[Condor-users] an issue in heterogeneous pool

["163aaronxue" <163aaronxue@xxxxxxx>]

 

I submit a job to worker nodes which have different architecture from that of submit box, and the submited jobs is always in idle state.

 

The following is the log of sched:

 

9/18 23:21:21 (pid:5089) condor_read(): recv() returned -1, errno = 104, assuming failure reading 21 bytes from unknown source.

9/18 23:21:21 (pid:5089) IO: Failed to read packet header

9/18 23:21:21 (pid:5089) Response problem from startd on <192.168.21.248:21560> (match <192.168.21.248:21560>#1250678162#1#...).

9/18 23:21:21 (pid:5089) Sent RELEASE_CLAIM to startd at <192.168.21.248:21560>

9/18 23:21:21 (pid:5089) Match record (<192.168.21.248:21560>, 8083, 0) deleted

 

 

Is there anyone who can give me some suggestions? Thank you.