stroblmeandClaude Opus 5
1a9753fa9d
A worker reported its labels and nothing about the machine behind them, so the engine could route a node to a GPU box but not tell whether that box had a GPU free. Inventory — cores, GPUs, memory — now arrives with the hello frame, and the run frame carries back what the engine allocated for that call. Which is protocol 2 on both ends. GPUs are never probed: asking a vendor tool would make the one dependency two, so a GPU is what the batch job says it was given or what --gpus says. A worker that reports nothing still attaches and is scheduled by its label alone. Two things a job scheduler needs: --max-idle stops a worker started for one job rather than letting it hold its allocation to the walltime, and a refusal is now fatal instead of a reconnect loop that reads as a hang in a job's log. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01A6HeySA27EkGANZN95QySW
53 lines
1.6 KiB
TOML
53 lines
1.6 KiB
TOML
[project]
|
|
name = "fluksio-worker"
|
|
version = "0.2.0"
|
|
description = "Runs Fluksio nodes on a machine the engine cannot reach"
|
|
readme = "README.md"
|
|
license = "AGPL-3.0-or-later"
|
|
license-files = ["LICENSE"]
|
|
requires-python = ">=3.12"
|
|
authors = [{ name = "Fluksio", email = "stroblme@posteo.de" }]
|
|
keywords = ["automation", "workflow", "distributed", "worker", "gpu"]
|
|
classifiers = [
|
|
"Development Status :: 3 - Alpha",
|
|
"Intended Audience :: Developers",
|
|
"Intended Audience :: Science/Research",
|
|
"Operating System :: MacOS",
|
|
"Operating System :: POSIX :: Linux",
|
|
"Programming Language :: Python :: 3",
|
|
"Programming Language :: Python :: 3.12",
|
|
"Programming Language :: Python :: 3.13",
|
|
"Topic :: Home Automation",
|
|
"Topic :: Scientific/Engineering",
|
|
"Topic :: System :: Distributed Computing",
|
|
]
|
|
dependencies = [
|
|
"websockets>=12",
|
|
]
|
|
|
|
[project.urls]
|
|
Homepage = "https://fluksio.com"
|
|
Documentation = "https://docs.fluksio.com/code/workers/"
|
|
|
|
[project.scripts]
|
|
fluksio-worker = "fluksio_worker.agent:main"
|
|
|
|
[build-system]
|
|
requires = ["hatchling"]
|
|
build-backend = "hatchling.build"
|
|
|
|
[tool.hatch.build.targets.wheel]
|
|
packages = ["fluksio_worker"]
|
|
|
|
[tool.ruff]
|
|
# The engine's config, so both distributions are linted the same way.
|
|
extend = "../backend/pyproject.toml"
|
|
|
|
[tool.ruff.lint.per-file-ignores]
|
|
# This one takes its own directory off sys.path before the rest of its imports
|
|
# run, which is the whole point of doing it there.
|
|
"fluksio_worker/worker_main.py" = ["E402"]
|
|
# Copied onto another machine it has no logger configured before it tells you
|
|
# the one dependency it is missing.
|
|
"fluksio_worker/agent.py" = ["T201"]
|