Add robust PyPI dependency caching with task queue
Replace unbounded thread spawning with managed worker pool:
- New pypi_cache_tasks table tracks caching jobs
- Thread pool with 5 workers (configurable via ORCHARD_PYPI_CACHE_WORKERS)
- Automatic retries with exponential backoff (30s, 60s, then fail)
- Deduplication to prevent duplicate caching attempts
New API endpoints for visibility and control:
- GET /pypi/cache/status - queue health summary
- GET /pypi/cache/failed - list failed tasks with errors
- POST /pypi/cache/retry/{package} - retry single package
- POST /pypi/cache/retry-all - retry all failed packages
This fixes silent failures in background dependency caching where
packages would fail to cache without any tracking or retry mechanism.
This commit is contained in:
Mondo Diaz
263
backend/tests/test_pypi_cache_worker.py
Normal file
263
backend/tests/test_pypi_cache_worker.py
Normal file
@@ -0,0 +1,263 @@
|
||||
"""Tests for PyPI cache worker module."""
|
||||
|
||||
import os
|
||||
import pytest
|
||||
import re
|
||||
from datetime import datetime, timedelta
|
||||
from unittest.mock import MagicMock, patch
|
||||
from uuid import uuid4
|
||||
|
||||
import httpx
|
||||
|
||||
|
||||
def get_base_url():
|
||||
"""Get the base URL for the Orchard server from environment."""
|
||||
return os.environ.get("ORCHARD_TEST_URL", "http://localhost:8080")
|
||||
|
||||
|
||||
class TestPyPICacheTaskModel:
|
||||
"""Tests for PyPICacheTask model."""
|
||||
|
||||
def test_model_creation(self):
|
||||
"""Test that PyPICacheTask model can be instantiated with explicit values."""
|
||||
from app.models import PyPICacheTask
|
||||
|
||||
task = PyPICacheTask(
|
||||
package_name="requests",
|
||||
version_constraint=">=2.25.0",
|
||||
depth=0,
|
||||
status="pending",
|
||||
attempts=0,
|
||||
max_attempts=3,
|
||||
)
|
||||
|
||||
assert task.package_name == "requests"
|
||||
assert task.version_constraint == ">=2.25.0"
|
||||
assert task.depth == 0
|
||||
assert task.status == "pending"
|
||||
assert task.attempts == 0
|
||||
assert task.max_attempts == 3
|
||||
|
||||
def test_model_fields_exist(self):
|
||||
"""Test that PyPICacheTask has all expected fields."""
|
||||
from app.models import PyPICacheTask
|
||||
|
||||
# Create with minimal required field
|
||||
task = PyPICacheTask(package_name="urllib3")
|
||||
|
||||
# Verify all expected attributes exist (SQLAlchemy defaults apply on flush)
|
||||
assert hasattr(task, "status")
|
||||
assert hasattr(task, "depth")
|
||||
assert hasattr(task, "attempts")
|
||||
assert hasattr(task, "max_attempts")
|
||||
assert hasattr(task, "version_constraint")
|
||||
assert hasattr(task, "parent_task_id")
|
||||
assert hasattr(task, "triggered_by_artifact")
|
||||
|
||||
|
||||
class TestEnqueueCacheTask:
|
||||
"""Tests for enqueue_cache_task function."""
|
||||
|
||||
def test_normalize_package_name(self):
|
||||
"""Test that package names are normalized per PEP 503."""
|
||||
# Test the normalization pattern used in the worker
|
||||
test_cases = [
|
||||
("Requests", "requests"),
|
||||
("typing_extensions", "typing-extensions"),
|
||||
("some.package", "some-package"),
|
||||
("UPPER_CASE", "upper-case"),
|
||||
("mixed-Case_name", "mixed-case-name"),
|
||||
]
|
||||
|
||||
for input_name, expected in test_cases:
|
||||
normalized = re.sub(r"[-_.]+", "-", input_name).lower()
|
||||
assert normalized == expected, f"Failed for {input_name}"
|
||||
|
||||
|
||||
class TestCacheWorkerFunctions:
|
||||
"""Tests for cache worker helper functions."""
|
||||
|
||||
def test_exponential_backoff_calculation(self):
|
||||
"""Test that exponential backoff is calculated correctly."""
|
||||
# The formula is: 30 * (2 ** (attempts - 1))
|
||||
# Attempt 1 failed → 30s
|
||||
# Attempt 2 failed → 60s
|
||||
# Attempt 3 failed → 120s
|
||||
|
||||
def calc_backoff(attempts):
|
||||
return 30 * (2 ** (attempts - 1))
|
||||
|
||||
assert calc_backoff(1) == 30
|
||||
assert calc_backoff(2) == 60
|
||||
assert calc_backoff(3) == 120
|
||||
|
||||
|
||||
class TestPyPICacheAPIEndpoints:
|
||||
"""Integration tests for PyPI cache API endpoints."""
|
||||
|
||||
@pytest.mark.integration
|
||||
def test_cache_status_endpoint(self):
|
||||
"""Test GET /pypi/cache/status returns queue statistics."""
|
||||
with httpx.Client(base_url=get_base_url(), timeout=30.0) as client:
|
||||
response = client.get("/pypi/cache/status")
|
||||
assert response.status_code == 200
|
||||
|
||||
data = response.json()
|
||||
assert "pending" in data
|
||||
assert "in_progress" in data
|
||||
assert "completed" in data
|
||||
assert "failed" in data
|
||||
|
||||
# All values should be non-negative integers
|
||||
assert isinstance(data["pending"], int)
|
||||
assert isinstance(data["in_progress"], int)
|
||||
assert isinstance(data["completed"], int)
|
||||
assert isinstance(data["failed"], int)
|
||||
assert data["pending"] >= 0
|
||||
assert data["in_progress"] >= 0
|
||||
assert data["completed"] >= 0
|
||||
assert data["failed"] >= 0
|
||||
|
||||
@pytest.mark.integration
|
||||
def test_cache_failed_endpoint(self):
|
||||
"""Test GET /pypi/cache/failed returns list of failed tasks."""
|
||||
with httpx.Client(base_url=get_base_url(), timeout=30.0) as client:
|
||||
response = client.get("/pypi/cache/failed")
|
||||
assert response.status_code == 200
|
||||
|
||||
data = response.json()
|
||||
assert isinstance(data, list)
|
||||
|
||||
# If there are failed tasks, verify structure
|
||||
if data:
|
||||
task = data[0]
|
||||
assert "id" in task
|
||||
assert "package" in task
|
||||
assert "error" in task
|
||||
assert "attempts" in task
|
||||
assert "depth" in task
|
||||
|
||||
@pytest.mark.integration
|
||||
def test_cache_failed_with_limit(self):
|
||||
"""Test GET /pypi/cache/failed respects limit parameter."""
|
||||
with httpx.Client(base_url=get_base_url(), timeout=30.0) as client:
|
||||
response = client.get("/pypi/cache/failed?limit=5")
|
||||
assert response.status_code == 200
|
||||
|
||||
data = response.json()
|
||||
assert isinstance(data, list)
|
||||
assert len(data) <= 5
|
||||
|
||||
@pytest.mark.integration
|
||||
def test_cache_retry_nonexistent_package(self):
|
||||
"""Test POST /pypi/cache/retry/{package} returns 404 for unknown package."""
|
||||
with httpx.Client(base_url=get_base_url(), timeout=30.0) as client:
|
||||
# Use a random package name that definitely doesn't exist
|
||||
response = client.post(f"/pypi/cache/retry/nonexistent-package-{uuid4().hex[:8]}")
|
||||
assert response.status_code == 404
|
||||
# Check for "no failed" or "not found" in error message
|
||||
detail = response.json()["detail"].lower()
|
||||
assert "no failed" in detail or "not found" in detail
|
||||
|
||||
@pytest.mark.integration
|
||||
def test_cache_retry_all_endpoint(self):
|
||||
"""Test POST /pypi/cache/retry-all returns success."""
|
||||
with httpx.Client(base_url=get_base_url(), timeout=30.0) as client:
|
||||
response = client.post("/pypi/cache/retry-all")
|
||||
assert response.status_code == 200
|
||||
|
||||
data = response.json()
|
||||
assert "count" in data
|
||||
assert "message" in data
|
||||
assert isinstance(data["count"], int)
|
||||
assert data["count"] >= 0
|
||||
|
||||
|
||||
class TestCacheTaskDeduplication:
|
||||
"""Tests for cache task deduplication logic."""
|
||||
|
||||
def test_find_cached_package_returns_none_for_uncached(self):
|
||||
"""Test that _find_cached_package returns None for uncached packages."""
|
||||
# This is a unit test pattern - mock the database
|
||||
from unittest.mock import MagicMock
|
||||
|
||||
mock_db = MagicMock()
|
||||
mock_db.query.return_value.filter.return_value.first.return_value = None
|
||||
|
||||
from app.pypi_cache_worker import _find_cached_package
|
||||
|
||||
result = _find_cached_package(mock_db, "nonexistent-package")
|
||||
assert result is None
|
||||
|
||||
|
||||
class TestCacheWorkerConfiguration:
|
||||
"""Tests for cache worker configuration."""
|
||||
|
||||
def test_config_settings_exist(self):
|
||||
"""Test that PyPI cache config settings are available."""
|
||||
from app.config import get_settings
|
||||
|
||||
settings = get_settings()
|
||||
|
||||
# Check that settings exist and have reasonable defaults
|
||||
assert hasattr(settings, "pypi_cache_workers")
|
||||
assert hasattr(settings, "pypi_cache_max_depth")
|
||||
assert hasattr(settings, "pypi_cache_max_attempts")
|
||||
|
||||
# Check aliases work
|
||||
assert settings.PYPI_CACHE_WORKERS == settings.pypi_cache_workers
|
||||
assert settings.PYPI_CACHE_MAX_DEPTH == settings.pypi_cache_max_depth
|
||||
assert settings.PYPI_CACHE_MAX_ATTEMPTS == settings.pypi_cache_max_attempts
|
||||
|
||||
def test_config_default_values(self):
|
||||
"""Test that PyPI cache config has sensible defaults."""
|
||||
from app.config import get_settings
|
||||
|
||||
settings = get_settings()
|
||||
|
||||
# These are the defaults from our implementation
|
||||
assert settings.pypi_cache_workers == 5
|
||||
assert settings.pypi_cache_max_depth == 10
|
||||
assert settings.pypi_cache_max_attempts == 3
|
||||
|
||||
|
||||
class TestFetchAndCachePackage:
|
||||
"""Tests for _fetch_and_cache_package function."""
|
||||
|
||||
def test_result_structure_success(self):
|
||||
"""Test that success result has correct structure."""
|
||||
# Mock a successful result
|
||||
result = {"success": True, "artifact_id": "abc123"}
|
||||
|
||||
assert result["success"] is True
|
||||
assert "artifact_id" in result
|
||||
|
||||
def test_result_structure_failure(self):
|
||||
"""Test that failure result has correct structure."""
|
||||
# Mock a failure result
|
||||
result = {"success": False, "error": "Package not found"}
|
||||
|
||||
assert result["success"] is False
|
||||
assert "error" in result
|
||||
|
||||
|
||||
class TestWorkerPoolLifecycle:
|
||||
"""Tests for worker pool initialization and shutdown."""
|
||||
|
||||
def test_init_shutdown_cycle(self):
|
||||
"""Test that worker pool can be initialized and shut down cleanly."""
|
||||
from app.pypi_cache_worker import (
|
||||
init_cache_worker_pool,
|
||||
shutdown_cache_worker_pool,
|
||||
_cache_worker_pool,
|
||||
_cache_worker_running,
|
||||
)
|
||||
|
||||
# Note: We can't fully test this in isolation because the module
|
||||
# has global state and may conflict with the running server.
|
||||
# These tests verify the function signatures work.
|
||||
|
||||
# The pool should be initialized by main.py on startup
|
||||
# We just verify the functions are callable
|
||||
assert callable(init_cache_worker_pool)
|
||||
assert callable(shutdown_cache_worker_pool)
|
||||
Reference in New Issue
Block a user