I currently have a web application installed on my 'domain.com'. My server makes use of Plesk. What I then did was copy my app on a subdomain called 'test.domain.com' The second one is what I use for development work and once I have coded and tested, I manually copy the files across to the folders in the 'domain.com' project.
It is a very tedious process and I sometimes loose track of changes. My background is electronics engineering where I did some embedded programming in C. I am familiar with SVN version control and I am aware how version control can make my life easier.
Does anyone know what I can do to implement GIT or other alternatives to simplify my development process?
You can link a git repo on Plesk, and also you can choose the branch you want to pull too.
Link the master to branch to your domain.com root directory and another one like "develop" on you test.domain.com.
Plesk will give you a webhook link you can add on your git repo to auto-pull when you pushed.
You can add some after pull command on plesk, like a schema update for your laravel project too.
Related
Is there any CI/CD tool for Netezza that can manage versions and can be used for migrating code across environments? We have used flywaydb for other databases and are happy with it, but that does not support Netezza. I have already googled and did not find a single tool, so any responses are good for me to begin analyzing further
To my knowledge, there's nothing specifically geared for Netezza. That said, with a bit of understanding of your target environment, it's certainly possible.
We use git and GitHub Enterprise (GHE). The reason for GHE is not particular to this solution, but rather because I work at a hospital. Here's what we do.
Setup
Build a repository at /home/nz on your production server. Depending on how you work nzlogs, nzbads, and other temporary files, you may need to fiddle quite a bit with the .gitignore file. We have dedicated log directories where temporary files should reside.
Push that repo into GHE.
If you have a development server, clone the repo in the /home/nz directory on that server. Clearly you'll lose all development work up until that point and will want to make sure that things like .bashrc are not versioned. Alternatively, you could set up a different branch and repo and try merging the prod and dev versions. We did this, but I'd recommend just wiping your development box with production code one slow day.
Assign your production box a dedicated branch in git. For this discussion, I'll call them prod and dev. Do the same for development, if you have it. This is mainly a mental thing, not a tech thing, but it's crucial, like setting up a remote for Heroku or Azure.
Find or develop a tiny web server that can listen for GitHub webhooks. I built a Sinatra server with a simple configuration file. Anything will do. Deploy the web server to each of the environments and tune them to perform the following activities on an update to the prod or dev branches, respective to the server.
git reset --hard
git clean -f
git pull
Set up webhooks in your GHE repository to send the push event to the web servers.
Of course, you can always have the web server do other things on a branch update if you want to get fancy (maybe update cron from a versioned file or update schemas from all new files).
Process
Fairly simply, follow the GitHub Flow workflow. You can pretty much follow whatever process you want with the understanding that your prod and dev branches should be protected and only removed or futzed with as an admin task. Create a feature branch, test it by pushing to dev, and then make a pull request for the prod branch.
Why GHE? Mainly because it keeps an open area where our code is available. You could absolutely do this by pushing directly to Netezza's git repo, but your workflow will suffer--it just isn't as clean as having all code in one clear place with discussion around pull requests.
I am new to Laravel, Laravel Homestead, Composer, and the development workflow associated with commiting changes to a Git repository and then pulling those changes to a development/production server. So far after much trial and error, I have managed to:
Set up my local Homestead environment with vagrant.
Create a new Laravel application
Run Composer to fetch dependencies
Access the application locally.
Create a Git repository for my application, commit changes, and push to an origin master branch.
Clone the repository on my remote server (shared hosting on 1and1) and pull the changes in.
For a long time, I couldn't understand why when I pulled the changes to the remote site, I would get PHP errors, but the local site ran just fine. It came down to the fact that the Laravel .gitignore file was ignoring the /vendor directory, which Laravel requires to function. Some Google-fu searches indicate that some people simply run composer update / (composer install ?) on their production servers. (I don't have access to Composer on my shared hosting server, so I am unable to do this)
My question to the community - what do you feel is the best workflow for my given situation? remove the /vendor directory from the .gitignore file? Something else?
Replies are much appreciated.
It looks like you are using GIT as a deployment tool which I dont think is a good idea.
Composer update/install is just for managing dependecies. Some servers dont allow you to run scripts from console or running them is complicated. In this situation you can run composer locally before deployment and send your code to server with all dependencies.
Here are some things that you should keep in mind when designing your workflow:
Use GIT to keep source code and configurations
Use composer to manage dependecies (downloaded dependencies should't be under version control in your GIT repository. Vendor directory and its contetnt is a dependency too)
For deployment use one of deployment tools eg. https://github.com/rocketeers/rocketeer
use the -f flag to forcefully include the vendor directory while using git add.
You are on the right track here, and many will do what you are doing.
The real trouble comes when you are doing multiple server deployments (load balanced, auto-scaling).
Typically what I've seen is a shell script that you would include and run whenever something happens that would require these commands to be run.
Inside of this shell script would be the commands that you want completed every time a new server instance is booted up.
You can do this with a number of tools for a single server environment as well.
I might look into continuous integration tools like Travis CI, Jenkins, etc. If this is a major headache of yours.
Otherwise, it might be overkill.... then just keep doing what you are doing.
adding the vendor directory to your git repo is against best practices.
This is also a decent option involving webhooks:
http://losstopschade.de/post/96967373358
Look at Deploy Laravel Webapp to 1and1
We're trying to set up github version control for a Jsp-project in NetBeans 7.0.1. The problem is we don't have a clue what to do. I Have set up a public account on github and done all the steps in the install guide on github, ssh keys and everything. So if I wanted to work on my own in this project I wouldn't have a problem.
The problem is how to get my collaborator started. He has an account on github. he set it up with ssh keys and such. In the admin view on github I added him as a collaborator, but we don't know the next step.
So the question is how to connect the collaborator to the project? something like this I suppose?
git remote add origin git#github.com:username/Hello-World.git
git pull
(another question: Do I git only the source files or the whole project folder?)
Regarding your second question... That's a tough one.
A few months ago I was working with a colleague on a JavaEE project and we initially decided to share the whole Eclipse project. Since I was working on Windows and he was working on Linux, we had much trouble maintaining everything. Also we had to make sure that we don't accidentally push up our .project dir, because that would overwrite the settings on the other persons machine, messing up the whole project. So we ended up removing all the project files from the repository and just keeping the source folders (src and WebContent).
Both of us set up an empty project, made our settings and than imported the source code from the repository. Was some trouble setting it up until everybody had the same project settings, but afterwards it worked like a charm.
For just two developers that is fine, I guess for a bigger team, there might be better solutions.
So, I guess Netbeans handles the project settings in a similar way. So in my opinion you should just share the code.
For the first access, what your collaborator should be able to do is a git clone of your repository.
That will set for him the remote address.
If he is declared as a collaborator, he then should be able to push/pull to that remote repo.
Note that your collaborator should have received a push notification access.
Are there any automated depoloyment tools out there for Magento sites?
If not does anyone have any best practices so to speak for maintaining and deploying Magento builds across local, staging and products?
This is how I've been working for the past few months and it works pretty well for me.
Install SVN on your server. Or get your host to do it. Or choose a host with SVN in place. Or git.
or
Use Springloops.
The 'trunk' is your live site.
Branches are for staging. Set up the webserver to treat these folders as subdomains.
The live database is regularly copied to branches. This refreshes the data for testing. (Consider anonymizing sales & customer data)
Each repository has it's own "app/etc/local.xml" file. Mark these with SVN:ignore so that one will not upset another.
Also SVN:ignore the "media" and "var" directories.
Each dev has a local webserver for working on. When they finish a change it is deployed to a branch ready for QA.
Nobody except the lead dev is allowed to merge branches to trunk on pain of death!
This means changes in code bubble up to the live site. Copies of the database bubble down to devs. Sometimes copies of the "media" dir are copied downwards as well. Extensions and upgrades are tested on branches too, I dislike using the Connect Manager on a live site.
Been using Git lately, so far liking it much more than SVN, this same flow could be applied to SVN as well I believe:
More details: http://nvie.com/posts/a-successful-git-branching-model/
Currently having, a local VM with a base install of Magento to setup for projects to roll out to new developers is the best approach I think. Most of us just use NetBeans inside the VM and use git pull/pushes as well as some custom build modules for deployment to all of our usual environments: local, integration, UAT, and production. Production or Integration is usually our system of record database wise.
Here is a base .gitignore file to start off with:
https://github.com/github/gitignore/blob/master/Magento.gitignore
A simple Git Deployment:
http://ryanflorence.com/simple-git-deployment/
You can try the packaged Magento that is automatically deployed with a help of Jelastic PaaS https://github.com/jelastic-jps/magento/tree/master/magento
You can get it pre-configured and installed with NGINX or LiteSpeed server and MariaDB.
After customization, you can clone the whole environment in order to get similar replicas for dev, test, stage and production. And when all needed changes are done on the cloned environment, you can just swap domains with current production and thus make the updated version available.
Or you can set up automated update process from Git/SVN.
I'm in the early stages of my first magento site. Its a big project, and my team and I have been discussing this very issue. We've seriously considered using a Git repository to maintain versioning across local, staging and live servers. Here is a good article on the subject. Its obviously focused on Wordpress, but I think the workflow would be almost identical.
And to answer your first question, I know of nothing automated.
We use SVN for very large scale projects. Almost any hosting service for your staging and product environments will be able to provide you with an SVN client to maintain sync with your repository.
Never heard of any automated deployment tools for Magento.
Using msysgit and copssh, is it possible to secure the ssh part such that it can only access the relevant git executables and also be constrained to access only one folder?
I have a feeling that a git server on windows will be very much more open than a svn server like visual svn. I'm hoping to be proved wrong.
I would use a Linux server for your central Git repository. Install gitolite. This will enable you to administer branch rights etc.
UPDATE:
As per your recent comments, just go with unfuddle and be done with it in 1 minute. If you're concerned about using up the 500MB of space they give, large non-private artifacts can be stored as a submodule that can be hosted on github.
hope this helps!
On Windows, I have found Apache and Smart Http ( git-http backend ) to be the best way to host a Git server.
https://web.archive.org/web/20100308035130/http://progit.org/2010/03/04/smart-http.html
And coming to access control, I would advice you to keep it simple and have an access conf file svn or even gitolite / gitosis and write simple hooks in the Git repo ( in Python, Ruby, etc. )
The hooks will provide you pretty good control to the Git repo. You can control checkins per branch, checkins to particular folders etc.
Have a look at the git hooks man page. pre-receive or update are the hooks that you can make use of for this purpose.
Look at this awesome chapter from Pro Git on how to use Git hooks on the server side to enforce policy - https://git-scm.com/book/en/v2/Customizing-Git-An-Example-Git-Enforced-Policy
You can easily adjust them and add functionality to suit your purpose.
I would very much recommend using one of the Git-HTTP projects.
See my answer at: https://serverfault.com/questions/58425/setting-up-git-repository-on-remote-windows-server/163065#163065
You're trying to make Windows behave like UNIX.
Better go with the flow, and use a .NET based solution as Git server backend.
When you have the deal with a small 2-person project (as you mentioned in the comments), you can also host the git repository on a Windows network share. It just works, and you clone the UNC path (or mapped drive letter) in your git client.
For UNC paths, when you use slashes instead of backslashes (i.e. //server01/git/myrepos.git).
An alternative might be to use https://github.com/jakubgarfield/Bonobo-Git-Server/wiki
When I started looking at setting up a corporate git service, we have the following requirements:
1. Manage git repositories as projects, where we can provide self-service access control at project level.
2. LDAP login integration
3. Low administrative effort
I evaluated vanilla git, git + git-http, gitolite. These solution would require an admin person to manage the access control. If the team is big, this will be a significant effort. If the team is small (5-10 developers), vanilla git is ok.
I looked at github enterprise, use github, and later bitbucket. We eventually bought bitbucket and have a on-prem version up and running. bitbucket meets all our requirements. In addition, we can selectively sync some of the AD group to bitbucket and manage access at group level.