Update hpctests to obey UCX_NET_DEVICES when RoCE devices present #421
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
sjpb
requested changes
Aug 7, 2024
sjpb
changed the title
This comment was marked as outdated.
This comment was marked as outdated.
Sorry, something went wrong.
sjpb
approved these changes
Aug 7, 2024
bertiethorpe
added a commit
that referenced
this pull request
Aug 9, 2024
* Turn off higher priority MPI net devices * Update pingmatrix.sh.j2 * Update pingmatrix.sh.j2 * Update pingpong.sh.j2 * Replace j2 comments with bash * Update pingpong.sh.j2 --------- Co-authored-by: Steve Brasier <[email protected]>
sjpb
added a commit
that referenced
this pull request
Aug 14, 2024
* add trivy image scanning * bump fatimage workflow to ubuntu 22.04 * make setup script work in CI TODO: FIXME * fix libguestfs install * run only 1x build per matrix entry, & only builds required * fix packer README * fix image download * Use shorter names for CI clusters (#415) * use run_number as a shorter ID for CI * slurmci group name warning * Revert "slurmci group name warning" - underscores not valid linux hostname and stripped in host, leading to slurmdbd config failure This reverts commit 61dfad6. --------- Co-authored-by: Bertie <[email protected]> * install ood apps in fatimage * add ood jupyter install to fatimage * jupyter_compute ood into fatimage * bump fatimage * allow items in compute mapping to have different keys e.g. only specify image_id for some compute groups (#412) * Support ansible-init for remote collections (#411) * Add ansible-init role to requirements.yml * Add ansible-init to groups and plays * Configure cluster_infra ansible-init metadata * Only run site.yml once ansible-init has completed * Wait for ansible init to finish before running bootstrap * revert to using cluster_infra metadata defaults * update image * revert sausage bastion changes * set ansible_init_wait as common var * use run_number as a shorter ID for CI * install ood apps in fatimage * add ood jupyter install to fatimage * bump image * jupyter_compute ood into fatimage * bump fatimage for jupyter_compute ood * Update stackhpc.yml * duplicate tuned inventory group name * Fix invalid group name for slurmci * Update stackhpc.yml undo groupname changes * slurmci group name warning * rm ood changes * bump fatimage * change azimuth collection in bootstrap * update azimuth image utils version * update requirements * Update bastion.yml * Use azimuth image utils collection for ansible-init * bump fatimage --------- Co-authored-by: bertie <[email protected]> Co-authored-by: bertiethorpe <[email protected]> * avoid python-openstackclient v7 due to rebuild bug (#420) * Update hpctests to obey UCX_NET_DEVICES when RoCE devices present (#421) * Turn off higher priority MPI net devices * Update pingmatrix.sh.j2 * Update pingmatrix.sh.j2 * Update pingpong.sh.j2 * Replace j2 comments with bash * Update pingpong.sh.j2 --------- Co-authored-by: Steve Brasier <[email protected]> * delete trivy scanned vulnerabilities * update grafana * bump image * Update environments/.stackhpc/hooks/post.yml Co-authored-by: Steve Brasier <[email protected]> * Update setup-env.sh --------- Co-authored-by: Bertie <[email protected]> Co-authored-by: bertiethorpe <[email protected]> Co-authored-by: bertiethorpe <[email protected]>
MaxBed4d
pushed a commit
that referenced
this pull request
Oct 15, 2024
* Turn off higher priority MPI net devices * Update pingmatrix.sh.j2 * Update pingmatrix.sh.j2 * Update pingpong.sh.j2 * Replace j2 comments with bash * Update pingpong.sh.j2 --------- Co-authored-by: Steve Brasier <[email protected]>
MaxBed4d
pushed a commit
that referenced
this pull request
Oct 15, 2024
* add trivy image scanning * bump fatimage workflow to ubuntu 22.04 * make setup script work in CI TODO: FIXME * fix libguestfs install * run only 1x build per matrix entry, & only builds required * fix packer README * fix image download * Use shorter names for CI clusters (#415) * use run_number as a shorter ID for CI * slurmci group name warning * Revert "slurmci group name warning" - underscores not valid linux hostname and stripped in host, leading to slurmdbd config failure This reverts commit 61dfad6. --------- Co-authored-by: Bertie <[email protected]> * install ood apps in fatimage * add ood jupyter install to fatimage * jupyter_compute ood into fatimage * bump fatimage * allow items in compute mapping to have different keys e.g. only specify image_id for some compute groups (#412) * Support ansible-init for remote collections (#411) * Add ansible-init role to requirements.yml * Add ansible-init to groups and plays * Configure cluster_infra ansible-init metadata * Only run site.yml once ansible-init has completed * Wait for ansible init to finish before running bootstrap * revert to using cluster_infra metadata defaults * update image * revert sausage bastion changes * set ansible_init_wait as common var * use run_number as a shorter ID for CI * install ood apps in fatimage * add ood jupyter install to fatimage * bump image * jupyter_compute ood into fatimage * bump fatimage for jupyter_compute ood * Update stackhpc.yml * duplicate tuned inventory group name * Fix invalid group name for slurmci * Update stackhpc.yml undo groupname changes * slurmci group name warning * rm ood changes * bump fatimage * change azimuth collection in bootstrap * update azimuth image utils version * update requirements * Update bastion.yml * Use azimuth image utils collection for ansible-init * bump fatimage --------- Co-authored-by: bertie <[email protected]> Co-authored-by: bertiethorpe <[email protected]> * avoid python-openstackclient v7 due to rebuild bug (#420) * Update hpctests to obey UCX_NET_DEVICES when RoCE devices present (#421) * Turn off higher priority MPI net devices * Update pingmatrix.sh.j2 * Update pingmatrix.sh.j2 * Update pingpong.sh.j2 * Replace j2 comments with bash * Update pingpong.sh.j2 --------- Co-authored-by: Steve Brasier <[email protected]> * delete trivy scanned vulnerabilities * update grafana * bump image * Update environments/.stackhpc/hooks/post.yml Co-authored-by: Steve Brasier <[email protected]> * Update setup-env.sh --------- Co-authored-by: Bertie <[email protected]> Co-authored-by: bertiethorpe <[email protected]> Co-authored-by: bertiethorpe <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Adds openmpi runtime options to prevent openmpi's own RoCE detection overriding UCX_NET_DEVICES, if set. See openucx/ucx#10049 for more information.