Skip to content

[feature] Add option to specify number of nodes#565

Merged
jan-janssen merged 6 commits intomainfrom
num_nodes
Feb 11, 2025
Merged

[feature] Add option to specify number of nodes#565
jan-janssen merged 6 commits intomainfrom
num_nodes

Conversation

@jan-janssen
Copy link
Member

@jan-janssen jan-janssen commented Feb 10, 2025

Summary by CodeRabbit

  • New Features

    • Enhanced job submission flexibility by introducing new options to specify the number of nodes and enable exclusive execution. These updates allow users to tailor job allocation and resource management more precisely for varying workload requirements.
    • Updated SLURM command generation to include new parameters for improved resource management.
  • Documentation

    • Updated documentation for executors to reflect the new parameters and their usage.

@coderabbitai
Copy link
Contributor

coderabbitai bot commented Feb 10, 2025

Caution

Review failed

The pull request is closed.

Walkthrough

This update introduces two optional parameters, num_nodes and exclusive, into the job spawner classes. In the Flux implementation, the FluxPythonSpawner constructor now assigns these parameters to instance variables and utilizes them in the bootup method for job specification creation. Similarly, for SLURM, the SrunSpawner constructor and the generate_slurm_command function are enhanced to accept these parameters, enabling the dynamic construction of SLURM commands with new flags for node count and exclusivity.

Changes

File(s) Change Summary
executorlib/.../flux.py Added optional parameters num_nodes and exclusive to FluxPythonSpawner.__init__; created _num_nodes and _exclusive variables; updated bootup to use them.
executorlib/.../slurm.py Added optional parameters num_nodes and exclusive to SrunSpawner.__init__ and generate_slurm_command; updated command generation to include -N and --exact flags.
executorlib/.../interfaces/flux.py Removed openmpi_oversubscribe and slurm_cmd_args from resource_dict; added num_nodes and exclusive to FluxJobExecutor, FluxClusterExecutor, and create_flux_executor.
executorlib/.../interfaces/slurm.py Added num_nodes and exclusive parameters to SlurmJobExecutor and create_slurm_executor, enhancing resource management.
tests/.../test_pysqa_subprocess.py Updated generate_slurm_command to include new parameters; modified expected command list length and content to reflect changes.

Sequence Diagram(s)

sequenceDiagram
    participant U as User
    participant F as FluxPythonSpawner
    participant J as JobspecV1
    U->>F: Call bootup(command_lst)
    F->>J: Create job spec using _num_nodes & _exclusive via from_command
    F->>J: Create job spec using _num_nodes & _exclusive via from_nest_command
    J-->>F: Return job specs
Loading
sequenceDiagram
    participant U as User
    participant S as SrunSpawner
    participant G as generate_slurm_command
    U->>S: Call generate_command()
    S->>G: Invoke with _num_nodes & _exclusive
    G-->>S: Return command list with flags (-N, --exact)
    S-->>U: Return complete SLURM command
Loading

Possibly related PRs

  • [bug] SLURM: Fix CPUs per task #569: The changes in the main PR and the retrieved PR are related as both involve modifications to the generate_slurm_command function in executorlib/interactive/slurm.py, with the main PR adding new parameters while the retrieved PR fixes the formatting of an existing parameter.

Poem

I hop through the code with joyous flair,
New options added with a gentle air.
Nodes and flags in a rhythmic dance,
Commanding jobs with every chance.
With whiskers twitching, I celebrate the change—
A bunny’s delight in a code rearranged!
🐇✨


📜 Recent review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 68f1e4c and d599a76.

📒 Files selected for processing (5)
  • executorlib/interactive/flux.py (4 hunks)
  • executorlib/interactive/slurm.py (7 hunks)
  • executorlib/interfaces/flux.py (3 hunks)
  • executorlib/interfaces/slurm.py (3 hunks)
  • tests/test_pysqa_subprocess.py (1 hunks)
✨ Finishing Touches
  • 📝 Generate Docstrings (Beta)

Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media?

❤️ Share
🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

  • Review comments: Directly reply to a review comment made by CodeRabbit. Example:
    • I pushed a fix in commit <commit_id>, please review it.
    • Generate unit testing code for this file.
    • Open a follow-up GitHub issue for this discussion.
  • Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
    • @coderabbitai generate unit testing code for this file.
    • @coderabbitai modularize this function.
  • PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
    • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
    • @coderabbitai read src/utils.ts and generate unit testing code.
    • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
    • @coderabbitai help me debug CodeRabbit configuration file.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

  • @coderabbitai pause to pause the reviews on a PR.
  • @coderabbitai resume to resume the paused reviews.
  • @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
  • @coderabbitai full review to do a full review from scratch and review all the files again.
  • @coderabbitai summary to regenerate the summary of the PR.
  • @coderabbitai generate docstrings to generate docstrings for this PR. (Beta)
  • @coderabbitai resolve resolve all the CodeRabbit review comments.
  • @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
  • @coderabbitai help to get help.

Other keywords and placeholders

  • Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
  • Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
  • Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

  • You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
  • Please see the configuration documentation for more information.
  • If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

  • Visit our Documentation for detailed information on how to use CodeRabbit.
  • Join our Discord Community to get help, request features, and share feedback.
  • Follow us on X/Twitter for updates and announcements.

Copy link
Contributor

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

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

Actionable comments posted: 1

🧹 Nitpick comments (3)
executorlib/interactive/slurm.py (2)

35-45: Update docstring to include new parameters.

The docstring is missing documentation for the new parameters num_nodes and exclusive.

Add the following lines to the docstring:

            gpus_per_core (int, optional): The number of GPUs per core. Defaults to 0.
+           num_nodes (int, optional): The number of nodes to allocate. Defaults to None.
+           exclusive (bool, optional): Whether to request exclusive node access. Defaults to False.
            openmpi_oversubscribe (bool, optional): Whether to oversubscribe the cores. Defaults to False.

93-105: Update docstring to include new parameters.

The docstring is missing documentation for the new parameters num_nodes and exclusive.

Add the following lines to the docstring:

        gpus_per_core (int, optional): The number of GPUs per core. Defaults to 0.
+       num_nodes (int, optional): The number of nodes to allocate. Defaults to None.
+       exclusive (bool, optional): Whether to request exclusive node access. Defaults to False.
        openmpi_oversubscribe (bool, optional): Whether to oversubscribe the cores. Defaults to False.
executorlib/interactive/flux.py (1)

24-37: Update docstring to include new parameters.

The docstring is missing documentation for the new parameters num_nodes and exclusive.

Add the following lines to the docstring:

        gpus_per_core (int, optional): The number of GPUs per base. Defaults to 0.
+       num_nodes (int, optional): The number of nodes to allocate. Defaults to None.
+       exclusive (bool, optional): Whether to request exclusive node access. Defaults to False.
        openmpi_oversubscribe (bool, optional): Whether to oversubscribe. Defaults to False.
📜 Review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between f7de7f7 and 68f1e4c.

📒 Files selected for processing (2)
  • executorlib/interactive/flux.py (3 hunks)
  • executorlib/interactive/slurm.py (5 hunks)
⏰ Context from checks skipped due to timeout of 90000ms (16)
  • GitHub Check: unittest_openmpi (ubuntu-latest, 3.10)
  • GitHub Check: unittest_openmpi (ubuntu-latest, 3.11)
  • GitHub Check: unittest_mpich (ubuntu-latest, 3.11)
  • GitHub Check: unittest_openmpi (ubuntu-latest, 3.12)
  • GitHub Check: unittest_mpich (ubuntu-latest, 3.12)
  • GitHub Check: unittest_openmpi (ubuntu-latest, 3.13)
  • GitHub Check: unittest_win
  • GitHub Check: unittest_mpich (ubuntu-latest, 3.13)
  • GitHub Check: unittest_openmpi (macos-latest, 3.13)
  • GitHub Check: unittest_old
  • GitHub Check: unittest_mpich (macos-latest, 3.13)
  • GitHub Check: unittest_flux_openmpi
  • GitHub Check: unittest_flux_mpich
  • GitHub Check: notebooks
  • GitHub Check: benchmark (ubuntu-latest, 3.13, .ci_support/environment-mpich.yml)
  • GitHub Check: benchmark (ubuntu-latest, 3.13, .ci_support/environment-openmpi.yml)
🔇 Additional comments (1)
executorlib/interactive/flux.py (1)

87-103: LGTM!

The implementation correctly passes the node count and exclusivity parameters to both job specification methods, maintaining consistency with the SLURM implementation.

if num_nodes is not None:
command_prepend_lst += ["-N", str(num_nodes)]
if threads_per_core > 1:
command_prepend_lst += ["--cpus-per-task" + str(threads_per_core)]
Copy link
Contributor

Choose a reason for hiding this comment

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

⚠️ Potential issue

Fix missing = in --cpus-per-task flag.

The --cpus-per-task flag is missing the = separator, which will cause the command to fail.

-        command_prepend_lst += ["--cpus-per-task" + str(threads_per_core)]
+        command_prepend_lst += ["--cpus-per-task=" + str(threads_per_core)]
📝 Committable suggestion

‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.

Suggested change
command_prepend_lst += ["--cpus-per-task" + str(threads_per_core)]
command_prepend_lst += ["--cpus-per-task=" + str(threads_per_core)]

@jan-janssen jan-janssen marked this pull request as draft February 10, 2025 19:01
@codecov
Copy link

codecov bot commented Feb 11, 2025

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 95.91%. Comparing base (ca707f9) to head (d599a76).
Report is 1 commits behind head on main.

Additional details and impacted files
@@            Coverage Diff             @@
##             main     #565      +/-   ##
==========================================
+ Coverage   95.89%   95.91%   +0.02%     
==========================================
  Files          26       26              
  Lines        1168     1176       +8     
==========================================
+ Hits         1120     1128       +8     
  Misses         48       48              

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

@jan-janssen
Copy link
Member Author

Documentation is still missing.

@jan-janssen jan-janssen marked this pull request as ready for review February 11, 2025 11:47
@jan-janssen jan-janssen merged commit 0ffd312 into main Feb 11, 2025
30 checks passed
@jan-janssen jan-janssen deleted the num_nodes branch February 11, 2025 11:47
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant