https://github.com/donkomura/fsspec-chfs

fsspec implementations for CHFS

https://github.com/donkomura/fsspec-chfs

Science Score: 13.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (7.2%) to scientific vocabulary

Keywords

dask fsspec high-performance-computing python
Last synced: 6 months ago · JSON representation

Repository

fsspec implementations for CHFS

Basic Info
  • Host: GitHub
  • Owner: donkomura
  • License: mit
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 19.5 KB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Topics
dask fsspec high-performance-computing python
Created over 3 years ago · Last pushed over 3 years ago
Metadata Files
Readme License

README.md

fsspec-chfs

fsspec-chfs is a file system interface to CHFS. CHFS is a parallel consistent hashing file system created instantly using node-local storages such as persistent memory and NVMe SSD for high performance computing. This repository includes the integration for Dask.

Requirements

Getting Started

Installation

$ pip install fsspec-chfs

Create file system

You can create CHFS by chfsctl and set CHFS_SERVER environmental variable.

$ eval `chfsctl start` $ chlist # show started servers

How to use fsspec-chfs

```python import fsspec

fs = fsspec.filesystem('chfs')

with fs.open('/hello') as f: f.write(b'world') ```

Use in Dask

fsspec-chfs provides CHFSClientDaemon plugin for Dask worker, and it optimizes CHFS initialization/termination in Dask.

python client = Client(LocalCluster()) plugin = CHFSClientDaemon() client.register_worker_plugin(plugin) def func(path, data): fs = fsspec.filesystem("chfs_stub") fs.pipe(path, data) return 0 future = client.submit(func, "/tmp/foo", b'abcde') counts = future.result()

Developing

VSCode devcontainer

You can use VSCode devcontainer to develop fsspec-chfs. The setup steps are follows:

  1. Install Docker and Remote-Container extension.
  2. Press Ctrl+Shift+P in VSCode.
  3. select Remote-Container: Open the folder in the Container

Testing

$ eval `chfsctl start` # start the server and set CHFS_SERVER $ tox

Owner

  • Name: donko
  • Login: donkomura
  • Kind: user
  • Location: Japan, Tsukuba

GitHub Events

Total
Last Year

Packages

  • Total packages: 1
  • Total downloads:
    • pypi 7 last-month
  • Total dependent packages: 0
  • Total dependent repositories: 0
  • Total versions: 1
  • Total maintainers: 1
pypi.org: fsspec-chfs

Pythonic file system for CHFS

  • Versions: 1
  • Dependent Packages: 0
  • Dependent Repositories: 0
  • Downloads: 7 Last month
Rankings
Dependent packages count: 6.6%
Forks count: 30.5%
Dependent repos count: 30.6%
Average: 32.1%
Stargazers count: 39.1%
Downloads: 53.9%
Maintainers (1)
Last synced: 6 months ago

Dependencies

Dockerfile docker
  • koyamaso/chfs master build
pyproject.toml pypi
setup.py pypi
  • pychfs >=0.0.1