> For the complete documentation index, see [llms.txt](https://docs.verge.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.verge.io/knowledge-base/troubleshooting/nvme-aer-reset-loop.md).

# NVMe Controllers Resetting Due to AER

How to interpret NVMe controller AER reset messages and diagnose hardware issues when one or multiple controllers reset repeatedly during installation or operation.

## Overview

{% hint style="info" %}
**Key Points**

* When one NVMe drive resets repeatedly, the problem is in that drive or its PCIe link.
* When several NVMe drives reset together in a short window, the problem is in a shared path component.
* Stabilize the shared path or PCIe link before you retry installation.
  {% endhint %}

The console or `dmesg` shows NVMe controllers resetting repeatedly with messages like:

```
nvme nvme0: resetting controller due to AER
nvme nvme0: 80/0/0 default/read/poll queues
```

This message indicates that the PCIe link reported an error and the kernel reset the NVMe controller to recover. AER stands for Advanced Error Reporting, a PCIe feature that reports hardware-level errors to the operating system.

## Prerequisites

* Physical or remote management access to the host.

## Understanding AER Reset Patterns

The pattern of resets shows whether the problem is in one NVMe drive or in a shared path that several NVMe drives use.

### Single Controller Resetting

When one NVMe controller resets repeatedly (for example, `nvme0` resets but `nvme1` through `nvme7` remain stable):

* The problem is in that NVMe drive or its PCIe link.
* Check the drive, its PCIe slot, and the PCIe link between the drive and the host.

### Multiple Controllers Resetting Together

When several NVMe controllers (for example, `nvme0` through `nvme7`) reset together within a short window:

* This is a shared-path symptom.
* The problem is not a single failing drive.
* Check the PCIe switch, backplane, power delivery, firmware, and root complex that all the affected drives share.

{% hint style="warning" %}
**Installation and vSAN Boot Failures**

VergeOS installation and vSAN boot can fail when NVMe controllers reset repeatedly. Stabilize the shared path or PCIe link before you retry the installation.
{% endhint %}

## What to Check

### For a Single Resetting Controller

1. Check the NVMe drive.
2. Check its PCIe slot.
3. Check the PCIe link between the drive and the host.

### For Multiple Controllers Resetting Together

1. Check the PCIe switch.
2. Check the backplane.
3. Check power delivery.
4. Check firmware.
5. Check the root complex.
6. Contact your hardware vendor to diagnose the shared path.

## Additional Resources

* [Node Sizing](https://docs.verge.io/plan-and-deploy/implementation-guide/sizing.md): Hardware requirements for VergeOS, including NVMe and storage controller recommendations.
* [Installation Guide](https://docs.verge.io/plan-and-deploy/implementation-guide/installation-guide.md): Complete installation procedure for VergeOS.
* [Pre-installation Checklist](https://docs.verge.io/plan-and-deploy/implementation-guide/pre-installation.md): Hardware and network verification steps before installation.

{% hint style="info" %}
**Need Help?**

If the PCIe link or shared path remains unstable after checking hardware connections and firmware, contact VergeOS support for assistance.
{% endhint %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.verge.io/knowledge-base/troubleshooting/nvme-aer-reset-loop.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
