Skip to content
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

[feat] Add the Firecrest slurm scheduler #3046

Draft
wants to merge 20 commits into
base: develop
Choose a base branch
from
Draft

[feat] Add the Firecrest slurm scheduler #3046

Show file tree
Hide file tree
Changes from 19 commits
Commits
Show all changes
20 commits
Select commit Hold shift + click to select a range
c4cf710
Add basic firecrest implementation
ekouts Nov 7, 2023
652ce7b
Merge branch 'develop' of https://github.com/reframe-hpc/reframe into…
ekouts Nov 7, 2023
88c5095
Revert gitignore
ekouts Nov 7, 2023
2cf0ac4
Fix the sync of files for the firecrest scheduler
ekouts Nov 14, 2023
37f6ea0
Disable checking for sane module system when resolve_module_conflicts…
ekouts Nov 16, 2023
8b04d51
Temporarily disable all module sanity checking
ekouts Nov 16, 2023
d146d00
Setup slurmfc from env vars
ekouts Nov 16, 2023
1495671
Make stagedir if it doesn't exist
ekouts Nov 16, 2023
e963330
Merge branch 'develop' of https://github.com/reframe-hpc/reframe into…
ekouts Nov 16, 2023
b54ba5c
Skip module init
ekouts Nov 21, 2023
bd8e796
Fix formatting
ekouts Nov 21, 2023
f73ccb6
Raise JobSchedulerError in firecrest sched for python 3.6
ekouts Nov 21, 2023
feebb9e
Merge branch 'feat/skip_module_init' of github.com:ekouts/reframe int…
ekouts Nov 30, 2023
aa57107
Small fixes
ekouts Nov 30, 2023
2d5a1f8
Fix formatting
ekouts Nov 30, 2023
022455d
Add pyfirecrest in setup.cfg
ekouts Nov 30, 2023
846a44b
Merge branch 'feat/skip_module_init' of github.com:ekouts/reframe int…
ekouts Dec 8, 2023
ef5be43
Merge branch 'develop' of https://github.com/reframe-hpc/reframe into…
ekouts Dec 11, 2023
5c2278c
Handle large files transfers with firecrest
ekouts Dec 11, 2023
b7f44fd
Split firecrest scheduler implementation
ekouts Dec 20, 2023
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
26 changes: 17 additions & 9 deletions reframe/core/pipeline.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1665,7 +1665,13 @@ def _setup_paths(self):
except OSError as e:
raise PipelineError('failed to set up paths') from e

def _create_job(self, job_type, force_local=False, **job_opts):
def _create_job(
self,
job_type,
force_local=False,
clean_up_stage=False,
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could you explain the purpose of this argument?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

So my issue was that the job is not aware if it's the first to write in the stage directory of the remote filesystem. If it is, we need to cleanup this directory.

**job_opts
):
'''Setup the job related to this check.'''

if force_local:
Expand All @@ -1692,14 +1698,16 @@ def _create_job(self, job_type, force_local=False, **job_opts):
script_filename=script_name,
workdir=self._stagedir,
sched_access=self._current_partition.access,
clean_up_stage=clean_up_stage,
**job_opts)

def _setup_build_job(self, **job_opts):
self._build_job = self._create_job(
'build', self.local or self.build_locally, **job_opts
)
def _setup_build_job(self, clean_up_stage=False, **job_opts):
self._build_job = self._create_job('build',
self.local or self.build_locally,
clean_up_stage,
**job_opts)

def _setup_run_job(self, **job_opts):
def _setup_run_job(self, clean_up_stage=False, **job_opts):
self._job = self._create_job(f'run', self.local, **job_opts)

def _setup_container_platform(self):
Expand Down Expand Up @@ -1743,7 +1751,7 @@ def setup(self, partition, environ, **job_opts):
self._current_partition = partition
self._current_environ = environ
self._setup_paths()
self._setup_build_job(**job_opts)
self._setup_build_job(clean_up_stage=True, **job_opts)
self._setup_run_job(**job_opts)
self._setup_container_platform()
self._resolve_fixtures()
Expand Down Expand Up @@ -2559,7 +2567,7 @@ def setup(self, partition, environ, **job_opts):
self._current_partition = partition
self._current_environ = environ
self._setup_paths()
self._setup_run_job(**job_opts)
self._setup_run_job(clean_up_stage=True, **job_opts)
self._setup_container_platform()
self._resolve_fixtures()

Expand Down Expand Up @@ -2616,7 +2624,7 @@ def setup(self, partition, environ, **job_opts):
self._current_partition = partition
self._current_environ = environ
self._setup_paths()
self._setup_build_job(**job_opts)
self._setup_build_job(clean_up_stage=True, **job_opts)
self._setup_container_platform()
self._resolve_fixtures()

Expand Down
5 changes: 4 additions & 1 deletion reframe/core/schedulers/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -326,7 +326,8 @@ def __init__(self,
stderr=None,
sched_flex_alloc_nodes=None,
sched_access=[],
sched_options=None):
sched_options=None,
clean_up_stage=False):

self._cli_options = list(sched_options) if sched_options else []
self._name = name
Expand Down Expand Up @@ -354,6 +355,8 @@ def __init__(self,
# in finished()
self._exception = None

self._clean_up_stage = clean_up_stage

@classmethod
def create(cls, scheduler, launcher, *args, **kwargs):
ret = scheduler.make_job(*args, **kwargs)
Expand Down
Loading