feat(causal): pipeline demo modes for the reserve-shortfall experiment

SMARM_CAUSAL_MODE selects the reserve stage's guard placement:
work (default, unchanged) | wide (guard over recv+work+send, the whole
serialized per-item path) | occupancy (no experiments; per-segment
timing of reserve's loop at baseline, reporting the unguarded
remainder δ and the impact ceiling it implies).

Discriminates the two candidate explanations for the demo's +84-vs-+100
@50% shortfall: physical recv/send time outside the guard (occupancy
sees δ≈30µs, wide recovers ~2x) vs. injection-side credit loss
(occupancy sees δ≈0, wide caps at ~+84 too — guard cadence identical).

examples/causal_pipeline.rs

@@ -20,6 +20,16 @@
 //! Run:
 //!   cargo run --release --example causal_pipeline --features smarm-causal
 //!
+//! Modes (`SMARM_CAUSAL_MODE`), for probing what the guard placement leaves
+//! out of the measurement (a site speeds up only what it wraps; `recv`/`send`
+//! on the serialized stage sit outside the canonical guard):
+//!   work (default) — guard wraps only the 400µs of work.
+//!   wide           — guard widened over recv + work + send, the whole
+//!                    serialized per-item path.
+//!   occupancy      — no experiments; times each segment of reserve's loop
+//!                    at baseline and reports the unguarded per-item
+//!                    overhead δ plus the impact ceiling it implies.
+//!
 //! Prints a summary, writes `profile.coz` (Coz plot-compatible), and — given
 //! enough cores for the pipeline to actually run in parallel — checks the
 //! expected separation and exits nonzero if it doesn't hold, so a CI box can
@@ -55,7 +65,32 @@ fn calibrate_iters_per_us() -> u64 {
     (n / (t.elapsed().as_micros().max(1) as u64)).max(1)
 }
 
+/// Guard placement for the `reserve` stage — see module doc.
+#[derive(Clone, Copy, PartialEq)]
+enum Mode {
+    Work,
+    Wide,
+    Occupancy,
+}
+
 fn main() {
+    let mode = match std::env::var("SMARM_CAUSAL_MODE").as_deref() {
+        Err(_) | Ok("") | Ok("work") => Mode::Work,
+        Ok("wide") => Mode::Wide,
+        Ok("occupancy") => Mode::Occupancy,
+        Ok(other) => {
+            eprintln!("unknown SMARM_CAUSAL_MODE {other:?} (work|wide|occupancy)");
+            std::process::exit(2);
+        }
+    };
+    println!(
+        "mode: {}",
+        match mode {
+            Mode::Work => "work",
+            Mode::Wide => "wide",
+            Mode::Occupancy => "occupancy",
+        }
+    );
     let per_us = calibrate_iters_per_us();
     println!("calibration: {per_us} work iters/µs");
     let work_us = move |us: u64| work_iters(us * per_us);
@@ -86,15 +121,71 @@ fn main() {
         });
 
         // Reserve: the true bottleneck (~400µs of work per item).
-        let reserve = smarm::spawn(move || {
-            while let Ok(item) = rx_ab.recv() {
-                {
-                    let _g = smarm::causal_site!("reserve");
-                    work_us(400);
+        let reserve = smarm::spawn(move || match mode {
+            Mode::Work => {
+                while let Ok(item) = rx_ab.recv() {
+                    {
+                        let _g = smarm::causal_site!("reserve");
+                        work_us(400);
+                    }
+                    if tx_bc.send(item).is_err() {
+                        break;
+                    }
                 }
+            }
+            // Whole serialized per-item path under the guard: a virtual
+            // speedup now also compresses recv/send, so the @50% cell should
+            // recover the theoretical 2× that `work` mode's placement caps.
+            Mode::Wide => loop {
+                let _g = smarm::causal_site!("reserve");
+                let Ok(item) = rx_ab.recv() else { break };
+                work_us(400);
                 if tx_bc.send(item).is_err() {
                     break;
                 }
+            },
+            // Time each segment at baseline; the recv+send remainder δ is
+            // the serialized time a `work`-placed guard cannot speed up.
+            Mode::Occupancy => {
+                let (mut recv_ns, mut work_ns, mut send_ns, mut n) = (0u64, 0u64, 0u64, 0u64);
+                loop {
+                    let t0 = Instant::now();
+                    let Ok(item) = rx_ab.recv() else { break };
+                    let t1 = Instant::now();
+                    {
+                        let _g = smarm::causal_site!("reserve");
+                        work_us(400);
+                    }
+                    let t2 = Instant::now();
+                    if tx_bc.send(item).is_err() {
+                        break;
+                    }
+                    recv_ns += (t1 - t0).as_nanos() as u64;
+                    work_ns += (t2 - t1).as_nanos() as u64;
+                    send_ns += t2.elapsed().as_nanos() as u64;
+                    n += 1;
+                }
+                let items = n.max(1) as f64;
+                let (r, w, s) = (
+                    recv_ns as f64 / items / 1e3,
+                    work_ns as f64 / items / 1e3,
+                    send_ns as f64 / items / 1e3,
+                );
+                let delta = r + s;
+                let total = w + delta;
+                println!("occupancy: {n} items; per item recv {r:.1}µs + work(guarded) {w:.1}µs + send {s:.1}µs");
+                println!(
+                    "occupancy: unguarded δ = {delta:.1}µs/item = {:.1}% of the serialized path",
+                    100.0 * delta / total
+                );
+                for pct in [25u32, 50] {
+                    let f = 1.0 - f64::from(pct) / 100.0;
+                    println!(
+                        "occupancy: predicted reserve impact @{pct}% -> {:+.1}%  (ceiling if δ were guarded: {:+.1}%)",
+                        100.0 * (total / (f * w + delta) - 1.0),
+                        100.0 * (1.0 / f - 1.0)
+                    );
+                }
             }
         });
 
@@ -121,6 +212,18 @@ fn main() {
         // Warm up so queues reach steady state before measuring.
         smarm::sleep(Duration::from_millis(300));
 
+        if mode == Mode::Occupancy {
+            // No experiments: hold steady state for a window, then drain and
+            // let the reserve actor print its segment report.
+            smarm::sleep(Duration::from_millis(1500));
+            stop.store(true, Ordering::Relaxed);
+            producer.join().unwrap();
+            reserve.join().unwrap();
+            notify.join().unwrap();
+            background.join().unwrap();
+            return;
+        }
+
         let results = smarm::causal::run_experiments(&smarm::causal::ExperimentPlan {
             speedups_pct: vec![0, 25, 50],
             experiment: Duration::from_millis(700),