Judoscale incident

Upscaling not working

Resolved after 1 hour 52 minutes, affecting Render autoscaling and Fly.io autoscaling and 1 more, on August 7, 2025.

resolved Aug 07, 2025, 01:52 PM UTC

Upscaling is working as expected. We'll be writing up a full report of what happened and what we're doing about it, but here's a summary: At 2025-08-07 00:25:00 UTC we ingested some unexpected queue metrics for a far-future date. It looks like a customer triggered this from their laptop. Our upscale logic looks at the most recent metrics bucket as a boundary, so this data broke our upscaling. We have many automated checks in place, but none caught this, and unfortunately it happened overnight for us, so we weren't aware of the issue until this morning around 2025-08-07 12:00:00 UTC. We identified the bad data and deleted it at 2025-08-07 12:36:00 UTC. Upscaling immediately started working as expected. We're implementing a permanent fix now, as well as automated checks so that we're alerted immediately in the future. Check our blog later today for a more thorough write-up.

Started
Aug 07, 2025, 12:00 PM UTC
Resolved
Aug 07, 2025, 01:52 PM UTC
Duration
1h 52m
Detected by Pingoru
Aug 07, 2025, 12:00 PM UTC

Affected components

Render autoscalingFly.io autoscalingHeroku autoscalingAmazon ECS autoscalingFly.io autoscalingRailway autoscaling

Update timeline

  1. investigating Aug 07, 2025, 12:00 PM UTC

    We've received some reports of upscaling not triggering, and are investigating.

  2. resolved Aug 07, 2025, 01:52 PM UTC

    Upscaling is working as expected. We'll be writing up a full report of what happened and what we're doing about it, but here's a summary: At 2025-08-07 00:25:00 UTC we ingested some unexpected queue metrics for a far-future date. It looks like a customer triggered this from their laptop. Our upscale logic looks at the most recent metrics bucket as a boundary, so this data broke our upscaling. We have many automated checks in place, but none caught this, and unfortunately it happened overnight for us, so we weren't aware of the issue until this morning around 2025-08-07 12:00:00 UTC. We identified the bad data and deleted it at 2025-08-07 12:36:00 UTC. Upscaling immediately started working as expected. We're implementing a permanent fix now, as well as automated checks so that we're alerted immediately in the future. Check our blog later today for a more thorough write-up.

Your product runs on more than Judoscale

Add the vendors you depend on and get one message when any of them reports trouble. Free for 3 vendors, no card.

Add your stack →