On 11-07-14 04:48 PM, Jeff Squyres wrote:
Sorry I should have said it doesn't get sent until the *master*
encounters an MPI_recv.
Then suddenly the slave finally gets the message and carries on its task.
I know that the slave is waiting because:
1.) it doesn't print anything
2.) I have attached to it with gdb previously to monitor the behaviour.
> On Jul 14, 2011, at 5:50 PM, dave fournier wrote:
>> I have a master-slave setup. I have noticed that when I send a message from the master to the slave
>> processes using MPI_Isend it never gets sent until I encounter an MPI_recv in the master process.
> How are you testing that?
>> As a result rhe slave processes are wasting time waiting for the message.
> Er... I'm not sure I can parse this. You said that the message doesn't go until the slave calls MPI_Recv. So I don't quite understand how the slave is wasting time...?
>> If I use MPI_Send
>> instead of MPI_Isend all works fine. I don't understand what is going on here.
> Define "fine" -- can you be a bit more precise about the exact behavior that you want to see, and the behavior that you are seeing, and the difference that MPI_SEND makes vs. MPI_ISEND?