[ale] Writing to NFS

Jonathan Glass jonathan.glass at ibb.gatech.edu
Tue Nov 11 09:03:14 EST 2003


2 weeks of daily aggravation and troubleshooting.  The slave node kept 
killing the master node (every 4 to 8 hours), and when the service 
rolled over, the NFS shares went to read-only b/c of the amount of 
traffic.  Shoving a GigE connection down a 100Mbit pipe doesn't work.  :(

Jonathan G.

James P. Kinney III wrote:

>On Tue, 2003-11-11 at 08:20, Jonathan Glass wrote:
>OK, I'll ask. How long did it take to track that error down?
>
>  
>
>>It also happens when you have a fail-over cluster, and the secondary 
>>machine has a slower network connection than the first.  :)  Ask how long 
>>it took to track that little thing down!
>>
>>Thanks and HTH
>>
>>Jonathan Glass
>>
>>_______________________________________________
>>Ale mailing list
>>Ale at ale.org
>>http://www.ale.org/mailman/listinfo/ale
>>    
>>
>>------------------------------------------------------------------------
>>
>>_______________________________________________
>>Ale mailing list
>>Ale at ale.org
>>http://www.ale.org/mailman/listinfo/ale
>>    
>>




More information about the Ale mailing list