Merge pull request #57 from stefanprodan/release-0.6.0

Release v0.6.0

.circleci/config.yml

@@ -0,0 +1,16 @@
+version: 2.1
+jobs:
+  e2e-testing:
+    machine: true
+    steps:
+      - checkout
+      - run: test/e2e-kind.sh
+      - run: test/e2e-istio.sh
+      - run: test/e2e-build.sh
+      - run: test/e2e-tests.sh
+
+workflows:
+  version: 2
+  build-and-test:
+    jobs:
+      - e2e-testing

.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"]
+}
+

.gitignore

@@ -11,3 +11,6 @@
 # Output of the go coverage tool, specifically when used with LiteIDE
 *.out
 .DS_Store
+
+bin/
+artifacts/gcloud/

.travis.yml

@@ -2,7 +2,7 @@ sudo: required
 language: go
 
 go:
-- 1.10.x
+- 1.11.x
 
 services:
 - docker
@@ -12,27 +12,36 @@ addons:
     packages:
     - docker-ce
 
+#before_script:
+#  - go get -u sigs.k8s.io/kind
+#  - curl https://raw.githubusercontent.com/kubernetes/helm/master/scripts/get | bash
+#  - curl -LO https://storage.googleapis.com/kubernetes-release/release/$(curl -s https://storage.googleapis.com/kubernetes-release/release/stable.txt)/bin/linux/amd64/kubectl && chmod +x kubectl && sudo mv kubectl /usr/local/bin/
+
 script:
-- set -e
-- make test
-- make build
+  - set -e
+  - 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

CHANGELOG.md

@@ -0,0 +1,155 @@
+# Changelog
+
+All notable changes to this project are documented in this file.
+
+## 0.6.0 (2019-02-25)
+
+Allows for [HTTPMatchRequests](https://istio.io/docs/reference/config/istio.networking.v1alpha3/#HTTPMatchRequest) 
+and [HTTPRewrite](https://istio.io/docs/reference/config/istio.networking.v1alpha3/#HTTPRewrite) 
+to be customized in the service spec of the canary custom resource.
+
+#### Features
+
+- Add HTTP match conditions and URI rewrite to the canary service spec [#55](https://github.com/stefanprodan/flagger/pull/55)
+- Update virtual service when the canary service spec changes 
+    [#54](https://github.com/stefanprodan/flagger/pull/54)
+    [#51](https://github.com/stefanprodan/flagger/pull/51)
+
+#### Improvements 
+
+- Run e2e testing on [Kubernetes Kind](https://github.com/kubernetes-sigs/kind) for canary promotion 
+    [#53](https://github.com/stefanprodan/flagger/pull/53)
+
+
+## 0.5.1 (2019-02-14)
+
+Allows skipping the analysis phase to ship changes directly to production
+
+#### Features
+
+- Add option to skip the canary analysis [#46](https://github.com/stefanprodan/flagger/pull/46)
+
+#### Fixes
+
+- Reject deployment if the pod label selector doesn't match `app: <DEPLOYMENT_NAME>` [#43](https://github.com/stefanprodan/flagger/pull/43)
+
+## 0.5.0 (2019-01-30)
+
+Track changes in ConfigMaps and Secrets [#37](https://github.com/stefanprodan/flagger/pull/37)
+
+#### Features
+
+- Promote configmaps and secrets changes from canary to primary
+- Detect changes in configmaps and/or secrets and (re)start canary analysis
+- Add configs checksum to Canary CRD status
+- Create primary configmaps and secrets at bootstrap
+- Scan canary volumes and containers for configmaps and secrets
+
+#### Fixes
+
+- Copy deployment labels from canary to primary at bootstrap and promotion
+
+## 0.4.1 (2019-01-24)
+
+Load testing webhook [#35](https://github.com/stefanprodan/flagger/pull/35)
+
+#### Features
+
+- Add the load tester chart to Flagger Helm repository
+- Implement a load test runner based on [rakyll/hey](https://github.com/rakyll/hey)
+- Log warning when no values are found for Istio metric due to lack of traffic
+
+#### Fixes
+
+- Run wekbooks before the metrics checks to avoid failures when using a load tester
+
+## 0.4.0 (2019-01-18)
+
+Restart canary analysis if revision changes [#31](https://github.com/stefanprodan/flagger/pull/31)
+
+#### Breaking changes
+
+- Drop support for Kubernetes 1.10
+
+#### Features
+
+- Detect changes during canary analysis and reset advancement
+- Add status and additional printer columns to CRD
+- Add canary name and namespace to controller structured logs
+
+#### Fixes
+
+- Allow canary name to be different to the target name
+- Check if multiple canaries have the same target and log error
+- Use deep copy when updating Kubernetes objects
+- Skip readiness checks if canary analysis has finished
+
+## 0.3.0 (2019-01-11)
+
+Configurable canary analysis duration [#20](https://github.com/stefanprodan/flagger/pull/20)
+
+#### Breaking changes
+
+- Helm chart: flag `controlLoopInterval` has been removed
+
+#### Features
+
+- CRD: canaries.flagger.app v1alpha3
+- Schedule canary analysis independently based on `canaryAnalysis.interval`
+- Add analysis interval to Canary CRD (defaults to one minute)
+- Make autoscaler (HPA) reference optional
+
+## 0.2.0 (2019-01-04)
+
+Webhooks [#18](https://github.com/stefanprodan/flagger/pull/18)
+
+#### Features
+
+- CRD: canaries.flagger.app v1alpha2
+- Implement canary external checks based on webhooks HTTP POST calls
+- Add webhooks to Canary CRD
+- Move docs to gitbook [docs.flagger.app](https://docs.flagger.app)
+
+## 0.1.2 (2018-12-06)
+
+Improve Slack notifications [#14](https://github.com/stefanprodan/flagger/pull/14)
+
+#### Features
+
+- Add canary analysis metadata to init and start Slack messages
+- Add rollback reason to failed canary Slack messages
+
+## 0.1.1 (2018-11-28)
+
+Canary progress deadline [#10](https://github.com/stefanprodan/flagger/pull/10)
+
+#### Features
+
+- Rollback canary based on the deployment progress deadline check
+- Add progress deadline to Canary CRD (defaults to 10 minutes)
+
+## 0.1.0 (2018-11-25)
+
+First stable release
+
+#### Features
+
+- CRD: canaries.flagger.app v1alpha1
+- Notifications: post canary events to Slack
+- Instrumentation: expose Prometheus metrics for canary status and traffic weight percentage
+- Autoscaling: add HPA reference to CRD and create primary HPA at bootstrap
+- Bootstrap: create primary deployment, ClusterIP services and Istio virtual service based on CRD spec
+
+
+## 0.0.1 (2018-10-07)
+
+Initial semver release
+
+#### Features
+
+- Implement canary rollback based on failed checks threshold
+- Scale up the deployment when canary revision changes
+- Add OpenAPI v3 schema validation to Canary CRD
+- Use CRD status for canary state persistence
+- Add Helm charts for Flagger and Grafana
+- Add canary analysis Grafana dashboard 

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",
@@ -170,42 +163,25 @@
   revision = "f2b4162afba35581b6d4a50d3b8f34e33c144682"
 
 [[projects]]
-  digest = "1:555e31114bd0e89c6340c47ab73162e8c8d873e4d88914310923566f487bfcd5"
+  digest = "1:05ddd9088c0cfb8eaa3adf3626977caa6d96b3959a3bd8c91fef932fd1696c34"
   name = "github.com/knative/pkg"
   packages = [
-    "apis",
-    "apis/duck",
-    "apis/duck/v1alpha1",
     "apis/istio",
     "apis/istio/authentication",
     "apis/istio/authentication/v1alpha1",
     "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/duck/v1alpha1",
+    "client/clientset/versioned/typed/authentication/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"
+  revision = "f9612ef73847258e381e749c4f45b0f5e03b66e9"
 
 [[projects]]
   digest = "1:5985ef4caf91ece5d54817c11ea25f182697534f8ae6521eadcd628c142ac4b6"
@@ -495,10 +471,9 @@
   version = "kubernetes-1.11.0"
 
 [[projects]]
-  digest = "1:4b0d523ee389c762d02febbcfa0734c4530ebe87abe925db18f05422adcb33e8"
+  digest = "1:83b01e3d6f85c4e911de84febd69a2d3ece614c5a4a518fbc2b5d59000645980"
   name = "k8s.io/apimachinery"
   packages = [
-    "pkg/api/equality",
     "pkg/api/errors",
     "pkg/api/meta",
     "pkg/api/resource",
@@ -547,42 +522,72 @@
   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 +680,30 @@
   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",
     "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 +711,7 @@
     "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",

Gopkg.toml

@@ -47,7 +47,7 @@ required = [
 
 [[constraint]]
   name = "github.com/knative/pkg"
-  revision = "c15d7c8f2220a7578b33504df6edefa948c845ae"
+  revision = "f9612ef73847258e381e749c4f45b0f5e03b66e9"
 
 [[override]]
   name = "github.com/golang/glog"

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.istio.weavedx.com \
+	-slack-url=https://hooks.slack.com/services/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 \
+	-slack-channel="devops-alerts"
 
 build:
 	docker build -t stefanprodan/flagger:$(TAG) . -f Dockerfile
 
 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 ./*
 	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)" && \
@@ -39,6 +46,7 @@ version-set:
 	sed -i '' "s/flagger:$$current/flagger:$$next/g" artifacts/flagger/deployment.yaml && \
 	sed -i '' "s/tag: $$current/tag: $$next/g" charts/flagger/values.yaml && \
 	sed -i '' "s/appVersion: $$current/appVersion: $$next/g" charts/flagger/Chart.yaml && \
+	sed -i '' "s/version: $$current/version: $$next/g" charts/flagger/Chart.yaml && \
 	echo "Version $$next set in code, deployment and charts"
 
 version-up:
@@ -52,10 +60,10 @@ 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 +76,11 @@ 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 +2,42 @@
 
 [![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 acceptance tests, 
+load tests or any other custom validation.
+
+Flagger implements a control loop that gradually shifts traffic to the canary while measuring key performance 
+indicators like HTTP requests success rate, requests average duration and pods health. 
+Based on analysis of the KPIs a canary is promoted or aborted, and the analysis result is published to Slack.
+
+![flagger-overview](https://raw.githubusercontent.com/stefanprodan/flagger/master/docs/diagrams/flagger-canary-overview.png)
+
+### Documentation
+
+Flagger documentation can be found at [docs.flagger.app](https://docs.flagger.app)
+
+* Install
+    * [Flagger install on Kubernetes](https://docs.flagger.app/install/flagger-install-on-kubernetes)
+    * [Flagger install on GKE](https://docs.flagger.app/install/flagger-install-on-google-cloud)
+* How it works
+    * [Canary custom resource](https://docs.flagger.app/how-it-works#canary-custom-resource)
+    * [Virtual Service](https://docs.flagger.app/how-it-works#virtual-service)
+    * [Canary deployment stages](https://docs.flagger.app/how-it-works#canary-deployment)
+    * [Canary analysis](https://docs.flagger.app/how-it-works#canary-analysis)
+    * [HTTP metrics](https://docs.flagger.app/how-it-works#http-metrics)
+    * [Webhooks](https://docs.flagger.app/how-it-works#webhooks)
+    * [Load testing](https://docs.flagger.app/how-it-works#load-testing)
+* Usage
+    * [Canary promotions and rollbacks](https://docs.flagger.app/usage/progressive-delivery)
+    * [Monitoring](https://docs.flagger.app/usage/monitoring)
+    * [Alerting](https://docs.flagger.app/usage/alerting)
+* Tutorials
+    * [Canary deployments with Helm charts and Weave Flux](https://docs.flagger.app/tutorials/canary-helm-gitops)
 
 ### Install 
 
@@ -19,120 +48,70 @@ 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
+### Canary CRD
 
-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 optionally a horizontal pod autoscaler (HPA),
+then creates a series of objects (Kubernetes deployments, ClusterIP services and Istio virtual services).
+These objects expose the application on the mesh and drive the canary analysis and promotion.
 
-![flagger-overview](https://raw.githubusercontent.com/stefanprodan/flagger/master/docs/diagrams/flagger-overview.png)
+Flagger keeps track of ConfigMaps and Secrets referenced by a Kubernetes Deployment and triggers a canary analysis if any of those objects change. 
+When promoting a workload in production, both code (container images) and configuration (config maps and secrets) are being synchronised.
 
-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:
+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
+    # Istio virtual service HTTP match conditions (optional)
+    match:
+      - uri:
+          prefix: /
+    # Istio virtual service HTTP rewrite (optional)
+    rewrite:
+      uri: /
+  # for emergency cases when you want to ship changes
+  # in production without analysing the canary (default false)
+  skipAnalysis: false
   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 +119,7 @@ spec:
     # canary increment step
     # percentage (0-100)
     stepWeight: 5
+    # Istio Prometheus checks
     metrics:
     - name: istio_requests_total
       # minimum req success rate (non 5xx responses)
@@ -150,256 +130,23 @@ 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:
- 
-_HTTP requests success rate percentage_
-
-```sql
-sum(
-    rate(
-        istio_requests_total{
-          reporter="destination",
-          destination_workload_namespace=~"$namespace",
-          destination_workload=~"$workload",
-          response_code!~"5.*"
-        }[$interval]
-    )
-) 
-/ 
-sum(
-    rate(
-        istio_requests_total{
-          reporter="destination",
-          destination_workload_namespace=~"$namespace",
-          destination_workload=~"$workload"
-        }[$interval]
-    )
-)
-```
-
-_HTTP requests milliseconds duration P99_
-
-```sql
-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
-```
+For more details on how the canary analysis and promotion works please [read the docs](https://docs.flagger.app/how-it-works).
 
 ### 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 A/B testing capabilities using fixed routing based on HTTP headers and cookies match conditions
 * 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
 

artifacts/canaries/canary.yaml

@@ -0,0 +1,68 @@
+apiVersion: flagger.app/v1alpha3
+kind: Canary
+metadata:
+  name: podinfo
+  namespace: test
+spec:
+  # deployment reference
+  targetRef:
+    apiVersion: apps/v1
+    kind: Deployment
+    name: podinfo
+  # 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.istio.weavedx.com
+    # Istio virtual service HTTP match conditions (optional)
+    match:
+      - uri:
+          prefix: /
+    # Istio virtual service HTTP rewrite (optional)
+    rewrite:
+      uri: /
+  # for emergency cases when you want to ship changes
+  # in production without analysing the canary
+  skipAnalysis: false
+  canaryAnalysis:
+    # schedule interval (default 60s)
+    interval: 10s
+    # max number of failed metric checks before rollback
+    threshold: 10
+    # max traffic percentage routed to canary
+    # 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:1.4.0
+        imagePullPolicy: IfNotPresent
+        ports:
+        - containerPort: 9898
+          name: http
+          protocol: TCP
+        command:
+        - ./podinfo
+        - --port=9898
+        - --level=info
+        - --random-delay=false
+        - --random-error=false
+        env:
+        - name: PODINFO_UI_COLOR
+          value: blue
+        livenessProbe:
+          exec:
+            command:
+            - podcli
+            - check
+            - http
+            - localhost:9898/healthz
+          initialDelaySeconds: 5
+          timeoutSeconds: 5
+        readinessProbe:
+          exec:
+            command:
+            - podcli
+            - check
+            - http
+            - localhost:9898/readyz
+          initialDelaySeconds: 5
+          timeoutSeconds: 5
+        resources:
+          limits:
+            cpu: 2000m
+            memory: 512Mi
+          requests:
+            cpu: 100m
+            memory: 64Mi

artifacts/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/cluster/namespaces/test.yaml

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

artifacts/cluster/releases/test/backend.yaml

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

artifacts/cluster/releases/test/frontend.yaml

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

artifacts/cluster/releases/test/loadtester.yaml

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

artifacts/configs/canary.yaml

@@ -0,0 +1,58 @@
+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/configs/configs.yaml

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

artifacts/configs/deployment.yaml

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

artifacts/configs/hpa.yaml

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

artifacts/configs/secrets.yaml

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

artifacts/flagger/crd.yaml

@@ -4,47 +4,82 @@ 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
+            skipAnalysis:
+              type: boolean
             canaryAnalysis:
               properties:
+                interval:
+                  type: string
+                  pattern: "^[0-9]+(m|s)"
                 threshold:
                   type: number
                 maxWeight:
@@ -56,12 +91,27 @@ 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

@@ -22,8 +22,8 @@ spec:
       serviceAccountName: flagger
       containers:
       - name: flagger
-        image: stefanprodan/flagger:0.0.1
-        imagePullPolicy: Always
+        image: quay.io/stefanprodan/flagger:0.6.0
+        imagePullPolicy: IfNotPresent
         ports:
         - name: http
           containerPort: 8080
@@ -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/gke/istio-gateway.yaml

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

artifacts/gke/istio-prometheus.yaml

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

artifacts/loadtester/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/destination-rule.yaml

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

artifacts/routing/match.yaml

@@ -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: 0.6.0
+appVersion: 0.6.0
+kubeVersion: ">=1.11.0-0"
+engine: gotpl
 description: Flagger is a Kubernetes operator that automates the promotion of canary deployments using Istio routing for traffic shifting and Prometheus metrics for canary analysis.
-home: https://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 +5,82 @@ 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
+            skipAnalysis:
+              type: boolean
             canaryAnalysis:
               properties:
+                interval:
+                  type: string
+                  pattern: "^[0-9]+(m|s)"
                 threshold:
                   type: number
                 maxWeight:
@@ -57,12 +92,28 @@ 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: 0.6.0
   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: 1.0.0
+appVersion: 5.4.3
+description: Grafana dashboards for monitoring Flagger canary deployments
+icon: https://raw.githubusercontent.com/stefanprodan/flagger/master/docs/logo/flagger-icon.png
+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

@@ -2,7 +2,6 @@
   "annotations": {
     "list": [
       {
-        "$$hashKey": "object:1587",
         "builtIn": 1,
         "datasource": "-- Grafana --",
         "enable": true,
@@ -16,12 +15,12 @@
   "editable": true,
   "gnetId": null,
   "graphTooltip": 0,
-  "id": null,
-  "iteration": 1534587617141,
+  "id": 1,
+  "iteration": 1549736611069,
   "links": [],
   "panels": [
     {
-      "content": "<div class=\"dashboard-header text-center\">\n<span>RED: $primary.$namespace</span>\n</div>",
+      "content": "<div class=\"dashboard-header text-center\">\n<span>RED: $canary.$namespace</span>\n</div>",
       "gridPos": {
         "h": 3,
         "w": 24,
@@ -179,7 +178,6 @@
       "tableColumn": "",
       "targets": [
         {
-          "$$hashKey": "object:2857",
           "expr": "sum(irate(istio_requests_total{reporter=\"destination\",destination_workload_namespace=~\"$namespace\",destination_workload=~\"$primary\",response_code!~\"5.*\"}[30s])) / sum(irate(istio_requests_total{reporter=\"destination\",destination_workload_namespace=~\"$namespace\",destination_workload=~\"$primary\"}[30s]))",
           "format": "time_series",
           "intervalFactor": 1,
@@ -344,7 +342,6 @@
       "tableColumn": "",
       "targets": [
         {
-          "$$hashKey": "object:2810",
           "expr": "sum(irate(istio_requests_total{reporter=\"destination\",destination_workload_namespace=~\"$namespace\",destination_workload=~\"$canary\",response_code!~\"5.*\"}[30s])) / sum(irate(istio_requests_total{reporter=\"destination\",destination_workload_namespace=~\"$namespace\",destination_workload=~\"$canary\"}[30s]))",
           "format": "time_series",
           "intervalFactor": 1,
@@ -363,7 +360,7 @@
           "value": "null"
         }
       ],
-      "valueName": "avg"
+      "valueName": "current"
     },
     {
       "aliasColors": {},
@@ -432,6 +429,7 @@
       ],
       "thresholds": [],
       "timeFrom": null,
+      "timeRegions": [],
       "timeShift": null,
       "title": "Primary: Request Duration",
       "tooltip": {
@@ -464,7 +462,11 @@
           "min": null,
           "show": false
         }
-      ]
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
     },
     {
       "aliasColors": {},
@@ -533,6 +535,7 @@
       ],
       "thresholds": [],
       "timeFrom": null,
+      "timeRegions": [],
       "timeShift": null,
       "title": "Canary: Request Duration",
       "tooltip": {
@@ -565,10 +568,14 @@
           "min": null,
           "show": false
         }
-      ]
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
     },
     {
-      "content": "<div class=\"dashboard-header text-center\">\n<span>USE: $primary.$namespace</span>\n</div>",
+      "content": "<div class=\"dashboard-header text-center\">\n<span>USE: $canary.$namespace</span>\n</div>",
       "gridPos": {
         "h": 3,
         "w": 24,
@@ -623,7 +630,6 @@
       "steppedLine": false,
       "targets": [
         {
-          "$$hashKey": "object:1685",
           "expr": "sum(rate(container_cpu_usage_seconds_total{cpu=\"total\",namespace=\"$namespace\",pod_name=~\"$primary.*\", container_name!~\"POD|istio-proxy\"}[1m])) by (pod_name)",
           "format": "time_series",
           "hide": false,
@@ -634,6 +640,7 @@
       ],
       "thresholds": [],
       "timeFrom": null,
+      "timeRegions": [],
       "timeShift": null,
       "title": "Primary: CPU Usage by Pod",
       "tooltip": {
@@ -651,7 +658,6 @@
       },
       "yaxes": [
         {
-          "$$hashKey": "object:1845",
           "format": "s",
           "label": "CPU seconds / second",
           "logBase": 1,
@@ -660,7 +666,6 @@
           "show": true
         },
         {
-          "$$hashKey": "object:1846",
           "format": "short",
           "label": null,
           "logBase": 1,
@@ -668,7 +673,11 @@
           "min": null,
           "show": false
         }
-      ]
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
     },
     {
       "aliasColors": {},
@@ -711,8 +720,7 @@
       "steppedLine": false,
       "targets": [
         {
-          "$$hashKey": "object:1685",
-          "expr": "sum(rate(container_cpu_usage_seconds_total{cpu=\"total\",namespace=\"$namespace\",pod_name=~\"$canary.*\", container_name!~\"POD|istio-proxy\"}[1m])) by (pod_name)",
+          "expr": "sum(rate(container_cpu_usage_seconds_total{cpu=\"total\",namespace=\"$namespace\",pod_name=~\"$canary.*\", pod_name!~\"$primary.*\", container_name!~\"POD|istio-proxy\"}[1m])) by (pod_name)",
           "format": "time_series",
           "hide": false,
           "intervalFactor": 1,
@@ -722,6 +730,7 @@
       ],
       "thresholds": [],
       "timeFrom": null,
+      "timeRegions": [],
       "timeShift": null,
       "title": "Canary: CPU Usage by Pod",
       "tooltip": {
@@ -739,7 +748,6 @@
       },
       "yaxes": [
         {
-          "$$hashKey": "object:1845",
           "format": "s",
           "label": "CPU seconds / second",
           "logBase": 1,
@@ -748,7 +756,6 @@
           "show": true
         },
         {
-          "$$hashKey": "object:1846",
           "format": "short",
           "label": null,
           "logBase": 1,
@@ -756,7 +763,11 @@
           "min": null,
           "show": false
         }
-      ]
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
     },
     {
       "aliasColors": {},
@@ -799,7 +810,6 @@
       "steppedLine": false,
       "targets": [
         {
-          "$$hashKey": "object:1685",
           "expr": "sum(container_memory_working_set_bytes{namespace=\"$namespace\",pod_name=~\"$primary.*\", container_name!~\"POD|istio-proxy\"}) by (pod_name)",
           "format": "time_series",
           "hide": false,
@@ -811,6 +821,7 @@
       ],
       "thresholds": [],
       "timeFrom": null,
+      "timeRegions": [],
       "timeShift": null,
       "title": "Primary: Memory Usage by Pod",
       "tooltip": {
@@ -828,7 +839,6 @@
       },
       "yaxes": [
         {
-          "$$hashKey": "object:1845",
           "decimals": null,
           "format": "bytes",
           "label": "",
@@ -838,7 +848,6 @@
           "show": true
         },
         {
-          "$$hashKey": "object:1846",
           "format": "short",
           "label": null,
           "logBase": 1,
@@ -846,7 +855,11 @@
           "min": null,
           "show": false
         }
-      ]
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
     },
     {
       "aliasColors": {},
@@ -889,8 +902,7 @@
       "steppedLine": false,
       "targets": [
         {
-          "$$hashKey": "object:1685",
-          "expr": "sum(container_memory_working_set_bytes{namespace=\"$namespace\",pod_name=~\"$canary.*\", container_name!~\"POD|istio-proxy\"}) by (pod_name)",
+          "expr": "sum(container_memory_working_set_bytes{namespace=\"$namespace\",pod_name=~\"$canary.*\", pod_name!~\"$primary.*\", container_name!~\"POD|istio-proxy\"}) by (pod_name)",
           "format": "time_series",
           "hide": false,
           "interval": "",
@@ -901,6 +913,7 @@
       ],
       "thresholds": [],
       "timeFrom": null,
+      "timeRegions": [],
       "timeShift": null,
       "title": "Canary: Memory Usage by Pod",
       "tooltip": {
@@ -918,7 +931,6 @@
       },
       "yaxes": [
         {
-          "$$hashKey": "object:1845",
           "decimals": null,
           "format": "bytes",
           "label": "",
@@ -928,7 +940,6 @@
           "show": true
         },
         {
-          "$$hashKey": "object:1846",
           "format": "short",
           "label": null,
           "logBase": 1,
@@ -936,7 +947,11 @@
           "min": null,
           "show": false
         }
-      ]
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
     },
     {
       "aliasColors": {},
@@ -975,12 +990,10 @@
       "renderer": "flot",
       "seriesOverrides": [
         {
-          "$$hashKey": "object:3641",
           "alias": "received",
           "color": "#f9d9f9"
         },
         {
-          "$$hashKey": "object:3649",
           "alias": "transmited",
           "color": "#f29191"
         }
@@ -990,7 +1003,6 @@
       "steppedLine": false,
       "targets": [
         {
-          "$$hashKey": "object:2598",
           "expr": "sum(rate (container_network_receive_bytes_total{namespace=\"$namespace\",pod_name=~\"$primary.*\"}[1m])) ",
           "format": "time_series",
           "intervalFactor": 1,
@@ -998,7 +1010,6 @@
           "refId": "A"
         },
         {
-          "$$hashKey": "object:3245",
           "expr": "-sum (rate (container_network_transmit_bytes_total{namespace=\"$namespace\",pod_name=~\"$primary.*\"}[1m]))",
           "format": "time_series",
           "intervalFactor": 1,
@@ -1008,6 +1019,7 @@
       ],
       "thresholds": [],
       "timeFrom": null,
+      "timeRegions": [],
       "timeShift": null,
       "title": "Primary: Network I/O",
       "tooltip": {
@@ -1025,7 +1037,6 @@
       },
       "yaxes": [
         {
-          "$$hashKey": "object:1845",
           "decimals": null,
           "format": "Bps",
           "label": "",
@@ -1035,7 +1046,6 @@
           "show": true
         },
         {
-          "$$hashKey": "object:1846",
           "format": "short",
           "label": null,
           "logBase": 1,
@@ -1043,7 +1053,11 @@
           "min": null,
           "show": false
         }
-      ]
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
     },
     {
       "aliasColors": {},
@@ -1082,12 +1096,10 @@
       "renderer": "flot",
       "seriesOverrides": [
         {
-          "$$hashKey": "object:3641",
           "alias": "received",
           "color": "#f9d9f9"
         },
         {
-          "$$hashKey": "object:3649",
           "alias": "transmited",
           "color": "#f29191"
         }
@@ -1097,16 +1109,14 @@
       "steppedLine": false,
       "targets": [
         {
-          "$$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",
           "refId": "A"
         },
         {
-          "$$hashKey": "object:3245",
-          "expr": "-sum (rate (container_network_transmit_bytes_total{namespace=\"$namespace\",pod_name=~\"$canary.*\"}[1m]))",
+          "expr": "-sum (rate (container_network_transmit_bytes_total{namespace=\"$namespace\",pod_name=~\"$canary.*\",pod_name!~\"$primary.*\"}[1m]))",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "transmited",
@@ -1115,6 +1125,7 @@
       ],
       "thresholds": [],
       "timeFrom": null,
+      "timeRegions": [],
       "timeShift": null,
       "title": "Canary: Network I/O",
       "tooltip": {
@@ -1132,7 +1143,6 @@
       },
       "yaxes": [
         {
-          "$$hashKey": "object:1845",
           "decimals": null,
           "format": "Bps",
           "label": "",
@@ -1142,7 +1152,6 @@
           "show": true
         },
         {
-          "$$hashKey": "object:1846",
           "format": "short",
           "label": null,
           "logBase": 1,
@@ -1150,10 +1159,14 @@
           "min": null,
           "show": false
         }
-      ]
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
     },
     {
-      "content": "<div class=\"dashboard-header text-center\">\n<span>IN/OUTBOUND: $primary.$namespace</span>\n</div>",
+      "content": "<div class=\"dashboard-header text-center\">\n<span>IN/OUTBOUND: $canary.$namespace</span>\n</div>",
       "gridPos": {
         "h": 3,
         "w": 24,
@@ -1205,7 +1218,6 @@
       "steppedLine": false,
       "targets": [
         {
-          "$$hashKey": "object:1953",
           "expr": "round(sum(irate(istio_requests_total{connection_security_policy=\"mutual_tls\", destination_workload_namespace=~\"$namespace\", destination_workload=~\"$primary\", reporter=\"destination\"}[30s])) by (source_workload, source_workload_namespace, response_code), 0.001)",
           "format": "time_series",
           "hide": false,
@@ -1215,7 +1227,6 @@
           "step": 2
         },
         {
-          "$$hashKey": "object:1954",
           "expr": "round(sum(irate(istio_requests_total{connection_security_policy!=\"mutual_tls\", destination_workload_namespace=~\"$namespace\", destination_workload=~\"$primary\", reporter=\"destination\"}[30s])) by (source_workload, source_workload_namespace, response_code), 0.001)",
           "format": "time_series",
           "hide": false,
@@ -1227,6 +1238,7 @@
       ],
       "thresholds": [],
       "timeFrom": null,
+      "timeRegions": [],
       "timeShift": null,
       "title": "Primary: Incoming Requests by Source And Response Code",
       "tooltip": {
@@ -1246,7 +1258,6 @@
       },
       "yaxes": [
         {
-          "$$hashKey": "object:1999",
           "format": "ops",
           "label": null,
           "logBase": 1,
@@ -1255,7 +1266,6 @@
           "show": true
         },
         {
-          "$$hashKey": "object:2000",
           "format": "short",
           "label": null,
           "logBase": 1,
@@ -1263,7 +1273,11 @@
           "min": null,
           "show": false
         }
-      ]
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
     },
     {
       "aliasColors": {},
@@ -1323,6 +1337,7 @@
       ],
       "thresholds": [],
       "timeFrom": null,
+      "timeRegions": [],
       "timeShift": null,
       "title": "Canary: Incoming Requests by Source And Response Code",
       "tooltip": {
@@ -1357,7 +1372,11 @@
           "min": null,
           "show": false
         }
-      ]
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
     },
     {
       "aliasColors": {},
@@ -1416,6 +1435,7 @@
       ],
       "thresholds": [],
       "timeFrom": null,
+      "timeRegions": [],
       "timeShift": null,
       "title": "Primary: Outgoing Requests by Destination And Response Code",
       "tooltip": {
@@ -1450,7 +1470,11 @@
           "min": null,
           "show": false
         }
-      ]
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
     },
     {
       "aliasColors": {},
@@ -1509,6 +1533,7 @@
       ],
       "thresholds": [],
       "timeFrom": null,
+      "timeRegions": [],
       "timeShift": null,
       "title": "Canary: Outgoing Requests by Destination And Response Code",
       "tooltip": {
@@ -1543,7 +1568,11 @@
           "min": null,
           "show": false
         }
-      ]
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
     }
   ],
   "refresh": "10s",
@@ -1555,10 +1584,12 @@
       {
         "allValue": null,
         "current": {
-          "text": "demo",
-          "value": "demo"
+          "selected": true,
+          "text": "test",
+          "value": "test"
         },
         "datasource": "prometheus",
+        "definition": "",
         "hide": 0,
         "includeAll": false,
         "label": "Namespace",
@@ -1568,6 +1599,7 @@
         "query": "query_result(sum(istio_requests_total) by (destination_workload_namespace) or sum(istio_tcp_sent_bytes_total) by (destination_workload_namespace))",
         "refresh": 1,
         "regex": "/.*_namespace=\"([^\"]*).*/",
+        "skipUrlSync": false,
         "sort": 0,
         "tagValuesQuery": "",
         "tags": [],
@@ -1578,10 +1610,12 @@
       {
         "allValue": null,
         "current": {
-          "text": "primary",
-          "value": "primary"
+          "selected": false,
+          "text": "backend-primary",
+          "value": "backend-primary"
         },
         "datasource": "prometheus",
+        "definition": "",
         "hide": 0,
         "includeAll": false,
         "label": "Primary",
@@ -1591,6 +1625,7 @@
         "query": "query_result(sum(istio_requests_total{destination_workload_namespace=~\"$namespace\"}) by (destination_service_name))",
         "refresh": 1,
         "regex": "/.*destination_service_name=\"([^\"]*).*/",
+        "skipUrlSync": false,
         "sort": 1,
         "tagValuesQuery": "",
         "tags": [],
@@ -1601,10 +1636,12 @@
       {
         "allValue": null,
         "current": {
-          "text": "canary",
-          "value": "canary"
+          "selected": true,
+          "text": "backend",
+          "value": "backend"
         },
         "datasource": "prometheus",
+        "definition": "",
         "hide": 0,
         "includeAll": false,
         "label": "Canary",
@@ -1614,6 +1651,7 @@
         "query": "query_result(sum(istio_requests_total{destination_workload_namespace=~\"$namespace\"}) by (destination_service_name))",
         "refresh": 1,
         "regex": "/.*destination_service_name=\"([^\"]*).*/",
+        "skipUrlSync": false,
         "sort": 1,
         "tagValuesQuery": "",
         "tags": [],
@@ -1653,7 +1691,7 @@
     ]
   },
   "timezone": "",
-  "title": "Flagger",
+  "title": "Flagger canary",
   "uid": "RdykD7tiz",
-  "version": 2
-}
+  "version": 3
+}

charts/grafana/templates/deployment.yaml

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

charts/grafana/values.yaml

@@ -6,7 +6,7 @@ replicaCount: 1
 
 image:
   repository: grafana/grafana
-  tag: 5.2.4
+  tag: 5.4.3
   pullPolicy: IfNotPresent
 
 service:
@@ -28,7 +28,7 @@ tolerations: []
 affinity: {}
 
 user: admin
-password: admin
+password:
 
 # Istio Prometheus instance
 url: http://prometheus:9090

charts/loadtester/.helmignore

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

charts/loadtester/Chart.yaml

@@ -0,0 +1,20 @@
+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/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

charts/podinfo/Chart.yaml

@@ -1,10 +1,10 @@
 apiVersion: v1
 version: 2.0.0
-appVersion: 1.2.1
+appVersion: 1.4.0
+name: podinfo
 engine: gotpl
-name: podinfo-flagger
-description: Podinfo Helm chart for Flagger progressive delivery
-home: https://github.com/stefanprodan/k8s-podinfo
+description: Flagger canary deployment demo chart
+home: https://github.com/stefanprodan/flagger
 maintainers:
 - email: stefanprodan@users.noreply.github.com
   name: stefanprodan

charts/podinfo/README.md

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

charts/podinfo/templates/NOTES.txt

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

charts/podinfo/templates/_helpers.tpl

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

charts/podinfo/templates/canary.yaml

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

charts/podinfo/templates/configmap.yaml

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

charts/podinfo/templates/deployment.yaml

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

charts/podinfo/templates/hpa.yaml

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

charts/podinfo/templates/service.yaml

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

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

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

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

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

charts/podinfo/values.yaml

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

cmd/flagger/main.go

@@ -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