SeaweedFS

SeaweedFS is a scalable distributed file system optimized for exabyte small files, supports FUSE, S3 API, Hadoop, k8s, replication, Cloud Drive, S3 gateway.

[SeaweedFS @SeaweedFS]

@venkat_systems test with SeaweedFS?

[SeaweedFS @SeaweedFS]

@almoggavra cold start time, vacuum time, flush time would be good metrics to see the storage cost.

[SeaweedFS @SeaweedFS]

SeaweedFS: 4.29 supports cluster-wide atomic S3 conditional writes (If-Match / If-None-Match / ...) with O(1) network roundtrip, without a costly distributed lock.

https://t.co/AkD2SP01fl

[SeaweedFS @SeaweedFS]

@StringKe @akazwz_ @marchliu Good point! The logs are unnecessarily verbose. Will fix it.

[SeaweedFS @SeaweedFS]

@StringKe @akazwz_ @marchliu Did you use "weed mini"?

Start a ready-to-use S3 object store with credentials and a pre-created bucket in one command:

AWS_ACCESS_KEY_ID=admin \
AWS_SECRET_ACCESS_KEY=secret \
S3_BUCKET=my-bucket \
weed mini -dir=/data

[SeaweedFS @SeaweedFS]

@HoytEmerson SeaweedFS supports table buckets and iceberg catalog. So this can be a datalake on prem.

[SeaweedFS @SeaweedFS]

@confusedqubit Interesting!

[Ænix @aenix_io]

💾 S3 Billing in Cozystack — Metering Object Storage

We've added S3 support to the our proprietary billing module (it could be installed over Cozystack). The billing API now recognizes S3 buckets as billable workloads and returns three consumption metrics per bucket:

• S3StorageGiBHours — logical volume × time (how much the tenant actually stored)
• S3PhysicalStorageGiBHours — physical volume × time (including replication factor)
• LifetimeHours — how long the bucket existed

⚙️ How It Works
The implementation reuses the same byte-seconds → GiB-hours formula already used for PersistentVolumes. Tested end-to-end on a dev cluster with SeaweedFS + CozyStack billing pipeline.

A UsageReport for a tenant with a bucket (10 MB, replication factor 2) looks like this:

YAML
𝚊𝚙𝚒𝚅𝚎𝚛𝚜𝚒𝚘𝚗: 𝚋𝚒𝚕𝚕𝚒𝚗𝚐.𝚊𝚎𝚗𝚒𝚡.𝚒𝚘/𝚟𝟷𝚊𝚕𝚙𝚑𝚊𝟷
𝚔𝚒𝚗𝚍: 𝚄𝚜𝚊𝚐𝚎𝚁𝚎𝚙𝚘𝚛𝚝
𝚚𝚞𝚎𝚛𝚢:
  𝚝𝚎𝚗𝚊𝚗𝚝: 𝚝𝚎𝚗𝚊𝚗𝚝–𝚝𝚎𝚜𝚝𝚒𝚗𝚐
  𝚜𝚝𝚊𝚛𝚝𝚃𝚒𝚖𝚎𝚜𝚝𝚊𝚖𝚙: "𝟸𝟶𝟸𝟼–𝟶𝟺–𝟷𝟺𝚃𝟷𝟶:𝟶𝟺:𝟷𝟷𝚉"
  𝚎𝚗𝚍𝚃𝚒𝚖𝚎𝚜𝚝𝚊𝚖𝚙: "𝟸𝟶𝟸𝟼–𝟶𝟺–𝟷𝟺𝚃𝟷𝟷:𝟶𝟺:𝟷𝟷𝚉"
𝚛𝚎𝚙𝚘𝚛𝚝:
  𝚌𝚘𝚗𝚜𝚞𝚖𝚎𝚛𝚜:
  – 𝚠𝚘𝚛𝚔𝚕𝚘𝚊𝚍: 𝚋𝚞𝚌𝚔𝚎𝚝–𝚋𝚞𝚌𝚔𝚎𝚝–𝚝𝚎𝚜𝚝–𝚋𝚒𝚕𝚕𝚒𝚗𝚐
    𝚝𝚎𝚗𝚊𝚗𝚝: 𝚝𝚎𝚗𝚊𝚗𝚝–𝚝𝚎𝚜𝚝𝚒𝚗𝚐
    𝚔𝚒𝚗𝚍: 𝚋𝚞𝚌𝚔𝚎𝚝
    𝚝𝚢𝚙𝚎: 𝚜𝟹
    𝚌𝚘𝚗𝚜𝚞𝚖𝚙𝚝𝚒𝚘𝚗𝚜:
    – 𝚛𝚎𝚜𝚘𝚞𝚛𝚌𝚎𝚃𝚢𝚙𝚎: 𝚂𝟹𝚂𝚝𝚘𝚛𝚊𝚐𝚎𝙶𝚒𝙱𝙷𝚘𝚞𝚛𝚜
      𝚚𝚞𝚊𝚗𝚝𝚒𝚝𝚢: 𝟶.𝟶𝟶𝟿𝟼
    – 𝚛𝚎𝚜𝚘𝚞𝚛𝚌𝚎𝚃𝚢𝚙𝚎: 𝚂𝟹𝙿𝚑𝚢𝚜𝚒𝚌𝚊𝚕𝚂𝚝𝚘𝚛𝚊𝚐𝚎𝙶𝚒𝙱𝙷𝚘𝚞𝚛𝚜
      𝚚𝚞𝚊𝚗𝚝𝚒𝚝𝚢: 𝟶.𝟶𝟷𝟿𝟸
    – 𝚛𝚎𝚜𝚘𝚞𝚛𝚌𝚎𝚃𝚢𝚙𝚎: 𝙻𝚒𝚏𝚎𝚝𝚒𝚖𝚎𝙷𝚘𝚞𝚛𝚜
      𝚚𝚞𝚊𝚗𝚝𝚒𝚝𝚢: 𝟶.𝟿𝟾𝟹

✨ What This Gives ISPs
Cloud providers running on Cozystack or Ænix Platform can now bill for object storage the same way as block storage and compute — per-resource, per-minute, through a single UsageReport API.

Links
🏢 Aenix — https://t.co/CC1oggm1MQ
🔗 GitHub — https://t.co/RVErIGzLJs
🌐 Website — https://t.co/tGK5GSBxnq
📖 Getting Started — https://t.co/R3Ryjgppnr
💬 Telegram — https://t.co/WtYejCviOy
🟦 Slack — https://t.co/aQoHpyJx5X

[SeaweedFS @SeaweedFS]

P2P sharing for SeaweedFS POSIX-compliant FUSE mount. High throughput download without overloading the server.

https://t.co/qqMy7kUVwG

[SeaweedFS @SeaweedFS]

@derekdfulton No. But you can sync the SeaweedFS s3 bucket content to Wasabi bucket.

[SeaweedFS @SeaweedFS]

100% POSIX tests passed!

SeaweedFS FUSE mount passed all pjdfstest tests and removed the last known failure.

https://t.co/Qko3RLBIKU

[Arkfile @Arkfile_OSP]

Refactor complete. Swapped out MinIO for SeaweedFS. Added an encrypted blob export and local offline decrypt option too via the arkfile-client Go CLI util.

https://t.co/D5rssIHHvM

Much of this would not be possible as a 1 man team w/o @PPQdotAI / @cline / @AnthropicAI Opus 4.6

[SeaweedFS @SeaweedFS]

@derekdfulton Welcome to create github issues for any performance problems. For optimization, "weed mount" has direct access to storage rather than limited by S3 APIs. Recently it added per-mount POSIX locks and writeback caching.

[SeaweedFS @SeaweedFS]

Nice! SeaweedFS already does this! Use FUSE mount to access the files in s3 buckets.

[Darryl Ruggles @RDarrylR]

A really big S3 announcement - #S3 Files!!

If you've ever had to copy data out of S3 just so a file-based tool could use it, you know the frustration. S3 Files lets you mount S3 buckets as file systems directly, no data duplication, no sync pipelines, no workarounds. Your data stays in S3 while apps access it natively.

This looks really useful and a nice improvement over previous approaches like S3 Mount Point. AI agents, ML pipelines, and traditional file-based applications can all read and write to S3 as a file system without code changes. #aws #S3Files

https://t.co/aVZYzcpsDT

[Darryl Ruggles @RDarrylR]

A really big S3 announcement - #S3 Files!!

If you've ever had to copy data out of S3 just so a file-based tool could use it, you know the frustration. S3 Files lets you mount S3 buckets as file systems directly, no data duplication, no sync pipelines, no workarounds. Your data stays in S3 while apps access it natively.

This looks really useful and a nice improvement over previous approaches like S3 Mount Point. AI agents, ML pipelines, and traditional file-based applications can all read and write to S3 as a file system without code changes. #aws #S3Files

https://t.co/aVZYzcpsDT

[SeaweedFS @SeaweedFS]

SeaweedFS on NVidia doc:

https://t.co/8bo1b0gBQG

[SeaweedFS @SeaweedFS]

@RisingWaveLabs Nice! Does it cache S3 listing requests?

[SeaweedFS @SeaweedFS]

@Sirupsen Cloud object stores all hosted mixed data together to increase storage efficiency. Latency is not a priority. Why not use your own object store?

[Siam Reza @MrLabbrow]

That left Garage and SeaweedFS. After trying to set up both on my low-end Oracle VPS, SeaweedFS won me over!

It’s incredibly lightweight, simple to get started with, and fits perfectly on my small AMD server.

(5/6) #SelfHosted #Developer