A walkthrough of the basic features of git-annex.

creating a repository

This is very straightforward. Just tell it a description of the repository.

# mkdir ~/annex
# cd ~/annex
# git init
# git annex init "my laptop"

adding a remote

Like any other git repository, git-annex repositories have remotes. Let's start by adding a USB drive as a remote.

# sudo mount /media/usb
# cd /media/usb
# git clone ~/annex
# cd annex
# git annex init "portable USB drive"
# git remote add laptop ~/annex
# cd ~/annex
# git remote add usbdrive /media/usb

This is all standard ad-hoc distributed git repository setup. The only git-annex specific part is telling it the name of the new repository created on the USB drive.

Notice that both repos are set up as remotes of one another. This lets either get annexed files from the other. You'll want to do that even if you are using git in a more centralized fashion.

adding files

# cd ~/annex
# cp /tmp/big_file .
# cp /tmp/debian.iso .
# git annex add .
add big_file ok
add debian.iso ok
# git commit -a -m added

When you add a file to the annex and commit it, only a symlink to the annexed content is committed. The content itself is stored in git-annex's backend.

renaming files

# cd ~/annex
# git mv big_file my_cool_big_file
# mkdir iso
# git mv debian.iso iso/
# git commit -m moved

You can use any normal git operations to move files around, or even make copies or delete them.

Notice that, since annexed files are represented by symlinks, the symlink will break when the file is moved into a subdirectory. But, git-annex will fix this up for you when you commit -- it has a pre-commit hook that watches for and corrects broken symlinks.

getting file content

A repository does not always have all annexed file contents available. When you need the content of a file, you can use "git annex get" to make it available.

We can use this to copy everything in the laptop's annex to the USB drive.

# cd /media/usb/annex
# git pull laptop master
# git annex get .
get my_cool_big_file (copying from laptop...) ok
get iso/debian.iso (copying from laptop...) ok

Notice that you had to git pull from laptop first, this lets git-annex know what has changed in laptop, and so it knows about the files present there and can get them.

transferring files: When things go wrong

After a while, you'll have serveral annexes, with different file contents. You don't have to try to keep all that straight; git-annex does location tracking for you. If you ask it to get a file and the drive or file server is not accessible, it will let you know what it needs to get it:

# git annex get video/hackity_hack_and_kaxxt.mov
get video/_why_hackity_hack_and_kaxxt.mov (not available)
  I was unable to access these remotes: usbdrive, server
  Try making some of these repositories available:
    5863d8c0-d9a9-11df-adb2-af51e6559a49  -- my home file server
    58d84e8a-d9ae-11df-a1aa-ab9aa8c00826  -- portable USB drive
    ca20064c-dbb5-11df-b2fe-002170d25c55  -- backup SATA drive
failed
# sudo mount /media/usb
# git annex get video/hackity_hack_and_kaxxt.mov
get video/hackity_hack_and_kaxxt.mov (copying from usbdrive...) ok
# git commit -a -m "got a video I want to rewatch on the plane"

removing files

You can always drop files safely. Git-annex checks that some other annex has the file before removing it.

# git annex drop iso/debian.iso
drop iso/Debian_5.0.iso ok
# git commit -a -m "freed up space"

removing files: When things go wrong

Before dropping a file, git-annex wants to be able to look at other remotes, and verify that they still have a file. After all, it could have been dropped from them too. If the remotes are not mounted/available, you'll see something like this.

# git annex drop important_file other.iso
drop important_file (unsafe)
  Could only verify the existence of 0 out of 1 necessary copies
  I was unable to access these remotes: usbdrive
  Try making some of these repositories available:
    58d84e8a-d9ae-11df-a1aa-ab9aa8c00826  -- portable USB drive
    ca20064c-dbb5-11df-b2fe-002170d25c55  -- backup SATA drive
  (Use --force to override this check, or adjust annex.numcopies.)
failed
drop other.iso (unsafe)
  Could only verify the existence of 0 out of 1 necessary copies
      No other repository is known to contain the file.
  (Use --force to override this check, or adjust annex.numcopies.)
failed

Here you might --force it to drop important_file if you trust your backup. But other.iso looks to have never been copied to anywhere else, so if it's something you want to hold onto, you'd need to transfer it to some other repository before dropping it.

modifying annexed files

Normally, the content of files in the annex is prevented from being modified. That's a good thing, because it might be the only copy, you wouldn't want to lose it in a fumblefingered mistake.

# echo oops > my_cool_big_file
bash: my_cool_big_file: Permission deined

In order to modify a file, it should first be unlocked.

# git annex unlock my_cool_big_file
unlock my_cool_big_file (copying...) ok

That replaces the symlink that normally points at its content with a copy of the content. You can then modify the file like any regular file. Because it is a regular file.

(If you decide you don't need to modify the file after all, or want to discard modifications, just use git annex lock.)

When you git commit, git-annex's pre-commit hook will automatically notice that you are committing an unlocked file, and add its new content to the annex. The file will be replaced with a symlink to the new content, and this symlink is what gets committed to git in the end.

# echo "now smaller, but even cooler" > my_cool_big_file
# git commit my_cool_big_file -m "changed an annexed file"
add my_cool_big_file ok
[master 64cda67] changed an annexed file
 2 files changed, 2 insertions(+), 1 deletions(-)
 create mode 100644 .git-annex/WORM:1289672605:30:file.log

There is one problem with using git commit like this: Git wants to first stage the entire contents of the file in its index. That can be slow for big files (sorta why git-annex exists in the first place). So, the automatic handling on commit is a nice safety feature, since it prevents the file content being accidentially commited into git. But when working with big files, it's faster to explicitly add them to the annex yourself before committing.

# echo "now smaller, but even cooler yet" > my_cool_big_file
# git annex add my_cool_big_file
add my_cool_big_file ok
# git commit my_cool_big_file -m "changed an annexed file"

using ssh remotes

So far in this walkthrough, git-annex has been used with a remote repository on a USB drive. But it can also be used with a git remote that is truely remote, a host accessed by ssh.

Say you have a desktop on the same network as your laptop and want to clone the laptop's annex to it:

# git clone ssh://mylaptop/home/me/annex ~/annex
# cd ~/annex
# git annex init "my desktop"

Now you can get files and they will be transferred (using rsync or scp):

# git annex get my_cool_big_file
get my_cool_big_file (getting UUID for origin...) (copying from origin...)
WORM:1285650548:2159:my_cool_big_file       100% 2159     2.1KB/s   00:00
ok

When you drop files, git-annex will ssh over to the remote and make sure the file's content is still there before removing it locally:

# git annex drop my_cool_big_file
drop my_cool_big_file (checking origin..) ok

Note that normally git-annex prefers to use non-ssh remotes, like a USB drive, before ssh remotes. They are assumed to be faster/cheaper to access, if available. There is a annex-cost setting you can configure in .git/config to adjust which repositories it prefers. See the man page for details.

Also, note that you need full shell access for this to work -- git-annex needs to be able to ssh in and run commands.

moving file content between repositories

Often you will want to move some file contents from a repository to some other one. For example, your laptop's disk is getting full; time to move some files to an external disk before moving another file from a file server to your laptop. Doing that by hand (by using git annex get and git annex drop) is possible, but a bit of a pain. git annex move makes it very easy.

# git annex move my_cool_big_file --to usbdrive
move my_cool_big_file (moving to usbdrive...) ok
# git annex move video/hackity_hack_and_kaxxt.mov --from fileserver
move video/hackity_hack_and_kaxxt.mov (moving from fileserver...)
WORM:1274316523:86050597:hackity_hack_and_kax 100%   82MB 199.1KB/s   07:02
ok

using the URL backend

git-annex has multiple key-value backends. So far this walkthrough has demonstrated the default, WORM (Write Once, Read Many) backend.

Another handy backend is the URL backend, which can fetch file's content from remote URLs. Here's how to set up some files in your repository that use this backend:

# git annex fromkey --backend=URL --key=http://www.archive.org/somefile somefile
fromkey somefile ok
# git commit -m "added a file from the Internet Archive"

Now you if you ask git-annex to get that file, it will download it, and cache it locally.

# git annex get somefile
get somefile (downloading)
#########################################################################100.0%
ok

You can always drop files downloaded by the URL backend. It is assumed that the URL is stable; no local backup is kept.

# git annex drop somefile
drop somefile (ok)

using the SHA1 backend

Another handy alternative to the default backend is the SHA1 backend. This backend provides more git-style assurance that your data has not been damanged. And the checksum means that when you add the same content to the annex twice, only one copy need be stored in the backend.

The only reason it's not the default is that it needs to checksum files when they're added to the annex, and this can slow things down significantly for really big files. To make SHA1 the detault, just add something like this to .gitattributes:

* annex.backend=SHA1

unused data

It's possible for data to accumulate in the annex that no files point to nymore. One way it can happen is if you git rm a file without first calling git annex drop. And, when you modify an annexed file, the old content of the file remains in the annex.

This might be historical data you want to preserve, so git-annex defaults to preserving it. So from time to time, you may want to check for such data and eliminate it to save space.

# git annex unused
unused  (checking for unused data...) 
  Some annexed data is no longer pointed to by any files in the repository.
    NUMBER  KEY
    1       WORM:1289672605:3:file
    2       WORM:1289672605:14:file
  (To see where data was previously used, try: git log --stat -S'KEY')
  (To remove unwanted data: git-annex dropunused NUMBER)
ok

After running git annex unused, you can follow the instructions to examine the history of files that used the data, and if you decide you don't need that data anymore, you can easily remove it:

# git annex dropunused 1
dropunused 1 ok

fsck: verifying your data

You can use the fsck subcommand to check for problems in your data. What can be checked depends on the backend you've used to store the data. For example, when you use the SHA1 backend, fsck will verify that the checksums of your files are good. Fsck also checks that the annex.numcopies setting is satisfied for all files.

# git annex fsck
unused  (checking for unused data...) ok
fsck my_cool_big_file (checksum...) ok
...

You can also specifiy the files to check. This is particularly useful if you're using sha1 and don't want to spend a long time checksumming everything.

# git annex fsck my_cool_big_file
fsck my_cool_big_file (checksum...) ok

fsck: When things go wrong

Fsck never deletes possibly bad data; instead it will be moved to .git/annex/bad/ for you to recover. Here is a sample of what fsck might say about a badly messed up annex:

# git annex fsck
fsck my_cool_big_file (checksum...)
git-annex: Bad file content; moved to .git/annex/bad/SHA1:7da006579dd64330eb2456001fd01948430572f2
git-annex: ** No known copies of the file exist!
failed
fsck important_file
git-annex: Only 1 of 2 copies exist. Run git annex get somewhere else to back it up.
failed
git-annex: 2 failed

backups

git-annex can be configured to require more than one copy of a file exists, as a simple backup for your data. This is controled by the "annex.numcopies" setting, which defaults to 1 copy. Let's change that to require 2 copies, and send a copy of every file to a USB drive.

# echo "* annex.numcopies=2" >> .gitattributes
# git annex copy . --to usbdrive

Now when we try to git annex drop a file, it will verify that it knows of 2 other repositories that have a copy before removing its content from the current repository.

You can also vary the number of copies needed, depending on the file name. So, if you want 3 copies of all your flac files, but only 1 copy of oggs:

# echo "*.ogg annex.numcopies=1" >> .gitattributes
# echo "*.flac annex.numcopies=3" >> .gitattributes

Or, you might want to make a directory for important stuff, and configure it so anything put in there is backed up more thoroughly:

# mkdir important_stuff
# echo "* annex.numcopies=3" > important_stuff/.gitattributes

For more details about the numcopies setting, see copies.