perf: compress text responses from the static server
GitHub Pages gzips for us, so the deployed site never had this problem. The Docker image serves through serve.ts, which did not — so a self-hoster shipped the bundle at 344 KB where the site sends 100 KB, and the feed at 90 KB where the site sends 10 KB. Roughly three times the bytes, and on anything slower than a laptop on wifi three times the download. Negotiated on `accept-encoding` and applied only to the text types this app serves; a PNG is left alone rather than spending CPU to grow it. `Vary` goes out on both answers, because a shared cache that does not know the response depends on the request header will hand gzipped bytes to a client that never asked. The compressed bytes are cached in memory and keyed by mtime — these files change only on deploy, so re-gzipping 344 KB per request is waste, and keying on mtime rather than holding forever keeps `bun run dev` serving what was just rebuilt. A failure to compress falls through to the raw file: this is an optimisation and never a reason to fail a request. Co-Authored-By: Claude Opus 5 (1M context) <[email protected]>
This commit is contained in:
co-authored by
Claude Opus 5
parent
a7cf59d8e4
commit
3e30ab07aa
@@ -23,6 +23,11 @@ beforeAll(async () => {
|
||||
"<!doctype html><html><body>shell</body></html>",
|
||||
);
|
||||
await writeFile(join(root, "sw.js"), "// worker");
|
||||
// Long and repetitive, so gzip is unambiguously smaller than the original —
|
||||
// a short string compresses to *more* bytes than it started with.
|
||||
await writeFile(join(root, "main.js"), `console.log("hello");\n`.repeat(400));
|
||||
// Already-compressed bytes, which must be served untouched.
|
||||
await writeFile(join(root, "shot.png"), Buffer.from([0x89, 0x50, 0x4e, 0x47, 0, 1, 2, 3]));
|
||||
await writeFile(
|
||||
join(root, "data", "events.v1.json"),
|
||||
JSON.stringify({ schemaVersion: 1, generatedAt: "", events: [], sources: [] }),
|
||||
@@ -110,3 +115,66 @@ describe("static server", () => {
|
||||
expect(res.headers.get("cache-control")).toBe("no-cache");
|
||||
});
|
||||
});
|
||||
|
||||
/**
|
||||
* Compression, which is the whole difference between the Docker image and the
|
||||
* deployed site.
|
||||
*
|
||||
* GitHub Pages gzips on our behalf, so the bundle crosses the wire at a third of
|
||||
* its size there and did not here — and this file is what the image runs. Three
|
||||
* times the bytes is the only thing a self-hoster would ever have seen.
|
||||
*/
|
||||
describe("static server: compression", () => {
|
||||
test("gzips a text asset for a client that asks", async () => {
|
||||
const res = await fetch(`${base}/main.js`, {
|
||||
headers: { "accept-encoding": "gzip" },
|
||||
});
|
||||
expect(res.headers.get("content-encoding")).toBe("gzip");
|
||||
// Decoded by `fetch` on the way in, so this is the original text back —
|
||||
// which is the property that matters: compression must be lossless.
|
||||
expect(await res.text()).toBe(`console.log("hello");\n`.repeat(400));
|
||||
});
|
||||
|
||||
test("and is actually smaller on the wire", async () => {
|
||||
// Announcing gzip while sending the same number of bytes would be a pure
|
||||
// regression, so compare the two content-lengths rather than trusting the
|
||||
// header.
|
||||
const gz = await fetch(`${base}/main.js`, {
|
||||
headers: { "accept-encoding": "gzip" },
|
||||
});
|
||||
const raw = await fetch(`${base}/main.js`, {
|
||||
headers: { "accept-encoding": "identity" },
|
||||
});
|
||||
const len = (r: Response) => Number(r.headers.get("content-length"));
|
||||
expect(len(gz)).toBeGreaterThan(0);
|
||||
expect(len(gz)).toBeLessThan(len(raw) / 2);
|
||||
});
|
||||
|
||||
test("sends it raw to a client that does not ask", async () => {
|
||||
const res = await fetch(`${base}/main.js`, {
|
||||
headers: { "accept-encoding": "identity" },
|
||||
});
|
||||
expect(res.headers.get("content-encoding")).toBeNull();
|
||||
});
|
||||
|
||||
test("varies on accept-encoding either way", async () => {
|
||||
// A shared cache that does not know the response depends on the request
|
||||
// header will hand gzipped bytes to a client that never asked, so the header
|
||||
// has to be there on the uncompressed answer too.
|
||||
for (const encoding of ["gzip", "identity"]) {
|
||||
const res = await fetch(`${base}/main.js`, {
|
||||
headers: { "accept-encoding": encoding },
|
||||
});
|
||||
expect(res.headers.get("vary")).toBe("accept-encoding");
|
||||
}
|
||||
});
|
||||
|
||||
test("leaves already-compressed bytes alone", async () => {
|
||||
// Gzipping a PNG spends CPU to make the file bigger.
|
||||
const res = await fetch(`${base}/shot.png`, {
|
||||
headers: { "accept-encoding": "gzip" },
|
||||
});
|
||||
expect(res.headers.get("content-encoding")).toBeNull();
|
||||
expect(res.headers.get("vary")).toBeNull();
|
||||
});
|
||||
});
|
||||
|
||||
Reference in New Issue
Block a user