clearml-agent/clearml_agent/backend_api/config/default/agent.conf

388 lines
19 KiB
Plaintext

{
# unique name of this worker, if None, created based on hostname:process_id
# Override with os environment: CLEARML_WORKER_ID
# worker_id: "clearml-agent-machine1:gpu0"
worker_id: ""
# worker name, replaces the hostname when creating a unique name for this worker
# Override with os environment: CLEARML_WORKER_NAME
# worker_name: "clearml-agent-machine1"
worker_name: ""
# Set GIT user/pass credentials (if user/pass are set, GIT protocol will be set to https)
# leave blank for GIT SSH credentials (set force_git_ssh_protocol=true to force SSH protocol)
# **Notice**: GitHub personal token is equivalent to password, you can put it directly into `git_pass`
# To learn how to generate git token GitHub/Bitbucket/GitLab:
# https://docs.github.com/en/authentication/keeping-your-account-and-data-secure/creating-a-personal-access-token
# https://support.atlassian.com/bitbucket-cloud/docs/app-passwords/
# https://docs.gitlab.com/ee/user/profile/personal_access_tokens.html
# git_user: ""
# git_pass: ""
# Limit credentials to a single domain, for example: github.com,
# all other domains will use public access (no user/pass). Default: always send user/pass for any VCS domain
# git_host: ""
# Force GIT protocol to use SSH regardless of the git url (Assumes GIT user/pass are blank)
force_git_ssh_protocol: false
# Force a specific SSH port when converting http to ssh links (the domain is kept the same)
# force_git_ssh_port: 0
# Force a specific SSH username when converting http to ssh links (the default username is 'git')
# force_git_ssh_user: git
# Set the python version to use when creating the virtual environment and launching the experiment
# Example values: "/usr/bin/python3" or "/usr/local/bin/python3.6"
# The default is the python executing the clearml_agent
python_binary: ""
# ignore any requested python version (Default: False, if a Task was using a
# specific python version and the system supports multiple python the agent will use the requested python version)
# ignore_requested_python_version: true
# Force the root folder of the git repository (instead of the working directory) into the PYHTONPATH
# default false, only the working directory will be added to the PYHTONPATH
# force_git_root_python_path: false
# if set, use GIT_ASKPASS to pass user/pass when cloning / fetch repositories
# it solves passing user/token to git submodules.
# this is a safer way to ensure multiple users using the same repository will
# not accidentally leak credentials
# Only supported on Linux systems, it will be the default in future releases
# enable_git_ask_pass: false
# in docker mode, if container's entrypoint automatically activated a virtual environment
# use the activated virtual environment and install everything there
# set to False to disable, and always create a new venv inheriting from the system_site_packages
# docker_use_activated_venv: true
# select python package manager:
# currently supported: pip, conda and poetry
# if "pip" or "conda" are used, the agent installs the required packages
# based on the "installed packages" section of the Task. If the "installed packages" is empty,
# it will revert to using `requirements.txt` from the repository's root directory.
# If Poetry is selected and the root repository contains `poetry.lock` or `pyproject.toml`,
# the "installed packages" section is ignored, and poetry is used.
# If Poetry is selected and no lock file is found, it reverts to "pip" package manager behaviour.
package_manager: {
# supported options: pip, conda, poetry
type: pip,
# specify pip version to use (examples "<20.2", "==19.3.1", "", empty string will install the latest version)
pip_version: ["<20.2 ; python_version < '3.10'", "<22.3 ; python_version >= '3.10'"],
# specify poetry version to use (examples "<2", "==1.1.1", "", empty string will install the latest version)
# poetry_version: "<2",
# virtual environment inherits packages from system
system_site_packages: false,
# install with --upgrade
force_upgrade: false,
# additional artifact repositories to use when installing python packages
# extra_index_url: ["https://allegroai.jfrog.io/clearml/api/pypi/public/simple"]
# additional conda channels to use when installing with conda package manager
conda_channels: ["pytorch", "conda-forge", "defaults", ]
# If set to true, Task's "installed packages" are ignored,
# and the repository's "requirements.txt" is used instead
# force_repo_requirements_txt: false
# set the priority packages to be installed before the rest of the required packages
# priority_packages: ["cython", "numpy", "setuptools", ]
# set the optional priority packages to be installed before the rest of the required packages,
# In case a package installation fails, the package will be ignored,
# and the virtual environment process will continue
priority_optional_packages: ["pygobject", ]
# set the post packages to be installed after all the rest of the required packages
# post_packages: ["horovod", ]
# set the optional post packages to be installed after all the rest of the required packages,
# In case a package installation fails, the package will be ignored,
# and the virtual environment process will continue
# post_optional_packages: []
# set to True to support torch nightly build installation,
# notice: torch nightly builds are ephemeral and are deleted from time to time
torch_nightly: false,
# if set to true, the agent will look for the "poetry.lock" file
# in the passed current working directory instead of the repository's root directory.
poetry_files_from_repo_working_dir: false
},
# target folder for virtual environments builds, created when executing experiment
venvs_dir = ~/.clearml/venvs-builds
# cached virtual environment folder
venvs_cache: {
# maximum number of cached venvs
max_entries: 10
# minimum required free space to allow for cache entry, disable by passing 0 or negative value
free_space_threshold_gb: 2.0
# unmark to enable virtual environment caching
path: ~/.clearml/venvs-cache
},
# cached git clone folder
vcs_cache: {
enabled: true,
path: ~/.clearml/vcs-cache
},
# use venv-update in order to accelerate python virtual environment building
# Still in beta, turned off by default
venv_update: {
enabled: false,
},
# cached folder for specific python package download (used for pytorch package caching)
pip_download_cache {
enabled: true,
path: ~/.clearml/pip-download-cache
},
translate_ssh: true,
# set "disable_ssh_mount: true" to disable the automatic mount of ~/.ssh folder into the docker containers
# default is false, automatically mounts ~/.ssh
# Must be set to True if using "clearml-session" with this agent!
# disable_ssh_mount: false
# reload configuration file every daemon execution
reload_config: false,
# pip cache folder mapped into docker, used for python package caching
docker_pip_cache = ~/.clearml/pip-cache
# apt cache folder mapped into docker, used for ubuntu package caching
docker_apt_cache = ~/.clearml/apt-cache
# optional arguments to pass to docker image
# these are local for this agent and will not be updated in the experiment's docker_cmd section
# extra_docker_arguments: ["--ipc=host", ]
# optional shell script to run in docker when started before the experiment is started
# extra_docker_shell_script: ["apt-get install -y bindfs", ]
# Install the required packages for opencv libraries (libsm6 libxext6 libxrender-dev libglib2.0-0),
# for backwards compatibility reasons, true as default,
# change to false to skip installation and decrease docker spin up time
# docker_install_opencv_libs: true
# optional uptime configuration, make sure to use only one of 'uptime/downtime' and not both.
# If uptime is specified, agent will actively poll (and execute) tasks in the time-spans defined here.
# Outside of the specified time-spans, the agent will be idle.
# Defined using a list of items of the format: "<hours> <days>".
# hours - use values 0-23, single values would count as start hour and end at midnight.
# days - use days in abbreviated format (SUN-SAT)
# use '-' for ranges and ',' to separate singular values.
# for example, to enable the workers every Sunday and Tuesday between 17:00-20:00 set uptime to:
# uptime: ["17-20 SUN,TUE"]
# optional downtime configuration, can be used only when uptime is not used.
# If downtime is specified, agent will be idle in the time-spans defined here.
# Outside of the specified time-spans, the agent will actively poll (and execute) tasks.
# Use the same format as described above for uptime
# downtime: []
# set to true in order to force "docker pull" before running an experiment using a docker image.
# This makes sure the docker image is updated.
docker_force_pull: false
default_docker: {
# default docker image to use when running in docker mode
image: "nvidia/cuda:10.2-cudnn7-runtime-ubuntu18.04"
# optional arguments to pass to docker image
# arguments: ["--ipc=host", ]
}
# set the OS environments based on the Task's Environment section before launching the Task process.
enable_task_env: false
# set the initial bash script to execute at the startup of any docker.
# all lines will be executed regardless of their exit code.
# {python_single_digit} is translated to 'python3' or 'python2' according to requested python version
# docker_init_bash_script = [
# "echo 'Binary::apt::APT::Keep-Downloaded-Packages \"true\";' > /etc/apt/apt.conf.d/docker-clean",
# "chown -R root /root/.cache/pip",
# "apt-get update",
# "apt-get install -y git libsm6 libxext6 libxrender-dev libglib2.0-0",
# "(which {python_single_digit} && {python_single_digit} -m pip --version) || apt-get install -y {python_single_digit}-pip",
# ]
# set the preprocessing bash script to execute at the startup of any docker.
# all lines will be executed regardless of their exit code.
# docker_preprocess_bash_script = [
# "echo \"starting docker\"",
#]
# If False replace \r with \n and display full console output
# default is True, report a single \r line in a sequence of consecutive lines, per 5 seconds.
# suppress_carriage_return: true
# CUDA versions used for Conda setup & solving PyTorch wheel packages
# Should be detected automatically. Override with os environment CUDA_VERSION / CUDNN_VERSION
# cuda_version: 10.1
# cudnn_version: 7.6
# Hide docker environment variables containing secrets when printing out the docker command by replacing their
# values with "********". Turning this feature on will hide the following environment variables values:
# CLEARML_API_SECRET_KEY, CLEARML_AGENT_GIT_PASS, AWS_SECRET_ACCESS_KEY, AZURE_STORAGE_KEY
# To include more environment variables, add their keys to the "extra_keys" list. E.g. to make sure the value of
# your custom environment variable named MY_SPECIAL_PASSWORD will not show in the logs when included in the
# docker command, set:
# extra_keys: ["MY_SPECIAL_PASSWORD"]
hide_docker_command_env_vars {
enabled: true
extra_keys: []
parse_embedded_urls: true
}
# Maximum execution time (in seconds) for Task's abort function call
abort_callback_max_timeout: 1800
# allow to set internal mount points inside the docker,
# especially useful for non-root docker container images.
docker_internal_mounts {
sdk_cache: "/clearml_agent_cache"
apt_cache: "/var/cache/apt/archives"
ssh_folder: "~/.ssh"
ssh_ro_folder: "/.ssh"
pip_cache: "/root/.cache/pip"
poetry_cache: "/root/.cache/pypoetry"
vcs_cache: "/root/.clearml/vcs-cache"
venv_build: "~/.clearml/venvs-builds"
pip_download: "/root/.clearml/pip-download-cache"
}
# Name docker containers created by the daemon using the following string format (supported from Docker 0.6.5)
# Allowed variables are task_id, worker_id and rand_string (random lower-case letters string, up to 32 characters)
# Note: resulting name must start with an alphanumeric character and
# continue with alphanumeric characters, underscores (_), dots (.) and/or dashes (-)
# docker_container_name_format: "clearml-id-{task_id}-{rand_string:.8}"
# Apply top-level environment section from configuration into os.environ
apply_environment: true
# Top-level environment section is in the form of:
# environment {
# key: value
# ...
# }
# and is applied to the OS environment as `key=value` for each key/value pair
# Apply top-level files section from configuration into local file system
apply_files: true
# Top-level files section allows auto-generating files at designated paths with a predefined contents
# and target format. Options include:
# contents: the target file's content, typically a string (or any base type int/float/list/dict etc.)
# format: a custom format for the contents. Currently supported value is `base64` to automatically decode a
# base64-encoded contents string, otherwise ignored
# path: the target file's path, may include ~ and inplace env vars
# target_format: format used to encode contents before writing into the target file. Supported values are json,
# yaml, yml and bytes (in which case the file will be written in binary mode). Default is text mode.
# overwrite: overwrite the target file in case it exists. Default is true.
#
# Example:
# files {
# myfile1 {
# contents: "The quick brown fox jumped over the lazy dog"
# path: "/tmp/fox.txt"
# }
# myjsonfile {
# contents: {
# some {
# nested {
# value: [1, 2, 3, 4]
# }
# }
# }
# path: "/tmp/test.json"
# target_format: json
# }
# }
# Specifies a custom environment setup script to be executed instead of installing a virtual environment.
# If provided, this script is executed following Git cloning. Script command may include environment variable and
# will be expanded before execution (e.g. "$CLEARML_GIT_ROOT/script.sh").
# The script can also be specified using the CLEARML_AGENT_CUSTOM_BUILD_SCRIPT environment variable.
#
# When running the script, the following environment variables will be set:
# - CLEARML_CUSTOM_BUILD_TASK_CONFIG_JSON: specifies a path to a temporary files containing the complete task
# contents in JSON format
# - CLEARML_TASK_SCRIPT_ENTRY: task entrypoint script as defined in the task's script section
# - CLEARML_TASK_WORKING_DIR: task working directory as defined in the task's script section
# - CLEARML_VENV_PATH: path to the agent's default virtual environment path (as defined in the configuration)
# - CLEARML_GIT_ROOT: path to the cloned Git repository
# - CLEARML_CUSTOM_BUILD_OUTPUT: a path to a non-existing file that may be created by the script. If created,
# this file must be in the following JSON format:
# ```json
# {
# "binary": "/absolute/path/to/python-executable",
# "entry_point": "/absolute/path/to/task-entrypoint-script",
# "working_dir": "/absolute/path/to/task-working/dir"
# }
# ```
# If provided, the agent will use these instead of the predefined task script section to execute the task and will
# skip virtual environment creation.
#
# In case the custom script returns with a non-zero exit code, the agent will fail with the same exit code.
# In case the custom script is specified but does not exist, or if the custom script does not write valid content
# into the file specified in CLEARML_CUSTOM_BUILD_OUTPUT, the agent will emit a warning and continue with the
# standard flow.
custom_build_script: ""
# Crash on exception: by default when encountering an exception while running a task,
# the agent will catch the exception, log it and continue running.
# Set this to `true` to propagate exceptions and crash the agent.
# crash_on_exception: true
# Disable task docker override. If true, the agent will use the default docker image and ignore any docker image
# and arguments specified in the task's container section (setup shell script from the task container section will
# be used in any case, if specified).
disable_task_docker_override: false
# Choose the default docker based on the Task properties,
# Examples: 'script.requirements', 'script.binary', 'script.repository', 'script.branch', 'project'
# Notice: Matching is done via regular expression, for example "^searchme$" will match exactly "searchme$" string
#
# "default_docker": {
# "image": "nvidia/cuda:10.2-cudnn7-runtime-ubuntu18.04",
# # optional arguments to pass to docker image
# # arguments: ["--ipc=host", ]
# "match_rules": [
# {
# "image": "sample_container:tag",
# "arguments": "-e VALUE=1 --ipc=host",
# "match": {
# "script": {
# "requirements": {
# "pip": {
# "tensorflow": "~=1.6"
# }
# },
# "repository": "",
# "branch": "master"
# },
# "project": "example"
# }
# },
# {
# "image": "better_container:tag",
# "arguments": "",
# "match": {
# "container": "replace_me_please"
# }
# },
# {
# "image": "another_container:tag",
# "arguments": "",
# "match": {
# "project": "^examples", # anything that starts with "examples", e.g. "examples", "examples/sub_project"
# }
# }
# ]
# },
#
}