Skip to content

[IntegTest][develop] For RHEL8, in test_slurm_memory_based_scheduling allocate more memory to avoid OOM kills in isolated regions #7101

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

Open
wants to merge 2 commits into
base: develop
Choose a base branch
from
+12 −2
Open

[IntegTest][develop] For RHEL8, in test_slurm_memory_based_scheduling allocate more memory to avoid OOM kills in isolated regions #7101

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
841c3f8
[IntegTest][Release-3.14] For RHEL8, in test_slurm_memory_based_sched…
hehe7318 Nov 13, 2025
3186b41
Merge branch 'develop' into wip/fix-test-slurm-mem-in-ADC-on-Rhel-dev
hehe7318 Nov 14, 2025
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
14 changes: 12 additions & 2 deletions tests/integration-tests/tests/schedulers/test_slurm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -724,13 +724,15 @@ def test_slurm_custom_config_parameters(
assert "4100" == slurm_commands.get_node_attribute("q1-dy-cr2-1", "Memory")


@pytest.mark.usefixtures("region", "os", "instance", "scheduler")
@pytest.mark.usefixtures("instance", "scheduler")
@pytest.mark.slurm_memory_based_scheduling
def test_slurm_memory_based_scheduling(
pcluster_config_reader,
clusters_factory,
test_datadir,
scheduler_commands_factory,
os,
region,
):
cluster_config = pcluster_config_reader()
cluster = clusters_factory(cluster_config)
Expand All @@ -757,6 +759,8 @@ def test_slurm_memory_based_scheduling(
remote_command_executor,
slurm_commands,
test_datadir,
os,
region,
)

_test_memory_based_scheduling_with_multiple_instance_types(slurm_commands)
Expand Down Expand Up @@ -2448,6 +2452,8 @@ def _test_memory_based_scheduling_enabled_true(
remote_command_executor,
slurm_commands,
test_datadir,
os,
region,
):
"""Test Slurm with memory-based scheduling feature enabled"""

Expand Down Expand Up @@ -2517,12 +2523,16 @@ def _test_memory_based_scheduling_enabled_true(
"raise_on_error": False,
}
)

# FIXME: This is a short term way to unblock the test in isolated regions under conditions we do not fully get.
# For RHEL8, allocate more memory to avoid OOM kills in isolated regions
mem_allocation = "3000" if os == "rhel8" and "us-iso" in region else "2500"
job_id_2 = slurm_commands.submit_command_and_assert_job_accepted(
submit_command_args={
"nodes": 1,
"slots": 1,
"command": "srun ./a.out 2000000000",
"other_options": "--mem=2500 -w queue1-st-ondemand1-i1-1",
"other_options": f"--mem={mem_allocation} -w queue1-st-ondemand1-i1-1",
"raise_on_error": False,
}
)
Expand Down
Loading