|
| 1 | +# Copyright DataStax, Inc. |
| 2 | +# |
| 3 | +# Licensed under the Apache License, Version 2.0 (the "License"); |
| 4 | +# you may not use this file except in compliance with the License. |
| 5 | +# You may obtain a copy of the License at |
| 6 | +# |
| 7 | +# http://www.apache.org/licenses/LICENSE-2.0 |
| 8 | +# |
| 9 | +# Unless required by applicable law or agreed to in writing, software |
| 10 | +# distributed under the License is distributed on an "AS IS" BASIS, |
| 11 | +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
| 12 | +# See the License for the specific language governing permissions and |
| 13 | +# limitations under the License. |
| 14 | + |
| 15 | +""" |
| 16 | +Micro-benchmark: was_applied fast path for known LWT statements. |
| 17 | +
|
| 18 | +Measures the speedup from skipping regex batch detection when the |
| 19 | +query already knows it's an LWT statement (is_lwt() returns True). |
| 20 | +
|
| 21 | +This benchmarks the real `cassandra.cluster.ResultSet.was_applied` property |
| 22 | +(not a simplified stand-in for it): a minimal `ResultSet` is constructed with |
| 23 | +a mocked `response_future` -- was_applied only reads |
| 24 | +`response_future.row_factory`/`response_future.query` -- and real |
| 25 | +`cassandra.query` statement objects, so both the fast-path `is_lwt()` check |
| 26 | +and the slow-path `ResultSet.batch_regex` match run exactly as they do in |
| 27 | +production. |
| 28 | +
|
| 29 | +Run: |
| 30 | + python benchmarks/bench_was_applied.py |
| 31 | +""" |
| 32 | +import timeit |
| 33 | +from unittest.mock import Mock |
| 34 | + |
| 35 | +from cassandra.cluster import ResultSet |
| 36 | +from cassandra.query import named_tuple_factory, SimpleStatement, PreparedStatement, BoundStatement |
| 37 | + |
| 38 | + |
| 39 | +def _make_result_set(query, row): |
| 40 | + """Build a minimal ResultSet with a mocked response_future, mirroring what |
| 41 | + Session.execute()/ResponseFuture.result() construct in production.""" |
| 42 | + response_future = Mock(row_factory=named_tuple_factory, query=query, |
| 43 | + _col_names=None, _col_types=None) |
| 44 | + return ResultSet(response_future, [row]) |
| 45 | + |
| 46 | + |
| 47 | +def bench_was_applied(): |
| 48 | + """Benchmark ResultSet.was_applied: fast path vs slow path.""" |
| 49 | + # Fast path: a BoundStatement bound from a PreparedStatement whose LWT |
| 50 | + # status was already resolved from the server's PREPARE response, so |
| 51 | + # was_applied can skip batch/regex detection entirely. |
| 52 | + prepared = PreparedStatement( |
| 53 | + column_metadata=None, query_id=b'\x00', routing_key_indexes=None, |
| 54 | + query="UPDATE t SET v=1 WHERE k=1 IF v=0", keyspace=None, |
| 55 | + protocol_version=4, result_metadata=None, result_metadata_id=None, |
| 56 | + is_lwt=True) |
| 57 | + lwt_query = BoundStatement(prepared) |
| 58 | + fast_rs = _make_result_set(lwt_query, (True,)) |
| 59 | + |
| 60 | + # Slow path: a plain SimpleStatement with unknown LWT status, so |
| 61 | + # was_applied must match the query string against the real |
| 62 | + # ResultSet.batch_regex to rule out a BEGIN BATCH. |
| 63 | + non_lwt_query = SimpleStatement("INSERT INTO t (k, v) VALUES (1, 2) IF NOT EXISTS") |
| 64 | + slow_rs = _make_result_set(non_lwt_query, (True,)) |
| 65 | + |
| 66 | + def fast_path(): |
| 67 | + _ = fast_rs.was_applied |
| 68 | + |
| 69 | + def slow_path(): |
| 70 | + _ = slow_rs.was_applied |
| 71 | + |
| 72 | + n = 500_000 |
| 73 | + t_fast = timeit.timeit(fast_path, number=n) |
| 74 | + t_slow = timeit.timeit(slow_path, number=n) |
| 75 | + |
| 76 | + print(f"Fast path (known LWT, {n} iters): {t_fast:.3f}s ({t_fast / n * 1e6:.2f} us/call)") |
| 77 | + print(f"Slow path (regex check, {n} iters): {t_slow:.3f}s ({t_slow / n * 1e6:.2f} us/call)") |
| 78 | + print(f"Speedup: {t_slow / t_fast:.1f}x") |
| 79 | + |
| 80 | + |
| 81 | +def main(): |
| 82 | + bench_was_applied() |
| 83 | + |
| 84 | + |
| 85 | +if __name__ == '__main__': |
| 86 | + main() |
0 commit comments