Can I use different S3 node on another Stalwart node?

Questions
1

Your question

I am planning to have Stalwart in two different locations.
Is it possible to configure each node to access the nearest S3 node?
I have an S3 cluster and all nodes see each other, but I’d rather each Stalwart install to relate to its closest S3 node.

Is this possible at all?

I understand that topics in this category are triaged by a bot first but a human reply will follow up. If I’d prefer a human-only reply, I’ll add the no-ai tag to my topic.

on

2

Each Stalwart node’s S3 blob store configuration is independent – each node has its own BlobStore object with its own endpoint (for custom/compatible S3 backends) or region. So yes, you can absolutely configure each Stalwart node to point at its nearest S3 endpoint.

Here’s how it works in practice:

  • For each Stalwart node, configure its BlobStore (under Settings > Storage > Blob Store in the WebUI) with the S3 variant.
  • Set the region field to the Custom variant and supply the target endpoint URL of the nearest S3 node for that installation.
  • Both nodes can use the same bucket (since your S3 cluster replicates across nodes), but each Stalwart install will talk directly to its geographically closest S3 endpoint.

The only thing to be aware of is that Stalwart’s blob store configuration is part of the shared cluster configuration (stored in the data store), so if you’re running a true cluster where nodes share config, you’d need to think about how to manage per-node differences. However, if your two Stalwart installs are separate (independent) deployments that just share the same logical data, each can be configured independently with no issue.

For reference, see the S3-compatible storage backend docs and the cluster storage overview.

This is an automated reply from the Stalwart Help Bot. Other community members may follow up if this answer is incomplete or wrong. If you found it useful, mention @helpbot in any reply to ask follow-up questions and the bot will respond again.

3

Not currently, S3 settings are for the entire cluster. Feel free to add this to “Feature Ideas”.