MPIX_COMM_GET_FAILED(3)

💫 MPIX_COMM_GET_FAILED 💫

okay so bestie, gather round, because this one is from Open MPI's manual pages and it's literally about finding out which of your processes are, um, 💀 no longer with us. It's called MPIX_Comm_get_failed and it hands you a group listing the failed processes in a communicator.

This is part of the User Level Fault Mitigation ULFM extension. iykyk ✨

---

📜 SYNTAX 📜

C Syntax

#include <mpi.h>
#include <mpi-ext.h>

int MPIX_Comm_get_failed(MPI_Comm comm, MPI_Group *failedgrp)

Fortran Syntax

USE MPI
USE MPI_EXT
! or the older form: INCLUDE 'mpif.h'

MPIX_COMM_GET_FAILED(COMM, FAILEDGRP, IERROR)
     INTEGER COMM, FAILEDGRP, IERROR

Fortran 2008 Syntax

USE mpi_f08
USE mpi_ext_f08

MPIX_Comm_get_failed(comm, failedgrp, ierror)
     TYPE(MPI_Comm), INTENT(IN) :: comm
     TYPE(MPI_Group), INTENT(OUT) :: failedgrp
     INTEGER, OPTIONAL, INTENT(OUT) :: ierror

---

📥 INPUT PARAMETERS 📥

• comm — the communicator, aka the handle. 🫶

📤 OUTPUT PARAMETERS 📤

• failedgrp — group (handle). this is where the sad news lands 💔
• ierror — Fortran only: error status (integer).

---

🌸 DESCRIPTION 🌸

So this is a local operation, meaning it only knows what this process knows. It returns the group failedgrp of processes from the communicator comm that are locally known to have failed. And heads up — that group can totally be empty, like, equal to MPI_GROUP_EMPTY. no failures, no drama, we love that for you 🎀

Now for the slightly brain-bending consistency guarantee: for any two groups you get from calling this routine at the same MPI process with the same comm, the intersection of the largest group with the smallest group is MPI_IDENT to the smallest group. Translation? The same processes keep the same ranks in both groups, all the way up to the size of the smallest group. consistent ranking, no cap. 👑

---

💀 PROCESS FAILURES 💀

MPI makes no assumption about asynchronous progress of the failure detection. A valid MPI implementation may choose to update the group of locally known failed MPI processes only when it enters a function that must raise a fault tolerance error. so don't come for the implementation, it's doing its best.

Also possible: only the calling MPI process has detected the reported failure. If you genuinely need global knowledge, MPI processes that detect failures should call MPIX_Comm_revoke to enforce an error at other ranks. go tell the whole group chat, fr fr. 📣

---

🌈 WHEN COMMUNICATOR IS AN INTER-COMMUNICATOR 🌈

When the communicator is an inter-communicator, the value of failedgrp contains the members known to have failed in both the local and the remote groups of comm. both sides, no secrets. 💅

---

😭 ERRORS 😭

Almost all MPI routines return an error value; C routines as the return result of the function and Fortran routines in the last argument. classic.

Before that error value comes back to you, the current MPI error handler associated with the communication object (e.g., communicator, window, file) gets called. If there's no communication object associated with the MPI call, then the call is considered attached to MPI_COMM_SELF and it'll call the associated MPI error handler. And when MPI_COMM_SELF is not initialized — that's before MPI_Init / MPI_Init_thread, after MPI_Finalize, or when you're using the Sessions Model exclusively — the error raises the initial error handler.

That initial error handler can be changed by:

• calling MPI_Comm_set_errhandler on MPI_COMM_SELF when using the World model, or
• the mpi_initial_errhandler CLI argument to mpiexec, or
• the info key to MPI_Comm_spawn / MPI_Comm_spawn_multiple.

If no other appropriate error handler has been set, then the MPI_ERRORS_RETURN error handler is called for MPI I/O functions and the MPI_ERRORS_ABORT error handler is called for all other MPI functions.

Open MPI includes three predefined error handlers you can use:

• MPI_ERRORS_ARE_FATAL — causes the program to abort all connected MPI processes. 💥
• MPI_ERRORS_ABORT — an error handler that can be invoked on a communicator, window, file, or session. When called on a communicator, it acts as if MPI_Abort was called on that communicator. If called on a window or file, it acts as if MPI_Abort was called on a communicator containing the group of processes in the corresponding window or file. If called on a session, it aborts only the local process.
• MPI_ERRORS_RETURN — returns an error code to the application. polite king. 🫡

MPI applications can also implement their own error handlers by calling:

• MPI_Comm_create_errhandler then MPI_Comm_set_errhandler
• MPI_File_create_errhandler then MPI_File_set_errhandler
• MPI_Session_create_errhandler then MPI_Session_set_errhandler or at MPI_Session_init
• MPI_Win_create_errhandler then MPI_Win_set_errhandler

⚠️ Note that MPI does not guarantee that an MPI program can continue past an error. so like… be mindful bestie 😭

See the MPI man page for a full list of MPI error codes.

See the Error Handling section of the MPI-3.1 standard for more information.

See also:

• MPIX_Comm_revoke
• MPIX_Comm_ack_failed

---

📚 Copyright 📚

2003-2026, The Open MPI Community

---

aaaand that's the whole thing, bestie 🦋 slay, you now know exactly how to find out which processes ghosted your communicator. this page was brought to you by Open MPI, dated Sep 10, 2026 — go forth and handle your failures, gorgeous 💖👑✨