Guide to Typical Cluster Installation

This section is all about deploying FindFace Enterprise Server in a cluster environment.

Tip

If after having read this section, you still have questions, do not hesitate to contact our experts by support@ntechlab.com.

The reasons for deploying FindFace Enterprise Server in a cluster are the following:

  • The necessity to distribute the video processing high load.

  • The necessity to process video streams from a group of cameras in the place of their physical location.

    Note

    The most common use cases where such need comes to the fore are hotel chains, chain stores, several security checkpoints in the same building, etc.

  • The necessity to distribute the biometric sample extraction high load.

  • A large number of faces to search through that requires the implementation of a distributed face database.

Before you start the deployment, outline your system architecture, depending on its load and allotted resources (see System Requirements). The most common distributed scheme is as follows:

  • One principal server with the following components: findface-ntls, findface-sf-api, findface-video-manager, findface-upload, findface-video-worker, findface-extraction-api, findface-tarantool-server, and third-parties.

  • Several additional video processing servers with installed findface-video-worker.

  • (If needed) Several additional biometric servers with installed findface-extraction-api.

  • (If needed) Additional database servers with multiple Tarantool shards.

This section describes the most common distributed deployment. In high load systems, it may also be necessary to distribute the API processing (findface-sf-api and findface-video-manager) across several additional servers. In this case, refer to Fully Customized Installation.

To deploy FindFace Enterprise Server in a cluster environment, follow the steps below:

Deploy Principal Server

To deploy the principal server as part of a distributed architecture, do the following:

  1. On the designated physical server, install FindFace Enterprise Server from the console installer as follows:

    • Product to install: FindFace Server.

    • Installation type: Single server, multiple video workers. In this case, FindFace Enterprise Server will be installed and configured to interact with additional remote findface-video-worker instances.

    • Type of the findface-video-worker acceleration (on the principal server): CPU or GPU, subject to your hardware configuration.

    • Type of the findface-extraction-api acceleration (on the principal server): CPU or GPU, subject to your hardware configuration.

    After the installation is complete, the following output will be shown on the console:

    Tip

    Be sure to save this data: you will need it later.

    #############################################################################
#                       Installation is complete                            #
#############################################################################
- upload your license to http://127.0.0.1:3185/
- FindFace SF-API address: http://172.20.77.78:18411/
- FindFace VideoManager address: http://172.20.77.78:18411/

  2. Upload the FindFace Enterprise Server license file via the findface-ntls web interface http://<ntls_host_IP_address>:3185.

    Note

    The IP address is shown in the links to the FindFace web services in the following way: as an external IP address if the host belongs to a network, or 127.0.0.1 otherwise.

  3. Allow the licensable services to access the findface-ntls license server from any IP address, To do so, open the /etc/findface-ntls.cfg configuration file and set listen = 0.0.0.0:3133.

    sudo vi /etc/findface-ntls.cfg

# Listen address of NTLS server where services will connect to.
# The format is IP:PORT
# Use 0.0.0.0:PORT to listen on all interfaces
# This parameter is mandatory and may occur multiple times
# if you need to listen on several specific interfaces or ports.
listen = 0.0.0.1:3133

Deploy Video Processing Servers

On an additional video processing server, install only a findface-video-worker instance following the step-by-step instructions. Answer the installer questions as follows:

  • Product to install: FindFace Video Worker.

  • Type of the findface-video-worker acceleration: CPU or GPU, subject to your hardware configuration.

  • FindFace Enterprise Server IP address: IP address of the principal server.

After that, the installation process will automatically begin. The answers will be saved to a file /tmp/<findface-installer-*>.json. Use this file to install FindFace Video Worker on other hosts without having to answer the questions again, by executing:

sudo ./<findface-security-and-server-xxx>.run -f /tmp/<findface-installer-*>.json

Note

After the installation, specify the findface-ntls and/or findface-video-manager IP addresses in the findface-video-worker configuration file.

sudo vi /etc/findface-video-worker-cpu.ini
sudo vi /etc/findface-video-worker-gpu.ini

In the ntls-addr parameter, specify the findface-ntls host IP address.

ntls-addr=127.0.0.1:3133

In the mgr-static parameter, specify the findface-video-manager host IP address, which provides findface-video-worker with settings and the video stream list.

mgr-static=127.0.0.1:18811

Deploy Biometric Servers

On an additional biometric server, install only a findface-extraction-api instance from the console installer. Answer the installer questions as follows:

  • Product to install: FindFace Server.

  • Installation type: Fully customized installation.

  • FindFace Enterprise Server components to install: findface-extraction-api and findface-data. To make a selection, first, deselect all the listed components by entering -* in the command line. Select findface-extraction-api and findface-data by entering their sequence number (keyword): 1 7. Enter done to save your selection and proceed to another step.

  • Type of findface-extraction-api acceleration: CPU or GPU.

  • Modification of the findface-extraction-api configuration file: specify the IP address of the findface-ntls server.

  • Neural network models to install: CPU or GPU model for face biometrics (mandatory), and (optional) CPU/GPU models for gender, age, emotions, glasses and/or beard recognition. To make a selection, first, deselect all the listed models by entering -* in the command line. Select required models by entering their sequence number (keyword), for example, 8 2 to select the GPU-models for biometric sample extraction and age recognition. Enter done to save your selection and proceed to another step. Be sure to choose the right acceleration type for each model, matching the acceleration type of findface-extraction-api: CPU or GPU. Be aware that findface-extraction-api on CPU can work only with CPU-models, while findface-extraction-api on GPU supports both CPU- and GPU-models. See Face Features Recognition for details.

    The following models are available:

    Face feature

    Acceleration

    Package

    face (biometry)

    CPU

    findface-data-grapefruit-160-cpu_3.0.0_amd64.deb, findface-data-grapefruit-480-cpu_3.0.0_amd64.deb

    GPU

    findface-data-grapefruit-160-gpu_3.0.0_amd64.deb, findface-data-grapefruit-480-gpu_3.0.0_amd64.deb

    age

    CPU

    findface-data-age.v1-cpu_3.0.0_amd64.deb

    GPU

    findface-data-age.v1-gpu_3.0.0_amd64.deb

    gender

    CPU

    findface-data-gender.v2-cpu_3.0.0_amd64.deb

    GPU

    findface-data-gender.v2-gpu_3.0.0_amd64.deb

    emotions

    CPU

    findface-data-emotions.v1-cpu_3.0.0_amd64.deb

    GPU

    findface-data-emotions.v1-gpu_3.0.0_amd64.deb

    glasses3

    CPU

    findface-data-glasses3.v0-cpu_3.0.0_amd64.deb

    GPU

    findface-data-glasses3.v0-gpu_3.0.0_amd64.deb

    beard

    CPU

    findface-data-beard.v0-cpu_3.0.0_amd64.deb

    GPU

    findface-data-beard.v0-gpu_3.0.0_amd64.deb

After that, the installation process will automatically begin. The answers will be saved to a file /tmp/<findface-installer-*>.json. Use this file to install findface-extraction-api on other hosts without having to answer the questions again.

sudo ./<findface-security-and-server-xxx>.run -f /tmp/<findface-installer-*>.json

After all the biometric servers are deployed, distribute load across them by using a load balancer.

Distribute Load across Biometric Servers

To distribute load across several biometric servers, you need to set up load balancing. The following step-by-step instructions demonstrate how to set up NGINX load balancing in a round-robin fashion for 3 findface-extraction-api instances located on different physical hosts: one on the FindFace Enterprise Server principal server (172.168.1.9), and 2 on additional remote servers (172.168.1.10, 172.168.1.11). Should you have more biometric servers in your system, load-balance them by analogy.

Tip

You can use any load balancer according to your preference. Please refer to the relevant official documentation for guidance.

To set up load balancing, do the following:

  1. Designate the FindFace Enterprise Server principal server (recommended) or any other server with NGINX as a gateway to all the biometric servers.

    Important

    You will have to specify the gateway server IP address when configuring the FindFace Enterprise Server network.

    Tip

    You can install NGINX as such:

    sudo apt update
sudo apt install nginx

  2. On the gateway server, create a new NGINX configuration file.

    sudo vi /etc/nginx/sites-available/extapi

  3. Insert the following entry into the newly created configuration file. In the upstream directive (upstream extapibackends), substitute the exemplary IP addresses with the actual IP addresses of the biometric servers. In the server directive, specify the gateway server listening port as listen. You will have to enter this port when configuring the FindFace Enterprise Server network.

    upstream extapibackends {
        server 172.168.1.9:18666; ## ``findface-extraction-api`` on principal server
        server 172.168.1.10:18666; ## 1st additional extraction server
        server 127.168.1.11:18666; ## 2nd additional extraction server
}
server {
        listen 18667;
        server_name extapi;
        client_max_body_size 64m;
        location / {
                proxy_pass http://extapibackends;
                proxy_next_upstream error;
        }
        access_log /var/log/nginx/extapi.access_log;
        error_log /var/log/nginx/extapi.error_log;
}

  4. Enable the load balancer in NGINX.

    sudo ln -s /etc/nginx/sites-available/extapi /etc/nginx/sites-enabled/

  5. Restart nginx.

    sudo service nginx restart

  6. On the principal server and each additional biometric server, open the /etc/findface-extraction-api.ini configuration file. Substitute localhost in the listen parameter with the relevant server address that you have specified in upstream extapibackends (/etc/nginx/sites-available/extapi) before. In our example, the address of the 1st additional extraction server has to be substituted as such:

    sudo vi /etc/findface-extraction-api.ini

listen: 172.168.1.10:18666

  7. Restart the findface-extraction-api on the principal server and each additional biometric server.

    sudo systemctl restart findface-extraction-api.service

The load balancing is now successfully set up. Be sure to specify the actual gateway server IP address and listening port, when configuring the FindFace Enterprise Server network.

Distribute Database

The findface-tarantool-server component connects the Tarantool database and the findface-sf-api component, transferring search results from the database to findface-sf-api for further processing. To increase search speed, multiple findface-tarantool-server shards can be created on each Tarantool host. Their running concurrently leads to a remarkable increase in performance. Each shard can handle up to approximately 10,000,000 faces. When deploying findface-tarantool-server from the console installer, shards are created automatically given the server hardware.

To distribute the face database, install only a findface-tarantool-server instance on each additional database server. Answer the installer questions as follows:

  • Product to install: FindFace Server.

  • Installation type: Fully customized installation.

  • FindFace Enterprise Server components to install: findface-tarantool-server. To make a selection, first, deselect all the listed components by entering -* in the command line. Select findface-tarantool-server by entering its sequence number (keyword): 13. Enter done to save your selection and proceed to another step.

After that, the installation process will automatically begin. The answers will be saved to a file /tmp/<findface-installer-*>.json. Use this file to install findface-tarantool-server on other hosts without having to answer the questions again.

sudo ./<findface-security-and-server-xxx>.run -f /tmp/<findface-installer-*>.json

As a result of the installation, findface-tarantool-server shards will be automatically installed in the amount of N = max(min(mem_mb // 2000, cpu_cores), 1), i.e., equal to the RAM size in MB divided by 2000, or the number of CPU physical cores (but at least 1 shard).

Be sure to specify the shards IP addresses and ports, when configuring the FindFace Enterprise Server network. To learn the port numbers, execute on each database server:

sudo cat /etc/tarantool/instances.enabled/*shard* | grep -E ".start|(listen =)"`

You will get the following result:

    listen = '127.0.0.1:33001',
FindFace.start("127.0.0.1", 8101, {
    listen = '127.0.0.1:33002',
FindFace.start("127.0.0.1", 8102, {

You can find the port number of a shard in the FindFace.start section, for example, 8101, 8102, etc.

Configure Network

After all the FindFace Enterprise Server components are deployed, configure their interaction over the network. Do the following:

  1. Open the findface-sf-api configuration file:

    sudo vi /etc/findface-sf-api.ini

    Specify the following parameters:

    Parameter

    Description

    extraction-api -> extraction-api

    IP address and listening port of the gateway biometric server with set up load balancing.

    storage-api -> shards -> master

    IP address and port of the findface-tarantool-server master shard. Specify each shard by analogy.

    upload_url

    WebDAV NGINX path to send original images, thumbnails and normalized face images to the findface-upload service.

    		 
    ...
extraction-api:
  extraction-api: http://172.168.1.9:18667

...
webdav:
  upload-url: http://127.0.0.1:3333/uploads/

...
storage-api:
  ...
  shards:
  - master: http://172.168.1.9:8101/v2/
    slave: ''
  - master: http://172.168.1.9:8102/v2/
    slave: ''
  - master: http://172.168.1.12:8101/v2/
    slave: ''
  - master: http://172.168.1.12:8102/v2/
    slave: ''
  - master: http://172.168.1.13:8102/v2/
    slave: ''
  - master: http://172.168.1.13:8102/v2/
    slave: ''

  2. Open the findface-facerouter configuration file. Specify the IP address of the findface-sf-api host.

    sudo vi /etc/findface-facerouter.py

sfapi_url                      = 'http://localhost:18411'

  3. Open the findface-video-manager configuration file. In the router_url parameter, specify the IP address and port of the findface-facerouter host to receive detected faces from findface-video-worker.

    sudo vi /etc/findface-video-manager.conf

...
router_url: http://127.0.0.1:18820/v0/frame

The FindFace Enterprise Server components interaction is now set up.