Infrastructure

System Status

Real-time operational status of all platform services.

All Systems Operational
REST API (v3)
Operational
12ms
WebSocket Streaming
Operational
4ms
Query Engine (Presto)
Operational
38ms avg
Data Ingestion Pipeline
Operational
< 1s lag
Object Storage (S3)
Operational
8ms
Authentication & Identity
Operational
6ms
Bulk Export Service
Operational
—
Researcher Dashboard
Operational
22ms

90-Day Uptime

REST API 99.98%
90 days agoToday
Query Engine 99.95%
90 days agoToday
Data Ingestion 99.97%
90 days agoToday

Recent Incidents

Elevated query latency — Presto cluster Resolved
Presto worker nodes experienced elevated GC pause times causing p99 query latency to exceed 500ms. Root cause: JVM heap fragmentation after rolling update.
Apr 3, 2026 14:22 UTC — Resolved. Rolling restart of worker nodes completed. Latency restored to normal levels.
Apr 3, 2026 13:45 UTC — Identified root cause. Initiating rolling restart of Presto worker fleet.
Apr 3, 2026 13:12 UTC — Investigating elevated p99 latency on query engine. API remains available.
CME futures data — delayed ingestion Resolved
CME MDP 3.0 feed experienced a gap due to upstream sequence number reset. Affected datasets: CME Futures Tick, CME Options on Futures.
Mar 28, 2026 16:05 UTC — Resolved. Backfill completed from secondary feed. No data loss confirmed.
Mar 28, 2026 15:30 UTC — Ingestion resumed. Backfill in progress for 15:00–15:28 gap.
Scheduled maintenance — Storage cluster migration Resolved
Planned migration of object storage from us-east-1a to us-east-1c for improved redundancy. Read-only access maintained during migration window.
Mar 15, 2026 06:00 UTC — Migration complete. Full read/write access restored.