MPIX_COMM_ACK_FAILED(3)

📦
version 5.0.10 · 4 versions
, in ubuntu stonking

💖 MPIX_COMM_ACK_FAILED(3) 💖

okay bestie, gather round, because we're talking about MPIX_Comm_ack_failed, and she is the girl 💅. Quick heads up though: the NAME line on this page literally says MPIX_Comm_get_failed — yes, really, that's what's printed, and no, we are not fixing it, that's just canon now 🙈. It's about acknowledging failed processes in a communicator.

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

✨ SYNTAX ✨

🎀 C Syntax

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

int MPIX_Comm_ack_failed(MPI_Comm comm, int num_to_ack, int *num_acked)

🎀 Fortran Syntax

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

MPIX_COMM_ACK_FAILED(COMM, NUM_TO_ACK, NUM_ACKED, IERROR)
     INTEGER COMM, NUM_TO_ACK, NUM_ACKED, IERROR

🎀 Fortran 2008 Syntax

USE mpi_f08
USE mpi_ext_f08

MPIX_Comm_ack_failed(comm, num_to_ack, num_acked, ierror)
     TYPE(MPI_Comm), INTENT(IN) :: comm
     INTEGER, INTENT(IN) :: num_to_ack
     INTEGER, INTENT(OUT) :: num_acked
     INTEGER, OPTIONAL, INTENT(OUT) :: ierror

🌸 INPUT PARAMETERS 🌸

  • comm — the communicator, bestie (it's a handle).
  • num_to_ack — the maximum number of process failures you want to acknowledge in comm (integer).

🦋 OUTPUT PARAMETERS 🦋

  • num_acked — the number of acknowledged failures in comm (integer).
  • ierror — Fortran only, babe: error status (integer).

👑 DESCRIPTION 👑

This is a local operation, and it's giving ✨control✨. It hands you a way to acknowledge the locally notified failures on comm.

It acknowledges the first num_to_ack process failures on comm. Translating that from manpage-ese: it acknowledges the failure of members with a rank lower than num_to_ack in the group that would be produced by a concurrent call to MPIX_Comm_get_failed on the same comm.

It also sets num_acked to the current number of acknowledged process failures in comm. And what does "acknowledged" mean here, exactly? A process failure has been acknowledged on comm if and only if the rank of the process is lower than num_acked in the group that would be produced by a subsequent call to MPIX_Comm_get_failed on the same comm.

Lowkey important: num_acked can be larger than num_to_ack when process failures have already been acknowledged in a prior call to MPIX_Comm_ack_failed. Not a bug, just math 💅.

💀 EFFECT OF ACKNOWLEDGING FAILURES 💀

Once an MPI process failure is acknowledged on comm, unmatched MPI_ANY_SOURCE receive operations on that same comm — the ones that would have raised an error of class MPIX_ERR_PROC_FAILED_PENDING — just proceed. No further errors about this acknowledged failure. slay.

Also: MPIX_Comm_agree on the same comm will not raise an error of class MPI_ERR_PROC_FAILED because of this acknowledged failure. 🫶

🌈 USAGE PATTERNS 🌈

  • Wanna peek at how many failures are currently acknowledged on comm, with zero side effects? Just supply 0 in num_to_ack. (The original spells it "aknowledged" and honestly? iconic spelling, we stan. 😭)
  • Wanna go the other way and unconditionally acknowledge all currently known process failures in comm? Supply the size of the group of comm in num_to_ack. Boom. done.
  • Note (this is a real note, bestie): the number of acknowledged processes returned in num_acked can be smaller or larger than the value you supplied in num_to_ack. It is however never larger than the size of the group returned by a subsequent call to MPIX_Comm_get_failed. Never. periodt.

🔥 EFFECT ON COLLECTIVE OPERATIONS 🔥

Calling MPIX_Comm_ack_failed on a communicator that has failed MPI processes has no effect on collective operations — with one exception, MPIX_Comm_agree.

So if a collective operation would raise an error because the communicator contains a failed process, it will keep raising that error even after the failure was acknowledged. Sorry babe, that's just how it is.

Want to actually use collective operations between MPI processes of a communicator that contains failed MPI processes? You need to create a new communicator (e.g., by calling MPIX_Comm_shrink). No cap.

🧚 WHEN COMMUNICATOR IS AN INTER-COMMUNICATOR 🧚

When the communicator is an inter-communicator, the failures of members in both the local group and the remote group of comm get acknowledged. both. all of them. 💜

😭 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.

Before the error value is returned, the current MPI error handler associated with the communication object (e.g., communicator, window, file) is called. If no communication object is associated with the MPI call, then the call is considered attached to MPI_COMM_SELF and will call the associated MPI error handler. When MPI_COMM_SELF is not initialized (i.e., before MPI_Init/MPI_Init_thread, after MPI_Finalize, or when using the Sessions Model exclusively) the error raises the initial error handler. The 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 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 that can be used:

  • MPI_ERRORS_ARE_FATAL — causes the program to abort all connected MPI processes. everyone. at once. 💀
  • 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. chill of her honestly.

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. fr fr. that's the whole warning.

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_get_failed
  • MPIX_Comm_agree

2003-2026, The Open MPI Community

okay that's the whole page bestie 🫶✨ this one came out of the Open MPI docs, dated Sep 10, 2026, and it lives on your system as MPIX_COMM_ACK_FAILED(3) — go forth and acknowledge those failures, queen 👑💖

📦 where this page comes from