User Guide

Gerrit is a Git server that provides access control for the hosted Git repositories and a web front-end for doing code review. Code review is a core functionality of Gerrit, but still it is optional and teams can decide to work without code review.

Gerrit speaks the git protocol. This means in order to work with Gerrit you do not need to install any Gerrit client, but having a regular git client, such as the git command line or EGit in Eclipse, is sufficient.

Still there are some client-side tools for Gerrit, which can be used optionally:

Cloning a Gerrit project is done the same way as cloning any other git repository by using the git clone command.

The URL for cloning the project can be found in the Gerrit web UI under Projects > List > <project-name> > General.

For git operations Gerrit supports the SSH and the HTTP/HTTPS protocols.

With Gerrit Code Review means to review every commit before it is accepted into the code base. The author of a code modification uploads a commit as a change to Gerrit. In Gerrit each change is stored in a staging area where it can be checked and reviewed. Only when it is approved and submitted it gets applied to the code base. If there is feedback on a change, the author can improve the code modification by amending the commit and uploading the new commit as a new patch set. This way a change is improved iteratively and it is applied to the code base only when is ready.

Uploading a change to Gerrit is done by pushing a commit to Gerrit. The commit must be pushed to a ref in the refs/for/ namespace which defines the target branch: refs/for/<target-branch>. The magic refs/for/ prefix allows Gerrit to differentiate commits that are pushed for review from commits that are pushed directly into the repository, bypassing code review. For the target branch it is sufficient to specify the short name, e.g. master, but you can also specify the fully qualified branch name, e.g. refs/heads/master.

When a commit is pushed for review, Gerrit stores it in a staging area which is a branch in the special refs/changes/ namespace. A change ref has the format refs/changes/XX/YYYY/ZZ where YYYY is the numeric change number, ZZ is the patch set number and XX is the last two digits of the numeric change number, e.g. refs/changes/20/884120/1. Understanding the format of this ref is not required for working with Gerrit.

Using the change ref git clients can fetch the corresponding commit, e.g. for local verification.

The refs/for/ prefix is used to map the Gerrit concept of "Pushing for Review" to the git protocol. For the git client it looks like every push goes to the same branch, e.g. refs/for/master but in fact for each commit that is pushed to this ref Gerrit creates a new branch under the refs/changes/ namespace. In addition Gerrit creates an open change.

A change consists of a Change-Id, meta data (owner, project, target branch etc.), one or more patch sets, comments and votes. A patch set is a git commit. Each patch set in a change represents a new version of the change and replaces the previous patch set. Only the latest patch set is relevant. This means all failed iterations of a change will never be applied to the target branch, but only the last patch set that is approved is integrated.

The Change-Id is important for Gerrit to know whether a commit that is pushed for code review should create a new change or whether it should create a new patch set for an existing change.

The Change-Id is a SHA-1 that is prefixed with an uppercase I. It is specified as footer in the commit message (last paragraph):

If a commit that has a Change-Id in its commit message is pushed for review, Gerrit checks if a change with this Change-Id already exists for this project and target branch, and if yes, Gerrit creates a new patch set for this change. If not, a new change with the given Change-Id is created.

If a commit without Change-Id is pushed for review, Gerrit creates a new change and generates a Change-Id for it. Since in this case the Change-Id is not included in the commit message, it must be manually inserted when a new patch set should be uploaded. Most projects already require a Change-Id when pushing the very first patch set. This reduces the risk of accidentally creating a new change instead of uploading a new patch set. Any push without Change-Id then fails with missing Change-Id in commit message footer. New patch sets can always be uploaded to a specific change (even without any Change-Id) by pushing to the change ref, e.g. refs/changes/74/67374.

Amending and rebasing a commit preserves the Change-Id so that the new commit automatically becomes a new patch set of the existing change, when it is pushed for review.

Change-Ids are unique for a branch of a project. E.g. commits that fix the same issue in different branches should have the same Change-Id, which happens automatically if a commit is cherry-picked to another branch. This way you can search by the Change-Id in the Gerrit web UI to find a fix in all branches.

Change-Ids can be created automatically by installing the commit-msg hook as described in the Change-Id documentation.

Instead of manually installing the commit-msg hook for each git repository, you can copy it into the git template directory. Then it is automatically copied to every newly cloned repository.

After uploading a change for review reviewers can inspect it via the Gerrit web UI. Reviewers can see the code delta and comment directly in the code on code blocks or lines. They can also post summary comments and vote on review labels. The documentation of the review UI explains the screens and controls for doing code reviews.

There are several options to control how patch diffs should be rendered. Users can configure their preferences in the diff preferences.

If there is feedback from code review and a change should be improved a new patch set with the reworked code should be uploaded.

This is done by amending the commit of the last patch set. If needed this commit can be fetched from Gerrit by using the fetch command from the download commands in the change screen.

It is important that the commit message contains the Change-Id of the change that should be updated as a footer (last paragraph). Normally the commit message already contains the correct Change-Id and the Change-Id is preserved when the commit is amended.

Pushing a new patch set triggers email notification to the reviewers.

Code review takes time, which can be used by the change author to implement other features. Each feature should be implemented in its own local feature branch that is based on the current HEAD of the target branch. This way there is no dependency to open changes and new features can be reviewed and applied independently. If wanted, it is also possible to base a new feature on an open change. This will create a dependency between the changes in Gerrit and each change can only be applied if all its predecessor are applied as well. Dependencies between changes can be seen from the Related Changes tab on the change screen.

To get to know about new changes you can watch the projects that you are interested in. For watched projects Gerrit sends you email notifications when a change is uploaded or modified. You can decide on which events you want to be notified and you can filter the notifications by using change search expressions. For example 'branch:master file:^.*\.txt$' would send you email notifications only for changes in the master branch that touch a 'txt' file.

It is common that the members of a project team watch their own projects and then pick the changes that are interesting to them for review.

Project owners may also configure notifications on project-level.

In the change screen reviewers can be added explicitly to a change. The added reviewer will then be notified by email about the review request.

Mainly this functionality is used to request the review of specific person who is known to be an expert in the modified code or who is a stakeholder of the implemented feature. Normally it is not needed to explicitly add reviewers on every change, but you rather rely on the project team to watch their project and to process the incoming changes by importance, interest, time etc.

There are also plugins which can add reviewers automatically (e.g. by configuration or based on git blame annotations). If this functionality is required it should be discussed with the project owners and the Gerrit administrators.

Gerrit supports a wide range of query operators to search for changes by different criteria, e.g. by status, change owner, votes etc.

The page that shows the results of a change query has the change query contained in its URL. This means you can bookmark this URL in your browser to save the change query. This way it can be easily re-executed later.

Several change queries can be also combined into a dashboard. A dashboard is a screen in Gerrit that presents the results of several change queries in different sections, each section having a descriptive title.

A default dashboard is available under My > Changes. It has sections to list outgoing reviews, incoming reviews and recently closed changes.

Users can also define custom dashboards. Dashboards can be bookmarked in a browser so that they can be re-executed later.

It is also possible to customize the My menu and add menu entries for custom queries or dashboards to it.

Dashboards are very useful to define own views on changes, e.g. you can have different dashboards for own contributions, for doing reviews or for different sets of projects.

Project owners can also define shared dashboards on project-level. The project dashboards can be seen in the web UI under Projects > List > <project-name> > Dashboards.

Submitting a change means that the code modifications of the current patch set are applied to the target branch. Submit requires the Submit access right and is done on the change screen by clicking on the Submit button.

In order to be submittable changes must first be approved by voting on the review labels. By default a change can only be submitted if it has a vote with the highest value on each review label and no vote with the lowest value (veto vote). Projects can configure custom labels and custom submit rules to control when a change becomes submittable.

How the code modification is applied to the target branch when a change is submitted is controlled by the submit type which can be configured on project-level.

Submitting a change may fail with conflicts. In this case you need to rebase the change locally, resolve the conflicts and upload the commit with the conflict resolution as new patch set.

If a change cannot be merged due to path conflicts this is highlighted on the change screen by a bold red Cannot Merge label.

While a change is in review the HEAD of the target branch can evolve. In this case the change can be rebased onto the new HEAD of the target branch. When there are no conflicts the rebase can be done directly from the change screen, otherwise it must be done locally.

Doing a manual rebase is only necessary when there are conflicts that cannot be resolved by Gerrit. If manual conflict resolution is needed also depends on the submit type that is configured for the project.

Generally changes shouldn’t be rebased without reason as it increases the number of patch sets and creates noise with notifications. However if a change is in review for a long time it may make sense to rebase it from time to time, so that reviewers can see the delta against the current HEAD of the target branch. It also shows that there is still an interest in this change.

Sometimes during code review a change is found to be bad and it should be given up. In this case the change can be abandoned so that it doesn’t appear in list of open changes anymore.

Abandoned changes can be restored if later they are needed again.

Changes can be grouped by topics. This is useful because it allows you to easily find related changes by using the topic search operator. Also on the change screen changes with the same topic are displayed so that you can easily navigate between them.

Often changes that together implement a feature or a user story are group by a topic.

Assigning a topic to a change can be done in the change screen.

It is also possible to set a topic on push, either by appending %topic=…​ to the ref name or through the use of the command line flag --push-option, aliased to -o, followed by topic=…​.

Changes can be uploaded as drafts. By default draft changes are only visible to the change owner. This gives you the possibility to have some staging before making your changes visible to the reviewers. Draft changes can also be used to backup unfinished changes.

A draft change is created by pushing to the magic refs/drafts/<target-branch> ref.

Draft changes have the state Draft and can be published or deleted from the change screen.

By adding reviewers to a draft change the change is made visible to these users. This way you can collaborate with other users in privacy.

By pushing to refs/drafts/<target-branch> you can also upload draft patch sets to non-draft changes. Draft patch sets are immediately visible to all reviewers of the change, but other users cannot see the draft patch set. A draft patch set can be published and deleted in the same way as a draft change.

It is possible to edit changes inline directly in the web UI. This is useful to make small corrections immediately and publish them as a new patch set.

It is also possible to create new changes inline.

Every project has a project owner that administrates the project. Project administration includes the configuration of the project access rights, but project owners have many more possibilities to customize the workflows for a project which are described in the project owner guide.

Doing code reviews with Gerrit is optional and you can use Gerrit without code review as a pure Git server.

User configuration data such as preferences is stored in the All-Users project under a per-user ref. The user’s ref is based on the user’s account id which is an integer. The user refs are sharded by the last two digits (nn) in the refname, leading to refs of the format refs/users/nn/accountid.

There are several options to control the rendering in the Gerrit web UI. Users can configure their preferences under Settings > Preferences. The user’s preferences are stored in a git config style file named preferences.config under the user’s ref in the All-Users project.

The following preferences can be configured:

In addition it is possible to customize the menu entries of the My menu. This can be used to make the navigation to frequently used screens, e.g. configured dashboards, quick.

Gerrit sends out email notifications to users and supports parsing back replies on some of them (when configured).

Gerrit supports replies on these notification emails:

While Gerrit supports a wide range of email clients, the following ones have been tested and are known to work:

Gerrit supports parsing back all comment types that can be applied to a change via the WebUI:

Please note that comments can only be sent in reply to a comment in the original notification email, while the change message is independent of those.

Gerrit supports parsing a user’s reply from both HTML and plaintext. Please note that some email clients extract the text from the HTML email they have received and send this back as a quoted reply if you have set the client to plaintext mode. In this case, Gerrit only supports parsing a change message. To work around this issue, consider setting a User Preference to receive only plaintext emails.

Example notification:

Example response from the user:

In this case, Gerrit will persist a change message ("Thanks, I’ll fix it."), a file comment ("Rename this file to File.java") as well as a reply to an inline comment ("Yeah, I see why, let me try again.").

Part of Gerrit Code Review