Hi Ralph. The version you have suggested works properly.
Thank you so much for the attention.
On Mon, Jul 4, 2011 at 3:42 PM, Ralph Castain wrote:
> If you download a 1.5 tarball tagged at r24853 or above, the problem should
> be fixed.
>
>
> On Jul 4, 2011, at 12:34 PM,
If you download a 1.5 tarball tagged at r24853 or above, the problem should be
fixed.
On Jul 4, 2011, at 12:34 PM, Rodrigo Oliveira wrote:
>
> Thanks for the response, Ralph.
>
> I checked my application and it seems not have a race condition in the accept
> stage. The server is started and
Thanks for the response, Ralph.
I checked my application and it seems not have a race condition in the
accept stage. The server is started and it stores the port name in a file.
When a client is started, it gets this port name and tries to connect. In my
tests the error happens about 1 time in 10
Looking deeper, I believe we may have a race condition in the code. Sadly, that
error message is actually irrelevant, but causes the code to abort.
It can be triggered by race conditions in the app as well, but ultimately is
something we need to clean up.
On Jun 27, 2011, at 9:29 AM, Rodrigo
How are you passing the port info between the server and client? You're hitting
a race condition between the two sides.
On Jun 27, 2011, at 9:29 AM, Rodrigo Oliveira wrote:
> Hi there.
> I am developing a server/client application using Open MPI 1.5.3. In a point
> of the server code I open a
Hi there.
I am developing a server/client application using Open MPI 1.5.3. In a
point of the server code I open a port to receive connections from a
client. After that, I call the function MPI_Comm_accept and on the
client side I call MPI_Comm_connect. Sometimes I get an
ORTE_ERROR_LOG, as