iris/tests/revision_cost.rs

//! Text-layout workloads with stable paragraphs for comparisons across revisions.
//! PR #19's base uses the older spelling of the fixed 40-pixel width and has
//! no diagnostics. The random generator changed with layout, so it cannot
//! provide the same workload across the full PR.
//!
//!     ROWS=40 FRAMES=500 cargo test --release --test revision_cost \
//!       -- --ignored --nocapture resize_cost
//!     PHASE=edit ROWS=40 FRAMES=2000 cargo test --release --test revision_cost \
//!       -- --ignored --nocapture text_updates_cost
//!     ROWS=2000 cargo test --release --test revision_cost \
//!       -- --ignored --nocapture text_memory
//!
//! `text_updates_cost` selects idle, repaint, edit, or scroll with `PHASE`.
//! It alternates a short suffix for edits so later frames do not get a longer
//! paragraph than earlier ones. These are CPU fixtures, with no GPU submission.
//!
//! Use repeated `perf stat -e instructions:u` runs on the executable directly;
//! process totals include font loading and the cold frame, so compare identical
//! row and frame counts. Wall time on this machine is not a stable comparison.

mod rig;

use iris::harness::Harness;
use iris::prelude::*;
use rig::env;
use std::time::Instant;

/// xorshift64, so one seed is one set of paragraphs on any machine.
struct Rng(u64);

impl Rng {
    fn bits(&mut self) -> u64 {
        self.0 ^= self.0 << 13;
        self.0 ^= self.0 >> 7;
        self.0 ^= self.0 << 17;
        self.0
    }

    fn below(&mut self, n: usize) -> usize {
        (self.bits() % n as u64) as usize
    }
}

const WORDS: [&str; 24] = [
    "wrapping",
    "shapes",
    "one",
    "source",
    "into",
    "as",
    "many",
    "lines",
    "as",
    "the",
    "box",
    "leaves",
    "room",
    "for",
    "paragraph",
    "height",
    "answer",
    "setting",
    "container",
    "width",
    "before",
    "knows",
    "measured",
    "again",
];

/// A run of its own words, so nothing here is fast for two texts being the
/// same string.
fn words(rng: &mut Rng, least: usize, most: usize) -> String {
    let words = least + rng.below(most - least);
    let mut out = String::new();
    for _ in 0..words {
        if !out.is_empty() {
            out.push(' ');
        }
        out.push_str(WORDS[rng.below(WORDS.len())]);
    }
    out
}

const OUTPUT: (f32, f32) = (900.0, 1200.0);

/// A row of a fixed-width rect beside a column of one wrapping and one
/// overflowing text: the shape that makes a container measure a child in a
/// box it will not keep.
fn build(h: &mut Harness, rows: usize) -> Vec<WidgetId> {
    let mut rng = Rng(1);
    let mut paragraphs = Vec::new();
    let mut col = Span::empty(Dir::DOWN);
    for _ in 0..rows {
        let mut row = Span::empty(Dir::RIGHT);
        row.push(
            rect(Color::RED)
                .width(LayoutLen::px(40.0))
                .add_strong(&mut h.rsc),
        );
        let mut body = Span::empty(Dir::DOWN);
        let para = wtext(words(&mut rng, 12, 52))
            .size(16)
            .wrap(true)
            .add_strong(&mut h.rsc);
        paragraphs.push(para.id());
        body.push(para);
        body.push(
            // Short, or its unwrapped width decides the row and the
            // paragraph beside it never wraps.
            wtext(words(&mut rng, 2, 6))
                .size(16)
                .wrap(false)
                .add_strong(&mut h.rsc),
        );
        row.push(body.add_strong(&mut h.rsc));
        col.push(row.add_strong(&mut h.rsc));
    }
    let root = col.add(&mut h.rsc);
    h.set_root(root);
    paragraphs
}

#[test]
#[ignore = "measurement, not a check"]
fn resize_cost() {
    let rows = env("ROWS", 40_usize);
    let frames = env("FRAMES", 500_usize);
    let mut h = Harness::new(OUTPUT);
    let paragraphs = build(&mut h, rows);
    // What it cost is only half the comparison: the old code is cheaper
    // partly because it wraps at the container's whole width rather than the
    // part left beside the rect, and draws past the edge of the output.
    println!("output width {}", OUTPUT.0);
    for (at, id) in paragraphs.iter().enumerate().take(3) {
        println!("paragraph {at}: {:?}", h.region(id));
    }

    // The sweep cycles 256 widths, avoiding the two-width cache-friendly case.
    let sweep = env("SWEEP", 0_usize) != 0;
    #[cfg(feature = "layout-diagnostics")]
    let _ = iris::core::layout_diagnostics::take();
    let mut elapsed = Vec::with_capacity(frames);
    for frame in 0..frames {
        let narrower = match sweep {
            true => (frame % 256) as f32,
            false => ((frame + 1) % 2) as f32 * 8.0,
        };
        h.resize((OUTPUT.0 - narrower, OUTPUT.1));
        let start = Instant::now();
        h.frame();
        elapsed.push(start.elapsed().as_secs_f64() * 1000.0);
    }
    #[cfg(feature = "layout-diagnostics")]
    print!(
        "{}",
        iris::core::layout_diagnostics::take().per_frame(frames)
    );
    elapsed.sort_by(|a, b| a.partial_cmp(b).unwrap());
    println!(
        "resize: {frames} frames, min {:.3} ms, median {:.3} ms, p99 {:.3} ms, \
         max {:.3} ms, total {:.1} ms",
        elapsed[0],
        elapsed[frames / 2],
        elapsed[frames * 99 / 100],
        elapsed[frames - 1],
        elapsed.iter().sum::<f64>()
    );
}

fn kb(field: &str) -> u64 {
    std::fs::read_to_string("/proc/self/status")
        .unwrap()
        .lines()
        .find(|line| line.starts_with(field))
        .and_then(|line| line.split_whitespace().nth(1)?.parse().ok())
        .unwrap()
}

fn report(label: &str) {
    println!(
        "{label:24} rss {:>7} kB   peak {:>7} kB",
        kb("VmRSS:"),
        kb("VmHWM:")
    );
}

/// Run this one on its own: the figures are the whole process's.
#[test]
#[ignore = "measurement, not a check"]
fn text_memory() {
    let rows = env("ROWS", 2000_usize);
    report("before");
    let mut h = Harness::new(OUTPUT);
    let paragraphs = build(&mut h, rows);
    report("after cold frame");
    for frame in 0..40 {
        h.resize((OUTPUT.0 - ((frame + 1) % 2) as f32 * 8.0, OUTPUT.1));
        h.frame();
    }
    report("after 40 resizes");
    // Settled: the output holds still and one leaf repaints per frame. Marked
    // by taking it mutably because the revision at the top of this file has no
    // `mark_for_redraw`, and the same source has to build against both.
    for _ in 0..10 {
        let _ = h.rsc.widgets_mut().get_dyn_mut(paragraphs[0]);
        h.frame();
    }
    report("after settling");
}

#[test]
#[ignore = "measurement, not a check"]
fn text_updates_cost() {
    let rows = env("ROWS", 40_usize);
    let frames = env("FRAMES", 1000_usize);
    let phase = env("PHASE", String::from("edit"));
    assert!(rows > 0 && frames > 0);
    assert!(["idle", "repaint", "edit", "scroll"].contains(&phase.as_str()));
    let mut h = Harness::new(OUTPUT);
    let mut rng = Rng(1);
    let mut col = Span::empty(Dir::DOWN);
    let first = wtext(words(&mut rng, 12, 52))
        .size(16)
        .wrap(true)
        .add(&mut h.rsc);
    col.push(first.add_strong(&mut h.rsc));
    for _ in 1..rows {
        col.push(
            wtext(words(&mut rng, 12, 52))
                .size(16)
                .wrap(true)
                .add_strong(&mut h.rsc),
        );
    }
    let root = col.scrollable().add(&mut h.rsc);
    h.set_root(root);
    #[cfg(feature = "layout-diagnostics")]
    let _ = iris::core::layout_diagnostics::take();
    let original = h.rsc[first].content.to_string();
    let alternate = format!("{original} another word");
    let start = Instant::now();
    for frame in 0..frames {
        match phase.as_str() {
            "idle" => {}
            "repaint" => {
                let _ = h.rsc.widgets_mut().get_dyn_mut(first.id());
            }
            "edit" => {
                h.rsc[first].content.clear();
                h.rsc[first].content.push_str(if frame % 2 == 0 {
                    &alternate
                } else {
                    &original
                });
            }
            "scroll" => h.rsc[root].scroll(if frame % 2 == 0 { -12.0 } else { 12.0 }),
            _ => unreachable!(),
        }
        h.frame();
    }
    println!(
        "{phase}: {rows} rows, {frames} frames, {:.1} ms",
        start.elapsed().as_secs_f64() * 1000.0
    );
    #[cfg(feature = "layout-diagnostics")]
    print!(
        "{}",
        iris::core::layout_diagnostics::take().per_frame(frames)
    );
}