Bug 897 - [Anolis7.9-iso][rhck][x86_64/aarch_64]安装mpich-3.0软件包后执行hydra_nameserver、hydra_persist、hydra_pmi_proxy二进制发生core dump
Summary: [Anolis7.9-iso][rhck][x86_64/aarch_64]安装mpich-3.0软件包后执行hydra_nameserver、hydra...
Status: CONFIRMED
Alias: None
Product: Anolis OS 7
Classification: Anolis OS
Component: BaseOS Packages (show other bugs) BaseOS Packages
Version: 7.9
Hardware: All Linux
: P3-Medium S3-normal
Target Milestone: ---
Assignee: layne-yang
QA Contact: shuming
URL:
Whiteboard:
Keywords:
Depends on:
Blocks:
 
Reported: 2022-04-24 15:12 UTC by yunmeng365524
Modified: 2022-05-05 17:46 UTC (History)
2 users (show)

See Also:


Attachments
centos7.9 test pic (3.30 MB, image/jpeg)
2022-04-29 17:30 UTC, 刘小平
Details
centos7.9 test pic (1.06 MB, image/jpeg)
2022-05-05 17:46 UTC, 刘小平
Details

Note You need to log in before you can comment on or make changes to this bug.
Description yunmeng365524 2022-04-24 15:12:03 UTC
Description of problem:
执行如下命令会产生coredump
/usr/lib64/mpich/bin/hydra_nameserver --help
/usr/lib64/mpich/bin/hydra_persist --help
/usr/lib64/mpich/bin/hydra_pmi_proxy --help

Version-Release number of selected component (if applicable):

uname -r
4.18.0-193.28.1.an7.aarch64

cat /etc/anolis-release
Anolis OS release 7.9

cat /etc/os-release
NAME="Anolis OS"
VERSION="7.9"
ID="anolis"
ID_LIKE="rhel fedora centos"
VERSION_ID="7.9"
PRETTY_NAME="Anolis OS 7.9"
ANSI_COLOR="0;31"
HOME_URL="https://openanolis.cn/"
BUG_REPORT_URL="https://bugs.openanolis.cn/"

CENTOS_MANTISBT_PROJECT="CentOS-7"
CENTOS_MANTISBT_PROJECT_VERSION="7"
REDHAT_SUPPORT_PRODUCT="centos"
REDHAT_SUPPORT_PRODUCT_VERSION="7"

问题发生概率:必现

How reproducible:
1、安装mpich-3.0软件包
2、执行如下命令
/usr/lib64/mpich/bin/hydra_nameserver --help
/usr/lib64/mpich/bin/hydra_persist --help
/usr/lib64/mpich/bin/hydra_pmi_proxy --help

Steps to Reproduce:
# gdb /usr/lib64/mpich/bin/hydra_persist -c core-hydra_persist-33184
GNU gdb (GDB) Red Hat Enterprise Linux 7.6.1-120.an7
Copyright (C) 2013 Free Software Foundation, Inc.
License GPLv3+: GNU GPL version 3 or later <http://gnu.org/licenses/gpl.html>
This is free software: you are free to change and redistribute it.
There is NO WARRANTY, to the extent permitted by law.  Type "show copying"
and "show warranty" for details.
This GDB was configured as "aarch64-redhat-linux-gnu".
For bug reporting instructions, please see:
<http://www.gnu.org/software/gdb/bugs/>...
Reading symbols from /usr/lib64/mpich/bin/hydra_persist...Reading symbols from /usr/lib64/mpich/bin/hydra_persist...(no debugging symbols found)...done.
(no debugging symbols found)...done.
[New LWP 33184]
[Thread debugging using libthread_db enabled]
Using host libthread_db library "/lib64/libthread_db.so.1".
Core was generated by `/usr/lib64/mpich/bin/hydra_persist --help'.
Program terminated with signal 11, Segmentation fault.
#0  0x0000ffff7ec28b5c in strcasecmp () from /lib64/libc.so.6
Missing separate debuginfos, use: debuginfo-install mpich-3.0-3.0.4-10.an7.aarch64
(gdb) bt
#0  0x0000ffff7ec28b5c in strcasecmp () from /lib64/libc.so.6
#1  0x00000000004049a8 in HYDU_parse_array ()
#2  0x0000000000402e4c in main ()
(gdb) quit
gdb /usr/lib64/mpich/bin/hydra_nameserver -c core-hydra_nameserve-33738
GNU gdb (GDB) Red Hat Enterprise Linux 7.6.1-120.an7
Copyright (C) 2013 Free Software Foundation, Inc.
License GPLv3+: GNU GPL version 3 or later <http://gnu.org/licenses/gpl.html>
This is free software: you are free to change and redistribute it.
There is NO WARRANTY, to the extent permitted by law.  Type "show copying"
and "show warranty" for details.
This GDB was configured as "aarch64-redhat-linux-gnu".
For bug reporting instructions, please see:
<http://www.gnu.org/software/gdb/bugs/>...
Reading symbols from /usr/lib64/mpich/bin/hydra_nameserver...Reading symbols from /usr/lib64/mpich/bin/hydra_nameserver...(no debugging symbols found)...done.
(no debugging symbols found)...done.

warning: core file may not match specified executable file.
[New LWP 33738]
[Thread debugging using libthread_db enabled]
Using host libthread_db library "/lib64/libthread_db.so.1".
Core was generated by `/usr/lib64/mpich/bin/hydra_nameserver --help'.
Program terminated with signal 11, Segmentation fault.
#0  0x0000ffff9c9a8b5c in strcasecmp () from /lib64/libc.so.6
Missing separate debuginfos, use: debuginfo-install mpich-3.0-3.0.4-10.an7.aarch64
(gdb) bt
#0  0x0000ffff9c9a8b5c in strcasecmp () from /lib64/libc.so.6
#1  0x0000000000404f28 in HYDU_parse_array ()
#2  0x0000000000403138 in main ()
(gdb) quit
gdb /usr/lib64/mpich/bin/hydra_pmi_proxy -c core-hydra_pmi_proxy-33748
GNU gdb (GDB) Red Hat Enterprise Linux 7.6.1-120.an7
Copyright (C) 2013 Free Software Foundation, Inc.
License GPLv3+: GNU GPL version 3 or later <http://gnu.org/licenses/gpl.html>
This is free software: you are free to change and redistribute it.
There is NO WARRANTY, to the extent permitted by law.  Type "show copying"
and "show warranty" for details.
This GDB was configured as "aarch64-redhat-linux-gnu".
For bug reporting instructions, please see:
<http://www.gnu.org/software/gdb/bugs/>...
Reading symbols from /usr/lib64/mpich/bin/hydra_pmi_proxy...Reading symbols from /usr/lib64/mpich/bin/hydra_pmi_proxy...(no debugging symbols found)...done.
(no debugging symbols found)...done.
[New LWP 33748]
[Thread debugging using libthread_db enabled]
Using host libthread_db library "/lib64/libthread_db.so.1".
Core was generated by `/usr/lib64/mpich/bin/hydra_pmi_proxy --help'.
Program terminated with signal 11, Segmentation fault.
#0  0x0000ffff807e8b5c in strcasecmp () from /lib64/libc.so.6
Missing separate debuginfos, use: debuginfo-install mpich-3.0-3.0.4-10.an7.aarch64
(gdb) bt
#0  0x0000ffff807e8b5c in strcasecmp () from /lib64/libc.so.6
#1  0x000000000041222c in HYDU_parse_array ()
#2  0x000000000040aa14 in HYD_pmcd_pmip_get_params ()
#3  0x0000000000403224 in main ()
(gdb) quit

Actual results:
产生coredump

Expected results:
不应该coredmp

Additional info:
软件包信息:
# yum info mpich-3.0
已加载插件:fastestmirror, langpacks, product-id, search-disabled-repos, subscription-manager

This system is not registered with an entitlement server. You can use subscription-manager to register.

Loading mirror speeds from cached hostfile
已安装的软件包
名称    :mpich-3.0
架构    :aarch64
版本    :3.0.4
发布    :10.an7
大小    :3.6 M
源    :installed
来自源:os
简介    : MPICH 3.0.x implementation of MPI
网址    :http://www.mpich.org
协议    : MIT
描述    : MPICH is a high-performance and widely portable implementation of the Message
         : Passing Interface (MPI) standard (MPI-1, MPI-2 and MPI-3). The goals of MPICH
         : are: (1) to provide an MPI implementation that efficiently supports different
         : computation and communication platforms including commodity clusters (desktop
         : systems, shared-memory systems, multicore architectures), high-speed networks
         : (10 Gigabit Ethernet, InfiniBand, Myrinet, Quadrics) and proprietary high-end
         : computing systems (Blue Gene, Cray) and (2) to enable cutting-edge research in
         : MPI through an easy-to-extend modular framework for other derived
         : implementations.
         :
         : The mpich binaries in this RPM packages were configured to use the default
         : process manager (Hydra) using the default device (ch3). The ch3 device
         : was configured with support for the nemesis channel that allows for
         : shared-memory and TCP/IP sockets based communication.
         :
         : This package provides compatibility for applications compiled with MPICH 3.0.4

x86 只有hydra_pmi_proxy 会产生coredump文件;
软件包mpich-3.2带的3个文件也有相同的问题。
yum info mpich-3.2
已加载插件:fastestmirror, langpacks, product-id, search-disabled-repos, subscription-manager

This system is not registered with an entitlement server. You can use subscription-manager to register.

Loading mirror speeds from cached hostfile
已安装的软件包
名称    :mpich-3.2
架构    :aarch64
版本    :3.2
发布    :2.an7
大小    :3.8 M
源    :installed
来自源:os
简介    : A high-performance implementation of MPI
网址    :http://www.mpich.org
协议    : MIT
描述    : MPICH is a high-performance and widely portable implementation of the Message
         : Passing Interface (MPI) standard (MPI-1, MPI-2 and MPI-3). The goals of MPICH
         : are: (1) to provide an MPI implementation that efficiently supports different
         : computation and communication platforms including commodity clusters (desktop
         : systems, shared-memory systems, multicore architectures), high-speed networks
         : (10 Gigabit Ethernet, InfiniBand, Myrinet, Quadrics) and proprietary high-end
         : computing systems (Blue Gene, Cray) and (2) to enable cutting-edge research in
         : MPI through an easy-to-extend modular framework for other derived
         : implementations.
         :
         : The mpich binaries in this RPM packages were configured to use the default
         : process manager (Hydra) using the default device (ch3). The ch3 device
         : was configured with support for the nemesis channel that allows for
         : shared-memory and TCP/IP sockets based communication.
Comment 1 yunmeng365524 2022-04-24 15:18:57 UTC
mvapich2-2.0\mvapich2-2.2\mvapich23都有类似的问题
Comment 2 刘小平 alibaba_cloud_group 2022-04-29 17:30:07 UTC
Created attachment 202 [details]
centos7.9 test pic

centos7.9 x86_64/aarch64存在相同问题 暂时降低优先级
Comment 3 刘小平 alibaba_cloud_group 2022-05-05 17:46:54 UTC
Created attachment 224 [details]
centos7.9 test pic

centos7.9 x86_64/aarch64存在相同问题 暂时降低优先级