Remove the hand-rolled analysis submit path (gitea #83)

b2luigi's AnalysisComputeTask now submits the per-(plot, chunk) jobs, so the
bespoke submit-file generator has nothing left to do:

- giant/analysis/condor.py -> giant/analysis/run.py, dropping SubmitConfig,
  the wrapper/submit-description templates, _job_walltimes and
  _resolve_giant_executable. What stays is the actual logic — prep,
  RunMeta, the rollout-YAML loading, compute_reduced/compute_one and
  merge_one/merge_all — and the module no longer submits anything, hence
  the name.
- `giant analyze submit` is gone; prep / compute-one / merge-one / list /
  render / metrics remain as the single-step primitives the workflow calls.
- tests/test_condor.py -> tests/test_analysis_run.py, minus the
  submit-description cases.

CLAUDE.md and README.md document the workflow package, the new `workflow`
extra, and — for whenever condor-gpu-train-rollout is merged — that its
train-submit/rollout-submit commands are deliberately superseded and must
not be revived.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
2026-08-26 11:59:47 +02:00
parent a482b04761
commit fc19934ba6
12 changed files with 61 additions and 345 deletions
@@ -1,8 +1,7 @@
"""Tests for the rollout-YAML(s) → run-directory flow, compute, and submit."""
"""Tests for the rollout-YAML(s) → run-directory flow, compute, and merge."""
from __future__ import annotations
import sys
from pathlib import Path
import pyarrow.parquet as pq
@@ -11,8 +10,6 @@ import yaml
from giant.analysis import (
RunMeta,
SubmitConfig,
catalog_ids,
compute_one,
compute_reduced,
derive_run_dir,
@@ -20,10 +17,8 @@ from giant.analysis import (
load_rollout_yamls,
merge_one,
prep,
write_submit,
)
from giant.analysis.catalog import get_spec
from giant.analysis.condor import Context
from giant.analysis.run import Context
from giant.analysis.reduced import Partial, Reduced
from giant.constants import PREDICT_COORD_METADATA_KEY, ROLLOUT_COORD_VALUE
from tests.test_analysis_reduce import _reference_frame, _rollout_frame
@@ -86,14 +81,6 @@ def _write_two_inputs(tmp_path: Path) -> tuple[Path, Path]:
return paths[0], paths[1]
def _fake_venv(repo_dir: Path) -> None:
"""Stand in for a `uv sync`'d venv: write_submit checks `.venv/bin/giant` exists."""
giant = repo_dir / ".venv" / "bin" / "giant"
giant.parent.mkdir(parents=True, exist_ok=True)
giant.write_text("#!/bin/bash\n")
giant.chmod(0o755)
def _prep(rollout_yamls, run_dir: str | Path | None = None, chunks: int = 1, labels=None) -> Path:
"""``prep`` with small test-sized context bins/sampling."""
return prep(
@@ -313,73 +300,6 @@ def test_compute_reduced_rejects_out_of_range_chunk(tmp_path: Path):
compute_one("marginal_edep", run_dir, chunk_index=1)
def test_write_submit_description(tmp_path: Path):
run_dir = _prep([_write_inputs(tmp_path)])
_fake_venv(tmp_path)
cfg = SubmitConfig(run_dir=run_dir, accounting_group="cms", repo_dir=tmp_path)
txt = write_submit(cfg).read_text()
assert "universe = docker" in txt
assert "docker_image = cverstege/alma9-gridjob" in txt
assert "requirements = TARGET.ProvidesETPResources" in txt
assert "accounting_group = cms" in txt
assert "+RequestWalltime = $(walltime)" in txt
assert "queue plotid,chunk,walltime from" in txt
jobs = [line.split(",") for line in (run_dir / "jobs.txt").read_text().split()]
assert [i for i, _, _ in jobs] == catalog_ids()
assert all(k == "0" for _, k, _ in jobs) # n_chunks=1 default
assert all(int(w) > 0 for _, _, w in jobs)
wrapper = run_dir / "run_compute.sh"
assert wrapper.exists() and (wrapper.stat().st_mode & 0o111)
body = wrapper.read_text()
assert "giant analyze compute-one --id" in body
assert "--chunk" in body and "--run-dir" in body
def test_write_submit_requires_synced_venv(tmp_path: Path, monkeypatch: pytest.MonkeyPatch):
run_dir = _prep([_write_inputs(tmp_path)])
cfg = SubmitConfig(run_dir=run_dir, accounting_group="cms", repo_dir=tmp_path)
# No `giant` next to the (fake) active interpreter, so this falls through
# to repo_dir/.venv/bin/giant, which _write_inputs/_prep also didn't create.
monkeypatch.setattr(sys, "executable", str(tmp_path / "not-a-venv" / "bin" / "python"))
with pytest.raises(FileNotFoundError, match="uv sync"):
write_submit(cfg)
def test_write_submit_remote_flag(tmp_path: Path):
run_dir = _prep([_write_inputs(tmp_path)])
_fake_venv(tmp_path)
cfg = SubmitConfig(run_dir=run_dir, accounting_group="cms", repo_dir=tmp_path, remote=True)
txt = write_submit(cfg).read_text()
assert "+RemoteJob = True" in txt
assert "ProvidesETPResources" not in txt
def test_write_submit_chunks_respect_chunkable(tmp_path: Path):
assert get_spec("router_gating").chunkable is False
run_dir = _prep([_write_inputs(tmp_path)], chunks=4)
_fake_venv(tmp_path)
cfg = SubmitConfig(run_dir=run_dir, accounting_group="cms", repo_dir=tmp_path, n_chunks=4)
write_submit(cfg)
jobs = [line.split(",") for line in (run_dir / "jobs.txt").read_text().split()]
counts: dict[str, int] = {}
for spec_id, _, _ in jobs:
counts[spec_id] = counts.get(spec_id, 0) + 1
assert counts["marginal_edep"] == 4
assert counts["router_gating"] == 1 # chunkable=False, ignores n_chunks
def test_write_submit_rejects_n_chunks_mismatch_with_run_meta(tmp_path: Path):
"""cfg.n_chunks must match the n_chunks the run_dir was actually prepped
with RunMeta.rows_per_chunk is sized to the prepped value, so a
mismatch would otherwise surface as a confusing IndexError deep inside
_job_walltimes instead of a clear error here."""
run_dir = _prep([_write_inputs(tmp_path)], chunks=2)
_fake_venv(tmp_path)
cfg = SubmitConfig(run_dir=run_dir, accounting_group="cms", repo_dir=tmp_path, n_chunks=4)
with pytest.raises(ValueError, match="n_chunks"):
write_submit(cfg)
def test_estimate_runtime_s_scales_with_rows_and_margin():
from giant.analysis import RUNTIME_SAFETY_MARGIN, estimate_runtime_s
from giant.analysis.runtime_estimate import _FIXED_OVERHEAD_S
@@ -389,18 +309,3 @@ def test_estimate_runtime_s_scales_with_rows_and_margin():
large = estimate_runtime_s("marginal_edep", 100_000_000)
assert small >= (1 + RUNTIME_SAFETY_MARGIN) * _FIXED_OVERHEAD_S
assert large > small # bigger chunk -> longer estimate
def test_write_submit_walltime_grows_with_chunk_rows(tmp_path: Path):
"""A chunked run's later job walltimes track that chunk's row count."""
from giant.analysis.runtime_estimate import estimate_runtime_s
run_dir = _prep([_write_inputs(tmp_path)], chunks=2)
meta = RunMeta.load(run_dir / "run_meta.json")
_fake_venv(tmp_path)
cfg = SubmitConfig(run_dir=run_dir, accounting_group="cms", repo_dir=tmp_path, n_chunks=2)
write_submit(cfg)
jobs = {(i, int(k)): int(w) for i, k, w in (line.split(",") for line in (run_dir / "jobs.txt").read_text().split())}
for chunk in range(2):
expected = estimate_runtime_s("marginal_edep", meta.rows_per_chunk[chunk])
assert jobs[("marginal_edep", chunk)] == expected
+5 -5
View File
@@ -206,21 +206,21 @@ def test_render_all_run_gallery_invokes_subprocess(tmp_path: Path, monkeypatch):
assert kwargs == {"check": True}
def test_render_run_glues_condor_run_meta_into_render_all(tmp_path: Path, monkeypatch):
from giant.analysis import condor as condor_mod
def test_render_run_glues_run_meta_into_render_all(tmp_path: Path, monkeypatch):
from giant.analysis import run as run_mod
run_dir = tmp_path / "run"
(run_dir / "reduced").mkdir(parents=True)
merge_calls = []
monkeypatch.setattr(condor_mod, "merge_all", lambda rd: merge_calls.append(Path(rd)))
meta = condor_mod.RunMeta(
monkeypatch.setattr(run_mod, "merge_all", lambda rd: merge_calls.append(Path(rd)))
meta = run_mod.RunMeta(
rollouts=[{"name": "rollout", "path": "rollout.parquet", "plot_meta": {"checkpoint": "ckpt/best.pt"}}],
reference="reference.parquet",
run_dir=str(run_dir),
title="my-run",
)
monkeypatch.setattr(condor_mod.RunMeta, "load", classmethod(lambda cls, p: meta))
monkeypatch.setattr(run_mod.RunMeta, "load", classmethod(lambda cls, p: meta))
Reduced("s", "species", "single_hist", "Single", "x", {"edges": [0, 1], "series": {"rollout": [1]}}).save(
run_dir / "reduced" / "s.json"