Interactive jobs fail and then hang


Issue: Interactive jobs fail and then hang.

Syslog: 

Jan 21 16:31:06 node99 pbs_mom: LOG_ERROR::No route to host (113) in start_interactive_session, cannot open interactive qsub socket to host headnode1:50408 - 'cannot connect to port 777 in client_to_svr - errno:113 ' - check routing tables/multi-homed host issues 


Jan 21 16:46:47 node99 pbs_mom: LOG_ERROR::No route to host (113) in start_interactive_session, cannot open interactive qsub socket to headnode1:10293 - '777 in client_to_svr - errno:113 ' - check routing tables/multi-homed host issues 

 

Solution:

 This message means that a connection can not be established due to a firewall, SELinux, or hostname resolution problems. Consider turning off your firewall to test and or disabling SELinix. Also make sure that you can resolve the node and server on both compute node and headnode.

 

 

 

Tags: interactive, job fail, job hang
Last update:
2016-01-26 18:52
Author:
Jason Booth
Revision:
1.2
Average rating:0 (0 Votes)

You cannot comment on this entry

Chuck Norris has counted to infinity. Twice.

Records in this category

Tags