Bug 2149873

Summary: [RHEL9.2] - some openmpi benchmarks time-out with return code of 1 when executed on CXGB4 devices
Product: Red Hat Enterprise Linux 9 Reporter: Brian Chae <bchae>
Component: openmpiAssignee: Kamal Heib <kheib>
Status: CLOSED MIGRATED QA Contact: Infiniband QE <infiniband-qe>
Severity: unspecified Docs Contact:
Priority: unspecified    
Version: 9.2CC: kheib, rdma-dev-team
Target Milestone: rcKeywords: MigratedToJIRA
Target Release: ---Flags: pm-rhel: mirror+
Hardware: Unspecified   
OS: Unspecified   
Whiteboard:
Fixed In Version: Doc Type: If docs needed, set a value
Doc Text:
Story Points: ---
Clone Of: Environment:
Last Closed: 2023-09-21 14:31:49 UTC Type: Bug
Regression: --- Mount Type: ---
Documentation: --- CRM:
Verified Versions: Category: ---
oVirt Team: --- RHEL 7.3 requirements from Atomic Host:
Cloudforms Team: --- Target Upstream Version:
Embargoed:

Description Brian Chae 2022-12-01 09:27:06 UTC
Description of problem:

Some of the OPENMPI benchmarks time-out with RC1 when run on CXGB4 devices.
The failed benchmarks are as the following:

      FAIL |      1 | openmpi IMB-IO P_Write_indv mpirun one_core
      FAIL |      1 | openmpi IMB-IO P_Write_expl mpirun one_core
      FAIL |      1 | openmpi IMB-IO P_Write_shared mpirun one_core
      FAIL |      1 | openmpi IMB-IO P_Write_priv mpirun one_core
      FAIL |      1 | openmpi IMB-IO C_Write_indv mpirun one_core
      FAIL |      1 | openmpi IMB-IO C_Write_expl mpirun one_core
      FAIL |      1 | openmpi IMB-IO C_Write_shared mpirun one_core
      FAIL |      1 | openmpi OSU get_acc_latency mpirun one_core
      FAIL |      1 | openmpi OSU mbw_mr mpirun one_core

This issue seems to be consistent in the following hosts.

a. rdma-qe-12 (cxgb4 t5 iw 40) / rdma-perf-06 (cxgb4 T6 iw 100)

   beaker job : https://beaker.engineering.redhat.com/jobs/7293293

b. rdma-dev-13 (cxgb4 t6 iw 100) / rdma-perf-06 (cxgb4 T6 iw 100)

   https://beaker.engineering.redhat.com/jobs/7292260 


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

Clients: rdma-perf-06
Servers: rdma-qe-12

DISTRO=RHEL-9.2.0-20221129.2

+ [22-11-30 18:38:52] cat /etc/redhat-release
Red Hat Enterprise Linux release 9.2 Beta (Plow)

+ [22-11-30 18:38:52] uname -a
Linux rdma-perf-06.rdma.lab.eng.rdu2.redhat.com 5.14.0-202.el9.x86_64 #1 SMP PREEMPT_DYNAMIC Mon Nov 28 08:49:47 EST 2022 x86_64 x86_64 x86_64 GNU/Linux

+ [22-11-30 18:38:52] cat /proc/cmdline
BOOT_IMAGE=(hd0,gpt2)/vmlinuz-5.14.0-202.el9.x86_64 root=UUID=60790874-ea0a-4a35-8447-d83f2475913b ro crashkernel=1G-4G:192M,4G-64G:256M,64G-:512M resume=UUID=08d83c36-2fab-45c6-a375-8bb16849b90a console=ttyS0,115200n81

+ [22-11-30 18:38:52] rpm -q rdma-core linux-firmware
rdma-core-41.0-3.el9.x86_64
linux-firmware-20221012-128.el9.noarch

+ [22-11-30 18:38:52] tail /sys/class/infiniband/cxgb4_0/fw_ver /sys/class/infiniband/hfi1_0/fw_ver /sys/class/infiniband/mlx5_0/fw_ver /sys/class/infiniband/mlx5_1/fw_ver /sys/class/infiniband/qedr0/fw_ver /sys/class/infiniband/qedr1/fw_ver
==> /sys/class/infiniband/cxgb4_0/fw_ver <==
1.27.0.0

==> /sys/class/infiniband/hfi1_0/fw_ver <==
1.27.0

==> /sys/class/infiniband/mlx5_0/fw_ver <==
20.99.5392

==> /sys/class/infiniband/mlx5_1/fw_ver <==
20.99.5392

==> /sys/class/infiniband/qedr0/fw_ver <==
8.59.1.0

==> /sys/class/infiniband/qedr1/fw_ver <==
8.59.1.0

+ [22-11-30 18:38:52] lspci
+ [22-11-30 18:38:52] grep -i -e ethernet -e infiniband -e omni -e ConnectX
19:00.0 Ethernet controller: QLogic Corp. FastLinQ QL41000 Series 10/25/40/50GbE Controller (rev 02)
19:00.1 Ethernet controller: QLogic Corp. FastLinQ QL41000 Series 10/25/40/50GbE Controller (rev 02)
19:00.2 Ethernet controller: QLogic Corp. FastLinQ QL41000 Series 10/25/40/50GbE Controller (rev 02)
19:00.3 Ethernet controller: QLogic Corp. FastLinQ QL41000 Series 10/25/40/50GbE Controller (rev 02)
5e:00.0 Ethernet controller: Chelsio Communications Inc T62100-LP-CR Unified Wire Ethernet Controller
5e:00.1 Ethernet controller: Chelsio Communications Inc T62100-LP-CR Unified Wire Ethernet Controller
5e:00.2 Ethernet controller: Chelsio Communications Inc T62100-LP-CR Unified Wire Ethernet Controller
5e:00.3 Ethernet controller: Chelsio Communications Inc T62100-LP-CR Unified Wire Ethernet Controller
5e:00.4 Ethernet controller: Chelsio Communications Inc T62100-LP-CR Unified Wire Ethernet Controller
af:00.0 Infiniband controller: Mellanox Technologies MT28908 Family [ConnectX-6]
af:00.1 Infiniband controller: Mellanox Technologies MT28908 Family [ConnectX-6]
d8:00.0 Fabric controller: Intel Corporation Omni-Path HFI Silicon 100 Series [discrete] (rev 11)

How reproducible:

100% in the above combinations of RDMA hosts

Steps to Reproduce:

1. Please refer to the beaker job outputs in client hosts mentioned above.
2.
3.

Actual results:


Expected results:


Additional info:

However, with the following CXGB4 hosts combinations, ALL OPENMPI benchmarks PASSED

a. mpi suite over rdma-iw-cxgb pool[ RHEL-9.2.0-20221129.2: rdma-perf-06/07 - mpich2,openmpi ]

   beaker job : https://beaker.engineering.redhat.com/jobs/7291986 

b. mpi suite over rdma-iw-cxgb pool[ RHEL-9.2.0-20221129.2: rdma-dev-13/rdma-qe-12 - mpich2,openmpi ]  - J:7293324

mpi/openmpi test results on rdma-dev-13/rdma-qe-12 & Beaker job J:7293324:
5.14.0-202.el9.x86_64, rdma-core-41.0-3.el9, cxgb4, iw, T520-CR & cxgb4_0
    Result | Status | Test
  ---------+--------+------------------------------------
Checking for failures and known issues:
  no test failures

  beaker job : https://beaker.engineering.redhat.com/jobs/7293324

Comment 1 Jakub Jelen 2022-12-01 10:05:31 UTC
I do not see how this is related to the opensc package. Was the component wrongly selected and should this be reported against openmpi? I will reassign. If I am wrong, please find the right component.

Comment 2 Brian Chae 2023-07-10 13:47:10 UTC
*** Bug 2149874 has been marked as a duplicate of this bug. ***

Comment 3 Brian Chae 2023-07-10 13:48:03 UTC
*** Bug 2149878 has been marked as a duplicate of this bug. ***

Comment 4 RHEL Program Management 2023-09-21 14:28:28 UTC
Issue migration from Bugzilla to Jira is in process at this time. This will be the last message in Jira copied from the Bugzilla bug.

Comment 5 RHEL Program Management 2023-09-21 14:31:49 UTC
This BZ has been automatically migrated to the issues.redhat.com Red Hat Issue Tracker. All future work related to this report will be managed there.

Due to differences in account names between systems, some fields were not replicated.  Be sure to add yourself to Jira issue's "Watchers" field to continue receiving updates and add others to the "Need Info From" field to continue requesting information.

To find the migrated issue, look in the "Links" section for a direct link to the new issue location. The issue key will have an icon of 2 footprints next to it, and begin with "RHEL-" followed by an integer.  You can also find this issue by visiting https://issues.redhat.com/issues/?jql= and searching the "Bugzilla Bug" field for this BZ's number, e.g. a search like:

"Bugzilla Bug" = 1234567

In the event you have trouble locating or viewing this issue, you can file an issue by sending mail to rh-issues. You can also visit https://access.redhat.com/articles/7032570 for general account information.