DEVX-146: fix: scale check_test_speed limits on CI runners
Post-merge / detect-and-configure (push) Successful in 20s
Post-merge / release-and-maintain (push) Successful in 2m2s

Co-authored-by: emil User <emil.simeonov@tutanota.com>
This commit was merged in pull request #233.
This commit is contained in:
2026-08-03 21:40:17 +00:00
committed by emo
parent 32193a0e6d
commit 9bb461e12f
5 changed files with 115 additions and 10 deletions
+48 -6
View File
@@ -11,6 +11,18 @@ Usage:
The module runs ``make test-unit`` with ``PYTEST_ADDOPTS=--durations=0`` so
that pytest emits per-test timing lines alongside the summary. Both the
total wall-clock time and individual test durations are parsed and validated.
CI runner scaling
-----------------
CI runners (Gitea Actions Docker containers) are typically 3-4x slower than
local development machines due to shared CPU, fewer cores, and container
overhead. When the ``CI`` environment variable is set (standard CI
convention), both the total and per-test limits are multiplied by
``CI_SCALE_FACTOR`` (default 4) to account for this. This keeps the local
budget strict while preventing false failures on slower CI runners.
The scale factor can be overridden via the ``DEVX_CI_SCALE_FACTOR``
environment variable.
"""
from __future__ import annotations
@@ -27,6 +39,12 @@ DEFAULT_MAX_SECONDS = 10.0
DEFAULT_MAX_SINGLE_SECONDS = 0.5
TEST_COMMAND = ["make", "test-unit"]
# CI runners are typically 3-4x slower than local machines (shared CPU,
# fewer cores, container overhead). Scale limits up when running on CI
# so the gate catches real regressions, not infrastructure slowness.
CI_SCALE_FACTOR = float(os.environ.get("DEVX_CI_SCALE_FACTOR", "4"))
_IS_CI = bool(os.environ.get("CI") or os.environ.get("GITEA_ACTIONS"))
# Matches pytest summary line: "234 passed in 0.70s"
_TIMING_RE = re.compile(r"(\d+) passed.* in ([0-9.]+)s")
@@ -38,6 +56,13 @@ _TIMING_RE = re.compile(r"(\d+) passed.* in ([0-9.]+)s")
_DURATION_LINE_RE = re.compile(r"^(\d+\.?\d*)s\s+call\s+(.+)$")
def _ci_scale_limit(limit: float) -> float:
"""Scale a time limit by the CI factor when running on CI."""
if _IS_CI:
return limit * CI_SCALE_FACTOR
return limit
def run_tests() -> tuple[str, str]:
"""Execute the unit-test suite and return (stdout, stderr).
@@ -123,21 +148,38 @@ def check_per_test_speed(
def main(max_seconds: float, max_single_seconds: float) -> None:
"""Run tests, parse timings, and enforce both budgets."""
# Scale limits for CI runners (slower CPU, fewer workers).
effective_max = _ci_scale_limit(max_seconds)
effective_single = _ci_scale_limit(max_single_seconds)
if _IS_CI:
click.echo(
_(
"[check-test-speed] CI environment detected — scaling limits by {factor}x "
"(total: {orig}s → {eff}s, per-test: {orig_s}s → {eff_s}s)",
factor=CI_SCALE_FACTOR,
orig=max_seconds,
eff=effective_max,
orig_s=max_single_seconds,
eff_s=effective_single,
)
)
stdout, stderr = run_tests()
combined = stdout + "\n" + stderr
click.echo(combined, err=False)
duration = parse_duration(combined)
check_speed(duration, max_seconds)
check_speed(duration, effective_max)
if max_single_seconds > 0:
if effective_single > 0:
per_test = parse_per_test_durations(combined)
violations = check_per_test_speed(per_test, max_single_seconds)
violations = check_per_test_speed(per_test, effective_single)
if violations:
msg = _(
"Per-test speed check FAILED: {count} test(s) exceed {limit}s limit.",
count=len(violations),
limit=max_single_seconds,
limit=effective_single,
)
click.echo(f"\n{msg}", err=True)
for v in violations:
@@ -148,8 +190,8 @@ def main(max_seconds: float, max_single_seconds: float) -> None:
_(
"Unit tests passed in {duration:.2f}s (under {max}s limit, all tests under {single}s per-test limit).",
duration=duration,
max=max_seconds,
single=max_single_seconds,
max=effective_max,
single=effective_single,
)
)
+9 -1
View File
@@ -3822,5 +3822,13 @@
"pl": "importlib.reload({mod}) called {n} time(s) in test '{test}' — odd count leaves module in modified state. Add a final reload to restore defaults or wrap in try/finally.",
"ru": "importlib.reload({mod}) called {n} time(s) in test '{test}' — odd count leaves module in modified state. Add a final reload to restore defaults or wrap in try/finally.",
"zh": "importlib.reload({mod}) called {n} time(s) in test '{test}' — odd count leaves module in modified state. Add a final reload to restore defaults or wrap in try/finally."
},
"[check-test-speed] CI environment detected — scaling limits by {factor}x (total: {orig}s → {eff}s, per-test: {orig_s}s → {eff_s}s)": {
"en": "[check-test-speed] CI environment detected — scaling limits by {factor}x (total: {orig}s → {eff}s, per-test: {orig_s}s → {eff_s}s)",
"bg": "[check-test-speed] CI environment detected — scaling limits by {factor}x (total: {orig}s → {eff}s, per-test: {orig_s}s → {eff_s}s)",
"de": "[check-test-speed] CI environment detected — scaling limits by {factor}x (total: {orig}s → {eff}s, per-test: {orig_s}s → {eff_s}s)",
"pl": "[check-test-speed] CI environment detected — scaling limits by {factor}x (total: {orig}s → {eff}s, per-test: {orig_s}s → {eff_s}s)",
"ru": "[check-test-speed] CI environment detected — scaling limits by {factor}x (total: {orig}s → {eff}s, per-test: {orig_s}s → {eff_s}s)",
"zh": "[check-test-speed] CI environment detected — scaling limits by {factor}x (total: {orig}s → {eff}s, per-test: {orig_s}s → {eff_s}s)"
}
}
}