damccorm opened a new pull request, #41174: URL: https://github.com/apache/beam/pull/41174
### Description Optimizes four worker harness hot paths across `operations.py`, `operations.pxd`, `sdk_worker.py`, `statesampler_fast.pyx`, and `opcounters.py`: 1. **`DoOperation` (`operations.py` / `operations.pxd`):** Unpickles `self.spec.serialized_fn` once in `__init__` (caching `self._fn_data` and `self.fn`) instead of unpickling it up to three separate times across `__init__`, `setup()`, and `_get_runtime_performance_hints()`. 2. **`ShortIdCache.get_short_id` (`sdk_worker.py`):** Adds a lock-free `self._info_key_to_short_id.get(key)` fast path before acquiring `self._lock`. 3. **`ScopedState` (`statesampler_fast.pyx` / `operations.pxd`):** Types `scoped_*_state` fields as `statesampler_fast.ScopedState` in `operations.pxd` and removes redundant `PyThread_acquire_lock` / `PyThread_release_lock` calls around C integer assignments in `ScopedState.__enter__` / `__exit__`. 4. **`OperationCounters` (`opcounters.py`):** Checks `if self._sample_counter < self._next_sample: return False` first in `_should_sample()` and resets `self._next_sample = 0` in `restart_sampling()`. ### Benchmarks & Performance Impact - **Microbenchmark:** [`bench_13_worker_do_op_and_statesampler` (`c2feb961eef`)](https://github.com/damccorm/beam/blob/c2feb961eef2e7d2410825aab9537c62a95e6790/sdks/python/apache_beam/testing/benchmarks/python_sdk_perf/microbenchmarks.py#L237-L248) (on branch [`perf/py-benchmarks-suite`](https://github.com/damccorm/beam/tree/perf/py-benchmarks-suite)) — `ShortIdCache.get_short_id` improved by **11.09x (`0.091s` -> `0.0082s`)**, `DoOperation` `serialized_fn` unpickling improved by **4.71x**, `ScopedState` transitions improved by **1.6x–2.3x**, and `OperationCounters` sampling improved by **1.54x**. - **End-to-End Cloud Dataflow Benchmark (`core_window_row_combine`):** Included in [`run_core_window_row_combine_pipeline` (`c2feb961eef`)](https://github.com/damccorm/beam/blob/c2feb961eef2e7d2410825aab9537c62a95e6790/sdks/python/apache_beam/testing/benchmarks/python_sdk_perf/dataflow_e2e_benchmarks.py#L274-L302) (3,000,000 generated events -> 9,000,000 sliding-windowed elements on a single `n2-standard-4` worker), which improved end-to-end worker stage execution time by **1.80x (`-44.5%`, `599.6s` -> `332.9s`)** and reduced total billable Dataflow vCPU/Memory/PD usage by **`-26.1%` (`1,134` -> `838` vCPU-s)**. ### Testing - Verified with `pytest sdks/python/apache_beam/runners/worker/sdk_worker_test.py sdks/python/apache_beam/runners/worker/statesampler_test.py sdks/python/apache_beam/runners/worker/opcounters_test.py`. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
