MPI_UNPUBLISH_NAME(3)
π MPI_UNPUBLISH_NAME π
ok so this is the MPI_UNPUBLISH_NAME(3) page from the Open MPI manual, and bestie, it's literally the "jk, nevermind" of the MPI name-service world. you published a name, and now you want it GONE. iconic. let's get into it π«Ά
β¨ NAME β¨
MPI_Unpublish_name β unpublishes a service name π
like, takes it back off the shelf. no cap.
β¨ SYNTAX β¨
π C Syntax π
#include <mpi.h>
int MPI_Unpublish_name(const char *service_name, MPI_Info info,
const char *port_name)
π Fortran Syntax π
USE MPI
! or the older form: INCLUDE 'mpif.h'
MPI_UNPUBLISH_NAME(SERVICE_NAME, INFO, PORT_NAME, IERROR)
CHARACTER*(*) SERVICE_NAME, PORT_NAME
INTEGER INFO, IERROR
π Fortran 2008 Syntax π
USE mpi_f08
MPI_Unpublish_name(service_name, info, port_name, ierror)
CHARACTER(LEN=*), INTENT(IN) :: service_name, port_name
TYPE(MPI_Info), INTENT(IN) :: info
INTEGER, OPTIONAL, INTENT(OUT) :: ierror
β¨ INPUT PARAMETERS β¨
service_nameβ a service name (string). the thing you're un-publishing, bestie πΈinfoβ options to the name service functions (handle) βport_nameβ a port name (string) π¦
β¨ OUTPUT PARAMETER β¨
ierrorβ Fortran only: error status (integer). yeah, the Fortran girlies get the output param, C girlies get the return value, that's just how it is π
β¨ DESCRIPTION β¨
ok so what this routine does: it removes the pair (service_name, port_name) so that applications can no longer retrieve port_name by calling MPI_Lookup_name. bye felicia πβ¨
β οΈ it is an error to unpublish aservice_namethat was not published viaMPI_Publish_name. so like, don't try to un-publish something you never published. that's not a vibe check you're gonna pass π
also β and this is the part people always mess up β both the service_name and port_name arguments to MPI_Unpublish_name must be identical to the arguments to the previous call to MPI_Publish_name. identical. character for character. no "close enough" energy π
β¨ INFO ARGUMENTS β¨
so the following keys for info are recognized:
rangeβ typechar *β scope from which to remove the service name. see the NAME SCOPE section below π
the range info key accepts one of two string values:
nspaceβ restrict the operation to processes in the same MPI job (PMIx namespace) as the calling process.sessionβ apply the operation across all processes in the same session.
if the info argument is MPI_INFO_NULL, or is a valid info object that does not contain a range key, session scope is used. and because MPI_Publish_name, MPI_Lookup_name, and MPI_Unpublish_name all share this default, a name published with MPI_INFO_NULL is found by a lookup with MPI_INFO_NULL. consistency is the moment π
π¨ any other value for range results in an error. periodt.
β¨ NAME SCOPE β¨
Open MPI supports two name scopes, selected by the range info key: nspace and session π
nspace scope restricts the (service_name, port_name) pair to processes in the publisher's own MPI job, i.e., processes sharing the publisher's PMIx namespace.
session scope makes the pair visible to every process in the same PMIx session. this includes jobs started by separate mpirun invocations that share a persistent DVM or scheduler allocation, as well as jobs created via MPI_Comm_spawn. session is the default scope. she's the default for a reason π
β οΈ the same scope must be used to publish, look up, and unpublish a given service name. MPI_Unpublish_name returns an error if the service name is not found in the indicated scope. mismatched scopes = sadness π
for a more detailed description of scoping rules, please see the MPI_Publish_name man page. she's the main character of scoping, honestly π
β¨ ERRORS β¨
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. okay that was a lot, but like, you got it π«Ά
Open MPI includes three predefined error handlers that can be used:
MPI_ERRORS_ARE_FATALβ causes the program to abort all connected MPI processes. dramatic, but make it fatal πMPI_ERRORS_ABORTβ an error handler that can be invoked on a communicator, window, file, or session. when called on a communicator, it acts as ifMPI_Abortwas called on that communicator. if called on a window or file, acts as ifMPI_Abortwas called on a communicator containing the group of processes in the corresponding window or file. if called on a session, aborts only the local process.MPI_ERRORS_RETURNβ returns an error code to the application. the chill one π
MPI applications can also implement their own error handlers by calling:
MPI_Comm_create_errhandlerthenMPI_Comm_set_errhandlerMPI_File_create_errhandlerthenMPI_File_set_errhandlerMPI_Session_create_errhandlerthenMPI_Session_set_errhandleror atMPI_Session_initMPI_Win_create_errhandlerthenMPI_Win_set_errhandler
β οΈ note that MPI does not guarantee that an MPI program can continue past an error. like, fr fr, don't count on it π₯
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.
β¨ SEE ALSO β¨
MPI_Publish_nameMPI_Lookup_nameMPI_Open_port
the whole friend group, honestly. go read them too π
β¨ COPYRIGHT β¨
2003-2026, The Open MPI Community π
and that's the page, bestie!! πΈπ¦β¨ this one's from the Open MPI crew, dated Sep 11, 2026, and it's the MPI_UNPUBLISH_NAME(3) page in the Open MPI manual β go unpublish something responsibly, mwah π
π
π¦ where this page comes from
- arch rolling: openmpi 5.0.11-1 Β· BSD-3-Clause AND LicenseRef-MPICH
- π girlified by deepseek-ai/DeepSeek-V4.1-Flash-1017 on : a language model's rewrite of the original, under its terms