me/p2p-rendering-computation
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

buit base functions

Browse Source
This commit is contained in:
Akilan Selvacoumar
2021-08-25 13:27:31 +04:00
parent 1a7035164b
commit e5334cbd3c
61 changed files with 124 additions and 908 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
.gitignore vendored
View File

@@ -14,4 +14,6 @@ p2p/iptable/
#ignore plugins added
plugin/deploy/
#ignore track container file
client/trackcontainers/
client/trackcontainers/
# Test generated files
generate/p2prctest

11
Makefile
View File

@@ -1,16 +1,7 @@
SHELL := /bin/bash
install:
go build -o p2prc
echo '# Paths for p2p rendering and computation'
echo 'export P2PRC=${PWD}'
echo 'export PATH=${PWD}:$${PATH}'
build:
go build -o p2prc
configfile:
./p2prc --SetDefaultConfig
sh install.sh p2prc
testcases:
sh plugin/generate_test_case.sh

6
README.md
View File

@@ -63,11 +63,7 @@ This project aims to create a peer to peer (p2p) network, where a user can use t
// Add them to your .bashrc file
export P2PRC=/<path>/p2p-rendering-computation
export PATH=/<path>/p2p-rendering-computation:${PATH}
5. Generate Config file
```
make configfile
```
5. Test if it works
```

72
generate/generate.go Normal file
View File

@@ -0,0 +1,72 @@
// Package generate The purpose of this package is to ensure that we can extend the use-case of P2PRC.
// We will create a project directory with the template to extend the use-case of P2PRC
package generate
import (
"fmt"
"github.com/otiai10/copy"
"os"
"strings"
)
func GenerateNewProject(name string) error {
// Get path of the current directory
curDir := os.Getenv("PWD")
// Add slash to the end
curDir = curDir + "/"
// Folder name of the new generated project
NewProject := curDir + name + "/"
fmt.Println(NewProject)
// Create a new folder based on name entered
err := CreateFolder(name, curDir)
if err != nil {
return err
}
// get path of P2PRC
P2PRCPATH := os.Getenv("P2PRC")
// Add slash to the end
P2PRCPATH = P2PRCPATH + "/"
// Steps:
// - copy all files from P2PRC
// - remove go.mod and go.sum and create new ones
// Files we require to skip
var Options copy.Options
// Skips the appropriate files and directories not needed
Options.Skip = func(src string) (bool, error) {
switch {
case strings.HasSuffix(src, "go.mod"):
return true, nil
case strings.HasSuffix(src, "go.sum"):
return true, nil
case strings.HasSuffix(src, name):
return true, nil
default:
return false, nil
}
}
// Copies all files from P2PRC to the new project created
err = copy.Copy(P2PRCPATH, NewProject,Options)
if err != nil {
return err
}
// Installing new project
//cmd := exec.Command("sh","install.sh",name)
//if err := cmd.Run(); err != nil {
// return err
//}
return nil
}
// CreateFolder Creates a new folder based on the name and path provided
func CreateFolder(name string,path string) error {
//Create a folder/directory at a full qualified path
err := os.Mkdir(path + name, 0755)
if err != nil {
return err
}
return nil
}

26
generate/generate_test.go Normal file
View File

@@ -0,0 +1,26 @@
package generate
import (
"fmt"
"testing"
)
// Tests the create folder function creates a folder
// This test will create a folder in the temporary
// directory
func TestCreateFolder(t *testing.T) {
err := CreateFolder("test", "/tmp/")
if err != nil {
t.Error(err)
}
}
// Testing if a new project is created successfully
func TestGenerateNewProject(t *testing.T) {
// Checking if a new project is created successfully
err := GenerateNewProject("p2prctest")
if err != nil {
fmt.Println(err)
t.Error(err)
}
}

3
go.mod
View File

@@ -18,6 +18,7 @@ require (
github.com/moby/sys/mount v0.2.0 // indirect
github.com/moby/term v0.0.0-20201110203204-bea5bbe245bf // indirect
github.com/morikuni/aec v1.0.0 // indirect
github.com/otiai10/copy v1.6.0
github.com/phayes/freeport v0.0.0-20180830031419-95f893ade6f2
github.com/shirou/gopsutil v3.20.12+incompatible
github.com/spf13/viper v1.4.0
@@ -29,6 +30,6 @@ require (
golang.org/x/text v0.3.5 // indirect
golang.org/x/time v0.0.0-20210220033141-f8bda1e9f3ba // indirect
google.golang.org/grpc v1.35.0 // indirect
gopkg.in/yaml.v2 v2.4.0 // indirect
gopkg.in/yaml.v2 v2.4.0
gotest.tools/v3 v3.0.3 // indirect
)

8
go.sum
View File

@@ -462,6 +462,14 @@ github.com/opencontainers/runtime-spec v1.0.3-0.20200929063507-e6143ca7d51d/go.m
github.com/opencontainers/runtime-tools v0.0.0-20181011054405-1d69bd0f9c39/go.mod h1:r3f7wjNzSs2extwzU3Y+6pKfobzPh+kKFJ3ofN+3nfs=
github.com/opencontainers/selinux v1.6.0/go.mod h1:VVGKuOLlE7v4PJyT6h7mNWvq1rzqiriPsEqVhc+svHE=
github.com/opencontainers/selinux v1.8.0/go.mod h1:RScLhm78qiWa2gbVCcGkC7tCGdgk3ogry1nUQF8Evvo=
github.com/otiai10/copy v1.6.0 h1:IinKAryFFuPONZ7cm6T6E2QX/vcJwSnlaA5lfoaXIiQ=
github.com/otiai10/copy v1.6.0/go.mod h1:XWfuS3CrI0R6IE0FbgHsEazaXO8G0LpMp9o8tos0x4E=
github.com/otiai10/curr v0.0.0-20150429015615-9b4961190c95/go.mod h1:9qAhocn7zKJG+0mI8eUu6xqkFDYS2kb2saOteoSB3cE=
github.com/otiai10/curr v1.0.0 h1:TJIWdbX0B+kpNagQrjgq8bCMrbhiuX73M2XwgtDMoOI=
github.com/otiai10/curr v1.0.0/go.mod h1:LskTG5wDwr8Rs+nNQ+1LlxRjAtTZZjtJW4rMXl6j4vs=
github.com/otiai10/mint v1.3.0/go.mod h1:F5AjcsTsWUqX+Na9fpHb52P8pcRX2CI6A3ctIT91xUo=
github.com/otiai10/mint v1.3.2 h1:VYWnrP5fXmz1MXvjuUvcBrXSjGE6xjON+axB/UrpO3E=
github.com/otiai10/mint v1.3.2/go.mod h1:/yxELlJQ0ufhjUwhshSj+wFjZ78CnZ48/1wtmBH1OTc=
github.com/pelletier/go-toml v1.2.0 h1:T5zMGML61Wp+FlcbWjRDT7yAxhJNAiPPLOFECq181zc=
github.com/pelletier/go-toml v1.2.0/go.mod h1:5z9KED0ma1S8pY6P1sdut58dfprrGBbd/94hg7ilaic=
github.com/peterbourgon/diskv v2.0.1+incompatible/go.mod h1:uqqh8zWWbv1HBMNONnaR/tNboyR3/BZd58JJSHlUSCU=

11
install.sh Normal file
View File

@@ -0,0 +1,11 @@
# This script setups up the project P2PRC
# Call: sh install.sh <name of binary>
echo '# Add the following paths to .bashrc or .zshrc based on the configuration you have set'
echo export P2PRC=$PWD
echo export PATH=$PWD:\${PATH}
export P2PRC=${PWD}
export PATH=${PWD}:${PATH}
# Expects an argument of the name of the binary
go build -o ${1}
./p2prc --dc

201
sample-run/tensorflow/LICENSE
View File

@@ -1,201 +0,0 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.

147
sample-run/tensorflow/README.md
View File

@@ -1,147 +0,0 @@
# Ansible p2p-rendering-computation
This repository contains an Ansible playbook and instructions to create and manage a single (or many) bare metal deep learning machines. For a description of why Ansible was chosen and what other alternatives were considered, please see [ToolSelection.md](ToolSelection.md)
## Quick Reference
If you've already [installed Ansible](#Installation), you can execute the entire playbook by running:
```bash
$ ansible-playbook packages.yml
```
You can also execute only the pieces you need by passing tags on the command line:
- Install only apt/pip [pre-requisites](roles/packages) to execute the other roles:
```bash
$ ansible-playbook packages.yml --tags "packages"
```
- Install [Docker CE](roles/docker):
```bash
$ ansible-playbook packages.yml --tags "docker"
```
- Install the [Nvidia CUDA GPU drivers](roles/cuda):
```bash
$ ansible-playbook packages.yml --tags "cuda"
```
- Install the [Nvidia Docker Runtime](roles/nvidia):
```bash
$ ansible-playbook packages.yml --tags "nvidia"
```
## What's Included
After running the ansible script your machines will be loaded with the following:
1. Docker
2. Nvidia CUDA GPU Drivers
3. Nvidia Docker Runtime
4. TensorFlow GPU Python3 Docker Container
5. JupyterLab
## Using This Repository to Configure Your Environment
1. [Installation](#Installation)
2. [Configuration](#Configuration)
3. [Running](#Running)
---
### Installation
Ansible runs on your local machine and sends commands to the remote (machine learning) machines. You'll need ansible installed locally (not on the machine learning boxes).
For macOS users, the easiest way to install Ansible is via [Homebrew](https://brew.sh/):
```bash
$ brew install ansible
```
If that's not your cup of tea, install Ansible by following the directions for your machine [here](https://docs.ansible.com/ansible/latest/installation_guide/intro_installation.html#installing-the-control-machine).
---
### Configuration
Gather the following:
- SSH key or user credentials for the remote account
**Note:** Ansible does not expose a channel to allow communication between the user and the ssh process to accept a password manually to decrypt an ssh key when using the ssh connection plugin (which is the default). The use of `ssh-agent` is highly recommended.
- List of servers you wish to manage:
- hostnames/IP addresses
- SSH port
- usernames
Copy [hosts.example] to `/etc/ansible/hosts` (if it does not already exist). Populate the `hosts` file (no extension) with the information about the servers you gathered above.
Confirm that you have populated your Ansible hosts file correctly:
```bash
$ ansible-inventory --list
```
---
### Running
Once you're satisfied that you correctly populated your `hosts` file, update the `- hosts:` line of [tensorflow.yml] to reflect the hosts or groups you want to configure.
Examples:
- Apply against a single host defined as `ml2` in `/etc/ansible/hosts`:
```yaml
- hosts: ml2
```
- Apply against a group of hosts defined as `production` in `/etc/ansible/hosts`:
```yaml
- hosts: production
```
- Apply against all hosts defined in `/etc/ansible/hosts`:
```yaml
- hosts: all
```
Then, when you're ready, run the playbook:
```bash
$ ansible-playbook packages.yml --ask-become-pass
```
**Note:** You must have `sudo` access to run the playbook!
Review the output:
- `[ok]` means no change (this task was already completed)
- `[changed]` means the task successfully ran and the change was applied
- `[unreachable]` means the host could not be reached
- `[failed]` means the task ran but failed to complete
`[ok]` and `[changed]` are successful outcomes. Any `[unreachable]` and `[failed]` outputs should be investigated and resolved.
**Note:** This Ansible playbook is idempotent; once a configuration has been successfully applied, if you apply it again, all actions will report `[ok]`.
## Executing Tensorflow Jobs in Your New Environment
1. Point your browser to http://&lt;hostname&gt;:8888 and login with the password you provided.
2. The `jupyter.volumes.source` folder will be mounted as the `notebooks` folder.
3. Edit and execute your Jupyter notebooks as normal!
### Command Line Access
If you need to drop into a GPU-powered TensorFlow environment, SSH into the remote machine and execute the following:
```bash
$ docker run --runtime=nvidia -it --rm tensorflow/tensorflow:latest-gpu-py3 bash
```
**Note:** You must be a member of the `docker` group or have `sudo` access on the _remote machine_ to execute docker commands.
---
## Additional Files
- [ansible.cfg](ansible.cfg) enables SSH credential forwarding. This is a necessary step during data synchronization, as Ansible delegates those credentials to the master/writer host to push the data folder out to each of the mirrors.
- [Dockerfile](Dockerfile) is used to build the Arricor TensorFlow image. See [Docker.md](Docker.md) for additional details.
- [hosts.example](hosts.example) is an example of the Ansible inventory hosts file saved in `/etc/ansible/hosts`
- [secrets.example.yml](secrets.example.yml) is an example of the expected structure of the `secrets.yml` file

93
sample-run/tensorflow/ToolSelection.md
View File

@@ -1,93 +0,0 @@
# Configuration Management Tool Selection
## Summary
Ansible is proposed as the configuration management tool for this project due to the following characteristics:
- no agent installation on the managed nodes
- push-based configuration changes do not require a separate machine to be provisioned
- commands can be pushed from any developer/operator workstation
- all updates are performed over SSH
## Tools Considered
Where a tool offers an open source and an enterprise version (e.g., Puppet, Terraform), only the open source version was considered. Web or other graphical user interfaces (GUIs) were not considered, as the goal of this phase is to produce infrastructure as code which can be run (and re-run) from the command line interface (CLI).
- [Ansible](#Ansible)
- [Chef](#Chef)
- [Puppet](#Puppet)
- [Salt](#Salt)
- [Terraform](#Terraform)
### Ansible
[Ansible's simple interface and usability fit right into the sys admin mindset, and in a shop with lots of Linux and Unix systems, Ansible is quick and easy to run right out of the gate](https://www.infoworld.com/article/2609482/data-center/data-center-review-puppet-vs-chef-vs-ansible-vs-Salt.html?page=4).
#### Ansible Pros
- Requires no agent installation on the managed nodes.
- Push-based.
- Does not require a separate machine to be provisioned. Commands can be pushed from any developer/operator workstation.
- All updates are performed over SSH.
#### Ansible Cons
- Push-based synchronization means that the configuration is only refreshed on demand.
### Chef
[Chef has a stable and well-designed layout, and while it's not quite up to the level of Puppet in terms of raw features, it's a very capable solution. Chef may pose the most difficult learning curve to administrators who lack significant programming experience, but it could be the most natural fit for development-minded admins and development shops](https://www.infoworld.com/article/2609482/data-center/data-center-review-puppet-vs-chef-vs-ansible-vs-Salt.html?page=4).
#### Chef Pros
- AWS OpsWorks is based on Chef; any future migration to AWS could benefit from the existing configuration files.
#### Chef Cons
- **(Fatal)** Requires a master server and a workstation that will need to be maintained separately from the already provisioned deep learning machines.
- **(Fatal)** Requires an agent (client) to be installed on each machine.
- Requires an on-premises Chef server and [Push Jobs](https://docs.chef.io/push_jobs.html) plugin to push configurations manually. Otherwise, managed machines must check in with the master on a schedule.
### Puppet
[Puppet is the most mature and probably the most approachable of the four from a usability standpoint, though a solid knowledge of Ruby is highly recommended. Puppet is not as streamlined as Ansible or Salt, and its configuration can get Byzantine at times. Puppet is the safest bet for heterogeneous environments, but you may find Ansible or Salt to be a better fit in a larger or more homogenous infrastructure](https://www.infoworld.com/article/2609482/data-center/data-center-review-puppet-vs-chef-vs-ansible-vs-salt.html?page=4).
#### Puppet Pros
- Configuration can be kept up to date via a schedule or manual configuration pushes.
#### Puppet Cons
- **(Fatal)** Requires a "puppet master" (server) that will need to be maintained separately from the already provisioned machines.
- **(Fatal)** Requires an agent (client) to be installed on each machine.
### Salt
[Salt is the sleekest and most robust of the four, and like Ansible it will resonate with sys admins. Highly scalable and quite capable, Salt is hamstrung only by the Web UI](https://www.infoworld.com/article/2609482/data-center/data-center-review-puppet-vs-chef-vs-ansible-vs-salt.html?page=4).
#### Salt Pros
- Push-based.
- Can function via regular SSH or via client agents called "minions".
#### Salt Cons
- When running agentless, push-based synchronization means that the configuration is only refreshed on demand.
### Terraform
The initial hope was that [Terraform](https://terraform.io) could be used for configuration management for this project. However, after reviewing the [available Terraform provider plugins](https://terraform.io/docs/providers) and other available material, it was agreed on 23 January 2019 that Terraform was not suitable for this stage of the project.
In the future, if Arricor migrates its instances to a cloud service provider (CSP) such as AWS, Azure, or Google Cloud Platform, this configuration may be reusable as a first step via the [terraform-provisioner-ansible](https://github.com/jonmorehouse/terraform-provisioner-ansible) plugin. This plugin allows the user to create CSP instances, then execute the given Ansible playbook against those instances.
#### Terraform Pros
- Cloud native with support for multiple service providers.
#### Terraform Cons
- **(Fatal)** No support for provisioning bare metal instances.
## Conclusion
Ansible allows for management of a server from scratch, with only the requirement to have a valid username and password. Additionally, its agentless approach avoids having to configure and maintain an admin server, further simplifying operations at the scale Arricor requires.

6
sample-run/tensorflow/ansible.cfg
View File

@@ -1,6 +0,0 @@
[defaults]
host_key_checking = False
inventory = hosts
[ssh_connection]
ssh_args = -o ForwardAgent=yes -o ControlMaster=auto -o ControlPersist=60s

12
sample-run/tensorflow/hosts
View File

@@ -1,12 +0,0 @@
---
all:
vars:
ansible_python_interpreter: /usr/bin/python3
test:
hosts:
test1:
ansible_host: 0.0.0.0 # Replace with your remote IP
ansible_port: 44003 # Replace with your remote SSH port
ansible_user: master # Replace wtih your username
ansible_ssh_pass: password
ansible_sudo_pass: password

25
sample-run/tensorflow/hosts.example
View File

@@ -1,25 +0,0 @@
---
all:
vars:
ansible_python_interpreter: /usr/bin/python3
test:
hosts:
test1:
ansible_host: 127.0.0.1 # Replace with your remote IP
ansible_port: 2222 # Replace with your remote SSH port
ansible_user: vagrant # Replace wtih your username
production:
hosts:
writer:
ansible_host: 192.168.1.100 # Replace with your remote IP
ansible_port: 2202 # Replace with your remote SSH port
ansible_user: ansible # Replace wtih your username
mirror1:
ansible_host: 192.168.1.101 # Replace with your remote IP
ansible_port: 2202 # Replace with your remote SSH port
ansible_user: ansible # Replace wtih your username
mirror2:
ansible_host: 192.168.1.102 # Replace with your remote IP
ansible_port: 2202 # Replace with your remote SSH port
ansible_user: ansible # Replace wtih your username

38
sample-run/tensorflow/packages.yml
View File

@@ -1,38 +0,0 @@
################################################################################
# This file consists of three main sections:
# 1. vars - variables used throughout the playbook are defined here. If you want to change packages or version, this is the place to do it.
# 2. tasks - these are the steps that will be executed by the playbook. This is a straightforward, sequential playbook.
# 3. handlers - these steps run only in response to specific events. If the event does not occur, the handler does not run.
################################################################################
---
- hosts: test # Alternatively, 'canary', 'blue'|'green', 'all' according to your deployment strategy and your /etc/ansible/hosts file
become: yes # All commands must run as root
strategy: free # Allows all hosts to run to the end of the playbook as fast as they can
vars_files:
- secrets.yml
roles:
- role: packages # General Dependencies
tags: [packages]
# - role: rsync # Rsync Setup
# tags: [rsync]
# vars:
# sync: "{{ secrets.sync }}"
# - role: docker # General Docker setup
# tags: [docker]
# vars:
# users: "{{ secrets.users }}"
- role: cuda # CUDA Driver Setup
tags: [cuda]
# - role: nvidia # NVIDIA-Docker Runtime Setup
# tags: [nvidia]
# - role: jupyter # Launch Jupyter Container in Docker
# tags: [jupyter]
# vars:
# volumes: "{{ secrets.volumes }}"

23
sample-run/tensorflow/roles/cuda/README.md
View File

@@ -1,23 +0,0 @@
# The `cuda` Role
The `cuda` role installs the Nvidia CUDA GPU repository and drivers.
This role may be executed independently by running:
```bash
$ ansible-playbook packages.yml --tags "cuda"
```
On execution, this role installs the following directly to the remote machine's operating system:
### Apt Repositories (Debian/Ubuntu)
- Nvidia CUDA
### Apt GPG Signing Keys (Debian/Ubuntu)
- cudatools <cudatools@nvidia.com>
### Operating System Packages (Debian/Ubuntu)
- cuda v10.x

0
sample-run/tensorflow/roles/cuda/defaults/.gitkeep
View File

BIN
sample-run/tensorflow/roles/cuda/files/cuda-11-3_11.3.1-1_amd64.deb
View File

Binary file not shown.

BIN
sample-run/tensorflow/roles/cuda/files/cuda-runtime-11-3_11.3.1-1_amd64.deb
View File

Binary file not shown.

5
sample-run/tensorflow/roles/cuda/handlers/main.yml
View File

@@ -1,5 +0,0 @@
---
# CUDA Driver Setup
- name: reboot the machine
reboot:
listen: "reboot the machine"

0
sample-run/tensorflow/roles/cuda/meta/.gitkeep
View File

22
sample-run/tensorflow/roles/cuda/tasks/debian.yml
View File

@@ -1,22 +0,0 @@
---
# Cuda Driver Package Installation
- name: copy the CUDA repo onto the machine
copy:
src: "{{ cuda.apt.repo }}"
dest: "{{ general.working_dir }}/{{ cuda.apt.repo }}"
- name: get the CUDA signing key
apt_key:
state: present
url: "{{ cuda.apt.signing_key_url }}"
- name: add the CUDA repo
apt:
deb: "{{ general.working_dir }}/{{ cuda.apt.repo }}"
state: present
- name: install the CUDA drivers
apt:
name: "{{ cuda.apt.package }}"
update_cache: yes
notify: "reboot the machine"

3
sample-run/tensorflow/roles/cuda/tasks/main.yml
View File

@@ -1,3 +0,0 @@
---
- import_tasks: debian.yml
when: ansible_facts['os_family']|lower == 'debian' # debian, ubuntu

0
sample-run/tensorflow/roles/cuda/templates/.gitkeep
View File

10
sample-run/tensorflow/roles/cuda/vars/main.yml
View File

@@ -1,10 +0,0 @@
---
cuda:
apt:
package: cuda=11.* # known good with 10.0.130-1
repo: cuda-11-3_11.3.1-1_amd64.deb # Network install
dependency: cuda-runtime-11-3_11.3.1-1_amd64.deb
signing_key_url: https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/7fa2af80.pub
general:
working_dir: /tmp

33
sample-run/tensorflow/roles/docker/README.md
View File

@@ -1,33 +0,0 @@
# The `docker` Role
The `docker` role installs the Docker CE repository and runtime packages.
This role may be executed independently by running:
```bash
$ ansible-playbook packages.yml --tags "docker"
```
On execution, this role installs the following directly to the remote machine's operating system:
### Apt Repositories (Debian/Ubuntu)
- Docker CE
### Apt GPG Signing Keys (Debian/Ubuntu)
- Docker Release (CE deb) <docker@docker.com>
### Operating System Packages (Debian/Ubuntu)
- docker-ce v5:18.x
### System Services
- `docker` (enabled and started)
### User Groups
- docker
All users listed under `secrets.users` in `secrets.yml` will be added to the `docker` group.

0
sample-run/tensorflow/roles/docker/defaults/.gitkeep
View File

0
sample-run/tensorflow/roles/docker/files/.gitkeep
View File

0
sample-run/tensorflow/roles/docker/handlers/.gitkeep
View File

0
sample-run/tensorflow/roles/docker/meta/.gitkeep
View File

17
sample-run/tensorflow/roles/docker/tasks/debian.yml
View File

@@ -1,17 +0,0 @@
---
# Docker Package Installation
- name: add Docker's official GPG key
apt_key:
state: present
url: "{{ docker.apt.signing_key_url }}"
- name: add Docker apt repository
apt_repository:
repo: "{{ docker.apt.repo }}"
state: present
- name: install Docker CE
apt:
name: "{{ docker.apt.package }}"
state: present
update_cache: yes

23
sample-run/tensorflow/roles/docker/tasks/main.yml
View File

@@ -1,23 +0,0 @@
---
# General Docker Setup
- import_tasks: debian.yml
when: ansible_facts['os_family']|lower == 'debian' # debian, ubuntu
- name: ensure the docker service starts at boot
systemd:
name: "{{ docker.service_name }}"
enabled: yes
state: started
- name: create Docker group to avoid running as root
group:
name: "{{ docker.group_name }}"
state: present
- name: add users to Docker group
user:
append: yes
groups:
- "{{ docker.group_name }}"
name: "{{ item }}"
loop: "{{ users }}"

0
sample-run/tensorflow/roles/docker/templates/.gitkeep
View File

8
sample-run/tensorflow/roles/docker/vars/main.yml
View File

@@ -1,8 +0,0 @@
---
docker:
apt:
package: docker-ce=5:18.* # known good with 5:18.09.1~3-0~ubuntu-bionic
repo: deb [arch=amd64] https://download.docker.com/linux/ubuntu bionic stable
signing_key_url: https://download.docker.com/linux/ubuntu/gpg
group_name: docker
service_name: docker

31
sample-run/tensorflow/roles/nvidia/README.md
View File

@@ -1,31 +0,0 @@
# The `nvidia` Role
The `nvidia` role installs the Nvidia Docker runtime, enabling access to Nvidia CUDA GPU hardware from within Docker containers.
This role may be executed independently by running:
```bash
$ ansible-playbook packages.yml --tags "nvidia"
```
On execution, this role installs the following directly to the remote machine's operating system:
### Apt Repositories (Debian/Ubuntu)
- libnvidia_container
- nvidia_container_runtime
- nvidia_docker
### Apt GPG Signing Keys (Debian/Ubuntu)
- NVIDIA CORPORATION (Open Source Projects) <cudatools@nvidia.com>
### Operating System Packages (Debian/Ubuntu)
- nvidia-docker2 v2.x
Containers are launched with the Nvidia Docker runtime by passing the `--runtime=nvidia` flag, e.g.,
```bash
$ docker run --rm --runtime=nvidia nvidia/cuda nvidia-smi
```

0
sample-run/tensorflow/roles/nvidia/defaults/.gitkeep
View File

0
sample-run/tensorflow/roles/nvidia/files/.gitkeep
View File

6
sample-run/tensorflow/roles/nvidia/handlers/main.yml
View File

@@ -1,6 +0,0 @@
---
- name: reload the docker service
systemd:
name: docker
state: reloaded
listen: "reload the docker service"

0
sample-run/tensorflow/roles/nvidia/meta/.gitkeep
View File

31
sample-run/tensorflow/roles/nvidia/tasks/debian.yml
View File

@@ -1,31 +0,0 @@
---
# Nvidia Docker Runtime Installation
- name: get the NVIDIA signing key
apt_key:
state: present
url: "{{ nvidia.apt.signing_key_url }}"
- name: add the libnvidia-container repo
apt_repository:
filename: "{{ nvidia.apt.repo_filename }}"
repo: "{{ nvidia.apt.repos.libnvidia_container }}"
state: present
- name: add the nvidia-container-runtime repo
apt_repository:
filename: "{{ nvidia.apt.repo_filename }}"
repo: "{{ nvidia.apt.repos.nvidia_container_runtime }}"
state: present
- name: add the nvidia-docker repo
apt_repository:
filename: "{{ nvidia.apt.repo_filename }}"
repo: "{{ nvidia.apt.repos.nvidia_docker }}"
state: present
- name: install the nvidia-docker2 runtime
apt:
name: "{{ nvidia.apt.package }}"
state: present
update_cache: yes
notify: "reload the docker service"

4
sample-run/tensorflow/roles/nvidia/tasks/main.yml
View File

@@ -1,4 +0,0 @@
---
# Nvidia Docker Runtime Setup
- import_tasks: debian.yml
when: ansible_facts['os_family']|lower == 'debian' # debian, ubuntu

0
sample-run/tensorflow/roles/nvidia/templates/.gitkeep
View File

10
sample-run/tensorflow/roles/nvidia/vars/main.yml
View File

@@ -1,10 +0,0 @@
---
nvidia:
apt:
package: nvidia-docker2=2.* # known good with 2.0.3+docker18.09.1-1
repo_filename: nvidia_github_io_nvidia_docker_ubuntu18_04_nvidia_docker.list
repos:
libnvidia_container: deb https://nvidia.github.io/libnvidia-container/ubuntu18.04/$(ARCH) /
nvidia_container_runtime: deb https://nvidia.github.io/nvidia-container-runtime/ubuntu18.04/$(ARCH) /
nvidia_docker: deb https://nvidia.github.io/nvidia-docker/ubuntu18.04/$(ARCH) /
signing_key_url: https://nvidia.github.io/nvidia-docker/gpgkey

26
sample-run/tensorflow/roles/packages/README.md
View File

@@ -1,26 +0,0 @@
# The `packages` Role
The `packages` role installs the operating system and Python pre-requisites that are required to execute the other roles.
This role may be executed independently by running:
```bash
$ ansible-playbook packages.yml --tags "packages"
```
On execution, this role installs the following directly to the remote machine's operating system:
### Operating System Packages (Debian/Ubuntu)
- apt-transport-https v1.x
- ca-certificates v20180409
- curl v7.x
- gnupg-agent v2.x
- python-apt v1.x
- python-pip v9.x
- python-setuptools v39.x
- software-properties-common v0.96.24.32.7
### Python (pip) Packages
- docker v3.7.0 or greater

0
sample-run/tensorflow/roles/packages/defaults/.gitkeep
View File

0
sample-run/tensorflow/roles/packages/files/.gitkeep
View File

0
sample-run/tensorflow/roles/packages/handlers/.gitkeep
View File

0
sample-run/tensorflow/roles/packages/meta/.gitkeep
View File

12
sample-run/tensorflow/roles/packages/tasks/debian.yml
View File

@@ -1,12 +0,0 @@
---
# General Dependencies
- name: install general apt dependencies
apt:
name: "{{ general.dependencies.apt }}"
state: present
update_cache: yes
- name: install general pip dependencies for Ansible
pip:
name: "{{ general.dependencies.pip }}"
state: present

3
sample-run/tensorflow/roles/packages/tasks/main.yml
View File

@@ -1,3 +0,0 @@
---
- import_tasks: debian.yml
when: ansible_facts['os_family']|lower == 'debian' # debian, ubuntu

0
sample-run/tensorflow/roles/packages/templates/.gitkeep
View File

15
sample-run/tensorflow/roles/packages/vars/main.yml
View File

@@ -1,15 +0,0 @@
---
# General Dependencies
general:
dependencies:
apt:
- apt-transport-https # known good with 1.6.6ubuntu0.1 all
- ca-certificates # known good with 20180409
- curl # known good with 7.58.0-2ubuntu3.5
- gnupg-agent # known good with 2.2.4-1ubuntu1.2
- python3-pip # known good with 9.0.1-2.3~ubuntu1
- software-properties-common # known good with 0.96.24.32.7
- git
- golang
pip:
- docker>=3.7.0 # known good with 3.7.0

0
sample-run/tensorflow/roles/rsync/defaults/.gitkeep
View File

16
sample-run/tensorflow/roles/rsync/files/rsyncd.example.conf
View File

@@ -1,16 +0,0 @@
motd file = /etc/rsyncd.motd
log file = /var/log/rsyncd.log
pid file = /var/run/rsyncd.pid
lock file = /var/run/rsync.lock
[jupyter_data]
path = /nfs/jupyter/data
comment = Jupyter data files
uid = nobody
gid = nobody
read only = yes
list = yes
auth users = @rsync:ro
secrets file = /etc/rsyncd.secrets
hosts allow = 192.168.1.0/24
hosts deny = 0.0.0.0/0

5
sample-run/tensorflow/roles/rsync/handlers/main.yml
View File

@@ -1,5 +0,0 @@
---
- name: restart the rsync service
systemd:
name: "{{ rsync.service_name }}"
state: restarted

0
sample-run/tensorflow/roles/rsync/meta/.gitkeep
View File

26
sample-run/tensorflow/roles/rsync/tasks/main.yml
View File

@@ -1,26 +0,0 @@
---
# Configure the rsync daemon on the master
- name: copy rsync.conf up to the server
copy:
src: "{{ rsync.config_file.src }}"
dest: "{{ rsync.config_file.dest }}"
notify:
- restart the rsync service
when: inventory_hostname == rsync.master
- name: configure rsync on the server
service:
enabled: yes
name: "{{ rsync.service_name }}"
state: started
when: inventory_hostname == rsync.master
# Synchronize the data deploy across hosts
- name: synchronize the data deploy
delegate_to: "{{ rsync.master }}"
synchronize:
src: "{{ sync.source }}"
dest: "{{ sync.destination }}"
rsync_opts: "{{ rsync.options }}"
use_ssh_args: yes
when: inventory_hostname != rsync.master

0
sample-run/tensorflow/roles/rsync/templates/.gitkeep
View File

10
sample-run/tensorflow/roles/rsync/vars/main.yml
View File

@@ -1,10 +0,0 @@
---
rsync:
config_file:
src: rsyncd.conf
dest: /etc/rsyncd.conf
master: ml1
options:
- "-e ssh"
- "--no-motd"
service_name: rsync

15
sample-run/tensorflow/secrets.example.yml
View File

@@ -1,15 +0,0 @@
################################################################################
# This file contains secrets that should not be checked into VCS.
################################################################################
---
secrets:
# Cachux7I
password_hash: sha1:b9bbcb5e92ad:0358d2ce7c34192afa50fc5e5143ed91d75eda0d
sync:
source: /nfs/data
destination: /nfs
users:
- ansible
volumes:
data: /nfs/data:/data
source: /nfs/src:/tf

15
sample-run/tensorflow/secrets.yml
View File

@@ -1,15 +0,0 @@
################################################################################
# This file contains secrets that should not be checked into VCS.
################################################################################
---
secrets:
# Cachux7I
password_hash: sha1:b9bbcb5e92ad:0358d2ce7c34192afa50fc5e5143ed91d75eda0d
sync:
source: /nfs/data
destination: /nfs
users:
- ansible
volumes:
data: /nfs/data:/data
source: /nfs/src:/tf