Originals cache size limit with least-recently-used eviction (closes #47)

Bounds the originals cache and evicts least-recently-used. cacheOriginalsMaxBytes default 100 GiB; the effective limit adapts down via fs.statfs to keep freeBelowBytes (default 50 GiB) free. Over-limit writes evict unpinned originals oldest-mtime-first (mtime touched on read); pinned files (favorites + latest week) are skipped and an over-budget on-demand fetch proceeds over-limit. Every in-flight write is excluded from eviction, so concurrent fetches never delete each other's just-stored file. Only cacheDirectory/originals is evicted; downloadDirectory and thumbnails never.

Model: opus-4-8

test/library/content-eviction.test.ts

@@ -0,0 +1,358 @@
+/**
+ * Tests for the originals cache size limit and LRU eviction (issue #47),
+ * layered on the on-disk content cache (#46).
+ *
+ * Only `cacheDirectory/originals` is bounded and evicted. Before each original
+ * write the effective limit is
+ *   min(cacheOriginalsMaxBytes, bytesUsedByOriginals + bytesFree - freeBelowBytes)
+ * with `bytesFree` read from `statfs` on the volume holding `cacheDirectory`.
+ * The limit therefore falls as the disk fills and rises as space returns. When
+ * a write would cross the limit, least-recently-used originals are removed until
+ * it fits; pinned files are skipped, and if only pinned files remain the write
+ * proceeds over-limit. Last-use is the file `mtime`, bumped whenever a read
+ * returns an original's path, so ordering survives a restart with no ledger.
+ *
+ * `statfs` is injected so the adaptive limit is exercised deterministically:
+ * `bsize` is 1, so `bavail` is the free byte count the formula sees. The source
+ * writes a controllable number of bytes per file, and tests set each stored
+ * file's `mtime` explicitly so LRU order does not depend on wall-clock timing.
+ */
+
+import { describe, it, expect, beforeEach, afterEach } from "vitest";
+import { mkdtempSync, rmSync, existsSync, statSync, utimesSync } from "node:fs";
+import { writeFile } from "node:fs/promises";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+
+import {
+    ContentCache,
+    type ContentSource,
+    type StatFsFn,
+} from "../../src/library/content.js";
+import { RequestPools } from "../../src/library/pools.js";
+import type { EnteFile } from "../../src/model/types.js";
+
+const file = (id: number): EnteFile => ({
+    id,
+    collectionID: 1,
+    ownerID: 1,
+    key: new Uint8Array([id & 0xff]),
+    metadata: {
+        title: `file-${id}.jpg`,
+        fileType: "image",
+        creationTime: 0,
+        modificationTime: 0,
+    },
+    file: { decryptionHeader: "aGVhZGVy" },
+    thumbnail: { decryptionHeader: "dGh1bWI=" },
+    updationTime: 0,
+});
+
+// A source that writes a controllable number of bytes per file (default 10).
+class SizedSource implements ContentSource {
+    sizeFor = new Map<number, number>();
+
+    async original(args: {
+        file: EnteFile;
+        destination: string;
+    }): Promise<{ bytesWritten: number }> {
+        const n = this.sizeFor.get(args.file.id) ?? 10;
+        await writeFile(args.destination, Buffer.alloc(n, 1));
+        return { bytesWritten: n };
+    }
+
+    async thumbnail(args: {
+        file: EnteFile;
+        destination: string;
+    }): Promise<{ bytesWritten: number }> {
+        await writeFile(args.destination, Buffer.alloc(10, 1));
+        return { bytesWritten: 10 };
+    }
+}
+
+// A source whose original() writes 10 bytes but blocks on a gate before
+// returning, so two fetches can be held in flight together. `bothStarted`
+// resolves once both originals have entered, and `release()` lets them finish.
+class GatedSource implements ContentSource {
+    private openGate!: () => void;
+    private readonly gate = new Promise<void>((r) => (this.openGate = r));
+    private inFlight = 0;
+    private reachedTwo!: () => void;
+    readonly bothStarted = new Promise<void>((r) => (this.reachedTwo = r));
+
+    async original(args: {
+        file: EnteFile;
+        destination: string;
+    }): Promise<{ bytesWritten: number }> {
+        this.inFlight += 1;
+        if (this.inFlight === 2) this.reachedTwo();
+        await this.gate;
+        await writeFile(args.destination, Buffer.alloc(10, 1));
+        return { bytesWritten: 10 };
+    }
+
+    async thumbnail(args: {
+        file: EnteFile;
+        destination: string;
+    }): Promise<{ bytesWritten: number }> {
+        await writeFile(args.destination, Buffer.alloc(10, 1));
+        return { bytesWritten: 10 };
+    }
+
+    release(): void {
+        this.openGate();
+    }
+}
+
+let root: string;
+let cacheDir: string;
+
+beforeEach(() => {
+    root = mkdtempSync(join(tmpdir(), "quak-eviction-"));
+    cacheDir = join(root, "cache");
+});
+
+afterEach(() => {
+    if (root && existsSync(root))
+        rmSync(root, { recursive: true, force: true });
+});
+
+const originalPath = (id: number): string =>
+    join(cacheDir, "originals", `${id}.jpg`);
+
+// Pin an original's mtime to a fixed second-resolution instant so LRU order is
+// deterministic. Lower `seconds` = older = evicted first.
+const setMtime = (id: number, seconds: number): void => {
+    utimesSync(originalPath(id), seconds, seconds);
+};
+
+const buildCache = (args: {
+    source?: ContentSource;
+    files?: EnteFile[];
+    statfs: StatFsFn;
+    cacheOriginalsMaxBytes?: number;
+    freeBelowBytes?: number;
+    isPinned?: (fileID: number) => boolean;
+}): { cache: ContentCache; source: SizedSource } => {
+    const source = (args.source as SizedSource) ?? new SizedSource();
+    const byID = new Map<number, EnteFile>();
+    for (const f of args.files ?? [file(1), file(2), file(3), file(4), file(5)])
+        byID.set(f.id, f);
+    const cache = new ContentCache({
+        pools: new RequestPools(),
+        source,
+        cacheDirectory: cacheDir,
+        getFile: (id) => byID.get(id),
+        statfs: args.statfs,
+        cacheOriginalsMaxBytes: args.cacheOriginalsMaxBytes,
+        freeBelowBytes: args.freeBelowBytes,
+        isPinned: args.isPinned,
+    });
+    return { cache, source };
+};
+
+// Plenty of free space, so the configured max governs the limit unless a test
+// dials it down. `bsize` of 1 makes `bavail` the free byte count.
+const abundantFree: StatFsFn = async () => ({
+    bsize: 1,
+    bavail: 1_000_000_000,
+});
+
+describe("originals eviction", () => {
+    it("removes least-recently-used originals to fit the limit", async () => {
+        // Each original is 10 bytes; a 25-byte cap holds two.
+        const { cache } = buildCache({
+            statfs: abundantFree,
+            cacheOriginalsMaxBytes: 25,
+            freeBelowBytes: 0,
+        });
+        await cache.open();
+
+        await cache.original(1);
+        setMtime(1, 1000);
+        await cache.original(2);
+        setMtime(2, 2000);
+        // Writing the third (total 30 > 25) evicts the oldest, file 1.
+        await cache.original(3);
+
+        expect(existsSync(originalPath(1))).toBe(false);
+        expect(existsSync(originalPath(2))).toBe(true);
+        expect(existsSync(originalPath(3))).toBe(true);
+        expect(cache.pathsFor(1).originalPath).toBeUndefined();
+        expect(cache.originalsStatus().usedBytes).toBe(20);
+    });
+
+    it("skips pinned files, evicting the oldest unpinned instead", async () => {
+        const { cache } = buildCache({
+            statfs: abundantFree,
+            cacheOriginalsMaxBytes: 25,
+            freeBelowBytes: 0,
+            isPinned: (id) => id === 1,
+        });
+        await cache.open();
+
+        await cache.original(1);
+        setMtime(1, 1000); // oldest, but pinned
+        await cache.original(2);
+        setMtime(2, 2000);
+        await cache.original(3);
+
+        // File 1 is oldest but pinned, so file 2 is evicted instead.
+        expect(existsSync(originalPath(1))).toBe(true);
+        expect(existsSync(originalPath(2))).toBe(false);
+        expect(existsSync(originalPath(3))).toBe(true);
+    });
+
+    it("proceeds over-limit when only pinned files remain", async () => {
+        // A 5-byte cap cannot hold even one 10-byte original.
+        const { cache } = buildCache({
+            statfs: abundantFree,
+            cacheOriginalsMaxBytes: 5,
+            freeBelowBytes: 0,
+            isPinned: () => true,
+        });
+        await cache.open();
+
+        const result = await cache.original(1);
+
+        expect(existsSync(result.path)).toBe(true);
+        const status = cache.originalsStatus();
+        expect(status.usedBytes).toBe(10);
+        expect(status.usedBytes).toBeGreaterThan(status.limitBytes ?? 0);
+    });
+
+    it("keeps a just-written original larger than the limit, evicting it only on a later write", async () => {
+        // A 5-byte cap cannot hold even one 10-byte original, but a fetch must
+        // never evict the file it just wrote and is about to return.
+        const { cache } = buildCache({
+            statfs: abundantFree,
+            cacheOriginalsMaxBytes: 5,
+            freeBelowBytes: 0,
+        });
+        await cache.open();
+
+        const result = await cache.original(1);
+
+        // The just-written original survives its own over-budget write and the
+        // returned path exists on disk.
+        expect(existsSync(result.path)).toBe(true);
+        expect(existsSync(originalPath(1))).toBe(true);
+        expect(cache.originalsStatus().usedBytes).toBe(10);
+        setMtime(1, 1000);
+
+        // A later write finds file 1 eligible and evicts it to make room, while
+        // the newly written file 2 is itself kept over-limit.
+        await cache.original(2);
+        expect(existsSync(originalPath(1))).toBe(false);
+        expect(existsSync(originalPath(2))).toBe(true);
+        expect(cache.originalsStatus().usedBytes).toBe(10);
+    });
+
+    it("adapts the limit down as the disk fills and up as space returns", async () => {
+        // The configured max is generous; free space drives the limit. Eviction
+        // only kicks in once free space falls below the protected reserve.
+        let free = 1_000_000;
+        const statfs: StatFsFn = async () => ({ bsize: 1, bavail: free });
+        const { cache } = buildCache({
+            statfs,
+            cacheOriginalsMaxBytes: 1000,
+            freeBelowBytes: 100,
+        });
+        await cache.open();
+
+        // Ample free space: the limit is the configured max and nothing is
+        // evicted as three 10-byte originals accumulate.
+        await cache.original(1);
+        setMtime(1, 1000);
+        await cache.original(2);
+        setMtime(2, 2000);
+        await cache.original(3);
+        setMtime(3, 3000);
+        expect(cache.originalsStatus().limitBytes).toBe(1000);
+        expect(cache.originalsStatus().usedBytes).toBe(30);
+
+        // The disk fills: only 95 bytes free, below the 100-byte reserve. The
+        // next write (used 40) sees limit = min(1000, 40 + 95 - 100) = 35 and
+        // evicts the oldest original (file 1) to fit.
+        free = 95;
+        await cache.original(4);
+        expect(cache.originalsStatus().limitBytes).toBe(35);
+        expect(existsSync(originalPath(1))).toBe(false);
+        expect(cache.originalsStatus().usedBytes).toBe(30);
+        setMtime(4, 4000);
+
+        // Space returns: the limit rises back to the configured max and the
+        // next write is kept without eviction.
+        free = 1_000_000;
+        await cache.original(5);
+        expect(cache.originalsStatus().limitBytes).toBe(1000);
+        expect(existsSync(originalPath(4))).toBe(true);
+        expect(existsSync(originalPath(5))).toBe(true);
+    });
+
+    it("bumps an original's mtime when a read returns its path", async () => {
+        const { cache } = buildCache({
+            statfs: abundantFree,
+            cacheOriginalsMaxBytes: 1000,
+            freeBelowBytes: 0,
+        });
+        await cache.open();
+
+        await cache.original(1);
+        // Age the file well into the past.
+        setMtime(1, 1000);
+        expect(statSync(originalPath(1)).mtimeMs).toBeLessThan(2_000_000);
+
+        // A second read is a cache hit that must touch the file.
+        const before = Date.now();
+        await cache.original(1);
+        expect(statSync(originalPath(1)).mtimeMs).toBeGreaterThanOrEqual(
+            before - 2000,
+        );
+    });
+
+    it("keeps both originals when two over-budget fetches race", async () => {
+        // A 15-byte cap holds one 10-byte original but not two. Two fetches are
+        // held in flight together; when both stored files cross the limit,
+        // neither eviction pass may delete the sibling whose path has not yet
+        // been returned, so both survive over-limit.
+        const source = new GatedSource();
+        const { cache } = buildCache({
+            source,
+            statfs: abundantFree,
+            cacheOriginalsMaxBytes: 15,
+            freeBelowBytes: 0,
+        });
+        await cache.open();
+
+        const p1 = cache.original(1);
+        const p2 = cache.original(2);
+        await source.bothStarted; // both downloads are in flight before either stores
+        source.release();
+        const [r1, r2] = await Promise.all([p1, p2]);
+
+        // Both returned paths exist on disk even though together they exceed the
+        // cap; nothing was evicted out from under a fetch still in progress.
+        expect(existsSync(r1.path)).toBe(true);
+        expect(existsSync(r2.path)).toBe(true);
+        expect(existsSync(originalPath(1))).toBe(true);
+        expect(existsSync(originalPath(2))).toBe(true);
+        expect(cache.originalsStatus().usedBytes).toBe(20);
+    });
+
+    it("never counts or evicts thumbnails", async () => {
+        const { cache } = buildCache({
+            statfs: abundantFree,
+            cacheOriginalsMaxBytes: 5,
+            freeBelowBytes: 0,
+        });
+        await cache.open();
+
+        await cache.thumbnail(1);
+        await cache.thumbnail(2);
+
+        expect(cache.pathsFor(1).thumbnailPath).toBeDefined();
+        expect(cache.pathsFor(2).thumbnailPath).toBeDefined();
+        expect(cache.originalsStatus().usedBytes).toBe(0);
+    });
+});