Files
cc-ci/tests/concurrency/test_abra_dir.py
autonomic-bot 84d90fb655
All checks were successful
continuous-integration/drone/push Build is passing
test(concurrency): real-kernel suite for the restructured model — 20 tests, 19 plan cases
tests/concurrency/ — NOT in the default `pytest tests/unit` gate; run explicitly with
`pytest tests/concurrency -q`. flock/prctl/alarm are never mocked: helper subprocesses
(helpers.py) hold real locks and install the real lifetime guards; locks live in a per-test
tmp dir via CCCI_APP_LOCK_DIR; every helper (and recorded grandchild) is reaped by fixture
cleanup.

- test_locks.py (cases 1-4): SIGKILL auto-release; LOCK_NB held/unheld semantics; PEP 446
  fd-not-inherited (holder's child survives, lock still releases); same-domain second acquire
  blocks until first holder exits.
- test_janitor.py (cases 5-12): orphan reaped once + lockfile unlinked; live holder never
  reaped + logged; new-run acquire blocks until a slow reap completes (reap-under-probe-lock);
  two overlapping janitors -> exactly one reaps (flock arbitration); reboot sim (no lockfile)
  reaps immediately with no age wait; >120min-held lock flagged 'possible leaked run' and NOT
  stolen; warm/canonical names never probed (no lockfile even created); directory-as-lockfile
  and missing lock dir degrade to skip+log, never crash.
- test_lifetime.py (cases 13-16): PDEATHSIG (wrapper parent SIGKILL'd -> guarded child TERM'd,
  teardown marker, lock released); already-orphaned helper REFUSES to run (ppid race); 2s
  deadline alarm -> teardown + exit 142 + lock released; SIGTERM -> teardown + exit 143 +
  lock released.
- test_abra_dir.py (cases 17-19 + 18b): per-run dir built + $ABRA_DIR exported before the
  first abra call (recording stub abra on PATH); two CONCURRENT same-recipe fetch+checkout
  flows into different ABRA_DIRs -> divergent correct trees, canonical staged clone untouched;
  .env written through the servers/ symlink lands in the canonical path (env_get/env_set
  agree); manual runs get pid-suffixed dirs.

On cc-ci: pytest tests/concurrency -q -> 20 passed; tests/unit -> 138 passed; lint PASS.
2026-06-10 04:29:36 +00:00

176 lines
7.7 KiB
Python

"""Per-run ABRA_DIR isolation (concurrency-restructure plan, cases 17-19). Real directories,
real symlinks, real git — abra itself is replaced by a recording stub where a CLI call is
involved (case 17), because these cases test OUR dir/env plumbing, not abra."""
from __future__ import annotations
import os
import stat
import subprocess
import sys
sys.path.insert(0, os.path.dirname(__file__))
sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "..", "runner"))
import run_recipe_ci # noqa: E402
from concutil import wait_marker # noqa: E402
from harness import abra # noqa: E402
RECIPE = "fakerecipe"
def _git(cwd, *args):
subprocess.run(
["git", "-c", "user.email=t@t", "-c", "user.name=t", *args],
cwd=cwd,
check=True,
capture_output=True,
)
def _make_fake_home(tmp_path):
"""A fake $HOME with a canonical ~/.abra: servers/default + catalogue dirs, and a recipe git
repo with two tags whose data.txt differs (v1 -> 'one', v2 -> 'two', HEAD at v2)."""
home = tmp_path / "home"
(home / ".abra" / "servers" / "default").mkdir(parents=True)
(home / ".abra" / "catalogue").mkdir(parents=True)
repo = home / ".abra" / "recipes" / RECIPE
repo.mkdir(parents=True)
_git(repo, "init", "-q")
(repo / "data.txt").write_text("one\n")
_git(repo, "add", "data.txt")
_git(repo, "commit", "-qm", "v1")
_git(repo, "tag", "v1")
(repo / "data.txt").write_text("two\n")
_git(repo, "add", "data.txt")
_git(repo, "commit", "-qm", "v2")
_git(repo, "tag", "v2")
return home
def test_17_per_run_dir_built_and_exported_before_abra(tmp_path, monkeypatch):
"""Case 17: setup_run_abra_dir builds the per-run dir correctly (servers/catalogue symlinks
resolve to the canonical tree, recipes/ empty + writable) and $ABRA_DIR is exported before
the first abra call — proven by a stub `abra` on PATH that records the env it saw."""
home = _make_fake_home(tmp_path)
monkeypatch.setenv("HOME", str(home))
monkeypatch.setenv("CCCI_RUNS_DIR", str(tmp_path / "runs"))
monkeypatch.setenv("DRONE_BUILD_NUMBER", "777")
monkeypatch.setenv("ABRA_DIR", "sentinel-to-be-overwritten") # so monkeypatch restores it
d = run_recipe_ci.setup_run_abra_dir()
assert d == str(tmp_path / "runs" / "777" / "abra")
assert os.environ["ABRA_DIR"] == d
assert os.readlink(os.path.join(d, "servers")) == str(home / ".abra" / "servers")
assert os.readlink(os.path.join(d, "catalogue")) == str(home / ".abra" / "catalogue")
# symlinks RESOLVE (targets exist) and recipes/ is empty + writable
assert os.path.isdir(os.path.join(d, "servers", "default"))
assert os.path.isdir(os.path.join(d, "catalogue"))
assert os.listdir(os.path.join(d, "recipes")) == []
probe = os.path.join(d, "recipes", ".write-probe")
open(probe, "w").close()
os.remove(probe)
# idempotent re-entry (Drone build-number retry): must not raise on existing symlinks
assert run_recipe_ci.setup_run_abra_dir() == d
# stub abra records $ABRA_DIR at call time; fetch_recipe's catalogue branch invokes it
stub_dir = tmp_path / "bin"
stub_dir.mkdir()
log = tmp_path / "abra-env.log"
stub = stub_dir / "abra"
stub.write_text(f'#!/bin/sh\necho "$ABRA_DIR" >> {log}\nexit 0\n')
stub.chmod(stub.stat().st_mode | stat.S_IEXEC)
monkeypatch.setenv("PATH", f"{stub_dir}{os.pathsep}{os.environ['PATH']}")
monkeypatch.delenv("CCCI_SKIP_FETCH", raising=False)
run_recipe_ci.fetch_recipe(RECIPE, None, None)
assert log.read_text().strip() == d, "abra was called without the per-run ABRA_DIR exported"
def test_18_concurrent_same_recipe_fetch_no_cross_talk(tmp_path, monkeypatch, pool):
"""Case 18: two CONCURRENT fetch+checkout flows of the SAME recipe into different ABRA_DIRs
produce two correct, divergent trees (v1 vs v2) — the old shared-tree corruption scenario,
now structurally safe with no lock. The canonical staged clone is untouched."""
home = _make_fake_home(tmp_path)
canonical_repo = home / ".abra" / "recipes" / RECIPE
head_before = subprocess.run(
["git", "-C", canonical_repo, "rev-parse", "HEAD"], capture_output=True, text=True
).stdout.strip()
runs = {}
for name, ref in (("runA", "v1"), ("runB", "v2")):
abra_dir = tmp_path / name / "abra"
abra_dir.mkdir(parents=True)
_, out = pool.spawn(
"fetch-checkout",
RECIPE,
ref,
env_extra={
"HOME": str(home),
"ABRA_DIR": str(abra_dir),
"CCCI_SKIP_FETCH": "1",
},
)
runs[name] = (out, ref, abra_dir)
expect = {"v1": "one", "v2": "two"}
for name, (out, ref, abra_dir) in runs.items():
line = wait_marker(out, "RESULT", timeout=30)
assert line, f"{name} never produced a RESULT"
_, head, content = line.split()
assert content == expect[ref], f"{name}@{ref}: tree content {content!r}"
tree = abra_dir / "recipes" / RECIPE
assert (tree / "data.txt").read_text().strip() == expect[ref]
assert (
head
== subprocess.run(
["git", "-C", tree, "rev-parse", "HEAD"], capture_output=True, text=True
).stdout.strip()
)
# the two trees genuinely diverge AND the canonical staged clone is untouched
a = (runs["runA"][2] / "recipes" / RECIPE / "data.txt").read_text()
b = (runs["runB"][2] / "recipes" / RECIPE / "data.txt").read_text()
assert a != b
head_after = subprocess.run(
["git", "-C", canonical_repo, "rev-parse", "HEAD"], capture_output=True, text=True
).stdout.strip()
assert head_after == head_before, "canonical clone must not be touched by per-run fetches"
def test_19_env_written_through_servers_symlink_lands_canonical(tmp_path, monkeypatch):
"""Case 19: an app .env written through the per-run servers/ symlink (what abra does under
$ABRA_DIR) lands in the CANONICAL shared path — so janitor discovery and every
expanduser('~/.abra/servers/...') reader keep working unchanged."""
home = _make_fake_home(tmp_path)
monkeypatch.setenv("HOME", str(home))
monkeypatch.setenv("CCCI_RUNS_DIR", str(tmp_path / "runs"))
monkeypatch.setenv("DRONE_BUILD_NUMBER", "778")
monkeypatch.setenv("ABRA_DIR", "sentinel-to-be-overwritten")
d = run_recipe_ci.setup_run_abra_dir()
domain = "test-abc123.ci.commoninternet.net"
via_symlink = os.path.join(d, "servers", "default", f"{domain}.env")
with open(via_symlink, "w") as f:
f.write("TYPE=fakerecipe:1.0.0\nDOMAIN=placeholder\n")
canonical = home / ".abra" / "servers" / "default" / f"{domain}.env"
assert canonical.is_file(), ".env written via the symlink must land in the canonical path"
# the canonical-path readers/writers (abra.env_get/env_set use ~/.abra) see the same file
assert abra.env_get(domain, "TYPE") == "fakerecipe:1.0.0"
abra.env_set(domain, "DOMAIN", domain)
with open(via_symlink) as f:
assert f"DOMAIN={domain}" in f.read()
def test_18b_run_id_manual_fallback_is_per_process(tmp_path, monkeypatch):
"""Companion to case 18: two concurrent MANUAL runs (no DRONE_BUILD_NUMBER) must not share an
abra dir either — the manual fallback is pid-suffixed."""
home = _make_fake_home(tmp_path)
monkeypatch.setenv("HOME", str(home))
monkeypatch.setenv("CCCI_RUNS_DIR", str(tmp_path / "runs"))
monkeypatch.delenv("DRONE_BUILD_NUMBER", raising=False)
monkeypatch.delenv("CCCI_APP_DOMAIN", raising=False)
monkeypatch.delenv("CCCI_RUN_ID", raising=False)
monkeypatch.setenv("ABRA_DIR", "sentinel-to-be-overwritten")
d = run_recipe_ci.setup_run_abra_dir()
assert f"manual-{os.getpid()}" in d