elasticgrid 0.1.0__tar.gz

elasticgrid-0.1.0/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

elasticgrid-0.1.0/PKG-INFO

@@ -0,0 +1,146 @@
+Metadata-Version: 2.4
+Name: elasticgrid
+Version: 0.1.0
+Summary: Cross-cloud elastic training grid for variable-size workloads
+License: Apache-2.0
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Programming Language :: Python :: 3.15
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: iroh-tinker>=0.3.0
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0; extra == "dev"
+Requires-Dist: pytest-asyncio>=0.23; extra == "dev"
+Requires-Dist: ruff>=0.5; extra == "dev"
+Requires-Dist: mypy>=1.10; extra == "dev"
+Dynamic: license-file
+
+# elasticgrid
+
+Cross-cloud elastic training grid for variable-size workloads, built on
+[iroh-tinker](https://github.com/scairesearch/iroh_tinker).
+
+elasticgrid is the control plane in front of iroh-tinker's multi-cloud launch
+layer. It answers two questions:
+
+* **How big should this job be right now?** A rolling window of training
+  steps (step time, queue time, throughput) feeds a scheduler that grows the
+  job when workers are waiting and shrinks it when the job is comfortably
+  faster than the target, with bounds, a cooldown and a deadline rule.
+* **Where should the nodes run?** A placement plan spreads the nodes over the
+  available providers, respects a spot/on-demand budget, costs the placement
+  and renders it as an iroh-tinker `LaunchSpec`.
+
+Nothing here provisions anything by itself: the placement is a plan, and
+iroh-tinker's `JobManager` executes it.
+
+## Install
+
+```bash
+pip install elasticgrid
+pip install -e ".[dev]"           # from a checkout
+```
+
+elasticgrid depends on the public `iroh-tinker` surface only.
+
+## Built on the iroh-tinker public surface
+
+| API | Used for |
+|---|---|
+| `iroh_tinker.cloud.spec.LaunchSpec` / `ResourcesSpec` / `RendezvousSpec` | the launch spec a placement renders into |
+| `iroh_tinker.cloud.job.JobManager` | executing the plan |
+| `iroh_tinker.hw.HardwareContext` / `infer_topology` / `select_topology_params` | topology hints for the placement |
+
+`iroh_tinker.AllreduceAlgorithm` is **not** exported from the top-level
+package; it lives in `iroh_tinker.comm`. elasticgrid does not depend on it.
+
+## CLI
+
+```bash
+elasticgrid providers                        # the configured grid
+elasticgrid plan --nodes 64                 # placement + cost
+elasticgrid plan --nodes 64 --max-spot-fraction 0.5
+elasticgrid spec --nodes 64 --name my-job   # the iroh-tinker launch spec
+elasticgrid simulate --samples steps.json   # what the scheduler would do
+```
+
+Every command accepts `--json`.
+
+## The scale decision
+
+The scheduler reads a window of step samples and applies the rules in order:
+
+1. **Never scale on thin evidence.** Fewer than `min_samples` observations
+   means hold.
+2. **Respect the bounds.** The target is clamped to `[min_nodes, max_nodes]`.
+3. **Honour the cooldown.** After a change, wait `cooldown_s`. Elastic
+   scaling without a cooldown oscillates.
+4. **Queue-bound means scale up.** If 20% or more of the step was spent
+   waiting for a worker, the job needs more workers.
+5. **Idle means scale down.** If the step is well inside `target_step_s` and
+   nobody is waiting, the current size is more than enough.
+6. **Do not scale up past the deadline.** Workers that cannot finish before
+   the deadline cost money and save nothing.
+
+Every decision carries the signals it was based on, so it can be replayed and
+reviewed:
+
+```json
+{
+  "action": "scale_up",
+  "current_nodes": 8,
+  "target_nodes": 16,
+  "reason": "80% of the step was spent waiting for a worker; scaling up 8 -> 16",
+  "signals": {"queue_fraction": 0.8, "mean_step_s": 10.0, "...": "..."}
+}
+```
+
+## The placement
+
+`GridPlanner.plan(nodes)` returns a placement: how many nodes each provider
+takes, what it costs per hour, and the ordered infra references that
+iroh-tinker fails over through.
+
+The policy is explicit:
+
+* providers are filled cheapest first;
+* `max_spot_fraction` caps the share of nodes on spot capacity;
+* if the spot budget cannot hold the job, the remaining nodes are placed
+  anyway, because a job that cannot start is worse than a job that breaks
+  the policy;
+* the placement is a pure function of (nodes, providers, policy), so the
+  same plan always gives the same answer.
+
+## Tests
+
+```bash
+pip install -e ".[dev]"
+pytest
+```
+
+The suite is credential-free: the planner and the scheduler are pure
+functions and are tested directly.
+
+## Layout
+
+```
+src/elasticgrid/
+  metrics.py   step samples and the rolling window of signals
+  scheduler.py the scale decision (bounds, cooldown, deadline)
+  grid.py      providers, placement, cost, launch spec
+  cli.py       elasticgrid providers | plan | spec | simulate
+```
+
+## Licence
+
+Apache-2.0. elasticgrid is a separate project from iroh-tinker, which stays
+MIT OR Apache-2.0.

elasticgrid-0.1.0/README.md

@@ -0,0 +1,120 @@
+# elasticgrid
+
+Cross-cloud elastic training grid for variable-size workloads, built on
+[iroh-tinker](https://github.com/scairesearch/iroh_tinker).
+
+elasticgrid is the control plane in front of iroh-tinker's multi-cloud launch
+layer. It answers two questions:
+
+* **How big should this job be right now?** A rolling window of training
+  steps (step time, queue time, throughput) feeds a scheduler that grows the
+  job when workers are waiting and shrinks it when the job is comfortably
+  faster than the target, with bounds, a cooldown and a deadline rule.
+* **Where should the nodes run?** A placement plan spreads the nodes over the
+  available providers, respects a spot/on-demand budget, costs the placement
+  and renders it as an iroh-tinker `LaunchSpec`.
+
+Nothing here provisions anything by itself: the placement is a plan, and
+iroh-tinker's `JobManager` executes it.
+
+## Install
+
+```bash
+pip install elasticgrid
+pip install -e ".[dev]"           # from a checkout
+```
+
+elasticgrid depends on the public `iroh-tinker` surface only.
+
+## Built on the iroh-tinker public surface
+
+| API | Used for |
+|---|---|
+| `iroh_tinker.cloud.spec.LaunchSpec` / `ResourcesSpec` / `RendezvousSpec` | the launch spec a placement renders into |
+| `iroh_tinker.cloud.job.JobManager` | executing the plan |
+| `iroh_tinker.hw.HardwareContext` / `infer_topology` / `select_topology_params` | topology hints for the placement |
+
+`iroh_tinker.AllreduceAlgorithm` is **not** exported from the top-level
+package; it lives in `iroh_tinker.comm`. elasticgrid does not depend on it.
+
+## CLI
+
+```bash
+elasticgrid providers                        # the configured grid
+elasticgrid plan --nodes 64                 # placement + cost
+elasticgrid plan --nodes 64 --max-spot-fraction 0.5
+elasticgrid spec --nodes 64 --name my-job   # the iroh-tinker launch spec
+elasticgrid simulate --samples steps.json   # what the scheduler would do
+```
+
+Every command accepts `--json`.
+
+## The scale decision
+
+The scheduler reads a window of step samples and applies the rules in order:
+
+1. **Never scale on thin evidence.** Fewer than `min_samples` observations
+   means hold.
+2. **Respect the bounds.** The target is clamped to `[min_nodes, max_nodes]`.
+3. **Honour the cooldown.** After a change, wait `cooldown_s`. Elastic
+   scaling without a cooldown oscillates.
+4. **Queue-bound means scale up.** If 20% or more of the step was spent
+   waiting for a worker, the job needs more workers.
+5. **Idle means scale down.** If the step is well inside `target_step_s` and
+   nobody is waiting, the current size is more than enough.
+6. **Do not scale up past the deadline.** Workers that cannot finish before
+   the deadline cost money and save nothing.
+
+Every decision carries the signals it was based on, so it can be replayed and
+reviewed:
+
+```json
+{
+  "action": "scale_up",
+  "current_nodes": 8,
+  "target_nodes": 16,
+  "reason": "80% of the step was spent waiting for a worker; scaling up 8 -> 16",
+  "signals": {"queue_fraction": 0.8, "mean_step_s": 10.0, "...": "..."}
+}
+```
+
+## The placement
+
+`GridPlanner.plan(nodes)` returns a placement: how many nodes each provider
+takes, what it costs per hour, and the ordered infra references that
+iroh-tinker fails over through.
+
+The policy is explicit:
+
+* providers are filled cheapest first;
+* `max_spot_fraction` caps the share of nodes on spot capacity;
+* if the spot budget cannot hold the job, the remaining nodes are placed
+  anyway, because a job that cannot start is worse than a job that breaks
+  the policy;
+* the placement is a pure function of (nodes, providers, policy), so the
+  same plan always gives the same answer.
+
+## Tests
+
+```bash
+pip install -e ".[dev]"
+pytest
+```
+
+The suite is credential-free: the planner and the scheduler are pure
+functions and are tested directly.
+
+## Layout
+
+```
+src/elasticgrid/
+  metrics.py   step samples and the rolling window of signals
+  scheduler.py the scale decision (bounds, cooldown, deadline)
+  grid.py      providers, placement, cost, launch spec
+  cli.py       elasticgrid providers | plan | spec | simulate
+```
+
+## Licence
+
+Apache-2.0. elasticgrid is a separate project from iroh-tinker, which stays
+MIT OR Apache-2.0.

elasticgrid-0.1.0/pyproject.toml

@@ -0,0 +1,77 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "elasticgrid"
+version = "0.1.0"
+description = "Cross-cloud elastic training grid for variable-size workloads"
+readme = "README.md"
+license = {text = "Apache-2.0"}
+requires-python = ">=3.10"
+dependencies = [
+    "iroh-tinker>=0.3.0",
+]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: Apache Software License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Programming Language :: Python :: 3.14",
+    "Programming Language :: Python :: 3.15",
+]
+
+[project.scripts]
+elasticgrid = "elasticgrid.cli:main"
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=8.0",
+    "pytest-asyncio>=0.23",
+    "ruff>=0.5",
+    "mypy>=1.10",
+]
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools.package-data]
+elasticgrid = ["py.typed"]
+
+[tool.ruff]
+line-length = 100
+target-version = "py310"
+src = ["src", "tests"]
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "UP", "W", "B", "C4", "PTH", "T20", "TID"]
+ignore = []
+
+[tool.ruff.lint.per-file-ignores]
+# The CLI is the one place that is allowed to print.
+"src/elasticgrid/cli.py" = ["T20"]
+
+[tool.mypy]
+python_version = "3.10"
+ignore_missing_imports = true
+warn_return_any = true
+warn_unused_configs = true
+disallow_untyped_defs = true
+disallow_incomplete_defs = true
+check_untyped_defs = true
+no_implicit_optional = true
+strict_optional = true
+warn_redundant_casts = true
+warn_unused_ignores = true
+show_error_codes = true
+pretty = true
+
+[tool.pytest.ini_options]
+asyncio_mode = "auto"
+testpaths = ["tests"]
+python_files = ["test_*.py"]
+python_functions = ["test_*"]

elasticgrid-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

elasticgrid-0.1.0/src/elasticgrid/__init__.py

@@ -0,0 +1,40 @@
+"""elasticgrid: a cross-cloud elastic training grid.
+
+elasticgrid decides **how big** a training job should be right now and
+**where** those nodes should run. It is the control plane in front of
+iroh-tinker's multi-cloud launch layer:
+
+* :mod:`elasticgrid.metrics` collects the signals (step time, queue time,
+  throughput) from a rolling window of training steps;
+* :mod:`elasticgrid.scheduler` turns those signals into a scale decision,
+  with bounds, a cooldown and a deadline rule;
+* :mod:`elasticgrid.grid` places the nodes over the available providers and
+  costs the placement, then renders an iroh-tinker ``LaunchSpec``.
+
+Nothing here provisions anything by itself: the placement is a plan, and
+iroh-tinker's ``JobManager`` executes it.
+"""
+from __future__ import annotations
+
+__version__ = "0.1.0"
+
+from .grid import GridPlanner, Placement, Provider, build_launch_spec, providers_from_dicts
+from .metrics import MetricsWindow, StepSample
+from .scheduler import ElasticScheduler, ScaleAction, ScaleDecision
+
+__all__ = [
+    "__version__",
+    # metrics
+    "MetricsWindow",
+    "StepSample",
+    # scheduler
+    "ElasticScheduler",
+    "ScaleAction",
+    "ScaleDecision",
+    # grid
+    "GridPlanner",
+    "Placement",
+    "Provider",
+    "build_launch_spec",
+    "providers_from_dicts",
+]