The system was pretty stable until now and we considered moving the storage to production this week. But this problem scared us!
On Tue, 22 Feb 2005 Michael Conrad Tadpol Tilstra wrote :
>Raj Kumar wrote:
>>Thanks for the information.
>>What could be the problem in my case? I didn't restart the servers yet with the concern that it might screw up the filesystem. I want to figure out what is the cause of the actual problem and correct it!!!
>I don't know. I've never seen a timeout error in the gulm_LT_recver before. The only clues would have come from other gulm messages in the logs, and since there aren't any, I cannot say much.
>What version of the code are you using?
>Restarting the servers at this point should not make things any worse.
>-- Michael Conrad Tadpol Tilstra
>Linux-cluster mailing list
>Linux-cluster redhat com