Class TestLargeDatasets

python/tests/test_stress_large_datasets.py:17–266

Stress tests with large datasets.

class TestLargeDatasets:
    """Stress tests with large datasets."""

    @pytest.mark.slow
    def test_one_million_sequential_insertions(self):
        """Test handling of 1M sequential insertions."""
        tree = BPlusTreeMap()
        size = 1_000_000

        start_time = time.time()

        # Insert 1M items
        for i in range(size):
            tree[i] = f"v{i}"

            # Periodic progress check
            if i % 100_000 == 0 and i > 0:
                elapsed = time.time() - start_time
                print(f"\nInserted {i:,} items in {elapsed:.2f}s")

        total_time = time.time() - start_time
        print(f"\nTotal insertion time for 1M items: {total_time:.2f}s")

        # Verify all items are present
        assert len(tree) == size

        # Spot check some values
        for i in range(0, size, 100_000):
            assert tree[i] == f"v{i}"

    @pytest.mark.slow
    def test_one_million_random_insertions(self):
        """Test handling of 1M random insertions."""
        tree = BPlusTreeMap()
        size = 1_000_000

        # Generate random keys
        keys = list(range(size))
        random.shuffle(keys)

        start_time = time.time()

        # Insert in random order
        for i, key in enumerate(keys):
            tree[key] = f"value_{key}"

            # Periodic progress check
            if i % 100_000 == 0 and i > 0:
                elapsed = time.time() - start_time
                print(f"\nInserted {i:,} random items in {elapsed:.2f}s")

        total_time = time.time() - start_time
        print(f"\nTotal random insertion time for 1M items: {total_time:.2f}s")

        # Verify all items are present and in order
        assert len(tree) == size

        # Check ordering