Celso L. Mendes

@MichaelBrim I am testing it with these settings in my job script: # [logio] export UNIFYFS_LOGIO_CHUNK_SIZE=$(expr 1 \* 1048576) export UNIFYFS_LOGIO_SHMEM_SIZE=$(expr 4300 \* 1048576) export UNIFYFS_LOGIO_SPILL_SIZE=$(expr 0 \* 1048576) export...

@adammood I do not see a clear error message in the server log. This is what I see near the end of that log, just around the time when the...

@adammoody , as suggested by @kathrynmohror in our latest call, I tested a slightly modified version of this example using two ranks, with two processors (in two distinct nodes, hence...

As verified by @adammoody during the debug session at today's call, the error was caused by the server being unable to handle a file with a single extent of 4GB...

This past week I finally had a chance to run again the large_file test program on one processor of the LASSEN system (IBM), and it worked just fine, even without...

I rested today the original ROMIO example (shared_fp.c) with the new Unify, and observed the same error. Even using WRITE_SYNC=1, the resulting file has only 4096 bytes, and in the...

For what it may be worth, these are the full traces that I obtained with Recorder in the non-Unify execution with 4 processors on 2 nodes of Catalyst (i.e. 2...

@adammoody , I just tested this example again using UnifyFS based on PR#587. The behavior improved, but it's not correct yet. Now, the resulting file has 8KB (i.e. more than...

@adammoody , after discussing about this with @CamStan earlier today, I reran this reproducer code on Lassen, and got a similar behavior, although with a slight difference in the observed...

Just a quick note to observe that today I tested this program again, after REMOVING the two MPI_Info_set calls, i.e. the info structure is no longer set. Thus, each of...