> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tensormesh.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Thresholds & Notifications

> Decide what counts as a problem, and get notified the moment it happens.

Thresholds turn live numbers into severity. Each metric on the Thresholds page has a
*degraded* (warn) and a *critical* band:

| Metric                          | Default warn / critical |
| ------------------------------- | ----------------------- |
| **L1 (host memory) cache fill** | 78% / 90%               |
| **GPU memory fill**             | 96% / 99%               |
| **L2 (secondary) storage fill** | 70% / 85%               |
| **Pod restarts**                | 0 / 2                   |
| **Prefetch failures**           | 1 / 10 per second       |
| **Evictions**                   | 100 / 300 per second    |

**Reset to Defaults** restores these baselines. High GPU *compute* utilization is
intentionally never alarmed — busy GPUs are the goal, not a fault.

Thresholds drive three things: the **severity colors** across the dashboard, the **Issues
list** on Overview (each issue linking to the worst offender), and **notifications**.

***

## Scope

Set global defaults, then override per engine where needed — an engine inherits the global
band for anything it doesn't override, and each level has a one-click revert.

<Note>
  Thresholds, node nicknames, and the notification toggle are saved **in your browser**, not
  on the cluster — the UI never writes to your cluster. They change what the dashboard
  *flags*, not how the engine behaves.
</Note>

***

## Notifications

The dashboard refreshes every **30 seconds**. When an issue turns **critical**, you get a
notification in the dashboard — and optionally on your desktop (enable **System alerts** in
the sidebar). Clicking it takes you straight to the affected node.

Three rules keep notifications worth reading:

* Only **new** problems notify — opening the page doesn't re-announce ones that already
  existed.
* The same problem won't notify again for **5 minutes**, so a metric bouncing in and out of
  critical doesn't spam you.
* Warning-level problems color the dashboard but never notify — only critical ones do.

***

## Related

* [Monitoring Your Fleet](/operator/ui/monitoring-your-fleet)
* [Troubleshooting & FAQ](/operator/ui/troubleshooting)