Files
DarkRoom/tools/bench/src/fixture.rs
T
dtourolle 84fade99ec Put the developer docs under docs/dev and index the folder for users first
docs/ had 26 developer documents flat beside the manual, and the two
audiences are very differently sized: most readers want the manual and
the gesture reference, a few want the register, the designs and the
measurements. The manual and gestures.md stay at the top; everything for
someone changing the code moves to docs/dev/, and the two documents that
name their own successors — the v0.1 milestone and the UI-refinement plan
— go to docs/dev/archive/ rather than being deleted, since both are still
cited. docs/README.md is the index, users first.

Every reference follows: code comments, Cargo manifests, the workflows,
the pre-commit hook, the bench and traceability tools (which locate the
repo root by docs/dev/requirements.md now), packaging, the Docker READMEs,
CLAUDE.md, CONTRIBUTING.md and the README. The matrix links one level
deeper and is regenerated. Links out of the moved documents into the tree
gain a level; a link checker over every Markdown file finds none broken.
2026-09-20 21:16:03 +02:00

449 lines
19 KiB
Rust
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
//! The synthetic 50k catalog, and the handful of real files it points at.
//!
//! `docs/dev/requirements.md` §8 asks for "an automated benchmark suite against a
//! synthetic 50k catalog". The hard part of that sentence is *50k*: a real
//! library of that size is several terabytes and cannot live in a repository,
//! in a CI cache, or on a laptop that also has to compile the thing.
//!
//! # The trick, and what it costs
//!
//! Rows are cheap and pixels are not. So this builds **fifty thousand catalog
//! rows** over a **pool of a dozen real image files**, each referenced by
//! several thousand of them. Everything the catalog half of the suite measures
//! — opening, counting, windowing, bucketing a timeline — touches only rows,
//! and is therefore exact. Everything the pixel half measures — decode,
//! downscale, orient, encode — touches one file at a time and does not care
//! how many rows point at it. The fixture is ~14 MB on disk instead of ~2 TB
//! and neither half is flattered by that.
//!
//! What it *does* cost is stated rather than hidden: the file pool is small
//! enough to sit in the OS page cache, so [`crate::thumbnails`] measures CPU
//! throughput with the read already paid for. That is the right thing to
//! measure for NFR-P3 — the target is written about the embedded preview path,
//! not about a disk — but it is not a claim about a cold library on spinning
//! rust, and the harness does not make one.
//!
//! # Reproducible from a seed
//!
//! Every value comes from [`Rng`], seeded once. Two machines running the same
//! seed build byte-comparable catalogs, which is the property that lets a
//! number measured on the reference desktop be compared with a number measured
//! anywhere else. [`Stamp`] records what a directory was built from, so a
//! fixture is reused when it matches and rebuilt when it does not — including
//! when `dr-catalog`'s schema version moves, since a catalog built by an older
//! build would otherwise be measured through a migration that a user's would
//! not run.
//!
//! # The sources are generated, not committed
//!
//! No photograph in this repository is licensed for redistribution, and a
//! dozen camera previews would be megabytes of binary in git for ever. So the
//! pool is synthesised: a coarse gradient with a fine dither on top, which is
//! the same shape `core/dr-gpu/examples/frame_budget.rs` synthesises its source
//! from and for the same reason. A flat frame lets the memory system serve
//! every sample from one cache line, which flatters a box filter by an amount
//! that has nothing to do with photographs; pure noise defeats the JPEG
//! encoder's entropy coder in the other direction and would make the encode
//! half of a thumbnail look worse than any real image ever does.
use std::path::{Path, PathBuf};
use anyhow::{Context, Result};
use dr_catalog::Catalog;
use serde::{Deserialize, Serialize};
use crate::stats::Rng;
/// How many distinct image files the pool holds.
///
/// Twelve rather than one, so that a decode measured over a batch is not one
/// file's quirks repeated — a single frame that happened to compress unusually
/// well would set the whole number — and rather than fifty thousand, so the
/// fixture stays a directory a person can look at.
pub const SOURCE_POOL: usize = 12;
/// The size of one pooled file, in pixels.
///
/// 1620×1080 is not a round number: it is what `core/dr-decode/src/preview.rs`
/// records a Canon CR2 carrying in IFD2, and the embedded preview is what
/// NFR-P3 names. A camera JPEG is 24 MP and a camera *preview* is about this,
/// so measuring the preview path against a 24 MP file would measure something
/// the sweep never does.
pub const PREVIEW: (u32, u32) = (1620, 1080);
/// Folders the rows are spread across.
///
/// Spread evenly and without regard to capture date, because what a folder
/// count decides is the cost of the folder filter's `IN (SELECT …)` and the
/// size of the `folders` table — not which image is in which.
const FOLDERS: usize = 400;
/// The earliest capture time in the fixture: 13 December 2015, UTC.
///
/// Fixed rather than relative to the clock. A library whose dates moved with
/// the calendar would make `timeline` bucket differently from one month to the
/// next, and a benchmark that measures a different query each time it runs is
/// not measuring a regression.
const EPOCH: i64 = 1_450_000_000;
/// The span capture times are drawn from: twelve years.
///
/// Long enough that the timeline query has real structure to bucket — at
/// monthly granularity that is ~144 buckets, which is the shape the scrubber
/// actually draws — and not so long that a year holds too few frames to look
/// like a library.
const SPAN: i64 = 12 * 365 * 86_400;
/// Bodies and lenses, for the columns the camera and lens filters read.
const CAMERAS: [&str; 6] = [
"Canon EOS R5",
"Nikon Z 7II",
"Sony ILCE-7RM5",
"Fujifilm X-T5",
"Panasonic DC-S5M2",
"OM SYSTEM OM-1",
];
const LENSES: [&str; 6] = [
"RF24-70mm F2.8 L IS USM",
"NIKKOR Z 50mm f/1.8 S",
"FE 85mm F1.4 GM",
"XF16-55mmF2.8 R LM WR",
"LUMIX S 20-60mm F3.5-5.6",
"M.Zuiko Digital ED 12-40mm F2.8",
];
/// What a fixture directory was built from.
///
/// Written beside the catalog and compared on every run. A mismatch rebuilds:
/// silently reusing a fixture built from a different seed, a different row
/// count or an older schema would compare two numbers that describe two
/// different workloads, which is worse than having no number at all.
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
pub struct Stamp {
/// Bumped by hand whenever anything in this file changes what gets built.
/// The seed cannot carry that: the same seed through different generation
/// code produces a different library.
pub generator: u32,
pub seed: u64,
pub images: usize,
pub sources: usize,
pub folders: usize,
pub preview_width: u32,
pub preview_height: u32,
/// `dr-catalog`'s schema version at build time.
pub schema_version: i64,
}
/// Bump on any change to what [`build`] writes.
const GENERATOR: u32 = 1;
/// A built fixture on disk.
pub struct Fixture {
pub dir: PathBuf,
pub catalog: PathBuf,
pub thumbs: PathBuf,
pub sources: Vec<PathBuf>,
pub stamp: Stamp,
/// The catalog file's size, reported because it is the thing an open has
/// to read and because it is the honest denominator for "is 2 s a lot".
pub catalog_bytes: u64,
}
/// Where a fixture lives by default.
///
/// The temporary directory rather than `target/`, for two reasons. It survives
/// `cargo clean`, so a fixture is built once per machine rather than once per
/// clean; and it is not inside anything CI caches, so a 14 MB catalog is not
/// uploaded and downloaded on every push to save the two seconds it takes to
/// generate. `DR_BENCH_DIR` overrides it.
pub fn default_dir() -> PathBuf {
match std::env::var_os("DR_BENCH_DIR") {
Some(dir) => PathBuf::from(dir),
None => std::env::temp_dir().join("darkroom-bench"),
}
}
/// Build the fixture under `dir`, or confirm the one already there.
///
/// Returns whether it had to be built, so the caller can say so: a run that
/// includes fixture generation has a warm page cache for the catalog file it
/// is about to open, and a reader comparing two numbers deserves to know which
/// of them was measured that way.
pub fn build(dir: &Path, seed: u64, images: usize) -> Result<(Fixture, bool)> {
let stamp = Stamp {
generator: GENERATOR,
seed,
images,
sources: SOURCE_POOL,
folders: FOLDERS,
preview_width: PREVIEW.0,
preview_height: PREVIEW.1,
schema_version: dr_catalog::schema::SCHEMA_VERSION,
};
let catalog = dir.join("catalog.sqlite");
let stamp_path = dir.join("stamp.json");
let sources: Vec<PathBuf> = (0..SOURCE_POOL)
.map(|i| dir.join("sources").join(format!("preview-{i:02}.jpg")))
.collect();
let usable = matches_stamp(&stamp_path, &stamp)
&& catalog.is_file()
&& sources.iter().all(|p| p.is_file());
if !usable {
std::fs::create_dir_all(dir.join("sources"))
.with_context(|| format!("creating the fixture directory {}", dir.display()))?;
// The stamp goes last. A build interrupted halfway leaves no stamp, so
// the next run rebuilds rather than measuring a truncated catalog.
let _ = std::fs::remove_file(&stamp_path);
write_sources(&sources, seed)?;
write_catalog(&catalog, seed, images)?;
std::fs::write(&stamp_path, serde_json::to_vec_pretty(&stamp)?)
.with_context(|| format!("writing {}", stamp_path.display()))?;
}
let catalog_bytes = std::fs::metadata(&catalog)
.with_context(|| format!("stat {}", catalog.display()))?
.len();
Ok((
Fixture {
dir: dir.to_path_buf(),
catalog,
thumbs: dir.join("thumbs"),
sources,
stamp,
catalog_bytes,
},
!usable,
))
}
fn matches_stamp(path: &Path, want: &Stamp) -> bool {
let Ok(text) = std::fs::read_to_string(path) else {
return false;
};
matches!(serde_json::from_str::<Stamp>(&text), Ok(have) if have == *want)
}
// ---------------------------------------------------------------------------
// The file pool
// ---------------------------------------------------------------------------
/// Write the pool of JPEGs the pixel half decodes.
///
/// Encoded through [`dr_thumbs::encode_rgba`] rather than a second encoder
/// call of this crate's own. That is the quality the store already uses (82),
/// which is a little below what a camera writes its previews at, and it is one
/// fewer place for an encoder setting to drift. Stated because it is visible
/// in the result: a slightly softer source decodes marginally faster than a
/// camera's own preview would.
fn write_sources(paths: &[PathBuf], seed: u64) -> Result<()> {
let (w, h) = PREVIEW;
for (i, path) in paths.iter().enumerate() {
let rgba = plausible_frame(w, h, seed ^ (i as u64));
let jpeg = dr_thumbs::encode_rgba(w, h, &rgba)
.map_err(|e| anyhow::anyhow!("encoding the fixture source {}: {e}", path.display()))?;
std::fs::write(path, jpeg).with_context(|| format!("writing {}", path.display()))?;
}
Ok(())
}
/// RGBA with detail at every scale: a coarse gradient plus a fine dither.
///
/// See this module's header for why neither a flat frame nor pure noise would
/// do. `salt` moves the gradient and the dither together so the twelve files
/// differ from one another rather than being twelve copies with different
/// names — a JPEG encoder that saw the same image twelve times would have the
/// same cache behaviour every time, which a library does not.
pub fn plausible_frame(w: u32, h: u32, salt: u64) -> Vec<u8> {
let mut rgba = vec![0u8; (w as usize) * (h as usize) * 4];
let bias = (salt % 97) as u32;
for y in 0..h as usize {
let row = y * (w as usize) * 4;
for x in 0..w as usize {
// A cheap integer hash, so neighbouring pixels differ and the
// encoder has real high-frequency content to spend bits on.
let n = (x.wrapping_mul(2_654_435_761) ^ y.wrapping_mul(1_640_531_527)) >> 13;
let dither = (n & 0x1f) as u32;
let gx = (x * 200 / (w as usize).max(1)) as u32;
let gy = (y * 55 / (h as usize).max(1)) as u32;
let px = &mut rgba[row + x * 4..row + x * 4 + 4];
px[0] = (30 + bias + gx + dither).min(255) as u8;
px[1] = (40 + gy + dither).min(255) as u8;
px[2] = (60 + gx / 2 + gy + dither).min(255) as u8;
px[3] = 255;
}
}
rgba
}
// ---------------------------------------------------------------------------
// The catalog
// ---------------------------------------------------------------------------
/// Write a catalog holding `images` rows, plus a default version for each.
///
/// The default versions are not decoration. `Catalog::open` backfills them for
/// any image that lacks one (see `schema::backfill`), so a fixture without
/// them would charge every measured open for fifty thousand inserts once and
/// nothing thereafter — a first number that bore no relation to the second,
/// and a benchmark whose result depended on whether it had been run before.
fn write_catalog(path: &Path, seed: u64, images: usize) -> Result<()> {
for suffix in ["", "-wal", "-shm"] {
let mut p = path.as_os_str().to_os_string();
p.push(suffix);
let _ = std::fs::remove_file(PathBuf::from(p));
}
let catalog = Catalog::open(path)
.map_err(|e| anyhow::anyhow!("creating the fixture catalog at {}: {e}", path.display()))?;
let conn = catalog.connection();
let mut rng = Rng::new(seed);
conn.execute_batch("BEGIN")?;
conn.execute(
"INSERT INTO roots(id, kind, label, last_seen, scan_generation)
VALUES (1, 'local', '/library', ?1, 1)",
rusqlite::params![EPOCH],
)?;
{
let mut folder = conn.prepare(
"INSERT INTO folders(id, root_id, parent_id, path, mtime, entry_count,
scanned_generation)
VALUES (?1, 1, NULL, ?2, ?3, ?4, 1)",
)?;
for f in 0..FOLDERS {
let id = f as i64 + 1;
let folder_path = format!("/library/{:04}/{:02}", 2016 + f / 12, f % 12 + 1);
let mtime = EPOCH + f as i64 * 86_400;
let entries = (images / FOLDERS.max(1)) as i64;
folder.execute(rusqlite::params![id, folder_path, mtime, entries])?;
}
}
{
let mut image = conn.prepare(
"INSERT INTO images(id, root_id, folder_id, source_ref, format, w, h,
captured_at, captured_offset, camera, lens, iso,
aperture, shutter, availability, file_size,
file_mtime, metadata_state, added_at)
VALUES (?1, 1, ?2, ?3, 'CR3', ?4, ?5, ?6, ?7, ?8, ?9, ?10, ?11, ?12,
?13, ?14, ?15, ?16, ?17)",
)?;
let mut version = conn.prepare(
"INSERT INTO versions(id, image_id, uuid, name, is_default, rating,
label, flag)
VALUES (?1, ?1, ?2, 'Original', 1, ?3, ?4, ?5)",
)?;
// Every value is bound to a local before it reaches `params!`. Not
// style: the macro takes a reference to each argument, and an
// expression like `TABLE[rng.below(n) as usize]` inside it borrows an
// element of a temporary array while `rng` is also being borrowed
// mutably. Locals make the evaluation order and the lifetimes obvious.
const OFFSETS: [i64; 5] = [0, 60, 120, -300, 540];
const ISOS: [i64; 7] = [100, 200, 400, 800, 1600, 3200, 6400];
const APERTURES: [f64; 6] = [1.4, 1.8, 2.8, 4.0, 5.6, 8.0];
const SHUTTERS: [f64; 6] = [0.004, 0.008, 0.0167, 0.005, 0.002, 0.5];
// Mostly metadata-only, as a large library on a laptop is: some
// previewed, a few with the original present.
const AVAILABILITY: [i64; 6] = [0, 0, 0, 1, 1, 2];
for i in 0..images {
let id = i as i64 + 1;
let bucket = i % FOLDERS;
let folder = bucket as i64 + 1;
let source_ref = format!(
"/library/{:04}/{:02}/IMG_{id:05}.CR3",
2016 + bucket / 12,
bucket % 12 + 1
);
let captured = EPOCH + rng.below(SPAN as u64) as i64;
// A quarter of the library shot in portrait, which is what makes
// the thumbnail path's orientation permutation a real cost rather
// than a branch that is never taken.
let (w, h) = if i % 4 == 3 {
(4000i64, 6000i64)
} else {
(6000i64, 4000i64)
};
// Two per cent still awaiting full EXIF — a library is never
// entirely finished being read, and the grid has to render that
// state (`metadata_state` 1).
let state: i64 = if rng.below(50) == 0 { 1 } else { 2 };
let camera = CAMERAS[rng.below(CAMERAS.len() as u64) as usize];
let lens = LENSES[rng.below(LENSES.len() as u64) as usize];
// Minutes east of UTC: a library shot in a handful of places.
let offset = OFFSETS[rng.below(OFFSETS.len() as u64) as usize];
let iso = ISOS[rng.below(ISOS.len() as u64) as usize];
let aperture = APERTURES[rng.below(APERTURES.len() as u64) as usize];
let shutter = SHUTTERS[rng.below(SHUTTERS.len() as u64) as usize];
let availability = AVAILABILITY[rng.below(AVAILABILITY.len() as u64) as usize];
let file_size = 20_000_000i64 + rng.below(30_000_000) as i64;
let file_mtime = captured + 60;
let added_at = captured + 3600;
image.execute(rusqlite::params![
id,
folder,
source_ref,
w,
h,
captured,
offset,
camera,
lens,
iso,
aperture,
shutter,
availability,
file_size,
file_mtime,
state,
added_at,
])?;
// Ratings skewed the way a culled library is: most unrated, a few
// picks, fewer still at five stars.
let rating: i64 = match rng.below(100) {
0..=69 => 0,
70..=84 => 1,
85..=93 => 2,
94..=97 => 3,
98 => 4,
_ => 5,
};
let flag: i64 = match rng.below(100) {
0..=79 => 0,
80..=94 => 1,
_ => 2,
};
let label: Option<i64> = match rng.below(100) {
0..=89 => None,
n => Some((n % 5) as i64 + 1),
};
let a = rng.next_u64();
let b = rng.next_u64();
let uuid = format!("{a:016x}{b:016x}");
version.execute(rusqlite::params![id, uuid, rating, label, flag])?;
}
}
conn.execute_batch("COMMIT")?;
// Deliberately no `ANALYZE`. The application never runs one, so a fixture
// that did would be measuring a query plan no user's catalog gets — and a
// plan chosen from statistics is exactly the sort of thing that would make
// the benchmark faster than the product.
// Dropping the connection checkpoints the WAL, so the file the next open
// reads is the whole catalog rather than a stub plus a journal.
drop(catalog);
Ok(())
}