Gerrit can automatically push any changes it makes to its managed Git repositories to another system. Usually this would be configured to provide mirroring of changes, for warm-standby backups, or a load-balanced public mirror farm.

The replication runs on a short delay. This gives Gerrit a small time window to batch updates going to the same project, such as when a user uploads multiple changes at once.

Typically replication should be done over SSH, with a passwordless public/private key pair. On a trusted network it is also possible to use replication over the insecure (but much faster) git:// protocol, by enabling the receive-pack service on the receiving system, but this configuration is not recommended.

Enabling Replication

If replicating over SSH (recommended), ensure the host key of the remote system(s) is already in the Gerrit user's ~/.ssh/known_hosts file. The easiest way to add the host key is to connect once by hand with the command line:

sudo su -c 'ssh mirror1.us.some.org echo' gerrit2

Next, create $site_path/replication.config as a Git-style config file, and restart Gerrit.

Example replication.config to replicate in parallel to four different hosts:

[remote "host-one"]
  url = gerrit2@host-one.example.com:/some/path/${name}.git
[remote "pubmirror"]
  url = mirror1.us.some.org:/pub/git/${name}.git
  url = mirror2.us.some.org:/pub/git/${name}.git
  url = mirror3.us.some.org:/pub/git/${name}.git
  push = +refs/heads/*
  push = +refs/tags/*
  threads = 3

To manually trigger replication at runtime, see gerrit replicate.

File replication.config

The optional file $site_path/replication.config is a Git-style config file that controls the replication settings for Gerrit.

The file is composed of one or more remote sections, each remote section provides common configuration settings for one or more destination URLs.

Each remote section uses its own thread pool. If pushing to multiple remotes, over differing types of network connections (e.g. LAN and also public Internet), its a good idea to put them into different remote sections, so that replication to the slower connection does not starve out the faster local one. The example file above does this.

Section remote

In the keys below, the <name> portion is unused by Gerrit, but must be unique to distinguish the different sections if more than one remote section appears in the file.

remote.<name>.url

Address of the remote server to push to. Multiple URLs may be specified within a single remote block, listing different destinations which share the same settings. Assuming sufficient threads in the thread pool, Gerrit pushes to all URLs in parallel, using one thread per URL.

Within each URL value the magic placeholder ${name} is replaced with the Gerrit project name. This is a Gerrit specific extension to the otherwise standard Git URL syntax.

See GIT URLS for details on Git URL syntax.

remote.<name>.receivepack

Path of the git-receive-pack executable on the remote system, if using the SSH transport.

Defaults to git-receive-pack.

remote.<name>.uploadpack

Path of the git-upload-pack executable on the remote system, if using the SSH transport.

Defaults to git-upload-pack.

remote.<name>.push

Standard Git refspec denoting what should be replicated. Setting this to +refs/heads/*:refs/heads/* would mirror only the active branches, but not the change refs under refs/changes/, or the tags under refs/tags/.

Multiple push keys can be supplied, to specify multiple patterns to match against. In the example file above, remote "pubmirror" uses two push keys to match both refs/heads/* and refs/tags/*, but excludes all others, including refs/changes/*.

Defaults to +refs/*:refs/* (all refs) if not specified.

remote.<name>.timeout

Number of seconds to wait for a network read or write to complete before giving up and declaring the remote side is not responding. If 0, there is no timeout, and the push client waits indefinitely.

A timeout should be large enough to mostly transfer the objects to the other side. 1 second may be too small for larger projects, especially over a WAN link, while 10-30 seconds is a much more reasonable timeout value.

Defaults to 0 seconds, wait indefinitely.

remote.<name>.replicationDelay

Number of seconds to wait before scheduling a remote push operation. Setting the delay to 0 effectively disables the delay, causing the push to start as soon as possible.

This is a Gerrit specific extension to the Git remote block.

By default, 15 seconds.

remote.<name>.threads

Number of worker threads to dedicate to pushing to the repositories described by this remote. Each thread can push one project at a time, to one destination URL. Scheduling within the thread pool is done on a per-project basis. If a remote block describes 4 URLs, allocating 4 threads in the pool will permit some level of parallel pushing.

By default, 1 thread.

File ~/.ssh/config

If present, Gerrit reads and caches ~/.ssh/config at startup, and supports most SSH configuration options. For example:

Host host-one.example.com:
  IdentityFile ~/.ssh/id_hostone
  PreferredAuthentications publickey
Host mirror*.us.some.org:
  User mirror-updater
  IdentityFile ~/.ssh/id_pubmirror
  PreferredAuthentications publickey

Supported options:

SSH authentication must be by passwordless public key, as there is no facility to read passphases on startup or passwords during the SSH connection setup, and SSH agents are not supported from Java.

Host keys for any destination SSH servers must appear in the user's ~/.ssh/known_hosts file, and must be added in advance, before Gerrit starts. If a host key is not listed, Gerrit will be unable to connect to that destination, and replication to that URL will fail.

Part of Gerrit Code Review