It seems likely that Phoenix does not natively support separating analytics (e.g., `px.Client().get_spans_dataframe()`) and tracing workloads onto different nodes out of the box. However, you can mitigate performance issues by running analytics queries on a replica or a separate read-only database, or by exporting traces for offline analysis, rather than querying large datasets directly from the production node. This approach is not explicitly documented, but users have reported UI and API slowdowns with large trace volumes and have addressed them by optimizing database usage and offloading heavy queries elsewhere. Upgrading Phoenix to the latest version may also help, as recent releases include performance improvements for large trace sets and lazy loading in the UI (<https://github.com/Arize-ai/phoenix/issues/6201|GitHub Issue #6201>, <https://arize-ai.slack.com/archives/C04R3GXC8HK/p1724775125.127529|Slack discussion>).
For exporting traces, you can use `px.Client().get_trace_dataset().save(directory=...)` to persist data for offline analysis, reducing load on your main Phoenix node (<https://arize.com/docs/phoenix/tracing/how-to-tracing/importing-and-exporting-traces/extract-data-from-spans|Export Data & Query Spans>). Running analytics on a separate environment or database replica is a common pattern in observability systems, though not directly described in Phoenix docs. Would you like more detail on how to set up such a workflow?
Sources:
- <https://github.com/Arize-ai/phoenix/issues/6201|GitHub Issue #6201>
- <https://arize-ai.slack.com/archives/C04R3GXC8HK/p1724775125.127529|Slack discussion>
- <https://arize.com/docs/phoenix/tracing/how-to-tracing/importing-and-exporting-traces/extract-data-from-spans|Export Data & Query Spans>
