perf(indexer): éliminer le pre-count WalkDir en mode incrémental + concurrence adaptative
- Incremental rebuild: remplace le WalkDir de comptage par un COUNT(*) SQL → incrémental 67s → 25s (-62%) sur disque externe - Full rebuild: conserve le WalkDir (DB vidée avant le comptage) - Concurrence par défaut: num_cpus/2 clampé [2,8] au lieu de 2 fixe - Ajoute num_cpus comme dépendance workspace - Backoffice jobs: un seul formulaire avec formAction par bouton (icônes rétablies) - infra/perf.sh: corrige l'endpoint /index/jobs/:id (pas /details), exporte BASE_API/TOKEN Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
17
Cargo.lock
generated
17
Cargo.lock
generated
@@ -863,6 +863,12 @@ version = "0.5.0"
|
|||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea"
|
checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea"
|
||||||
|
|
||||||
|
[[package]]
|
||||||
|
name = "hermit-abi"
|
||||||
|
version = "0.5.2"
|
||||||
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
|
checksum = "fc0fef456e4baa96da950455cd02c081ca953b141298e41db3fc7e36b1da849c"
|
||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "hex"
|
name = "hex"
|
||||||
version = "0.4.3"
|
version = "0.4.3"
|
||||||
@@ -1171,6 +1177,7 @@ dependencies = [
|
|||||||
"futures",
|
"futures",
|
||||||
"image",
|
"image",
|
||||||
"notify",
|
"notify",
|
||||||
|
"num_cpus",
|
||||||
"parsers",
|
"parsers",
|
||||||
"rand 0.8.5",
|
"rand 0.8.5",
|
||||||
"rayon",
|
"rayon",
|
||||||
@@ -1639,6 +1646,16 @@ dependencies = [
|
|||||||
"libm",
|
"libm",
|
||||||
]
|
]
|
||||||
|
|
||||||
|
[[package]]
|
||||||
|
name = "num_cpus"
|
||||||
|
version = "1.17.0"
|
||||||
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
|
checksum = "91df4bbde75afed763b708b7eee1e8e7651e02d97f6d5dd763e89367e957b23b"
|
||||||
|
dependencies = [
|
||||||
|
"hermit-abi",
|
||||||
|
"libc",
|
||||||
|
]
|
||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "once_cell"
|
name = "once_cell"
|
||||||
version = "1.21.3"
|
version = "1.21.3"
|
||||||
|
|||||||
@@ -33,6 +33,7 @@ tracing = "0.1"
|
|||||||
tracing-subscriber = { version = "0.3", features = ["env-filter", "fmt"] }
|
tracing-subscriber = { version = "0.3", features = ["env-filter", "fmt"] }
|
||||||
uuid = { version = "1.12", features = ["serde", "v4"] }
|
uuid = { version = "1.12", features = ["serde", "v4"] }
|
||||||
natord = "1.0"
|
natord = "1.0"
|
||||||
|
num_cpus = "1.16"
|
||||||
pdfium-render = { version = "0.8", default-features = false, features = ["pdfium_latest", "image_latest", "thread_safe"] }
|
pdfium-render = { version = "0.8", default-features = false, features = ["pdfium_latest", "image_latest", "thread_safe"] }
|
||||||
unrar = "0.5"
|
unrar = "0.5"
|
||||||
walkdir = "2.5"
|
walkdir = "2.5"
|
||||||
|
|||||||
@@ -2,7 +2,7 @@ import { revalidatePath } from "next/cache";
|
|||||||
import { redirect } from "next/navigation";
|
import { redirect } from "next/navigation";
|
||||||
import { listJobs, fetchLibraries, rebuildIndex, rebuildThumbnails, regenerateThumbnails, IndexJobDto, LibraryDto } from "../../lib/api";
|
import { listJobs, fetchLibraries, rebuildIndex, rebuildThumbnails, regenerateThumbnails, IndexJobDto, LibraryDto } from "../../lib/api";
|
||||||
import { JobsList } from "../components/JobsList";
|
import { JobsList } from "../components/JobsList";
|
||||||
import { Card, CardHeader, CardTitle, CardDescription, CardContent, Button, FormField, FormSelect, FormRow } from "../components/ui";
|
import { Card, CardHeader, CardTitle, CardContent, Button, FormField, FormSelect, FormRow } from "../components/ui";
|
||||||
|
|
||||||
export const dynamic = "force-dynamic";
|
export const dynamic = "force-dynamic";
|
||||||
|
|
||||||
@@ -57,100 +57,54 @@ export default async function JobsPage({ searchParams }: { searchParams: Promise
|
|||||||
Index Jobs
|
Index Jobs
|
||||||
</h1>
|
</h1>
|
||||||
</div>
|
</div>
|
||||||
|
|
||||||
<Card className="mb-6">
|
<Card className="mb-6">
|
||||||
<CardHeader>
|
<CardHeader>
|
||||||
<CardTitle>Queue New Job</CardTitle>
|
<CardTitle>Queue New Job</CardTitle>
|
||||||
<CardDescription>Rebuild index, full rebuild, generate missing thumbnails, or regenerate all thumbnails</CardDescription>
|
|
||||||
</CardHeader>
|
</CardHeader>
|
||||||
<CardContent className="space-y-4">
|
<CardContent>
|
||||||
<form action={triggerRebuild}>
|
<form>
|
||||||
<FormRow>
|
<FormRow>
|
||||||
<FormField className="flex-1">
|
<FormField className="flex-1 max-w-xs">
|
||||||
<FormSelect name="library_id" defaultValue="">
|
<FormSelect name="library_id" defaultValue="">
|
||||||
<option value="">All libraries</option>
|
<option value="">All libraries</option>
|
||||||
{libraries.map((lib) => (
|
{libraries.map((lib) => (
|
||||||
<option key={lib.id} value={lib.id}>
|
<option key={lib.id} value={lib.id}>{lib.name}</option>
|
||||||
{lib.name}
|
|
||||||
</option>
|
|
||||||
))}
|
))}
|
||||||
</FormSelect>
|
</FormSelect>
|
||||||
</FormField>
|
</FormField>
|
||||||
<Button type="submit">
|
<div className="flex flex-wrap gap-2">
|
||||||
<svg className="w-4 h-4 mr-2" fill="none" stroke="currentColor" viewBox="0 0 24 24">
|
<Button type="submit" formAction={triggerRebuild}>
|
||||||
<path strokeLinecap="round" strokeLinejoin="round" strokeWidth={2} d="M4 4v5h.582m15.356 2A8.001 8.001 0 004.582 9m0 0H9m11 11v-5h-.581m0 0a8.003 8.003 0 01-15.357-2m15.357 2H15" />
|
<svg className="w-4 h-4 mr-2" fill="none" stroke="currentColor" viewBox="0 0 24 24">
|
||||||
</svg>
|
<path strokeLinecap="round" strokeLinejoin="round" strokeWidth={2} d="M4 4v5h.582m15.356 2A8.001 8.001 0 004.582 9m0 0H9m11 11v-5h-.581m0 0a8.003 8.003 0 01-15.357-2m15.357 2H15" />
|
||||||
Queue Rebuild
|
</svg>
|
||||||
</Button>
|
Rebuild
|
||||||
</FormRow>
|
</Button>
|
||||||
</form>
|
<Button type="submit" formAction={triggerFullRebuild} variant="warning">
|
||||||
|
<svg className="w-4 h-4 mr-2" fill="none" stroke="currentColor" viewBox="0 0 24 24">
|
||||||
<form action={triggerFullRebuild}>
|
<path strokeLinecap="round" strokeLinejoin="round" strokeWidth={2} d="M19 7l-.867 12.142A2 2 0 0116.138 21H7.862a2 2 0 01-1.995-1.858L5 7m5 4v6m4-6v6m1-10V4a1 1 0 00-1-1h-4a1 1 0 00-1 1v3M4 7h16" />
|
||||||
<FormRow>
|
</svg>
|
||||||
<FormField className="flex-1">
|
Full Rebuild
|
||||||
<FormSelect name="library_id" defaultValue="">
|
</Button>
|
||||||
<option value="">All libraries</option>
|
<Button type="submit" formAction={triggerThumbnailsRebuild} variant="secondary">
|
||||||
{libraries.map((lib) => (
|
<svg className="w-4 h-4 mr-2" fill="none" stroke="currentColor" viewBox="0 0 24 24">
|
||||||
<option key={lib.id} value={lib.id}>
|
<path strokeLinecap="round" strokeLinejoin="round" strokeWidth={2} d="M4 16l4.586-4.586a2 2 0 012.828 0L16 16m-2-2l1.586-1.586a2 2 0 012.828 0L20 14m-6-6h.01M6 20h12a2 2 0 002-2V6a2 2 0 00-2-2H6a2 2 0 00-2 2v12a2 2 0 002 2z" />
|
||||||
{lib.name}
|
</svg>
|
||||||
</option>
|
Generate thumbnails
|
||||||
))}
|
</Button>
|
||||||
</FormSelect>
|
<Button type="submit" formAction={triggerThumbnailsRegenerate} variant="warning">
|
||||||
</FormField>
|
<svg className="w-4 h-4 mr-2" fill="none" stroke="currentColor" viewBox="0 0 24 24">
|
||||||
<Button type="submit" variant="warning">
|
<path strokeLinecap="round" strokeLinejoin="round" strokeWidth={2} d="M4 4v5h.582m15.356 2A8.001 8.001 0 004.582 9m0 0H9m11 11v-5h-.581m0 0a8.003 8.003 0 01-15.357-2m15.357 2H15" />
|
||||||
<svg className="w-4 h-4 mr-2" fill="none" stroke="currentColor" viewBox="0 0 24 24">
|
</svg>
|
||||||
<path strokeLinecap="round" strokeLinejoin="round" strokeWidth={2} d="M19 7l-.867 12.142A2 2 0 0116.138 21H7.862a2 2 0 01-1.995-1.858L5 7m5 4v6m4-6v6m1-10V4a1 1 0 00-1-1h-4a1 1 0 00-1 1v3M4 7h16" />
|
Regenerate thumbnails
|
||||||
</svg>
|
</Button>
|
||||||
Full Rebuild
|
</div>
|
||||||
</Button>
|
|
||||||
</FormRow>
|
|
||||||
</form>
|
|
||||||
|
|
||||||
<form action={triggerThumbnailsRebuild}>
|
|
||||||
<FormRow>
|
|
||||||
<FormField className="flex-1">
|
|
||||||
<FormSelect name="library_id" defaultValue="">
|
|
||||||
<option value="">All libraries</option>
|
|
||||||
{libraries.map((lib) => (
|
|
||||||
<option key={lib.id} value={lib.id}>
|
|
||||||
{lib.name}
|
|
||||||
</option>
|
|
||||||
))}
|
|
||||||
</FormSelect>
|
|
||||||
</FormField>
|
|
||||||
<Button type="submit" variant="secondary">
|
|
||||||
<svg className="w-4 h-4 mr-2" fill="none" stroke="currentColor" viewBox="0 0 24 24">
|
|
||||||
<path strokeLinecap="round" strokeLinejoin="round" strokeWidth={2} d="M4 16l4.586-4.586a2 2 0 012.828 0L16 16m-2-2l1.586-1.586a2 2 0 012.828 0L20 14m-6-6h.01M6 20h12a2 2 0 002-2V6a2 2 0 00-2-2H6a2 2 0 00-2 2v12a2 2 0 002 2z" />
|
|
||||||
</svg>
|
|
||||||
Generate thumbnails
|
|
||||||
</Button>
|
|
||||||
</FormRow>
|
|
||||||
</form>
|
|
||||||
|
|
||||||
<form action={triggerThumbnailsRegenerate}>
|
|
||||||
<FormRow>
|
|
||||||
<FormField className="flex-1">
|
|
||||||
<FormSelect name="library_id" defaultValue="">
|
|
||||||
<option value="">All libraries</option>
|
|
||||||
{libraries.map((lib) => (
|
|
||||||
<option key={lib.id} value={lib.id}>
|
|
||||||
{lib.name}
|
|
||||||
</option>
|
|
||||||
))}
|
|
||||||
</FormSelect>
|
|
||||||
</FormField>
|
|
||||||
<Button type="submit" variant="warning">
|
|
||||||
<svg className="w-4 h-4 mr-2" fill="none" stroke="currentColor" viewBox="0 0 24 24">
|
|
||||||
<path strokeLinecap="round" strokeLinejoin="round" strokeWidth={2} d="M4 4v5h.582m15.356 2A8.001 8.001 0 004.582 9m0 0H9m11 11v-5h-.581m0 0a8.003 8.003 0 01-15.357-2m15.357 2H15" />
|
|
||||||
</svg>
|
|
||||||
Regenerate thumbnails
|
|
||||||
</Button>
|
|
||||||
</FormRow>
|
</FormRow>
|
||||||
</form>
|
</form>
|
||||||
</CardContent>
|
</CardContent>
|
||||||
</Card>
|
</Card>
|
||||||
|
|
||||||
<JobsList
|
<JobsList
|
||||||
initialJobs={jobs}
|
initialJobs={jobs}
|
||||||
libraries={libraryMap}
|
libraries={libraryMap}
|
||||||
highlightJobId={highlight}
|
highlightJobId={highlight}
|
||||||
|
|||||||
@@ -13,6 +13,7 @@ chrono.workspace = true
|
|||||||
futures = "0.3"
|
futures = "0.3"
|
||||||
image.workspace = true
|
image.workspace = true
|
||||||
notify = "6.1"
|
notify = "6.1"
|
||||||
|
num_cpus.workspace = true
|
||||||
parsers = { path = "../../crates/parsers" }
|
parsers = { path = "../../crates/parsers" }
|
||||||
rand.workspace = true
|
rand.workspace = true
|
||||||
rayon.workspace = true
|
rayon.workspace = true
|
||||||
|
|||||||
@@ -67,7 +67,10 @@ async fn load_thumbnail_config(pool: &sqlx::PgPool) -> ThumbnailConfig {
|
|||||||
}
|
}
|
||||||
|
|
||||||
async fn load_thumbnail_concurrency(pool: &sqlx::PgPool) -> usize {
|
async fn load_thumbnail_concurrency(pool: &sqlx::PgPool) -> usize {
|
||||||
let default_concurrency = 2;
|
// Default: half the logical CPUs, clamped between 2 and 8.
|
||||||
|
// Archive extraction is I/O bound but benefits from moderate parallelism.
|
||||||
|
let cpus = num_cpus::get();
|
||||||
|
let default_concurrency = (cpus / 2).clamp(2, 8);
|
||||||
let row = sqlx::query(r#"SELECT value FROM app_settings WHERE key = 'limits'"#)
|
let row = sqlx::query(r#"SELECT value FROM app_settings WHERE key = 'limits'"#)
|
||||||
.fetch_optional(pool)
|
.fetch_optional(pool)
|
||||||
.await;
|
.await;
|
||||||
|
|||||||
@@ -238,27 +238,42 @@ pub async fn process_job(
|
|||||||
.await?
|
.await?
|
||||||
};
|
};
|
||||||
|
|
||||||
// Count total files for progress estimation
|
// Count total files for progress estimation.
|
||||||
let library_paths: Vec<String> = libraries
|
// For incremental rebuilds, use the DB count (instant) — the filesystem will be walked
|
||||||
.iter()
|
// once during discovery anyway, no need for a second full WalkDir pass.
|
||||||
.map(|library| {
|
// For full rebuilds, the DB is already cleared, so we must walk the filesystem.
|
||||||
crate::utils::remap_libraries_path(&library.get::<String, _>("root_path"))
|
let library_ids: Vec<uuid::Uuid> = libraries.iter().map(|r| r.get("id")).collect();
|
||||||
})
|
|
||||||
.collect();
|
|
||||||
|
|
||||||
let total_files: usize = library_paths
|
let total_files: usize = if !is_full_rebuild {
|
||||||
.par_iter()
|
let count: i64 = sqlx::query_scalar(
|
||||||
.map(|root_path| {
|
"SELECT COUNT(*) FROM book_files bf JOIN books b ON b.id = bf.book_id WHERE b.library_id = ANY($1)"
|
||||||
walkdir::WalkDir::new(root_path)
|
)
|
||||||
.into_iter()
|
.bind(&library_ids)
|
||||||
.filter_map(Result::ok)
|
.fetch_one(&state.pool)
|
||||||
.filter(|entry| {
|
.await
|
||||||
entry.file_type().is_file()
|
.unwrap_or(0);
|
||||||
&& parsers::detect_format(entry.path()).is_some()
|
count as usize
|
||||||
})
|
} else {
|
||||||
.count()
|
let library_paths: Vec<String> = libraries
|
||||||
})
|
.iter()
|
||||||
.sum();
|
.map(|library| {
|
||||||
|
crate::utils::remap_libraries_path(&library.get::<String, _>("root_path"))
|
||||||
|
})
|
||||||
|
.collect();
|
||||||
|
library_paths
|
||||||
|
.par_iter()
|
||||||
|
.map(|root_path| {
|
||||||
|
walkdir::WalkDir::new(root_path)
|
||||||
|
.into_iter()
|
||||||
|
.filter_map(Result::ok)
|
||||||
|
.filter(|entry| {
|
||||||
|
entry.file_type().is_file()
|
||||||
|
&& parsers::detect_format(entry.path()).is_some()
|
||||||
|
})
|
||||||
|
.count()
|
||||||
|
})
|
||||||
|
.sum()
|
||||||
|
};
|
||||||
|
|
||||||
info!(
|
info!(
|
||||||
"[JOB] Found {} libraries, {} total files to index",
|
"[JOB] Found {} libraries, {} total files to index",
|
||||||
|
|||||||
Reference in New Issue
Block a user