Merge pull request #11 from keptn-contrib/release-0.1.0

Release 0.1.0

.dockerignore

@@ -0,0 +1,5 @@
+.vscode/
+.idea/
+docs/
+deploy/
+Dockerfile

.gitignore

@@ -0,0 +1,8 @@
+.vscode
+
+.idea/*
+# allow shared run configurations
+!.idea/runConfigurations/
+
+vendor
+

.travis.yml

@@ -0,0 +1,118 @@
+dist: xenial
+language: bash
+services:
+  - docker
+env:
+  global:
+    - GO111MODULE=on
+before_install:
+  - export TZ=Europe/Vienna
+  - IMAGE=keptn/prometheus-sli-service
+  - REPO_URL="$(git remote get-url --all origin)"
+  # get the last tag
+  - GIT_LAST_TAG=$(git describe --tags $(git rev-list --tags) || echo "0.0.0")
+  - GIT_NUM_COMMITS_SINCE_LAST_TAG=$(git rev-list ${GIT_LAST_TAG}..HEAD --count || echo "trunk")
+  # get current branch name
+  - GIT_BRANCH_NAME=$(git branch | grep \* | cut -d ' ' -f2)
+  - GIT_SHA=$(git rev-parse --short HEAD)
+  - GIT_BRANCH_AND_COMMIT=$(git describe --exact-match 2> /dev/null || echo "`git symbolic-ref HEAD 2> /dev/null | cut -b 12-`-`git log --pretty=format:\"%h\" -1`")
+  # find out if we are on a tag (= exact match)
+  # if not: use tag + number of commit + commit hash
+  - VERSION="$(cat version | tr -d '[:space:]')"
+  - DATE="$(date +'%Y%m%d.%H%M')"
+  - ./writeManifest.sh
+  - cat MANIFEST
+  # uncomment certain lines from Dockerfile that are for travis builds only
+  - sed -i '/#travis-uncomment/s/^#travis-uncomment //g' Dockerfile
+jobs:
+  include:
+    - stage: codestyle
+      # Check Codestyle using go fmt
+      services: []
+      language: go
+      go:
+        - 1.12.x
+      # skip install
+      install: true
+      script:
+        - echo "Checking code style..."
+        - unformatted=$(gofmt -l .)
+        - |
+          if [ ! -z "$unformatted" ]; then
+            echo "Code Style Check failed for the following files: ${unformatted}".
+            echo "Please run: gofmt -w ."
+            echo "After that ammend your commit (e.g.: git add ${unformatted} && git commit --amend --no-edit) and force push the changes (git push -f)."
+            travis_terminate 1
+          fi
+
+    - stage: tests
+      # Run tests
+      services: []
+      language: go
+      go:
+        - 1.12.x
+      # cache some go files
+      cache:
+        directories:
+          - $HOME/.cache/go-build
+          - $HOME/gopath/pkg/mod
+      addons:
+        sonarcloud:
+          organization: "keptn-contrib"
+      script:
+        - sonar-scanner
+        - go build
+        - go test -race -v ./...
+
+    - stage: feature/bug/hotfix/patch
+      # build docker images for feature/bug/hotfix/patch branches
+      if: branch =~ ^feature.*$ OR branch =~ ^bug.*$ OR branch =~ ^hotfix.*$ OR branch =~ ^patch.*$
+      script:
+        - echo $TRAVIS_BUILD_STAGE_NAME
+        - TYPE="$(echo $TRAVIS_BRANCH | cut -d'/' -f1)"
+        - NUMBER="$(echo $TRAVIS_BRANCH | cut -d'/' -f2)"
+        - docker build . -t "${IMAGE}:${GIT_SHA}"
+        - docker tag "${IMAGE}:${GIT_SHA}" "${IMAGE}:${TYPE}.${NUMBER}.${DATE}"
+      after_success:
+        - echo "$REGISTRY_PASSWORD" | docker login --username $REGISTRY_USER --password-stdin
+        - docker push "${IMAGE}:${GIT_SHA}"
+        - docker push "${IMAGE}:${TYPE}.${NUMBER}.${DATE}"
+
+
+    - stage: develop
+      # build docker images for develop branch
+      if: branch = develop AND NOT type = pull_request
+      script:
+        - echo $TRAVIS_BUILD_STAGE_NAME
+        - docker build . -t "${IMAGE}:${GIT_SHA}"
+        - docker tag "${IMAGE}:${GIT_SHA}" "${IMAGE}:${DATE}"
+        - docker tag "${IMAGE}:${GIT_SHA}" "${IMAGE}:latest"
+      after_success:
+        - echo "$REGISTRY_PASSWORD" | docker login --username $REGISTRY_USER --password-stdin
+        - docker push "${IMAGE}:${GIT_SHA}"
+        - docker push "${IMAGE}:${DATE}"
+        - docker push "${IMAGE}:latest"
+
+    - stage: release-branch
+      # build docker images for release branches
+      if: branch =~ ^release.*$ AND NOT type = pull_request
+      script:
+        - echo $TRAVIS_BUILD_STAGE_NAME
+        - docker build . -t "${IMAGE}:${GIT_SHA}"
+        - docker tag "${IMAGE}:${GIT_SHA}" "${IMAGE}:${VERSION}.${DATE}"
+        - docker tag "${IMAGE}:${GIT_SHA}" "${IMAGE}:${VERSION}.latest"
+      after_success:
+        - echo "$REGISTRY_PASSWORD" | docker login --username $REGISTRY_USER --password-stdin
+        - docker push "${IMAGE}:${GIT_SHA}"
+        - docker push "${IMAGE}:${VERSION}.${DATE}"
+        - docker push "${IMAGE}:${VERSION}.latest"
+
+    - stage: tags
+      # build docker images for tags
+      if: tag IS present
+      script:
+        - echo $TRAVIS_BUILD_STAGE_NAME
+        - docker build . -t "${IMAGE}:${VERSION}"
+      after_success:
+        - echo "$REGISTRY_PASSWORD" | docker login --username $REGISTRY_USER --password-stdin
+        - docker push "${IMAGE}:${VERSION}"

CODEOWNERS

@@ -1,4 +1,5 @@
 # Lines starting with '#' are comments.
 # Each line is a file pattern followed by one or more owners.
 
-# These owners will be the default owners for everything in the repo.
+# These owners will be the default owners for everything in the repo.
+* @christian-kreuzberger-dtx @bacherfl

Dockerfile

@@ -0,0 +1,54 @@
+# from https://skaffold.dev/docs/workflows/debug/
+# Use the offical Golang image to create a build artifact.
+# This is based on Debian and sets the GOPATH to /go.
+# https://hub.docker.com/_/golang
+FROM golang:1.12 as builder
+
+WORKDIR /go/src/github.com/keptn-contrib/prometheus-sli-service
+
+ENV GO111MODULE=on
+ENV BUILDFLAGS=""
+
+# Copy `go.mod` for definitions and `go.sum` to invalidate the next layer
+# in case of a change in the dependencies
+COPY go.mod go.sum ./
+
+# download dependencies
+RUN go mod download
+
+ARG debugBuild
+
+# set buildflags for debug build
+RUN if [ ! -z "$debugBuild" ]; then export BUILDFLAGS='-gcflags "all=-N -l"'; fi
+
+# finally Copy local code to the container image.
+COPY . .
+
+# Build the command inside the container.
+# (You may fetch or manage dependencies here, either manually or with a tool like "godep".)
+RUN CGO_ENABLED=0 GOOS=linux go build $BUILDFLAGS -v -o prometheus-sli-service
+
+# Use a Docker multi-stage build to create a lean production image.
+# https://docs.docker.com/develop/develop-images/multistage-build/#use-multi-stage-builds
+FROM alpine:3.7
+RUN apk add --no-cache ca-certificates
+
+ARG debugBuild
+
+# IF we are debugging, we need to install libc6-compat for delve to work on alpine based containers
+RUN if [ ! -z "$debugBuild" ]; then apk add --no-cache libc6-compat; fi
+
+# Copy the binary to the production image from the builder stage.
+COPY --from=builder /go/src/github.com/keptn-contrib/prometheus-sli-service/prometheus-sli-service /prometheus-sli-service
+
+EXPOSE 8080
+
+# required for external tools to detect this as a go binary
+ENV GOTRACEBACK=all
+
+# KEEP THE FOLLOWING LINES COMMENTED OUT!!! (they will be included within the travis-ci build)
+#travis-uncomment ADD MANIFEST /
+#travis-uncomment COPY entrypoint.sh /
+#travis-uncomment ENTRYPOINT ["/entrypoint.sh"]
+
+CMD ["/prometheus-sli-service"]

MANIFEST

@@ -0,0 +1,8 @@
+##########
+branch: MANIFEST_BRANCH
+repository: MANIFEST_REPOSITORY
+commitlink: MANIFEST_REPOSITORY/commit/MANIFEST_COMMIT
+repolink: MANIFEST_REPOSITORY/tree/MANIFEST_COMMIT
+travisbuild: MANIFEST_TRAVIS_JOB_URL
+timestamp: MANIFEST_DATE
+##########

README.md

@@ -1,6 +1,103 @@
 # Prometheus SLI Service
+![GitHub release (latest by date)](https://img.shields.io/github/v/release/keptn-contrib/prometheus-sli-service)
+[![Build Status](https://travis-ci.org/keptn-contrib/prometheus-sli-service.svg?branch=master)](https://travis-ci.org/keptn-contrib/prometheus-sli-service)
+[![Go Report Card](https://goreportcard.com/badge/github.com/keptn-contrib/prometheus-sli-service)](https://goreportcard.com/report/github.com/keptn-contrib/prometheus-sli-service)
 
-The *prometheus-sli-service* is a Keptn service that is responsible for retrieving the values of Keptn-supported SLIs from a Prometheus API endpoint.
+This service is used for retrieving service level indicators (SLIs) from a prometheus API endpoint. Per default, it fetches metrics from the prometheus instance set up by Keptn
+(`prometheus-service.monitoring.svc.cluster.local:8080`), but it can also be configures to use any reachable Prometheus endpoint using basic authentication by providing the credentials
+via a secret in the `keptn` namespace of the cluster.
+
+The supported default SLIs are:
+
+ - throughput
+ - error_rate
+ - response_time_p50
+ - response_time_p90
+ - response_time_p95
+
+The provided SLIs are based on the [RED metrics](https://grafana.com/files/grafanacon_eu_2018/Tom_Wilkie_GrafanaCon_EU_2018.pdf)
+
+## Basic Usage 
+
+Per default, the service works with the following assumptions regarding the setup of the Prometheus instance:
+
+ - Each **service** within a **stage** of a **project** has a Prometheus scrape job definition with the name: `<service>-<project>-<stage>`
+
+    For example, if `project=sockshop`, `stage=production` and `service=carts`, the scrape job name would have to be `carts-sockshop-production`.
+
+ - Every service provides the following Metrics for its corresponding scrape job:
+     - http_response_time_milliseconds (Histogram)
+     - http_requests_total (Counter)
+
+       This metric has to contain the `status` label, indicating the HTTP response code of the requests handled by the service.
+       It is highly recommended that this metric also provides a label to query metric values for specific endpoints, e.g. `handler`
+
+       An example of an entry would look like this: `http_requests_total{method="GET",handler="VersionController.getInformation",status="200",} 4.0`
+
+ - Based on those metrics, the queries for the SLIs are built as follows:
+
+   - **throughput**: `sum(rate(http_requests_total{job="<service>-<project>-<stage>-canary"}[<test_duration_in_seconds>s]))`
+   - **error_rate**: `sum(rate(http_requests_total{job="<service>-<project>-<stage>-canary",status!~'2..'}[<test_duration_in_seconds>s]))/sum(rate(http_requests_total{job="<service>-<project>-<stage>-canary"}[<test_duration_in_seconds>s]))`
+   - **response_time_p50**: `histogram_quantile(0.50, sum(rate(http_response_time_milliseconds_bucket{job='<service>-<project>-<stage>-canary'}[<test_duration_in_seconds>s])) by (le))`
+   - **response_time_p90**: `histogram_quantile(0.90, sum(rate(http_response_time_milliseconds_bucket{job='<service>-<project>-<stage>-canary'}[<test_duration_in_seconds>s])) by (le))`
+   - **response_time_p95**: `histogram_quantile(0.95, sum(rate(http_response_time_milliseconds_bucket{job='<service>-<project>-<stage>-canary'}[<test_duration_in_seconds>s])) by (le))` 
+
+## Advanced Usage
+
+### Using an external Prometheus instance
+To use a Prometheus instance other than the one that's being managed by Keptn for a certain project, a secret containing the URL and the access credentials has to be deployed into the `keptn` namespace. The secret must have the following format:
+
+```yaml
+user: test
+password: test
+url: http://prometheus-service.monitoring.svc.cluster.local:8080
+```
+
+If this information is stored in a file, e.g. `prometheus-creds.yaml`, it can be stored with the following command (don't forget to replace the `<project>` placeholder with the name of your project:
+
+```bash
+kubectl create secret -n keptn generic prometheus-credentials-<project> --from-file=prometheus-credentials=./mock_secret.yaml
+```
+
+Please note that there is a naming convention for the secret, because this can be configured per **project**. Therefore, the secret has to have the name `prometheus-credentials-<project>`
+
+
+### Custom SLI queries
+
+Users can override the predefined queries, as well as add custom SLI queries by creating a `ConfigMap` with the name `prometheus-sli-config-<project>` in the `keptn` namespace.
+In this ConfigMap, a YAML object containing the queries can be defined, e.g.:
+
+```yaml
+kind: ConfigMap
+apiVersion: v1
+metadata:
+  name: prometheus-sli-config-sockshop
+  namespace: keptn
+data:
+  custom-queries: |
+    throughput: "rate(my_custom_metric{job='$SERVICE-$PROJECT-$STAGE',handler=~'$handler'}[$DURATION_SECONDS])"
+    error_rate: "sum(rate(my_custom_metric{job='$SERVICE-$PROJECT-$STAGE',handler=~'$handler',status!~'2..'}[1s]))/sum(rate(my_custom_metric{job='$SERVICE-$PROJECT-$STAGE',handler=~'$handler'}[$DURATION_SECONDS]))"
+    response_time_p50: "histogram_quantile(0.50,sum(rate(my_custom_response_time_metric{job='$SERVICE-$PROJECT-$STAGE'}[$DURATION_SECONDS]))by(le))"
+    response_time_p90: "histogram_quantile(0.90,sum(rate(my_custom_response_time_metric{job='$SERVICE-$PROJECT-$STAGE'}[$DURATION_SECONDS]))by(le))"
+    response_time_p95: "histogram_quantile(0.95,sum(rate(my_custom_response_time_metric{job='$SERVICE-$PROJECT-$STAGE'}[$DURATION_SECONDS]))by(le))"
+    # Example for a custom SLI that is not part of the default SLIs
+    cpu_usage: avg(rate(container_cpu_usage_seconds_total{namespace="$PROJECT-$STAGE",pod_name=~"$SERVICE-primary-.*"}[5m]))
+```
+
+Note that, similarly, to the custom endpoint configuration, the name of the ConfigMap has to be `prometheus-sli-config-<project>`, and has to be stored in the `keptn` namespace.
+
+Within the user-defined queries, the following variables can be used to dynamically build the query, depending on the project/stage/service, and the time frame:
+
+- $PROJECT: will be replaced with the name of the project
+- $STAGE: will be replaced with the name of the stage
+- $SERVICE: will be replaced with the name of the service
+- $DURATION_SECONDS: will be replaced with the test run duration, e.g. 30s
+
+For example, if an evaluation for the service **carts**  in the stage **production** of the project **sockshop** is triggered, and the tests ran for 30s these will be the resulting queries:
+
+```
+rate(my_custom_metric{job='$SERVICE-$PROJECT-$STAGE',handler=~'$handler'}[$DURATION_SECONDS]) => rate(my_custom_metric{job='carts-sockshop-production',handler=~'$handler'}[30s])
+```
 
 ## Installation
 

deploy/distributor.yaml

@@ -0,0 +1,36 @@
+---
+## prometheus-sli-service sh.keptn.internal.event.get-sli-distributor
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: prometheus-sli-service-monitoring-configure-distributor
+  namespace: keptn
+spec:
+  selector:
+    matchLabels:
+      run: distributor
+  replicas: 1
+  template:
+    metadata:
+      labels:
+        run: distributor
+    spec:
+      containers:
+      - name: distributor
+        image: keptn/distributor:latest
+        ports:
+        - containerPort: 8080
+        resources:
+          requests:
+            memory: "32Mi"
+            cpu: "50m"
+          limits:
+            memory: "128Mi"
+            cpu: "500m"
+        env:
+        - name: PUBSUB_URL
+          value: 'nats://keptn-nats-cluster'
+        - name: PUBSUB_TOPIC
+          value: 'sh.keptn.internal.event.get-sli'
+        - name: PUBSUB_RECIPIENT
+          value: 'prometheus-sli-service'