Nmi Functionality; Troubleshooting Resources - HPE ProLiant ML110 Gen11 User Manual

Table of Contents

To monitor

Single server

Multiple servers

Single or multiple servers

Managing Linux-based high performance compute clusters

Provision, manage, and monitor clusters.

Optimize your applications.

Optimize software library for low latency and high bandwidth, both

on-node and off-node, for point-to-point and collective

communications.

Troubleshooting

Subtopics

NMI functionality

NMI functionality

An NMI crash dump enables administrators to create crash dump files when a system is not responding to traditional debugging methods.

An analysis of the crash dump log is an essential part of diagnosing reliability problems, such as hanging operating systems, device drivers,

and applications. Many crashes freeze a system, and the only available action for administrators is to cycle the system power. Resetting the

system erases any information that could support problem analysis, but the NMI feature preserves that information by performing a

memory dump before a hard reset.

To force the OS to initiate the NMI handler and generate a crash dump log, the administrator can use the iLO Generate NMI feature.

Troubleshooting resources

See

HPE iLO

https://www.hpe.com/support/ilo6

HPE OneView

https://www.hpe.com/support/oneview-docs

HPE GreenLake for Compute Ops Management

https://www.hpe.com/info/com-docs

Use

HPE Performance Cluster Manager

https://www.hpe.com/support/hpcm_manuals

HPE Performance Analysis Tools

https://www.hpe.com/info/perftools

HPE Cray Programming Environment User Guide

https://www.hpe.com/info/cray-pe-user-guides

HPE ProLiant ML110 Gen11 Server User Guide

203

Table of Contents