STEP 3. Server preparation 
=================================

.. _step3: 

CPU server preparation
------------------------

To prepare a CPU server to FindFace Lite, please, install `Docker Engine (19.03+) and Docker Compose (2.2.3+) <https://docs.docker.com/engine/install/#server>`_ . 

Before you install `Docker Engine (19.03+) and Docker Compose (2.2.3+) <https://docs.docker.com/engine/install/#server>`_  for the first time on a new host machine, you need to set up the Docker repository. 

Steps from setting up the **Docker repository** to **Docker and Docker Compose installation** are described in the guides for Ubuntu OS and CentOS below.



Ubuntu OS 
+++++++++++

.. _ubuntu_cpu:

1. Update :code:`apt` and install packages for data encryption to use the repository over HTTPS:

 .. code-block:: bash

    sudo apt-get update
    sudo apt-get install \
        ca-certificates \
        curl \
        gnupg \
        lsb-release

2. Add the GPG key given by Docker. Use the command below:

 .. code-block:: bash

    sudo mkdir -p /etc/apt/keyrings
    curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo gpg --dearmor -o /etc/apt/keyrings/docker.gpg

3. Add the Docker repository using the following command:

 .. code-block:: bash
    
    echo \
    "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.gpg] https://download.docker.com/linux/ubuntu \
    $(lsb_release -cs) stable" | sudo tee /etc/apt/sources.list.d/docker.list > /dev/null

4. Update the :code:`apt`:

 .. code-block:: bash
    
    sudo apt-get update

5. Install **Docker** and **Docker Compose Plugin**:

 .. code-block:: bash

    sudo apt-get install docker-ce docker-ce-cli containerd.io docker-compose-plugin

6. Check on how the **Docker** was installed using the command which downloads a test image and runs it in a container:

 .. code-block:: bash

    sudo docker run hello-world

 The container will be started, you will see the operation success message, then the container will automatically be stopped.

 .. image:: /images/helloworld.png
   :scale: 40%
 
7. Make sure the **Docker Compose Plugin** is also installed correctly. Use the following command to check:

 .. code-block:: bash

    docker compose version

 .. image:: /images/docker_compose_v.png
   :scale: 60%

Now all requirements for FindFace Lite are followed, please, go to the next :ref:`STEP <step4>` to upload FindFace Lite installer and license on the server.




CentOS
+++++++++++

  
1. Install the :code:`yum-utils` package and set up the repository. Use the command below: 

 .. code-block:: bash

    sudo yum install -y yum-utils
    sudo yum-config-manager \
        --add-repo \
        https://download.docker.com/linux/centos/docker-ce.repo

2.  Install **Docker** and **Docker Compose Plugin**:

 .. code-block:: bash

    sudo yum install docker-ce docker-ce-cli containerd.io docker-compose-plugin

 .. note::

    If prompted to accept the GPG key, verify that the fingerprint matches **060A 61C5 1B55 8A7F 742B 77AA C52F EB6B 621E 9F35** value, and if so, accept it.

3. Start Docker using the following command:

 .. code-block:: bash
    
    sudo systemctl start docker

4. Check on how the **Docker** was installed using the command which downloads a test image and runs it in a container:

 .. code-block:: bash

    sudo docker run hello-world

 The container will be started, you will see the operation success message, then the container will automatically be stopped.

 .. image:: /images/helloworld.png
   :scale: 40%
 
5. Make sure the **Docker Compose Plugin** is also installed correctly. Use the following command to check:

 .. code-block:: bash

    docker compose version

 .. image:: /images/docker_compose_v.png
   :scale: 60%

Now all requirements for FindFace Lite are followed, please, go to the next :ref:`STEP <step4>` to upload FindFace Lite installer and license on the server.






GPU server preparation
------------------------

To prepare a GPU server to FindFace Lite, please, install `NVIDIA Container Toolkit <https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html#installation-guide>`_.

Before you install NVIDIA Container Toolkit for the first time on a new host machine, you need to prepare server according requrements: 

* NVIDIA Linux drivers >= 418.81.07 (note that older driver releases or branches are unsupported, to install drivers go to the official `NVIDIA guide <https://docs.nvidia.com/datacenter/tesla/tesla-installation-notes/index.html>`_);

* NVIDIA GPU with Architecture >= Kepler;

* Docker >= 19.03.

Steps from checking GPU server configuration to the **Docker software** and **NVIDIA Container Toolkit** installation are described in the guides for Ubuntu OS and CentOS below.


Ubuntu OS 
+++++++++++


1. Chek the GPU drivers version using the command below:

 .. code-block:: bash

    nvidia-smi

 **Driver Version:** should be >= 418.81.07.

 .. image:: /images/nvidia-smi.png
   :scale: 40% 


 If it is not so, please, go to the official `NVIDIA guide <https://docs.nvidia.com/datacenter/tesla/tesla-installation-notes/index.html>`_ to install the drivers.

2. Check a graphics card model using command below:

 .. code-block:: bash

    nvidia-smi -L

3. Verify that graphics card has architecture >= **Kepler**. Find your graphics cards model in the list below and check:

  +---------------------------------------------------+------------------------------------------------------------------------+
  | **Architecture (from the oldest to the newest)**  | **Series**                                                             |
  +===================================================+========================================================================+
  | **Fermi**                                         | GeForce 400 and 500: GTX 480, GTX 470, GTX 580, GTX 570;               |
  +---------------------------------------------------+------------------------------------------------------------------------+
  | **Kepler**                                        | GeForce 600 and 700: Nvidia GTX 680, 670, 660, GTX 780, GTX 770;       |
  +---------------------------------------------------+------------------------------------------------------------------------+
  | **Maxwell**                                       | GeForce 900: GTX 960, GTX 970, GTX 980;                                |
  +---------------------------------------------------+------------------------------------------------------------------------+
  | **Pascal**                                        | GeForce 1000: GTX 1050, 1050 Ti, 1060, 1080;                           |
  +---------------------------------------------------+------------------------------------------------------------------------+
  | **Turing**                                        | GeForce RTX 2000 and GTX 1600: GTX 1660, GTX 1650, RTX 2060, RTX 2080; |
  +---------------------------------------------------+------------------------------------------------------------------------+
  | **Ampere**                                        | GeForce RTX 3080, RTX 3090, RTX 3070, etc.                             |
  +---------------------------------------------------+------------------------------------------------------------------------+

4. Install the latest version of Docker using the command below: 

 .. code-block:: bash

    curl https://get.docker.com | sh \

  && sudo systemctl --now enable docker

 .. warning::

    If the command doesn't work, please, follow all the steps of :ref:`Docker installation on CPU server <ubuntu_cpu>`.

5. Setup the **NVIDIA package repository** and the **GPG key**:

 .. code-block:: bash

    distribution=$(. /etc/os-release;echo $ID$VERSION_ID) \
      && curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey | sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg \
      && curl -s -L https://nvidia.github.io/libnvidia-container/$distribution/libnvidia-container.list | \
            sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' | \
            sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list

6. Update the :code:`apt` package:

 .. code-block:: bash

    sudo apt-get update

7. Install the **nvidia-docker2 package** and dependencies: 

 .. code-block:: bash

    sudo apt-get install -y nvidia-docker2

8. Restart the **Docker daemon** to complete the installation after setting the default runtime:

 .. code-block:: bash

    sudo systemctl restart docker

9. Check the runtime in the config:

 .. code-block:: bash

    cat /etc/docker/daemon.json

 If there is the **nvidia-container-runtime** in the output, installation is succesful.

 .. image:: /images/nvidia-deamon.png
   :scale: 40%

Now all requirements for FindFace Lite are followed, please, go to the next :ref:`STEP <step4>` to upload FindFace Lite installer and license on the server.


CentOS
++++++++

1. Chek the GPU drivers version using the command below:

 .. code-block:: bash

    nvidia-smi

 **Driver Version:** should be >= 418.81.07.

 .. image:: /images/nvidia-smi.png
   :scale: 40%  


 If it is not so, please, go to the official `NVIDIA guide <https://docs.nvidia.com/datacenter/tesla/tesla-installation-notes/index.html>`_ to install the drivers.

2. Check graphics card model using command below:

 .. code-block:: bash

    nvidia-smi -L

3. Verify that graphics card has architecture >= **Kepler**. Find your graphics cards model in the list below and check:

  +---------------------------------------------------+------------------------------------------------------------------------+
  | **Architecture (from the oldest to the newest)**  | **Series**                                                             |
  +===================================================+========================================================================+
  | **Fermi**                                         | GeForce 400 and 500: GTX 480, GTX 470, GTX 580, GTX 570;               |
  +---------------------------------------------------+------------------------------------------------------------------------+
  | **Kepler**                                        | GeForce 600 and 700: Nvidia GTX 680, 670, 660, GTX 780, GTX 770;       |
  +---------------------------------------------------+------------------------------------------------------------------------+
  | **Maxwell**                                       | GeForce 900: GTX 960, GTX 970, GTX 980;                                |
  +---------------------------------------------------+------------------------------------------------------------------------+
  | **Pascal**                                        | GeForce 1000: GTX 1050, 1050 Ti, 1060, 1080;                           |
  +---------------------------------------------------+------------------------------------------------------------------------+
  | **Turing**                                        | GeForce RTX 2000 and GTX 1600: GTX 1660, GTX 1650, RTX 2060, RTX 2080; |
  +---------------------------------------------------+------------------------------------------------------------------------+
  | **Ampere**                                        | GeForce RTX 3080, RTX 3090, RTX 3070, etc.                             |
  +---------------------------------------------------+------------------------------------------------------------------------+

4. Setup the official **Docker CE repository**: 

 .. code-block:: bash

    sudo yum-config-manager --add-repo=https://download.docker.com/linux/centos/docker-ce.repo

5. Install the :code:`containerd.io` package:

 .. code-block:: bash

    sudo yum install -y https://download.docker.com/linux/centos/7/x86_64/stable/Packages/containerd.io-1.4.3-3.1.el7.x86_64.rpm

6. Install the latest version of **Docker** using the command below: 

 .. code-block:: bash

    sudo yum install docker-ce -y

7. Ensure the Docker service is running with the following command:

 .. code-block:: bash

    sudo systemctl --now enable docker

8. Test your Docker installation by running the hello-world container:

 .. code-block:: bash

    sudo docker run --rm hello-world

 The container will be started, you will see the operation success message, then the container will automatically be stopped.

 .. image:: /images/helloworld.png
  :scale: 40%

9. After **Docker** is installed continue with **NVIDIA** installation. Setup the repository and the GPG key using the command below:

 .. code-block:: bash

    distribution=$(. /etc/os-release;echo $ID$VERSION_ID) \
        && curl -s -L https://nvidia.github.io/libnvidia-container/$distribution/libnvidia-container.repo | sudo tee /etc/yum.repos.d/nvidia-container-toolkit.repo

10. Update the :code:`yam` package:

 .. code-block:: bash

    sudo yum clean expire-cache

11. Install the :code:`nvidia-docker2 package` and dependencies:

 .. code-block:: bash
     
    sudo yum install -y nvidia-docker2

12. Restart the Docker daemon to complete the installation after setting the default runtime:

 .. code-block:: bash 

    sudo systemctl restart docker

13. Check the runtime in the config:

 .. code-block:: bash

    cat /etc/docker/daemon.json 

If there is the **nvidia-container-runtime** in the output, installation is succesful.

.. image:: /images/nvidia-deamon.png
   :scale: 40%

Now all requirements for FindFace Lite are followed, please, go to the next :ref:`STEP <step4>` to upload FindFace Lite installer and license on the server.