The lightweight Arch Linux based distro that runs, without root privileges, upon any Linux distro.
| Project Status | Donation | Communication |
|---|---|---|
  |
  |
  |
Table of Contents
- Description
- Quickstart
- Installation
- Usage
- Advanced usage
- Internals
- Troubleshooting
- More documentation
- Contributing
- Donating
- Authors
JuNest (Jailed User NEST) is a lightweight Arch Linux based distribution that allows to have disposable and partial isolated GNU/Linux environments within any generic GNU/Linux host OS and without the need to have root privileges for installing packages.
JuNest contains mainly the package managers (called pacman that allows to access to a wide range of packages from the Arch Linux repositories.
The main advantages on using JuNest are:
- Install packages without root privileges.
- Partial isolated environment in which you can install packages without affecting a production system.
- Access to a wide range of packages, in particular on GNU/Linux distros that may contain limited repositories (such as CentOS and RedHat).
- Available for
x86_64andarmarchitectures but you can build your own image from scratch too! - Run on a different architecture from the host OS via QEMU
- All Arch Linux lovers can have their favourite distro everywhere!
JuNest follows the Arch Linux philosophy.
Although JuNest sounds similar to a virtualisation/Linux container -like system, JuNest is quite different from solutions like Docker or Vagrant. In fact, the purpose of JuNest is not to build a complete isolated environment but, conversely, is the ability to run programs as they were running natively from the host OS. Almost everything is shared between host OS and the JuNest sandbox (kernel, process subtree, network, mounting, etc) and only the root filesystem gets isolated (since the programs installed in JuNest need to reside elsewhere).
This allows interaction between processes belonging to both host OS and JuNest.
For instance, you can install top command in JuNest in order to monitor
any processes belonging to the host OS.
The first operation required is to install the JuNest environment in the
location of your choice (by default ~/.junest, configurable via the environment variable JUNEST_HOME):
junest setupThe script will download the image from the repository and will place it to the default directory ~/.junest.
JuNest uses the Linux namespaces (aka ns) as the default backend program. To access via ns just type:
junestYou can use the command sudo to acquire fakeroot privileges and
install/remove packages.
Alternatively, you can access fakeroot privileges without using sudo all the
time with the -f (or --fakeroot) option:
junest -fAnother execution mode is via Proot:
junest proot [-f]There are multiple backend programs, each with its own pros/cons. To know more about the JuNest execution modes depending on the backend program used, see the Usage section below.
Program installed within JuNest can be accessible directly from host machine
without entering directly into a JuNest session
(no need to call junest command first).
For instance, supposing the host OS is an Ubuntu distro you can directly
run pacman by simply updating the PATH variable:
export PATH="$PATH:~/.junest/usr/bin_wrappers"
sudoj pacman -S htop
htopBy default the wrappers use ns mode. To use the ns --fakeroot you can use the convenient command helper sudoj.
For more control on backend mode you can use the JUNEST_ARGS environment variable.
For instance, if you want to run iftop with real root privileges:
sudoj pacman -S iftop
sudo JUNEST_ARGS="groot" iftop
Bin wrappers can be always recreated (e.g. in case for some reasons they get corrupted) with:
junest create-bin-wrappers -f
In ns mode, you can easily install package from AUR repository
using the already available yay
command. In proot mode, JuNest does no longer support the building of AUR packages.
Remember that in order to build packages from AUR, base-devel package group is required
first:
pacman -Syu --ignore sudo base-devel
:: sudo is in IgnorePkg/IgnoreGroup. Install anyway? [Y/n] n
...
...JuNest uses a modified version of sudo. That's why the original sudo
package must be ignored in the previous command.
If you are new on Arch Linux and you are not familiar with pacman package manager
visit the pacman rosetta page.
JuNest comes with a very short list of dependencies in order to be installed in most of GNU/Linux distributions. Before installing JuNest be sure that all dependencies are properly installed in your system:
Just clone the JuNest repo somewhere (for example in ~/.local/share/junest):
git clone https://github.com/fsquillace/junest.git ~/.local/share/junest
export PATH=~/.local/share/junest/bin:$PATHOptionally you want to use the wrappers to run commands installed in JuNest directly from host:
export PATH="$PATH:~/.junest/usr/bin_wrappers"Update your ~/.bashrc or ~/.zshrc to get always the wrappers available.
If you are using an Arch Linux system you can, alternatively, install JuNest from the AUR repository.
JuNest will be located in /opt/junest/
There are three different ways you can run JuNest depending on the backend program you decide to use.
The Linux namespaces represents the default backend program for JuNest. The requirements for having Linux namespaces working are:
- Kernel starting from Linux 3.8 allows unprivileged processes to create user and mount namespaces.
- The Linux kernel distro must have the user namespace enabled.
In the last years, the majority of GNU/Linux distros have the user namespace enabled by default. This means that you do not need to have root privileges to access to the JuNest environment via this method. This wiki provides the state of the user namespace on several GNU/Linux distros.
In order to run JuNest via Linux namespaces:
- As normal user - Allow to make basic operations or install/remove packages
with
sudocommand:junest nsorjunest - As fakeroot - Allow to install/remove packages:
junest ns -forjunest -f
This mode is based on the fantastic
bubblewrap command.
Proot represents a portable solution which allows unprivileged users to execute programs inside a sandbox and works well in most of GNU/Linux distros available.
In order to run JuNest via Proot:
-
As normal user - Allow to make basic operations:
junest proot -
As fakeroot - Allow to install/remove packages:
junest proot -f
In proot mode, the minimum recommended Linux kernel for the host OS is 2.6.32 on x86 (64 bit)
and ARM architectures. It is still possible to run JuNest on lower
2.6.x host OS kernels but errors may appear, and some applications may
crash. For further information, read the Troubleshooting
section below.
This solution suits only for privileged users. JuNest provides the possibility
to run the environment via chroot program.
In particular, it uses a special program called GRoot, a small and portable
version of
arch-chroot
wrapper, that allows to bind mount directories specified by the user, such as
/proc, /sys, /dev, /tmp and $HOME, before
executing any programs inside the JuNest sandbox. In case the mounting will not
work, JuNest is even providing the possibility to run the environment directly via
the pure chroot command.
In order to run JuNest via chroot solutions:
-
As root via
GRoot- Allow to have fully root privileges inside JuNest environment (you need to be root for executing this):junest groot -
As root via
chroot- Allow to have fully root privileges inside JuNest environment (you need to be root for executing this):junest root
The following table shows the capabilities that each backend program is able to perform:
| QEMU | Root privileges required | Manage Official Packages | Manage AUR Packages | Portability | Support | User modes | |
|---|---|---|---|---|---|---|---|
| Linux Namespaces | NO | NO | YES | YES | Poor | YES | Normal user and fakeroot |
| Proot | YES | NO | YES | NO | YES | YES | Normal user and fakeroot |
| Chroot | NO | YES | YES | YES | YES | YES | root only |
You can build a new JuNest image from scratch by running the following command:
junest build [-n]The script will create a directory containing all the essentials
files in order to make JuNest working properly (such as pacman and proot).
The option -n will skip the final validation tests if they are not needed.
Remember that the script to build the image must run in an Arch Linux OS with
arch-install-scripts and the base-devel packages installed.
To change the build directory just use the JUNEST_TEMPDIR (by default /tmp).
After creating the image junest-x86_64.tar.gz you can install it by running:
junest setup -i junest-x86_64.tar.gzFor more details, you can also take a look at junest-builder that contains the script and systemd service used for the automatic building of the JuNest image.
Related wiki page:
The following command will download the ARM JuNest image and will run QEMU in
case the host OS runs on x86_64 architecture:
$> export JUNEST_HOME=~/.junest-arm
$> junest setup -a arm
$> junest proot -- uname -m
armv7lTo bind a host directory to a guest location:
junest -b "--bind /home/user/mydata /mnt/mydata"Or using proot arguments:
junest proot -b "-b /mnt/mydata:/home/user/mydata"The option -b to provide options to the backend program will work with PRoot, Namespace and GRoot backend programs.
Check out the backend program options by passing --help option:
junest [u|g|p] -b "--help"Although JuNest has not been designed to be a complete container, it is even possible to virtualize the process tree thanks to the systemd container. The JuNest containter allows to run services inside the container that can be visible from the host OS through the network. The drawbacks of this are that the host OS must use systemd as a service manager, and the container can only be executed using root privileges.
To boot a JuNest container:
sudo systemd-nspawn -bD ~/.junestRelated wiki page:
JuNest attempts first to run the executables in the host OS located in different
positions (/usr/bin, /bin, /usr/sbin and /sbin).
As a fallback it tries to run the same executable if it is available in the JuNest
environment.
There is a periodic automation build of the JuNest images for x86_64 arch
only.
The JuNest image for arm architecture may not be always up to date because
the build is performed manually.
There are static QEMU binaries included in JuNest image that allows to run JuNest
in a different architecture from the host system. They are located in /opt/qemu
directory.
For Arch Linux related FAQs take a look at the General troubleshooting page.
Q: Why do I get the following error when I try to install a package?
Cannot find the gzip binary required for compressing man and info pages.
A: JuNest comes with a very basic number of packages. In order to install AUR packages you need to install the package group
base-develfirst that contains all the essential packages for compiling from source code (such as gcc, make, patch, etc):
#> pacman -S --ignore sudo base-devel
Remember to ignore
sudoas it conflicts withsudo-fakepackage.
Q: In ns mode when installing package I get the following error:
warning: warning given when extracting /usr/file... (Can't set user=0/group=0 for
/usr/file...)
A: This is because as fakeroot is not possible to set the owner/group of files as root. The package will still be installed correctly even though this message is showed.
Q: Why I cannot install packages?
#> pacman -S lsof
Packages (1): lsof-4.88-2
Total Download Size: 0.09 MiB
Total Installed Size: 0.21 MiB
error: no servers configured for repository: core
error: no servers configured for repository: community
error: failed to commit transaction (no servers configured for repository)
Errors occurred, no packages were upgraded.
A: You need simply to update the mirrorlist file according to your location:
# Uncomment the repository line according to your location
#> nano /etc/pacman.d/mirrorlist
#> pacman -Syy
Q: How do I find which package a certain file belongs to?
A: JuNest is a really small distro, therefore you frequently need to find the package name for a certain file.
pkgfileis an extremely useful package that allows you to detect the package of a given file. For instance, if you want to find the package name for the commandgetopt:
#> pacman -S pkgfile
#> pkgfile --update
$> pkgfile getop
core/util-linux
Alternatively, you can use directly
pacmancommand only. Take a look here.
Q: Why do I get the error: "FATAL: kernel too old"?
A: This is because the binaries from the precompiled package are compiled for Linux kernel 2.6.32. When JuNest is started without further options, it tries to run a shell from the JuNest chroot. The system sees that the host OS kernel is too old and refuses to start the shell.
The solution is to present a higher "fake" kernel version to the JuNest chroot. PRoot offers the -k option for this, and JuNest passes this option on to PRoot when -p is prepended. For example, to fake a kernel version of 3.10, issue the following command:
$> junest proot -b "-k 3.10"
As Arch Linux ships binaries for kernel version 2.6.32, the above error is not unique to the precompiled package from JuNest. It will also appear when trying to run binaries that were later installed in the JuNest chroot with the
pacmancommand.
In order to check if an executable inside JuNest chroot is compatible with the kernel of the host OS just use the
filecommand, for instance:
$> file ~/.junest/usr/bin/bash
ELF 64-bit LSB executable, x86-64, version 1 (SYSV), dynamically linked
(uses shared libs), for GNU/Linux 2.6.32,
BuildID[sha1]=ec37e49e7188ff4030052783e61b859113e18ca6, stripped
The output shows the minimum recommended Linux kernel version.
Q: Why do I get the warning: "kompat: this kernel doesn't support private futexes and PRoot can't emulate them."?
A: This happens on older host OS kernels when the trick of showing a fake kernel version to the JuNest chroot is applied (see above: Kernel too old).
The consequence of showing a fake kernel version to the JuNest chroot is that in the background, PRoot needs to translate requests from applications in the chroot to the old kernel of the host OS. Some of the newer kernel functionality can be emulated, but private futexes cannot be translated.
Private Futexes were introduced in Linux kernel 2.6.22. Therefore, the above problem likely appears on old Linux systems, for example RHEL5 systems, which are based on Linux kernel 2.6.18. Many of the core tools like
which,man, orvimrun without problems while others, especially XOrg-based programs, are more likely to show the warning. These are also more likely to crash unexpectedly.
Currently, there is no (easy) workaround for this. In order to be fully compatible with kernels below 2.6.22, both the precompiled package from JuNest and all software that is installed later needs to be compiled for this kernel. Most likely this can only be achieved by building the needed software packages from source, which kind of contradicts JuNest's distro-in-a-distro philosophy.
Q: Why I do not have permissions for ping?
$> ping www.google.com
ping: icmp open socket: Operation not permitted
A: The ping command uses suid permissions that allow to execute the command using root privileges. The fakeroot mode is not able to execute a command set with suid, and you may need to use root privileges. There are other few commands that have suid permission, you can list the commands from your JuNest environment with the following command:
$> find /usr/bin -perm +4000
Q: Why I do not see any characters in the application I have installed?
A: This is probably because there are no fonts installed in the system.
To quick fix this, you can just install a fonts package:
#> pacman -S gnu-free-fonts
Q: Why do I get warning when I install a package using root privileges?
#> pacman -S systat
...
warning: directory ownership differs on /usr/
filesystem: 1000:100 package: 0:0
...
A: In these cases the package installation went smoothly anyway. This should happen every time you install package with root privileges since JuNest will try to preserve the JuNest environment by assigning ownership of the files to the real user.
Q: Why do I get this warning when I run JuNest via Linux namespaces?
$> junest ns
Unprivileged user namespace is disabled at kernel compile time or kernel too old (<3.8). Proceeding anyway...
A: This means that JuNest detected that the host OS either does not have a newer kernel version or the unprivileged user namespace is not enabled at kernel compile time. JuNest does not stop the execution of the program but it attempts to run it anyway. Try to use Proot as backend program in case is not possible to invoke namespaces.
Q: Why do I get this warning when I run JuNest via Linux namespaces?
$> junest ns
Unprivileged user namespace disabled. Root permissions are required to enable it: sudo sysctl kernel.unprivileged_userns_clone=1
A: This means that JuNest detected that the host OS either does not have a newer Linux version or the user namespace is not enabled. JuNest does not stop the execution of the program but it attempts to run it anyway. If you have root permissions try to enable it, otherwise try to use Proot as backend program.
There are additional tutorials in the JuNest wiki page.
Contributions are welcome! You could help improving JuNest in the following ways:
To sustain the project please consider funding by donations through the GitHub Sponsors page.
JuNest was originally created in late 2014 by Filippo Squillace (feel.sqoox@gmail.com).
Here is a list of really appreciated contributors!
