Unplanned downtime -- white.prgmr.com

| | Comments (0)
UPDATE 16:41 PST: All guests are up now. Affected customers will be receiving a credit.

The console had gone down and the error was not captured. I rebooted the console server but that did not make white's console work again.  The serial console would not switch to xen, but it could have hypothetically been related to the console going down. I rebooted and checked the bios error log and there was no indication of an error. The linux kernel log did not indicate an error. I increased the swiotlb value since it had been a problem on other servers.

The PDU port white is plugged into is not working correctly which is why I had to go to the data center. I wanted to change it to a working port on a different PDU but I could not contact Luke to get confirmation on whether this would cause any other problems, so I didn't. I will follow up with Luke on this.

White went down unexpectedly just now.  We are unable to bring the Xen console back up so it may be a serial issue. 

Sarah is heading to the data center now to work on the server.  We will post updates as we have them.

Leave a comment

About this Entry

This page contains a single entry by Dan Linehan published on April 13, 2015 3:52 PM.

13 minute downtime on dish was the previous entry in this blog.

white down again is the next entry in this blog.

Find recent content on the main index or look in the archives to find all content.