Scribd
Upload
1 views

Quick Checklist for Troubleshooting Host Issues

This document provides a checklist for troubleshooting host issues, including checking HBA health, verifying multipathing, and monitoring system performance. It emphasizes running a specific GUDS script during active issues and notes that the current I/O performance is normal. Additionally, it highlights timeout events from Hitachi Storage and suggests contacting the vendor for further verification and potential adjustments to storage parameters.

Uploaded by

ashis
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
1 views

Quick Checklist for Troubleshooting Host Issues

This document provides a checklist for troubleshooting host issues, including checking HBA health, verifying multipathing, and monitoring system performance. It emphasizes running a specific GUDS script during active issues and notes that the current I/O performance is normal. Additionally, it highlights timeout events from Hitachi Storage and suggests contacting the vendor for further verification and potential adjustments to storage parameters.

Uploaded by

ashis
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 1

 Quick Checklist for Troubleshooting Host Issues :

 Check HBA health, driver versions, and queue depths.


 Verify multipathing and load balancing.
 Monitor CPU, memory, and queue saturation on the host.
 Optimize I/O scheduler and application I/O patterns.
 Analyze network performance environments.
 Review timeout settings between host and storage.

Quick Checklist for Troubleshooting Host Issues :

What I can recommend is in the event the issue does occur again, please make sure to run the GUDS script,
while the problem is active, using the following command:

# ./guds -q -r -L -T -X 3 -c 30 -M -i 1 -n 5 -w 0 -s <SR Reference> -d "description_of_symptoms"

 Check HBA health, driver versions, and queue depths.

- The FC-HBA cards are running the latest firmware version 8.08.04 and are operating at a maximum speed
of 32GB.

- The latest QLogic driver version is 5.12 (delivered in SRU 69), while the host is using driver version 5.11.

 Verify multipathing and load balancing.

The multipathing has been configured with 4 and 8 paths, in accordance with the zoning established by the
SAN administrator.

• Optimize I/O scheduler and application I/O patterns.

- The Solaris system's I/O performance is operating under normal conditions.


- The current workload is being handled efficiently by the configured I/O subsystems, and there are no
indications of bottlenecks or performance issues.

Review timeout settings between host and storage.

- During the specified timeframe, I found some fmdump events indicating that the Hitachi Storage
experienced an internal timeout, which is reflected in specific remote targets.: 50060e8008789516,
50060e8008789501, 50060e8008789506, 50060e8008789511

It is important to note that this code does not imply any issues with the QLogic HBAs.

Please contact the Hitachi vendor to verify the array loads and targets. If they recommend it, add the
max_throttle parameter for both storage systems (EMC and Hitachi) under the SD driver.

You might also like