Skip to main content

Run many `adaptive.Learner`s on many cores (>10k) using `mpi4py.futures`, `ipyparallel`, `dask-mpi`, or `process-pool`.

Project description

PyPI Conda Downloads Build Status Documentation Status

Run many adaptive.Learners on many cores (>10k) using mpi4py.futures, ipyparallel, or distributed.

What is this?

The Adaptive scheduler solves the following problem, you need to run more learners than you can run with a single runner and/or can use >1k cores.

ipyparallel and distributed provide very powerful engines for interactive sessions. However, when you want to connect to >1k cores it starts to struggle. Besides that, on a shared cluster there is often the problem of starting an interactive session with ample space available.

Our approach is to schedule a different job for each adaptive.Learner. The creation and running of these jobs are managed by adaptive-scheduler. This means that your calculation will definitely run, even though the cluster might be fully occupied at the moment. Because of this approach, there is almost no limit to how many cores you want to use. You can either use 10 nodes for 1 job (learner) or 1 core for 1 job (learner) while scheduling hundreds of jobs.

Everything is written such that the computation is maximally local. This means that is one of the jobs crashes, there is no problem and it will automatically schedule a new one and continue the calculation where it left off (because of Adaptive’s periodic saving functionality). Even if the central “job manager” dies, the jobs will continue to run (although no new jobs will be scheduled.)

Design goals

  1. Needs to be able to run on efficiently >30k cores

  2. Works seamlessly with the Adaptive package

  3. Minimal load on the file system

  4. Removes all boilerplate of working with a scheduler

    1. writes job script

    2. (re)submits job scripts

  5. Handles random crashes (or node evictions) with minimal data loss

  6. Preserves Python kernel and variables inside a job (in contrast to submitting jobs for every parameter)

  7. Separates the simulation definition code from the code that runs the simulation

  8. Maximizes computation locality, jobs continue to run when the main process dies

How does it work?

You create a bunch of learners and corresponding fnames such that they can be loaded, like:

import adaptive
from functools import partial

def h(x, pow, a):
    return a * x**pow

combos = adaptive.utils.named_product(
    pow=[0, 1, 2, 3, 4, 5, 6, 7, 8, 9],
    a=[0.1, 0.5],
)  # returns list of dicts, cartesian product of all values

learners = [adaptive.Learner1D(partial(h, **combo),
            bounds=(-1, 1)) for combo in combos]
fnames = [f"data/{combo}" for combo in combos]

Then you start a process that creates and submits as many job-scripts as there are learners. Like:

import adaptive_scheduler

def goal(learner):
    return learner.npoints > 200

scheduler = adaptive_scheduler.scheduler.SLURM(cores=10)  # every learner get this many cores

run_manager = adaptive_scheduler.server_support.RunManager(
    log_interval=30,  #  write info such as npoints, cpu_usage, time, etc. to the job log file
    save_interval=300,  # save the data every 300 seconds

That’s it! You can run which will display an interactive ipywidget that shows the amount of running, pending, and finished jobs, buttons to cancel your job, and other useful information.

Widget demo

But how does it really work?

The ~adaptive_scheduler.server_support.RunManager basically does the following. So, you need to create N learners and fnames (like in the section above). Then a “job manager” writes and submits max(N, max_simultaneous_jobs) job scripts but doesn’t know which learner it is going to run! This is the responsibility of the “database manager”, which keeps a database of job_id <--> learner. The job script starts a Python file in which the learner is run.

In a Jupyter notebook we can start the “job manager” and the “database manager”, and create the like:

import adaptive_scheduler
from adaptive_scheduler import server_support

# create a scheduler
scheduler = adaptive_scheduler.scheduler.SLURM(cores=10, run_script="",)

# create a new database that keeps track of job <-> learner
db_fname = "running.json"
url = (
)  # get a url where we can run the database_manager
database_manager = server_support.DatabaseManager(
   url, scheduler, db_fname, learners, fnames

# create the Python script that runs a learner (

# create unique names for the jobs
n_jobs = len(learners)
job_names = [f"test-job-{i}" for i in range(n_jobs)]

job_manager = server_support.JobManager(job_names, database_manager, scheduler)

Then when the job have been running for a while you can check server_support.parse_log_files(job_names, database_manager, scheduler).

And use scheduler.cancel(job_names) to cancel the jobs.

You don’t actually ever have to leave the Jupter notebook, take a look at the example notebook.

Jupyter notebook example

See example.ipynb.


WARNING: This is still the pre-alpha development stage.

Install the latest stable version from conda with (recommended)

conda install adaptive-scheduler

or from PyPI with

pip install adaptive_scheduler

or install master with

pip install -U

or clone the repository and do a dev install (recommended for dev)

git clone
cd adaptive-scheduler
pip install -e .


In order to not pollute the history with the output of the notebooks, please setup the git filter by executing


in the repository.

We also use pre-commit, so pip install pre_commit and run

pre-commit install

in the repository.


Right now adaptive_scheduler is only working for SLURM and PBS, however only a class like adaptive_scheduler/ would have to be implemented for another type of scheduler. Also there are no tests at all!

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

adaptive_scheduler-1.6.0.tar.gz (47.9 kB view hashes)

Uploaded source

Built Distribution

adaptive_scheduler-1.6.0-py3-none-any.whl (48.6 kB view hashes)

Uploaded py3

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Huawei Huawei PSF Sponsor Microsoft Microsoft PSF Sponsor NVIDIA NVIDIA PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page