perf: precompute mangas.sort_author for the author sort

?sort=author used a correlated min(lower(a.name)) subquery as the ORDER BY
key, evaluated per filter-matching row before LIMIT. Materialize it into
mangas.sort_author (indexed by mangas_sort_author_idx), maintained by triggers
on manga_authors and backfilled in the migration, so the sort is a plain
indexed column read. Author names are immutable, so only join changes matter.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
MechaCat02
2026-07-11 14:29:26 +02:00
parent c11df3182c
commit 5b1ce581f3
6 changed files with 107 additions and 13 deletions

2
backend/Cargo.lock generated
View File

@@ -1558,7 +1558,7 @@ checksum = "c41e0c4fef86961ac6d6f8a82609f55f31b05e4fce149ac5710e439df7619ba4"
[[package]]
name = "mangalord"
version = "0.124.23"
version = "0.124.24"
dependencies = [
"anyhow",
"argon2",

View File

@@ -1,6 +1,6 @@
[package]
name = "mangalord"
version = "0.124.23"
version = "0.124.24"
edition = "2021"
default-run = "mangalord"

View File

@@ -0,0 +1,51 @@
-- Precomputed author sort key for `?sort=author`.
--
-- The author sort used a correlated `min(lower(a.name))` subquery as the ORDER
-- BY key, evaluated per filter-matching row before LIMIT — it scaled worse than
-- the indexed date/title sorts. Materialize the same value on `mangas` so the
-- sort is a plain indexed column read.
--
-- `sort_author` = the alphabetically-first attached author's lowercased name,
-- or NULL when the manga has no authors (kept last via NULLS LAST in the query).
-- Author names are immutable (authors are upserted by unique lowercased name and
-- never renamed), so the value only changes when the manga_authors join changes
-- — maintained by the triggers below.
ALTER TABLE mangas ADD COLUMN sort_author text;
CREATE INDEX mangas_sort_author_idx ON mangas (sort_author, id);
-- Backfill from existing links.
UPDATE mangas m
SET sort_author = (
SELECT min(lower(a.name))
FROM manga_authors ma
JOIN authors a ON a.id = ma.author_id
WHERE ma.manga_id = m.id
);
CREATE OR REPLACE FUNCTION refresh_manga_sort_author(mid uuid) RETURNS void AS $$
BEGIN
UPDATE mangas
SET sort_author = (
SELECT min(lower(a.name))
FROM manga_authors ma
JOIN authors a ON a.id = ma.author_id
WHERE ma.manga_id = mid
)
WHERE id = mid;
END;
$$ LANGUAGE plpgsql;
CREATE OR REPLACE FUNCTION mangas_sort_author_on_ma_change() RETURNS trigger AS $$
BEGIN
-- On a manga cascade-delete the UPDATE simply no-ops (row already gone).
PERFORM refresh_manga_sort_author(COALESCE(NEW.manga_id, OLD.manga_id));
RETURN NULL;
END;
$$ LANGUAGE plpgsql;
CREATE TRIGGER manga_authors_sort_author_ins AFTER INSERT ON manga_authors
FOR EACH ROW EXECUTE FUNCTION mangas_sort_author_on_ma_change();
CREATE TRIGGER manga_authors_sort_author_del AFTER DELETE ON manga_authors
FOR EACH ROW EXECUTE FUNCTION mangas_sort_author_on_ma_change();

View File

@@ -168,16 +168,11 @@ pub async fn list(pool: &PgPool, query: &ListQuery) -> AppResult<(Vec<Manga>, Op
SortField::Created => "created_at",
SortField::Updated => "updated_at",
SortField::Title => "lower(title)",
// Sorts on the alphabetically-first attached author. As an ORDER BY
// key this correlated subquery is evaluated per filter-matching row
// before LIMIT applies, so it scales worse than the indexed date/title
// sorts — revisit with a LATERAL join or precomputed sort-name column
// if the library grows large.
SortField::Author => {
"(SELECT min(lower(a.name)) \
FROM manga_authors ma JOIN authors a ON a.id = ma.author_id \
WHERE ma.manga_id = mangas.id)"
}
// Sorts on the alphabetically-first attached author. Precomputed into
// `mangas.sort_author` (migration 0037, maintained by triggers on
// manga_authors) and index-backed by `mangas_sort_author_idx`, so this
// is a plain column read rather than a per-row correlated subquery.
SortField::Author => "sort_author",
};
let dir = match query.order {
SortOrder::Asc => "ASC",

View File

@@ -326,6 +326,54 @@ async fn patch_updates_status_authors_and_genres(pool: PgPool) {
assert_eq!(body["genres"][0]["name"], "Drama");
}
#[sqlx::test(migrations = "./migrations")]
async fn patch_authors_updates_precomputed_sort_author(pool: PgPool) {
// The precomputed mangas.sort_author (used by ?sort=author) must track
// author edits: changing the alphabetically-first author reorders the
// author sort. Two mangas whose relative author order flips after a PATCH.
let h = common::harness(pool.clone());
let (_, cookie) = common::register_user(&h.app).await;
let a = id_of(&create_manga(&h.app, &cookie, json!({ "title": "A", "authors": ["Zeta"] })).await);
let _b = id_of(&create_manga(&h.app, &cookie, json!({ "title": "B", "authors": ["Mid"] })).await);
// Initially: Mid < Zeta, so B before A.
let ids = list_titles(&h.app, "sort=author&order=asc").await;
assert_eq!(ids, vec!["B", "A"]);
// Re-author A to "Alpha", which now sorts first.
let resp = h
.app
.clone()
.oneshot(common::patch_json_with_cookie(
&format!("/api/v1/mangas/{a}"),
json!({ "authors": ["Alpha"] }),
&cookie,
))
.await
.unwrap();
assert_eq!(resp.status(), StatusCode::OK);
// Now A (Alpha) sorts before B (Mid) — proving sort_author was recomputed.
let ids = list_titles(&h.app, "sort=author&order=asc").await;
assert_eq!(ids, vec!["A", "B"]);
}
async fn list_titles(app: &axum::Router, query: &str) -> Vec<String> {
let resp = app
.clone()
.oneshot(common::get(&format!("/api/v1/mangas?{query}")))
.await
.unwrap();
let body = common::body_json(resp).await;
body["items"]
.as_array()
.unwrap()
.iter()
.map(|m| m["title"].as_str().unwrap().to_string())
.collect()
}
#[sqlx::test(migrations = "./migrations")]
async fn patch_404_on_unknown_id(pool: PgPool) {
let h = common::harness(pool);

View File

@@ -1,6 +1,6 @@
{
"name": "mangalord-frontend",
"version": "0.124.23",
"version": "0.124.24",
"private": true,
"type": "module",
"scripts": {