggerv1beta1.FlaggerV1beta1Interface
+	Flagger() flaggerv1alpha3.FlaggerV1alpha3Interface
 }
 
 // Clientset contains the clients for groups. Each group has exactly one
 // version included in a Clientset.
 type Clientset struct {
 	*discovery.DiscoveryClient
-	flaggerV1beta1 *flaggerv1beta1.FlaggerV1beta1Client
+	flaggerV1alpha3 *flaggerv1alpha3.FlaggerV1alpha3Client
 }
 
-// FlaggerV1beta1 retrieves the FlaggerV1beta1Client
-func (c *Clientset) FlaggerV1beta1() flaggerv1beta1.FlaggerV1beta1Interface {
-	return c.flaggerV1beta1
+// FlaggerV1alpha3 retrieves the FlaggerV1alpha3Client
+func (c *Clientset) FlaggerV1alpha3() flaggerv1alpha3.FlaggerV1alpha3Interface {
+	return c.flaggerV1alpha3
 }
 
 // Deprecated: Flagger retrieves the default version of FlaggerClient.
 // Please explicitly pick a version.
-func (c *Clientset) Flagger() flaggerv1beta1.FlaggerV1beta1Interface {
-	return c.flaggerV1beta1
+func (c *Clientset) Flagger() flaggerv1alpha3.FlaggerV1alpha3Interface {
+	return c.flaggerV1alpha3
 }
 
 // Discovery retrieves the DiscoveryClient
@@ -66,7 +66,7 @@ func NewForConfig(c *rest.Config) (*Clientset, error) {
 	}
 	var cs Clientset
 	var err error
-	cs.flaggerV1beta1, err = flaggerv1beta1.NewForConfig(&configShallowCopy)
+	cs.flaggerV1alpha3, err = flaggerv1alpha3.NewForConfig(&configShallowCopy)
 	if err != nil {
 		return nil, err
 	}
@@ -82,7 +82,7 @@ func NewForConfig(c *rest.Config) (*Clientset, error) {
 // panics if there is an error in the config.
 func NewForConfigOrDie(c *rest.Config) *Clientset {
 	var cs Clientset
-	cs.flaggerV1beta1 = flaggerv1beta1.NewForConfigOrDie(c)
+	cs.flaggerV1alpha3 = flaggerv1alpha3.NewForConfigOrDie(c)
 
 	cs.DiscoveryClient = discovery.NewDiscoveryClientForConfigOrDie(c)
 	return &cs
@@ -91,7 +91,7 @@ func NewForConfigOrDie(c *rest.Config) *Clientset {
 // New creates a new Clientset for the given RESTClient.
 func New(c rest.Interface) *Clientset {
 	var cs Clientset
-	cs.flaggerV1beta1 = flaggerv1beta1.New(c)
+	cs.flaggerV1alpha3 = flaggerv1alpha3.New(c)
 
 	cs.DiscoveryClient = discovery.NewDiscoveryClient(c)
 	return &cs