Problem using parallel Fluent
I'm running parallel Fluent on a 5 machine Windows XP Cluster. I've no problem running a problem on 4 machines, but once I want to run the same case on 5, it gives the following error while loading the case file:
999999 (..\..\src\mpsystem.c@1210): mpt_read: failed: errno = 10054
999999: mpt_read: error: read failed trying to read 4 bytes: Invalid argument The Parallel FLUENT process could not be started.
After this happens, the rsh service stops on the last machine that was spawned, and cannot be restarted without rebooting. Sometimes the whole networking stops on that machine, so that it cannot see or be seen by the others.
Has anybody else come across this same problem? The master node has 2 GB RAM, and the 4 slave nodes all have 512 MB RAM, and they're connected via Gigabit Ethernet.
|All times are GMT -4. The time now is 15:26.|