If a GitLab project is configured on GitLab CI, is there a way to run the build locally?
I don't want to turn my laptop into a build "runner", I just want to take advantage of Docker and .gitlab-ci.yml to run tests locally (i.e. it's all pre-configured). Another advantage of that is that I'm sure that I'm using the same environment locally and on CI.
Here is an example of how to run Travis builds locally using Docker, I'm looking for something similar with GitLab.
Since a few months ago this is possible using gitlab-runner:
gitlab-runner exec docker my-job-name
Note that you need both docker and gitlab-runner installed on your computer to get this working.
You also need the image key defined in your .gitlab-ci.yml file. Otherwise won't work.
Here's the line I currently use for testing locally using gitlab-runner:
gitlab-runner exec docker test --docker-volumes "/home/elboletaire/.ssh/id_rsa:/root/.ssh/id_rsa:ro"
Note: You can avoid adding a --docker-volumes with your key setting it by default in /etc/gitlab-runner/config.toml. See the official documentation for more details. Also, use gitlab-runner exec docker --help to see all docker-based runner options (like variables, volumes, networks, etc.).
Due to the confusion in the comments, I paste here the gitlab-runner --help result, so you can see that gitlab-runner can make builds locally:
gitlab-runner --help
NAME:
gitlab-runner - a GitLab Runner
USAGE:
gitlab-runner [global options] command [command options] [arguments...]
VERSION:
1.1.0~beta.135.g24365ee (24365ee)
AUTHOR(S):
Kamil Trzciński <ayufan#ayufan.eu>
COMMANDS:
exec execute a build locally
[...]
GLOBAL OPTIONS:
--debug debug mode [$DEBUG]
[...]
As you can see, the exec command is to execute a build locally.
Even though there was an issue to deprecate the current gitlab-runner exec behavior, it ended up being reconsidered and a new version with greater features will replace the current exec functionality.
Note that this process is to use your own machine to run the tests using docker containers. This is not to define custom runners. To do so, just go to your repo's CI/CD settings and read the documentation there. If you wanna ensure your runner is executed instead of one from gitlab.com, add a custom and unique tag to your runner, ensure it only runs tagged jobs and tag all the jobs you want your runner to be responsible of.
I use this docker-based approach:
Edit: 2022-10
docker run --entrypoint bash --rm -w $PWD -v $PWD:$PWD -v /var/run/docker.sock:/var/run/docker.sock gitlab/gitlab-runner:latest -c 'git config --global --add safe.directory "*";gitlab-runner exec docker test'
For all git versions > 2.35.2. You must add safe.directory within the container to avoid fatal: detected dubious ownership in repository at.... This also true for patched git versions < 2.35.2. The old command will not work anymore.
Details
0. Create a git repo to test this answer
mkdir my-git-project
cd my-git-project
git init
git commit --allow-empty -m"Initialize repo to showcase gitlab-runner locally."
1. Go to your git directory
cd my-git-project
2. Create a .gitlab-ci.yml
Example .gitlab-ci.yml
image: alpine
test:
script:
- echo "Hello Gitlab-Runner"
3. Create a docker container with your project dir mounted
docker run -d \
--name gitlab-runner \
--restart always \
-v $PWD:$PWD \
-v /var/run/docker.sock:/var/run/docker.sock \
gitlab/gitlab-runner:latest
(-d) run container in background and print container ID
(--restart always) or not?
(-v $PWD:$PWD) Mount current directory into the current directory of the container - Note: On Windows you could bind your dir to a fixed location, e.g. -v ${PWD}:/opt/myapp. Also $PWD will only work at powershell not at cmd
(-v /var/run/docker.sock:/var/run/docker.sock) This gives the container access to the docker socket of the host so it can start "sibling containers" (e.g. Alpine).
(gitlab/gitlab-runner:latest) Just the latest available image from dockerhub.
4. Execute with
Avoid fatal: detected dubious ownership in repository at... More info
docker exec -it -w $PWD gitlab-runner git config --global --add safe.directory "*"
Actual execution
docker exec -it -w $PWD gitlab-runner gitlab-runner exec docker test
# ^ ^ ^ ^ ^ ^
# | | | | | |
# (a) (b) (c) (d) (e) (f)
(a) Working dir within the container. Note: On Windows you could use a fixed location, e.g. /opt/myapp.
(b) Name of the docker container
(c) Execute the command "gitlab-runner" within the docker container
(d)(e)(f) run gitlab-runner with "docker executer" and run a job named "test"
5. Prints
...
Executing "step_script" stage of the job script
$ echo "Hello Gitlab-Runner"
Hello Gitlab-Runner
Job succeeded
...
Note: The runner will only work on the commited state of your code base. Uncommited changes will be ignored. Exception: The .gitlab-ci.yml itself does not have be commited to be taken into account.
Note: There are some limitations running locally. Have a look at limitations of gitlab runner locally.
I'm currently working on making a gitlab runner that works locally.
Still in the early phases, but eventually it will become very relevant.
It doesn't seem like gitlab want/have time to make this, so here you go.
https://github.com/firecow/gitlab-runner-local
If you are running Gitlab using the docker image there: https://hub.docker.com/r/gitlab/gitlab-ce, it's possible to run pipelines by exposing the local docker.sock with a volume option: -v /var/run/docker.sock:/var/run/docker.sock. Adding this option to the Gitlab container will allow your workers to access to the docker instance on the host.
The GitLab runner appears to not work on Windows yet and there is an open issue to resolve this.
So, in the meantime I am moving my script code out to a bash script, which I can easily map to a docker container running locally and execute.
In this case I want to build a docker container in my job, so I create a script 'build':
#!/bin/bash
docker build --pull -t myimage:myversion .
in my .gitlab-ci.yaml I execute the script:
image: docker:latest
services:
- docker:dind
before_script:
- apk add bash
build:
stage: build
script:
- chmod 755 build
- build
To run the script locally using powershell I can start the required image and map the volume with the source files:
$containerId = docker run --privileged -d -v ${PWD}:/src docker:dind
install bash if not present:
docker exec $containerId apk add bash
Set permissions on the bash script:
docker exec -it $containerId chmod 755 /src/build
Execute the script:
docker exec -it --workdir /src $containerId bash -c 'build'
Then stop the container:
docker stop $containerId
And finally clean up the container:
docker container rm $containerId
Another approach is to have a local build tool that is installed on your pc and your server at the same time.
So basically, your .gitlab-ci.yml will basically call your preferred build tool.
Here an example .gitlab-ci.yml that i use with nuke.build:
stages:
- build
- test
- pack
variables:
TERM: "xterm" # Use Unix ASCII color codes on Nuke
before_script:
- CHCP 65001 # Set correct code page to avoid charset issues
.job_template: &job_definition
except:
- tags
build:
<<: *job_definition
stage: build
script:
- "./build.ps1"
test:
<<: *job_definition
stage: test
script:
- "./build.ps1 test"
variables:
GIT_CHECKOUT: "false"
pack:
<<: *job_definition
stage: pack
script:
- "./build.ps1 pack"
variables:
GIT_CHECKOUT: "false"
only:
- master
artifacts:
paths:
- output/
And in nuke.build i've defined 3 targets named like the 3 stages (build, test, pack)
In this way you have a reproducible setup (all other things are configured with your build tool) and you can test directly the different targets of your build tool.
(i can call .\build.ps1 , .\build.ps1 test and .\build.ps1 pack when i want)
I am on Windows using VSCode with WSL
I didn't want to register my work PC as a runner so instead I'm running my yaml stages locally to test them out before I upload them
$ sudo apt-get install gitlab-runner
$ gitlab-runner exec shell build
yaml
image: node:10.19.0 # https://hub.docker.com/_/node/
# image: node:latest
cache:
# untracked: true
key: project-name
# key: ${CI_COMMIT_REF_SLUG} # per branch
# key:
# files:
# - package-lock.json # only update cache when this file changes (not working) #jkr
paths:
- .npm/
- node_modules
- build
stages:
- prepare # prepares builds, makes build needed for testing
- test # uses test:build specifically #jkr
- build
- deploy
# before_install:
before_script:
- npm ci --cache .npm --prefer-offline
prepare:
stage: prepare
needs: []
script:
- npm install
test:
stage: test
needs: [prepare]
except:
- schedules
tags:
- linux
script:
- npm run build:dev
- npm run test:cicd-deps
- npm run test:cicd # runs puppeteer tests #jkr
artifacts:
reports:
junit: junit.xml
paths:
- coverage/
build-staging:
stage: build
needs: [prepare]
only:
- schedules
before_script:
- apt-get update && apt-get install -y zip
script:
- npm run build:stage
- zip -r build.zip build
# cache:
# paths:
# - build
# <<: *global_cache
# policy: push
artifacts:
paths:
- build.zip
deploy-dev:
stage: deploy
needs: [build-staging]
tags: [linux]
only:
- schedules
# # - branches#gitlab-org/gitlab
before_script:
- apt-get update && apt-get install -y lftp
script:
# temporarily using 'verify-certificate no'
# for more on verify-certificate #jkr: https://www.versatilewebsolutions.com/blog/2014/04/lftp-ftps-and-certificate-verification.html
# variables do not work with 'single quotes' unless they are "'surrounded by doubles'"
- lftp -e "set ssl:verify-certificate no; open mediajackagency.com; user $LFTP_USERNAME $LFTP_PASSWORD; mirror --reverse --verbose build/ /var/www/domains/dev/clients/client/project/build/; bye"
# environment:
# name: staging
# url: http://dev.mediajackagency.com/clients/client/build
# # url: https://stg2.client.co
when: manual
allow_failure: true
build-production:
stage: build
needs: [prepare]
only:
- schedules
before_script:
- apt-get update && apt-get install -y zip
script:
- npm run build
- zip -r build.zip build
# cache:
# paths:
# - build
# <<: *global_cache
# policy: push
artifacts:
paths:
- build.zip
deploy-client:
stage: deploy
needs: [build-production]
tags: [linux]
only:
- schedules
# - master
before_script:
- apt-get update && apt-get install -y lftp
script:
- sh deploy-prod
environment:
name: production
url: http://www.client.co
when: manual
allow_failure: true
The idea is to keep check commands outside of .gitlab-ci.yml. I use Makefile to run something like make check and my .gitlab-ci.yml runs the same make commands that I use locally to check various things before committing.
This way you'll have one place with all/most of your commands (Makefile) and .gitlab-ci.yml will have only CI-related stuff.
I have written a tool to run all GitLab-CI job locally without have to commit or push, simply with the command ci-toolbox my_job_name.
The URL of the project : https://gitlab.com/mbedsys/citbx4gitlab
Years ago I build this simple solution with Makefile and docker-compose to run the gitlab runner in docker, you can use it to execute jobs locally as well and should work on all systems where docker works:
https://gitlab.com/1oglop1/gitlab-runner-docker
There are few things to change in the docker-compose.override.yaml
version: "3"
services:
runner:
working_dir: <your project dir>
environment:
- REGISTRATION_TOKEN=<token if you want to register>
volumes:
- "<your project dir>:<your project dir>"
Then inside your project you can execute it the same way as mentioned in other answers:
docker exec -it -w $PWD runner gitlab-runner exec <commands>..
I recommend using gitlab-ci-local
https://github.com/firecow/gitlab-ci-local
It's able to run specific jobs as well.
It's a very cool project and I have used it to run simple pipelines on my laptop.
Before i start, let me tell you that i'm newbie to Gitlab CI file :)
i'm looking to automate deployments of spring boot microservice app to custom server (a namecheap VPS).
(I'm using the Gitlab shared runner)
i have used jHipster ci-cd to generate the .gitlab-ci.yml file. Doing that, i have: build, package, release stages working.
i even could see the image repository built in Gitlab Container registery.
What last, is the deployment. i know that i have to use a docker container to deploy it, but i don't know how.
I'm stuck in deploying the image repository to my VPS.
(as it's my first microservice, my VPS is still new, having only java installed).
Here is my .gitlab-ci.yml file:
#image: jhipster/jhipster:v6.9.0
image: openjdk:11-jdk
cache:
key: "$CI_COMMIT_REF_NAME"
paths:
- .maven/
stages:
- check
- build
# - test
# - analyze
- package
- release
- deploy
before_script:
- chmod +x mvnw
- git update-index --chmod=+x mvnw
- export NG_CLI_ANALYTICS="false"
- export MAVEN_USER_HOME=`pwd`/.maven
nohttp:
stage: check
script:
- ./mvnw -ntp checkstyle:check -Dmaven.repo.local=$MAVEN_USER_HOME
maven-compile:
stage: build
script:
- ./mvnw -ntp compile -P-webpack -Dmaven.repo.local=$MAVEN_USER_HOME
artifacts:
paths:
- target/classes/
- target/generated-sources/
expire_in: 1 day
#maven-test:
# stage: test
# script:
# - ./mvnw -ntp verify -P-webpack -Dmaven.repo.local=$MAVEN_USER_HOME
# artifacts:
# reports:
# junit: target/test-results/**/TEST-*.xml
# paths:
# - target/test-results
# - target/jacoco
# expire_in: 1 day
maven-package:
stage: package
script:
- ./mvnw -ntp verify -Pprod -DskipTests -Dmaven.repo.local=$MAVEN_USER_HOME
artifacts:
paths:
- target/*.jar
- target/classes
expire_in: 1 day
# Uncomment the following line to use gitlabs container registry. You need to adapt the REGISTRY_URL in case you are not using gitlab.com
docker-push:
stage: release
variables:
REGISTRY_URL: registry.gitlab.com
IMAGE_TAG: $CI_REGISTRY_IMAGE:$CI_COMMIT_REF_SLUG-$CI_COMMIT_SHA
dependencies:
- maven-package
script:
- ./mvnw -ntp compile jib:build -Pprod -Djib.to.image=$IMAGE_TAG -Djib.to.auth.username=gitlab-ci-token -Djib.to.auth.password=$CI_BUILD_TOKEN -Dmaven.repo.local=$MAVEN_USER_HOME
docker-deploy:
image: docker:stable-git
stage: deploy
script:
when: manual
only:
- master
Thanks for your help :)
I'm using Google Cloud Build to run CI for my Nx workspace. Here's the cloudbuild.yaml file:
steps:
- name: 'gcr.io/cloud-builders/docker'
id: Test_Affected_Projects
entrypoint: 'sh'
args: [
'-c',
'docker build --build-arg NPM_TOKEN=$$NPM_TOKEN --file ./test/Dockerfile.test-runner -t mha-test-runner .']
secretEnv: ['NPM_TOKEN']
# Remove the docker image
secrets:
- kmsKeyName: /path/to/key
secretEnv:
NPM_TOKEN: some_key_value
(There are currently two steps, but I removed the second for brevity. The second step just removes the created docker image.)
Now the command inside the Docker image here runs all the tests for the Nx workspace. The thing is, Nx has a great command where only the affected libraries will be tested. But for the command to run, the git history of the project needs to be available.
I've tried to get the git history in the cloud build context, but I haven't been able to get it working. This is the step I added to try and get everything working:
steps:
- name: 'gcr.io/cloud-builders/git'
args: ['fetch', '--unshallow']
- name: 'gcr.io/cloud-builders/docker'
id: Test_Affected_Projects
entrypoint: 'sh'
args: [
'-c',
'docker build --build-arg NPM_TOKEN=$$NPM_TOKEN --file ./test/Dockerfile.test-runner -t mha-test-runner .']
secretEnv: ['NPM_TOKEN']
# Remove the docker image
secrets:
- kmsKeyName: /path/to/key
secretEnv:
NPM_TOKEN: some_key_value
That new first command, which should get the git history, fails. The error message says that it's not a git repo, so the command fails.
My question is: how can I get the git history in the cloud build context so that I can use it with different commands in the build/testing process?
I think the reason this isn't working is that you need to store the github credentials in the cloud build environment.
I believe this guide can help.
will allow you to do so, and then you will be able to call the git fetch --unshallow as you already have.
I'm trying to deploy a java maven project on aws with Gitlab CI/CD.
This is my .gitlab-ci.yml
image: maven:3-jdk-8
services:
- docker:dind
stages:
- test
- build
- deploy
maven-test:
stage: test
script:
- echo "Test stage"
- mvn clean validate compile test -B
maven-build:
stage: build
script:
- echo "Build stage"
- mvn install -B -DskipTests
artifacts:
paths:
- ./target/*.jar
maven-deploy:
stage: deploy
script:
- echo "Deploy stage"
- scp -v -o StrictHostKeyChecking=no -I "mykey.pem" ./target/*.jar ubuntu#xxxxxxx.com:*.jar
when: manual
If I execute the scp command on a terminal in my pc then the jar is uploaded in aws ec2 instance while in gitlab I have errors and the jar is not uploaded.
This is my first approach with Gitlab CI and aws, so can someone explain step by step what I need to do to deploy the project in aws ec2 instance with Gitlab CI?
Thanks!
Since you have not posted much about your problem nor did you post the error I will just suggest a few things to look at:
From a GitLab perspective:
Are you sure that the "mykey.pem" is available within the repository when running that command(maven-deploy) on the the gitlab-runner.?
Also are you sure that you are using a docker gitlab-runner, if you are not then you can't use the image: directive and therefore it might not not have mvn/scp locally.
You might want to look into the dependencies directive and ensure you make that artifact available in next task. This should be done by default!
From an AWS perspective:
Make sure that the ubuntu target machine/server has port 22 exposed to the EC2 machine running the gitlab-runner.
Edit:
If the error you are receiving is with the pem files permissions then take a look at this resolution for AWS EC2 pem file issue. Another similar resolution is here.
Seems like if you put chmod 400 mykey.pem before the scp it might fix your problem.
I am new to BitBucket pipelines, as I used Webhook for deploying my changes to FTP.
I have set reccommended atlassian/ftp-deploy:0.2.0 pipeline and it works fine, BUT I would like to set that ONLY CHANGED files are taken and sent to FTP.
image: node:10.15.3
pipelines:
default:
- step:
name: FTP Deploy
script: # Modify the commands below to build your repository.
- pipe: atlassian/ftp-deploy:0.2.0
variables:
USER: 'myFTPusername'
PASSWORD: 'myFTPpass'
SERVER: 'myFTPserver'
REMOTE_PATH: 'myFTPpath'
- step:
name: Deploy message
deployment: test
script:
- echo "Deploying to main environment"
Any help how to set this up so it sends only changed files to FTP?
Expected output is code for bitbucket-pipelines.yml
atlassian/ftp-deploy:0.3.6 delete all files, I found this image wagnerstephan/bitbucket-git-ftp:latest it's very useful, light and runs well and updates only changed files.
The first pipeline will run with an error, so select the commit then run again the pipeline with the init option selected.
image: wagnerstephan/bitbucket-git-ftp:latest
pipelines:
custom:
init:
- step:
script:
- git reset --hard
- git ftp init -u "$FTP_USERNAME" -p "$FTP_PASSWORD" ftp://$FTP_HOST/
deploy:
- step:
script:
- git reset --hard
- git ftp push -u "$FTP_USERNAME" -p "$FTP_PASSWORD" ftp://$FTP_HOST/--all
branches:
develop:
- step:
name: Deploy Develop
deployment: develop
script:
- git reset --hard
- git ftp push -u "$FTP_USERNAME" -p "$FTP_PASSWORD" ftp://$FTP_HOST/
master:
- step:
name: Deploy production
deployment: production
script:
- git reset --hard
- git ftp push -u "$FTP_USERNAME" -p "$FTP_PASSWORD" ftp://$FTP_HOST/
NOTE: check the name of the environments in the Bitbucket repository.