Add small in-actor LRU cache for hot assets

AssetStoreServer runs on a single dedicated smarm actor thread, so a
plain HashMap+VecDeque LRU in front of the SQLite lookup needs no
locking. Capacity configurable via CCC_CACHE_CAPACITY (default 256).

Bench (bench/RPS): +42-47% RPS under a cache-sized/hot-set workload,
but a small net loss under adversarial uniform-random access with a
cache smaller than the catalog. Real traffic is hot-set skewed, so
net win in practice; capacity should be tuned to the expected hot set.

.gitignore

@@ -3,3 +3,7 @@
 
 /staging/*
 !/staging/.gitkeep
+
+# bench harness generates these locally (see bench/RPS); not meant to be committed
+bench/urls*.txt
+bench/full_urls*.txt

README.md

@@ -27,6 +27,8 @@ docker compose exec ccc /usr/local/bin/ccc add demo /staging/app.js 1.0.0
 (Alternatively `docker cp` a file straight into the container if you'd
 rather not use the staging mount.)
 
+_See [bench/RPS](bench/RPS) for an RPS bench of the store's LRU cache vs. raw SQLite._
+
 ## License
 
 AGPL-3.0-only - see [LICENSE](LICENSE). If you run a modified version

bench/RPS

@@ -0,0 +1,78 @@
+# CCC bench: RPS ceiling + LRU cache impact
+
+Quick and dirty throughput bench, run locally on a 24-core box. Not
+scientific, just enough to sanity-check the actor-based SQLite store and
+the small LRU cache in front of it.
+
+## Harness
+
+- `bench/seed.py` fills a fresh `cdn.db` with random packages/versions/
+  assets (default: 500 packages x 5 versions = 2500 assets, 512B-8KB
+  gzipped JS each) and writes `bench/urls.txt` (one `/assets/...` path per
+  line, for every seeded asset).
+- Server pinned to 2 CPUs, load generator (`oha`, via
+  `nix-shell -p oha`) pinned to 6 CPUs, both via `taskset`, so client
+  capacity is never the bottleneck.
+
+```
+nix-shell -p python3 --run "python3 bench/seed.py cdn.db"
+awk '{print "http://127.0.0.1:8333"$0}' bench/urls.txt > /tmp/full_urls.txt
+
+CCC_DB_PATH=$(pwd)/cdn.db taskset -c 0,1 ./target/release/CCC serve --port 8333 &
+
+nix-shell -p oha --run \
+  "taskset -c 2-7 oha -z 8s -c 200 --no-tui --urls-from-file /tmp/full_urls.txt"
+```
+
+Skewed/hot-set workload (80% of requests hit the top 50 of 2500 assets,
+i.e. a realistic CDN access pattern) was generated with a short Python
+snippet sampling from `bench/urls.txt` with `random.random() < 0.8` picking
+from the first 50 lines, else uniformly from the rest, written to a
+`urls_hot80_20.txt` file and expanded the same way as above.
+
+## Results: no cache (baseline)
+
+Single-threaded `smarm` actor (`AssetStoreServer::loop_runner`) serializes
+every asset lookup onto one thread/one SQLite connection, so this is
+inherently CPU-bound on the 2 pinned cores regardless of client
+concurrency.
+
+| Server CPUs | Client concurrency | RPS |
+|---|---|---|
+| 2 | 50  | ~56.7k |
+| 2 | 100 | ~60.1k |
+| 2 | 200 | ~62.1k (peak, server at ~176-200% CPU, saturated) |
+| 2 | 400 | ~60.0k (plateaued) |
+| 2 | 800 | ~55.9k (queueing overhead) |
+| 2 (client sends `Accept-Encoding: gzip`, server skips decompression) | 200 | ~60.4k |
+| 1 | 200 | ~30.8k (confirms CPU-bound, scales with cores) |
+
+Client (6 CPUs) stayed at ~4% usr / 8% sys throughout - never the
+bottleneck.
+
+## Results: with the LRU cache (`CCC_CACHE_CAPACITY`, default 256)
+
+The cache lives inside `AssetStoreServer` itself (see `src/main.rs`), so
+it needs no locking - the actor thread is already strictly sequential.
+
+| Scenario | Cache capacity | RPS | vs. no-cache baseline (62.1k) |
+|---|---|---|---|
+| Uniform-random over all 2500 assets | 256 (default) | ~55.3k | **-11%** |
+| Uniform-random over all 2500 assets | 3000 (covers full catalog) | ~88.1k | **+42%** |
+| 80/20 hot-set (50 hot assets get 80% of traffic) | 256 (default) | ~91.1k | **+47%** |
+
+### Caveat
+
+Under a purely uniform-random access pattern with a cache smaller than
+the catalog (low hit rate), the cache is a net loss: every request now
+pays HashMap lookup + insert + eviction bookkeeping on top of the SQLite
+query, for a hit rate too low to earn it back. The `touch()` on hit is
+also an O(n) scan of the recency queue, which doesn't help at low
+capacities.
+
+Real CDN traffic is essentially never uniform-random (it's hot-set/
+power-law skewed), so in practice this is a clear win, but `CCC_CACHE_CAPACITY`
+should be sized to the actual hot set rather than left at the arbitrary
+default of 256. A follow-up would swap the O(n) recency scan for a proper
+O(1) LRU (e.g. an intrusive linked-hashmap) to remove the downside case
+entirely.

bench/seed.py

@@ -0,0 +1,70 @@
+#!/usr/bin/env python3
+"""Seed cdn.db with random packages/versions/files for benchmarking."""
+import gzip
+import os
+import random
+import sqlite3
+import string
+import sys
+
+DB_PATH = sys.argv[1] if len(sys.argv) > 1 else "cdn.db"
+N_PACKAGES = int(os.environ.get("N_PACKAGES", 500))
+VERSIONS_PER_PKG = int(os.environ.get("VERSIONS_PER_PKG", 5))
+MIN_SIZE = int(os.environ.get("MIN_SIZE", 512))
+MAX_SIZE = int(os.environ.get("MAX_SIZE", 8192))
+
+random.seed(42)
+
+if os.path.exists(DB_PATH):
+    os.remove(DB_PATH)
+
+conn = sqlite3.connect(DB_PATH)
+conn.execute("""CREATE TABLE IF NOT EXISTS packages (
+    name     TEXT PRIMARY KEY,
+    archived INTEGER NOT NULL DEFAULT 0
+)""")
+conn.execute("""CREATE TABLE IF NOT EXISTS versions (
+    package        TEXT NOT NULL REFERENCES packages(name),
+    version        TEXT NOT NULL,
+    filename       TEXT NOT NULL,
+    mime_type      TEXT NOT NULL,
+    gzipped_bytes  BLOB NOT NULL,
+    archived       INTEGER NOT NULL DEFAULT 0,
+    PRIMARY KEY (package, version)
+)""")
+
+def rand_name(n=10):
+    return "".join(random.choices(string.ascii_lowercase, k=n))
+
+def rand_body(size):
+    chars = string.ascii_letters + string.digits + " \n"
+    return "".join(random.choices(chars, k=size)).encode()
+
+manifest = []  # (package, version, filename) for the load generator
+
+pkg_names = [f"pkg-{rand_name(8)}-{i}" for i in range(N_PACKAGES)]
+
+for name in pkg_names:
+    conn.execute("INSERT INTO packages (name, archived) VALUES (?, 0)", (name,))
+    for v in range(VERSIONS_PER_PKG):
+        version = f"{v+1}.0.0"
+        filename = f"{rand_name(6)}.js"
+        size = random.randint(MIN_SIZE, MAX_SIZE)
+        raw = rand_body(size)
+        gz = gzip.compress(raw, compresslevel=6)
+        conn.execute(
+            "INSERT INTO versions (package, version, filename, mime_type, gzipped_bytes, archived) "
+            "VALUES (?, ?, ?, 'application/javascript', ?, 0)",
+            (name, version, filename, gz),
+        )
+        manifest.append((name, version, filename))
+
+conn.commit()
+conn.close()
+
+with open("bench/urls.txt", "w") as f:
+    for pkg, ver, fn in manifest:
+        f.write(f"/assets/{pkg}/{ver}/{fn}\n")
+
+print(f"seeded {len(pkg_names)} packages, {len(manifest)} versions -> {DB_PATH}")
+print(f"wrote {len(manifest)} urls -> bench/urls.txt")

src/main.rs

@@ -1,6 +1,7 @@
 mod store;
 
 use rusqlite::{params, Connection};
+use std::collections::{HashMap, VecDeque};
 use std::io::Read;
 use std::sync::OnceLock;
 use flate2::read::GzDecoder;
@@ -13,6 +14,72 @@ pub struct AssetPayload {
     pub mime_type: String,
 }
 
+/// Identifies a single (package, version, filename) asset for cache lookups.
+type AssetKey = (String, String, String);
+
+/// Small hand-rolled LRU cache for hot assets, sitting in front of SQLite.
+///
+/// `AssetStoreServer` runs on a single dedicated actor thread (see
+/// `loop_runner`), so this cache needs no locking whatsoever - every call
+/// happens strictly sequentially. Capacity is intentionally small; this is
+/// meant to absorb hot-asset traffic, not replace the DB as a working set.
+struct AssetCache {
+    capacity: usize,
+    entries: HashMap<AssetKey, AssetPayload>,
+    // Recency queue, most-recently-used at the back. Kept simple (O(n)
+    // scan on hit) since capacity is small and this is a single thread.
+    order: VecDeque<AssetKey>,
+}
+
+impl AssetCache {
+    fn new(capacity: usize) -> Self {
+        Self { capacity, entries: HashMap::new(), order: VecDeque::new() }
+    }
+
+    fn get(&mut self, key: &AssetKey) -> Option<AssetPayload> {
+        if self.capacity == 0 {
+            return None;
+        }
+        let hit = self.entries.get(key).cloned();
+        if hit.is_some() {
+            self.touch(key);
+        }
+        hit
+    }
+
+    fn put(&mut self, key: AssetKey, value: AssetPayload) {
+        if self.capacity == 0 {
+            return;
+        }
+        if self.entries.contains_key(&key) {
+            self.entries.insert(key.clone(), value);
+            self.touch(&key);
+            return;
+        }
+        if self.entries.len() >= self.capacity {
+            if let Some(oldest) = self.order.pop_front() {
+                self.entries.remove(&oldest);
+            }
+        }
+        self.order.push_back(key.clone());
+        self.entries.insert(key, value);
+    }
+
+    fn touch(&mut self, key: &AssetKey) {
+        if let Some(pos) = self.order.iter().position(|k| k == key) {
+            let k = self.order.remove(pos).unwrap();
+            self.order.push_back(k);
+        }
+    }
+}
+
+fn cache_capacity() -> usize {
+    std::env::var("CCC_CACHE_CAPACITY")
+        .ok()
+        .and_then(|v| v.parse().ok())
+        .unwrap_or(256)
+}
+
 #[derive(Serialize)]
 pub struct PackageListing {
     name: String,
@@ -33,15 +100,16 @@ pub enum GenServerMsg {
 
 pub struct AssetStoreServer {
     conn: Connection,
+    cache: AssetCache,
 }
 
 impl AssetStoreServer {
     pub fn new() -> Self {
         let conn = store::open().expect("Failed to open SQLite database");
-        Self { conn }
+        Self { conn, cache: AssetCache::new(cache_capacity()) }
     }
 
-    pub fn loop_runner(self, rx: smarm::Receiver<GenServerMsg>) {
+    pub fn loop_runner(mut self, rx: smarm::Receiver<GenServerMsg>) {
         while let Ok(msg) = rx.recv() {
             match msg {
                 GenServerMsg::FetchAsset { package, version, filename, reply_to } => {
@@ -56,7 +124,12 @@ impl AssetStoreServer {
         }
     }
 
-    fn fetch_asset(&self, package: &str, version: &str, filename: &str) -> Result<Option<AssetPayload>, String> {
+    fn fetch_asset(&mut self, package: &str, version: &str, filename: &str) -> Result<Option<AssetPayload>, String> {
+        let key: AssetKey = (package.to_string(), version.to_string(), filename.to_string());
+        if let Some(cached) = self.cache.get(&key) {
+            return Ok(Some(cached));
+        }
+
         let mut stmt = self.conn
             .prepare(
                 "SELECT gzipped_bytes, mime_type FROM versions
@@ -69,7 +142,9 @@ impl AssetStoreServer {
         if let Some(row) = rows.next().map_err(|e| e.to_string())? {
             let gzipped_bytes: Vec<u8> = row.get(0).map_err(|e| e.to_string())?;
             let mime_type: String = row.get(1).map_err(|e| e.to_string())?;
-            Ok(Some(AssetPayload { gzipped_bytes, mime_type }))
+            let payload = AssetPayload { gzipped_bytes, mime_type };
+            self.cache.put(key, payload.clone());
+            Ok(Some(payload))
         } else {
             Ok(None)
         }