Hedging: when it helps and when it does not (about 40 minutes)

# /// script
# requires-python = ">=3.10"
# ///
# Copyright (c) 2026 Aayush Sharma · SPDX-License-Identifier: MIT
# https://thedataengineering.com/lab-code/LICENSE.txt
"""Hedging: when it helps and when it does not.

Each attempt takes 10 ms, or 200 ms with probability 0.05. A hedge sends a
second copy at 40 ms and takes whichever answers first. If slowness belongs
to the attempt, the hedge almost always wins; if it belongs to the request,
both copies are slow.
"""
import argparse, json, random

p = argparse.ArgumentParser(description=__doc__.splitlines()[0])
p.add_argument("--requests", type=int, default=1_000_000, help="Simulated requests.")
p.add_argument("--slow-share", type=float, default=0.05, help="Probability that an attempt (or a request) is slow.")
p.add_argument("--hedge-at", type=float, default=40, help="Milliseconds before the second copy is sent.")
p.add_argument("--seed", type=int, default=0, help="Random seed.")
p.add_argument("--json", help="Also write the results to this JSON file.")
args = p.parse_args()
random.seed(args.seed)
N, P, H = args.requests, args.slow_share, args.hedge_at

def attempt(): return 200 if random.random() < P else 10
def plain(): return attempt()
def hedged(): return min(attempt(), H + attempt())
def request_local_hedged():
    slow = random.random() < P
    return min(200 if slow else 10, H + (200 if slow else 10))

rows = []
for name, f in (("no hedge", plain), ("hedge, attempt-local slowness", hedged), ("hedge, request-local slowness", request_local_hedged)):
    lat = [f() for _ in range(N)]
    slow = sum(x > 100 for x in lat) / N
    hedge_rate = sum(x > H for x in lat) / N if "hedge," in name else 0.0
    rows.append({"variant": name, "slow_pct": slow * 100, "hedge_rate_pct": hedge_rate * 100})
    print(f"{name:<32} slow (>100 ms): {slow:7.3%}   hedges sent: {hedge_rate:6.2%}")

if args.json:
    with open(args.json, "w") as f:
        json.dump({"tables": {"variants": rows}}, f)