SeaweedFS is a scalable distributed file system optimized for exabyte small files, supports FUSE, S3 API, Hadoop, k8s, replication, Cloud Drive, S3 gateway.
SeaweedFS Table Buckets can tier each part independently, automatically based on data temperature.
⚡ Metadata → replicated SSD
📦 Parquet data → HDD
🧊 Cold data → erasure coding / cloud
⚡ Parquet footers → cached back on SSD
Why choose between Iceberg and Lance? You can analyze with Iceberg, and serve with Lance point lookups and vector search, with DuckDB joins them together.
SeaweedFS can host both table formats on the same object store, with built-in catalogs for each.
SeaweedFS + Cloud
⚡ reads at local-disk latency
☁️ writes synced back to Cloud
With SeaweedFS, cloud S3 can remain the durable source of truth while SeaweedFS provides a nearby cache.
WALGit is a great example of this.
SeaweedFS Table Buckets now support Lance 🚀
Use LanceDB directly on SeaweedFS for vector search, with data + indexes stored in S3.
Iceberg for analytics.
Lance for vectors.
One storage layer.