perf: Skip redundant __init__ assignments and remove dead attributes in ResponseFuture (-32ns/call - 4.7% improvement for the common case, +43ns (+4.5%) for the non-common case, - code cleanup also)

[mykaul]

Summary

• Remove 3 dead class attributes from ResponseFuture:
  • default_timeout — belongs to Session, never used in RF
  • _profile_manager — belongs to Session, never used in RF
  • _warned_timeout — never read or written anywhere in the codebase
• Skip 4 redundant STORE_ATTR operations in __init__ when parameters are None (matching the class-level default): _metrics, prepared_statement, _host, _continuous_paging_state
• Move prepared_statement and _continuous_paging_state class defaults (previously only set in __init__) to class level so the conditional skip works correctly

Thread Safety

All skipped attributes have class-level None defaults and are only set during __init__ or by the owning thread after construction. No lazy initialization of shared mutable state is introduced — the thread-safety invariants are preserved.

Benchmark

ResponseFuture.__init__ micro-benchmark, min() of 7 × 200k iterations:

Scenario	Before	After	Δ
Common case (all 4 params = None)	670 ns/call	638 ns/call	-32 ns/call (4.7%)
Non-None case (metrics + prepared_statement + host set)	957 ns/call	1001 ns/call	+43 ns/call (+4.5%)

The common case (simple queries without metrics/prepared statements/host pinning) is the dominant path. The non-None case overhead is from the added if checks, but these params are rarely all non-None simultaneously.

Tests

All 645 unit tests pass (43 skipped), matching the origin/master baseline.

[mykaul]

Follow-up commit: reorder isinstance chain in _create_response_future

Commit: 40f45ecf5 — perf: reorder isinstance chain to check BoundStatement first in _create_response_future

Change

Swapped the isinstance check order so BoundStatement is checked before SimpleStatement in the _create_response_future dispatch chain. For prepared-statement workloads (the perf-critical case), this saves one wasted isinstance() call per dispatch.

BoundStatement and SimpleStatement are sibling classes under Statement — no subclass relationship — so reorder is safe with no behavioral change.

Benchmark results (benchmarks/bench_isinstance_dispatch.py)

Simulated workload mix: 80% BoundStatement, 15% SimpleStatement, 5% other:

Python 3.14.3
SimpleStatement first: 32.8 ns/dispatch
BoundStatement first:  23.2 ns/dispatch
Speedup: ~1.4–1.7x (~10–15 ns/dispatch saved)

Tests

607 unit tests passed, 0 failures.