Skip to content

mpirun is terminated saying stack smashing detected when hostname is long #13358

@ktns

Description

@ktns

Background information

What version of Open MPI are you using? (e.g., v4.1.6, v5.0.1, git branch name and hash, etc.)

both

  • 4.1.6-7ubuntu2 on ubuntu 24.04
  • 4.1.8 built from source on ubuntu 24.04

Describe how Open MPI was installed (e.g., from a source/distribution tarball, from a git clone, from an operating system distribution package, etc.)

  • apt-get install
  • built from source tarball

If you are building/installing from a git clone, please copy-n-paste the output from git submodule status.

Please describe the system on which you are running

  • Operating system/version: ubuntu 24.04
  • Computer hardware: Intel(R) Xeon(R) Gold 6254 / ThinkPad X1 nano gen1
  • Network type: n/a

Details of the problem

When hostname is longer than 56 characters, mpirun is immediately terminated saying

*** stack smashing detected ***: terminated

I found it in a k8s pod with openmpi 4.1.8 built from source tarball, but I can reproduce it with 4.1.6-ubuntu2 installed via apt-get on ubuntu 24.04 in a docker container.

docker run --rm -h dpzwksxgqlelrdfraudrnnjnpwvsfxgeqozkukzhzlkzfyfotdsuflkja ubuntu:24.04 bash -c 'apt-get update ; apt-get install openmpi-bin -y ; mpirun --allow-run-as-root -np 2 true'
....
*** stack smashing detected ***: terminated
[dpzwksxgqlelrdfraudrnnjnpwvsfxgeqozkukzhzlkzfyfotdsuflkja:00001] *** Process received signal ***
[dpzwksxgqlelrdfraudrnnjnpwvsfxgeqozkukzhzlkzfyfotdsuflkja:00001] Signal: Segmentation fault (11)
[dpzwksxgqlelrdfraudrnnjnpwvsfxgeqozkukzhzlkzfyfotdsuflkja:00001] Signal code:  (128)
[dpzwksxgqlelrdfraudrnnjnpwvsfxgeqozkukzhzlkzfyfotdsuflkja:00001] Failing at address: (nil)
[dpzwksxgqlelrdfraudrnnjnpwvsfxgeqozkukzhzlkzfyfotdsuflkja:00001] [ 0] /lib/x86_64-linux-gnu/libc.so.6(+0x45330)[0x7b6da6245330]
[dpzwksxgqlelrdfraudrnnjnpwvsfxgeqozkukzhzlkzfyfotdsuflkja:00001] [ 1] /lib/x86_64-linux-gnu/libc.so.6(abort+0x182)[0x7b6da62289a2]
[dpzwksxgqlelrdfraudrnnjnpwvsfxgeqozkukzhzlkzfyfotdsuflkja:00001] [ 2] /lib/x86_64-linux-gnu/libc.so.6(+0x297b6)[0x7b6da62297b6]
[dpzwksxgqlelrdfraudrnnjnpwvsfxgeqozkukzhzlkzfyfotdsuflkja:00001] [ 3] /lib/x86_64-linux-gnu/libc.so.6(+0x136c19)[0x7b6da6336c19]
[dpzwksxgqlelrdfraudrnnjnpwvsfxgeqozkukzhzlkzfyfotdsuflkja:00001] [ 4] /lib/x86_64-linux-gnu/libc.so.6(+0x137ea4)[0x7b6da6337ea4]
[dpzwksxgqlelrdfraudrnnjnpwvsfxgeqozkukzhzlkzfyfotdsuflkja:00001] [ 5] /usr/lib/x86_64-linux-gnu/openmpi/lib/openmpi3/mca_regx_fwd.so(+0x2404)[0x7b6da3b40404]
[dpzwksxgqlelrdfraudrnnjnpwvsfxgeqozkukzhzlkzfyfotdsuflkja:00001] [ 6] /lib/x86_64-linux-gnu/libopen-rte.so.40(orte_odls_base_default_get_add_procs_data+0x156)[0x7b6da659fce6]
[dpzwksxgqlelrdfraudrnnjnpwvsfxgeqozkukzhzlkzfyfotdsuflkja:00001] [ 7] /lib/x86_64-linux-gnu/libopen-rte.so.40(orte_plm_base_launch_apps+0x1aa)[0x7b6da65a9bba]
[dpzwksxgqlelrdfraudrnnjnpwvsfxgeqozkukzhzlkzfyfotdsuflkja:00001] [ 8] /lib/x86_64-linux-gnu/libevent_core-2.1.so.7(+0x1f2a8)[0x7b6da646e2a8]
[dpzwksxgqlelrdfraudrnnjnpwvsfxgeqozkukzhzlkzfyfotdsuflkja:00001] [ 9] /lib/x86_64-linux-gnu/libevent_core-2.1.so.7(event_base_loop+0x4af)[0x7b6da646ffaf]
[dpzwksxgqlelrdfraudrnnjnpwvsfxgeqozkukzhzlkzfyfotdsuflkja:00001] [10] mpirun(+0x128c)[0x581b3fb3028c]
[dpzwksxgqlelrdfraudrnnjnpwvsfxgeqozkukzhzlkzfyfotdsuflkja:00001] [11] /lib/x86_64-linux-gnu/libc.so.6(+0x2a1ca)[0x7b6da622a1ca]
[dpzwksxgqlelrdfraudrnnjnpwvsfxgeqozkukzhzlkzfyfotdsuflkja:00001] [12] /lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0x8b)[0x7b6da622a28b]
[dpzwksxgqlelrdfraudrnnjnpwvsfxgeqozkukzhzlkzfyfotdsuflkja:00001] [13] mpirun(+0x1415)[0x581b3fb30415]
[dpzwksxgqlelrdfraudrnnjnpwvsfxgeqozkukzhzlkzfyfotdsuflkja:00001] *** End of error message ***

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions