hpc / hpc/mpifileutils

integrate MPIFileUtils with S3 backends

Open
#675 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
C
Stars
200
Forks
85
Avg merge
3d 21h
Merged PRs (30d)
2

Description

This is firmly in the "wishlist" camp so far, mainly just seeing if there is interest behind this.

It would be useful for MPIFileUtils commands to be able to read/write/list from/to S3 buckets for migration between archive and online storage. This would allow scalable parallel data movement for large datasets.

Some restrictions would be needed on how the S3 backend was accessed, for example only migrating a single object/file with a single task, or chunking large files into multi-part uploads.

The POSIX attribute save/restore should follow existing conventions used by AWS and others on how they are stored in tags on the objects, so that import/export can preserve the file attributes across a round-trip.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

The issue names MPIFileUtils commands but no files or tests; start by locating their existing storage and POSIX attribute handling, then review AWS S3 object-tag conventions. Done would require an agreed design and implementation for S3 read, write, list, parallel migration, multipart uploads, and attribute round-tripping.

Written by the indexing model from the issue text.

Assessment

Tech stack
aws, c
Domain
cloud, distributed-systems
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.