blcr

After have been investigating my problem for weeks I have found some information from the hexdump of the context(I got one without C/R error (links at the end of this question, but no restart success)) (context-num0-0-0, DropBox ) <<cut>> cri_sig_handle.Failed to reregister signal %d in process %d. Saw %p when expecting %p (%s) or %p (cri_sig_handler)....cri_run_sig_handler. Failed to allocate signal %d in process %d: got signal %d instead...sigfillset() failed: %s.sigaction() failed: %s..LIBCR_DISABLE_NSCD <<cut>> Seems that checkpointing works. I have asked some questions concerning the C/R

UPDATE I have an university project in which I should build up a cluster with RPis. Now we have a fully functional system with BLCR/MPICH on. BLCR works very well with normal processes linked with the lib. Demonstrations we have to show from our management web interface are: parallel execution of a job migration of processes across the nodes fault tolerance with MPI We are allowed to use the simplest computations. The first one we got easily, with MPI too. The second point we actually have only working with normal processes (without MPI). Regarding the third point I have less idea how to