Skip to content

Update DcgmRpmCheck after maintenance failure #497

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
jgphpc merged 2 commits into from
Jan 15, 2026
Merged

Update DcgmRpmCheck after maintenance failure #497

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1f2cce7
sort
Jan 15, 2026
7cc1d6d
fix
Jan 15, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion checks/system/gssr/dcgm_hook.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,7 @@ class GssrCeHookCheck(rfm.RunOnlyRegressionTest, ContainerEngineMixin):
pytorch_image_tag = parameter(['25.01-py3_nvrtc-12.9'])
container_env_table = {'annotations.com.hooks': {'dcgm.enabled': 'true'}}
executable = './dcgm_hook.sh'
time_limit = '5m'
time_limit = '3m'

@run_after('init')
def setup_ce(self):
Expand Down
30 changes: 15 additions & 15 deletions checks/system/gssr/src/rpm/3.3.6.ref
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,31 +1,31 @@
927f450bab750ea72a96a5470d39480c69e954d6 /usr/lib64/libdcgm_cublas_proxy11.so
70f725c08b045b1db839ec5e2d8de5bcdd471443 /usr/lib64/libdcgm_cublas_proxy12.so
058d0865436f374041992c1977b12f2616cb4491 /usr/lib64/libdcgmmoduleconfig.so
058d0865436f374041992c1977b12f2616cb4491 /usr/lib64/libdcgmmoduleconfig.so.3
058d0865436f374041992c1977b12f2616cb4491 /usr/lib64/libdcgmmoduleconfig.so.3.3.6
139ab86052ab0f0e49029b18861bf57bf9de4075 /usr/lib64/libdcgmmodulediag.so
139ab86052ab0f0e49029b18861bf57bf9de4075 /usr/lib64/libdcgmmodulediag.so.3
139ab86052ab0f0e49029b18861bf57bf9de4075 /usr/lib64/libdcgmmodulediag.so.3.3.6
61b29e9b76115a38050a28bfa966881bb1868e2b /usr/lib64/libdcgmmodulehealth.so
61b29e9b76115a38050a28bfa966881bb1868e2b /usr/lib64/libdcgmmodulehealth.so.3
61b29e9b76115a38050a28bfa966881bb1868e2b /usr/lib64/libdcgmmodulehealth.so.3.3.6
1fba633b0658723dc49bf5cf1361eef322d7e445 /usr/lib64/libdcgmmoduleintrospect.so
1fba633b0658723dc49bf5cf1361eef322d7e445 /usr/lib64/libdcgmmoduleintrospect.so.3
1fba633b0658723dc49bf5cf1361eef322d7e445 /usr/lib64/libdcgmmoduleintrospect.so.3.3.6
b794d06da807500c6a6e367857c65e4f1b4e12b1 /usr/lib64/libdcgmmodulenvswitch.so
b794d06da807500c6a6e367857c65e4f1b4e12b1 /usr/lib64/libdcgmmodulenvswitch.so.3
b794d06da807500c6a6e367857c65e4f1b4e12b1 /usr/lib64/libdcgmmodulenvswitch.so.3.3.6
4ff9cc6b3d77147891d9c30ef9664800a1a18ef6 /usr/lib64/libdcgmmodulepolicy.so
4ff9cc6b3d77147891d9c30ef9664800a1a18ef6 /usr/lib64/libdcgmmodulepolicy.so.3
4ff9cc6b3d77147891d9c30ef9664800a1a18ef6 /usr/lib64/libdcgmmodulepolicy.so.3.3.6
9c65abce613a9fd49f49a20bb23d72eadb450223 /usr/lib64/libdcgmmoduleprofiling.so
9c65abce613a9fd49f49a20bb23d72eadb450223 /usr/lib64/libdcgmmoduleprofiling.so.3
9c65abce613a9fd49f49a20bb23d72eadb450223 /usr/lib64/libdcgmmoduleprofiling.so.3.3.6
742b248ee4d398a87f126634174e155d5f2a6541 /usr/lib64/libdcgmmodulesysmon.so
742b248ee4d398a87f126634174e155d5f2a6541 /usr/lib64/libdcgmmodulesysmon.so.3
742b248ee4d398a87f126634174e155d5f2a6541 /usr/lib64/libdcgmmodulesysmon.so.3.3.6
51bb0404a54979daf962a18379d6304667d3117b /usr/lib64/libdcgm.so
51bb0404a54979daf962a18379d6304667d3117b /usr/lib64/libdcgm.so.3
51bb0404a54979daf962a18379d6304667d3117b /usr/lib64/libdcgm.so.3.3.6
f9daed6594a004fb42975bc5b020881ff55e5baf /usr/lib64/libdcgm_stub.a
568e9d75300dd50c16f2bd04ad401512bb16511c /usr/lib64/libnvperf_dcgm_host.so
61b29e9b76115a38050a28bfa966881bb1868e2b /usr/lib64/libdcgmmodulehealth.so
61b29e9b76115a38050a28bfa966881bb1868e2b /usr/lib64/libdcgmmodulehealth.so.3
61b29e9b76115a38050a28bfa966881bb1868e2b /usr/lib64/libdcgmmodulehealth.so.3.3.6
70f725c08b045b1db839ec5e2d8de5bcdd471443 /usr/lib64/libdcgm_cublas_proxy12.so
742b248ee4d398a87f126634174e155d5f2a6541 /usr/lib64/libdcgmmodulesysmon.so
742b248ee4d398a87f126634174e155d5f2a6541 /usr/lib64/libdcgmmodulesysmon.so.3
742b248ee4d398a87f126634174e155d5f2a6541 /usr/lib64/libdcgmmodulesysmon.so.3.3.6
927f450bab750ea72a96a5470d39480c69e954d6 /usr/lib64/libdcgm_cublas_proxy11.so
9c65abce613a9fd49f49a20bb23d72eadb450223 /usr/lib64/libdcgmmoduleprofiling.so
9c65abce613a9fd49f49a20bb23d72eadb450223 /usr/lib64/libdcgmmoduleprofiling.so.3
9c65abce613a9fd49f49a20bb23d72eadb450223 /usr/lib64/libdcgmmoduleprofiling.so.3.3.6
b794d06da807500c6a6e367857c65e4f1b4e12b1 /usr/lib64/libdcgmmodulenvswitch.so
b794d06da807500c6a6e367857c65e4f1b4e12b1 /usr/lib64/libdcgmmodulenvswitch.so.3
b794d06da807500c6a6e367857c65e4f1b4e12b1 /usr/lib64/libdcgmmodulenvswitch.so.3.3.6
f9daed6594a004fb42975bc5b020881ff55e5baf /usr/lib64/libdcgm_stub.a
2 changes: 1 addition & 1 deletion checks/system/gssr/src/rpm/dcgm_rpm.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,5 +5,5 @@ which dcgmi

# test2:
export dcgmi_version=$(dcgmi --version |grep version |awk '{print $3}')
shasum /usr/lib64/*dcgm* &> _${dcgmi_version}.rpt
shasum /usr/lib64/*dcgm* |sort &> _${dcgmi_version}.rpt
diff -s ${dcgmi_version}.ref _${dcgmi_version}.rpt