//! Raw run-queue microbench (ROADMAP_v0.5 phase 4).
//!
//! Benches the three queue STRUCTURES directly — no runtime, no actors — to
//! isolate the data structure under contention. All three types compile in
//! every build, so this binary covers the whole matrix in one run; it does
//! NOT need the rq-* feature rebuild dance (that's `rq_runtime`).
//!
//! Sweeps thread count × producer:consumer ratio. Queues are sized to the
//! item count, so the occupancy contract holds trivially and producers never
//! block on capacity.
//!
//! Knobs (env):
//!   SMARM_BENCH_THREADS  space-separated sweep, default "1 2 4"
//!   SMARM_BENCH_ITEMS    items per measurement, default 200_000
//!   SMARM_BENCH_RUNS     repetitions per config (median reported), default 5
//!
//! Output: the house table, plus one machine-readable line per config:
//!   RQCSV,micro,<structure>,<threads>,<p:c>,<items>,<median_us>,<items_per_s>
//!
//! NOTE: numbers from a 1-core sandbox only validate the harness; real
//! contention curves come from the many-core box (scripts/bench_rq.sh).

use smarm::pid::Pid;
use smarm::run_queue::{MpmcRing, MutexQueue, StripedRing};
use std::sync::atomic::{AtomicUsize, Ordering};
use std::sync::Arc;
use std::time::Instant;

fn env_usize(key: &str, default: usize) -> usize {
    std::env::var(key).ok().and_then(|v| v.parse().ok()).unwrap_or(default)
}

fn env_threads() -> Vec<usize> {
    std::env::var("SMARM_BENCH_THREADS")
        .map(|v| v.split_whitespace().filter_map(|t| t.parse().ok()).collect())
        .unwrap_or_else(|_| vec![1, 2, 4])
}

/// Generic driver: `producers` threads push `items` total, `consumers`
/// threads pop until everything is accounted for. Returns elapsed µs.
fn drive<Q: Send + Sync + 'static>(
    q: Arc<Q>,
    push: fn(&Q, Pid),
    pop: fn(&Q) -> Option<Pid>,
    producers: usize,
    consumers: usize,
    items: usize,
) -> u128 {
    let remaining = Arc::new(AtomicUsize::new(items));
    let start = Instant::now();
    let mut hs = Vec::new();
    let per = items / producers;
    for p in 0..producers {
        let q = q.clone();
        // Give the last producer the remainder.
        let n = if p == producers - 1 { items - per * (producers - 1) } else { per };
        hs.push(std::thread::spawn(move || {
            let pid = Pid::new(p as u32, 0);
            for _ in 0..n {
                push(&q, pid);
            }
        }));
    }
    for _ in 0..consumers {
        let q = q.clone();
        let remaining = remaining.clone();
        hs.push(std::thread::spawn(move || loop {
            // Claim-then-pop so consumers exit promptly when the budget hits
            // zero; the claim is backed out on a miss.
            let r = remaining.load(Ordering::Relaxed);
            if r == 0 {
                return;
            }
            if pop(&q).is_some() {
                remaining.fetch_sub(1, Ordering::Relaxed);
            } else {
                std::hint::spin_loop();
            }
        }));
    }
    for h in hs {
        h.join().unwrap();
    }
    start.elapsed().as_micros()
}

/// Single-thread alternating push/pop (the T = 1 case).
fn drive_single<Q>(q: &Q, push: fn(&Q, Pid), pop: fn(&Q) -> Option<Pid>, items: usize) -> u128 {
    let pid = Pid::new(0, 0);
    let start = Instant::now();
    for _ in 0..items {
        push(q, pid);
        assert!(pop(q).is_some());
    }
    start.elapsed().as_micros()
}

struct Case {
    structure: &'static str,
    threads: usize,
    producers: usize,
    consumers: usize,
}

fn ratios_for(threads: usize) -> Vec<(usize, usize)> {
    if threads < 2 {
        return vec![(1, 1)]; // label only; T=1 runs the alternating driver
    }
    let mut v = vec![(threads / 2, threads - threads / 2)]; // balanced
    if threads >= 4 {
        v.push((3 * threads / 4, threads - 3 * threads / 4)); // producer-heavy
        v.push((threads / 4, threads - threads / 4)); // consumer-heavy
    }
    v
}

fn main() {
    let threads_sweep = env_threads();
    let items = env_usize("SMARM_BENCH_ITEMS", 200_000);
    let runs = env_usize("SMARM_BENCH_RUNS", 5);

    println!("\n{}", "=".repeat(86));
    println!("  run-queue raw structures — items={items}, runs={runs} (median)");
    println!("{}", "=".repeat(86));
    println!(
        "{:>10} | {:>7} | {:>7} | {:>10} | {:>14}",
        "structure", "threads", "p:c", "median µs", "items/s"
    );
    println!("{}", "-".repeat(86));

    let mut cases = Vec::new();
    for &t in &threads_sweep {
        for (p, c) in ratios_for(t) {
            for s in ["mutex", "mpmc", "striped"] {
                cases.push(Case { structure: s, threads: t, producers: p, consumers: c });
            }
        }
    }

    for case in cases {
        let mut times: Vec<u128> = (0..runs)
            .map(|_| {
                // Fresh queue per run; capacity = items so pushes never stall.
                match case.structure {
                    "mutex" => {
                        let q = Arc::new(MutexQueue::new(case.threads, items));
                        if case.threads < 2 {
                            drive_single(&*q, MutexQueue::push, MutexQueue::pop, items)
                        } else {
                            drive(q, MutexQueue::push, MutexQueue::pop, case.producers, case.consumers, items)
                        }
                    }
                    "mpmc" => {
                        let q = Arc::new(MpmcRing::with_capacity(items));
                        if case.threads < 2 {
                            drive_single(&*q, MpmcRing::push, MpmcRing::pop, items)
                        } else {
                            drive(q, MpmcRing::push, MpmcRing::pop, case.producers, case.consumers, items)
                        }
                    }
                    "striped" => {
                        let q = Arc::new(StripedRing::new(case.threads.max(1), items));
                        if case.threads < 2 {
                            drive_single(&*q, StripedRing::push, StripedRing::pop, items)
                        } else {
                            drive(q, StripedRing::push, StripedRing::pop, case.producers, case.consumers, items)
                        }
                    }
                    _ => unreachable!(),
                }
            })
            .collect();
        times.sort_unstable();
        let median = times[times.len() / 2];
        let per_s = (items as f64 / (median as f64 / 1e6)) as u64;
        let ratio = format!("{}:{}", case.producers, case.consumers);
        println!(
            "{:>10} | {:>7} | {:>7} | {:>10} | {:>14}",
            case.structure, case.threads, ratio, median, per_s
        );
        println!(
            "RQCSV,micro,{},{},{},{},{},{}",
            case.structure, case.threads, ratio, items, median, per_s
        );
    }
}