Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Ada: Parsing Millions of URLs per Second

Daniel Lemire
November 02, 2023
76

Ada: Parsing Millions of URLs per Second

With the end of Dennard scaling, the cost of computing is no longer falling at the hardware level: to improve efficiency, we need better software. Competing JavaScript runtimes are sometimes faster than Node.js: can we bridge the gap? We show that Node.js can not only match faster competitors but even surpass them given enough effort. URLs are the most fundamental element in web applications. Node.js 16 was significantly slower than competing engines (Bun and Deno) at URL parsing. By reducing the number of instructions and vectorizing sub-algorithms, we multiplied by three the speed of URL parsing in Node.js (as of Node.js 20). If you have upgraded Node.js, you have the JavaScript engine with the fastest URL parsing in the industry with uncompromising support for the latest WHATGL URL standard. We share our strategies for accelerating both C++ and JavaScript processing in practice.

Daniel Lemire

November 02, 2023
Tweet

Transcript

  1. Software performance Reduces cost (AWS, Azure) Improves latency Reduce complexity

    (parallelism, caching) Don't cause climate change D 2
  2. State of Node.js Performance 2023 Since Node.js 18, a new

    URL parser dependency was added to Node.js — Ada. This addition bumped the Node.js performance when parsing URLs to a new level. Some results could reach up to an improvement of 400%. (State of Node.js Performance 2023) D 3
  3. Just had a benchmark for a code change go from

    11 seconds to complete down to about half a second to complete. This makes me very happy. James Snell, Cloudflare Referencing adding Ada URL to Cloudflare Workers Y 4
  4. Examples non-ASCII: http:// 你好你好. 在线 File: file:///foo/bar/test/node.js JavaScript: javascript:alert("node is

    awesome"); Percent Encoding: https://\%E4\%BD\%A0/foo Pathname with dots: https://example.org/./a/../b/./c Ipv4 address with hex/octal digits: https://127.0.0x0.1 D 6
  5. WHATWG URL input string https://7-Eleven.com/Home/../P/Montréal PHP unchanged Python unchanged WHATWG

    URL https://xn--7eleven-506c.com/Home/P/Montr%C3%A9al curl 7.87 https://7-Eleven.com/P/Montr%C3%A9al Go runtime ( net/url ) https://7-Eleven.com/Home/../P/Montr%C3%A9al D 7
  6. Assumptions Does URL parsing really matter? Is it bottleneck to

    some performance metric? Tbh i care more about JS runtimes to handle CI/CD processes faster and more parallelized. URLs are free, you don't gain anything by overloading them. Y 8
  7. HTTP Benchmark const f = require('fastify')() f.post('/simple', async (request) =>

    { const { url } = request.body return { parsed: url } }) f.post('/href', async (request) => { const { url } = request.body return { parsed: new URL(url).href } }) Input: { "url": "https://www.google.com/hello-world?query=search\#value" } Y 9
  8. Wrote a C++ library (called Ada) Named after Ada Nizipli

    Full WHATWG URL support No dependency, full portability Over 20,000 lines of code Six months of work, 25 contributors Apache-2.0, MIT licensed Available at https://github.com/ada-url/ada Y 11
  9. 6 million URLs parsed/second Apple M2, LLVM 14 Wide range

    of realistic data sources Faster than alternatives in C, C++, Rust WHATWG URL: whatwg-url and rust-url D 12
  10. Trick 1: perfect hashing std::string_view names[] = {"http", " ",

    "https", "ws", "ftp", "wss", "file", " "}; enum type : uint8_t { HTTP, NOT_SPECIAL, HTTPS, WS, FTP, WSS, FILE}; type get_scheme_type(std::string_view scheme) noexcept { int hash_value = (2 * scheme.size() + scheme[0]) % 8; const std::string_view target = names[hash_value]; if (target == scheme) { return type(hash_value); } else { return NOT_SPECIAL; } } D 13
  11. Trick 2: use memoization (tables) https://en.wikipedia.org/wiki/Memoization uint8_t contains_bad_char(unsigned char* input,

    size_t length) { uint8_t accumulator = 0; for (size_t i = 0; i < length; i++) { accumulator |= is_bad_char[input[i]]; } return accumulator; } D 14
  12. Trick 3: use vectorization Do no process byte-by-byte when you

    can process 16-byte by 16-byte. bool has_tabs_or_newline(std::string_view user_input) { size_t i = 0; const __m128i mask1 = _mm_set1_epi8('\r'); const __m128i mask2 = _mm_set1_epi8('\n'); const __m128i mask3 = _mm_set1_epi8('\t'); __m128i running{0}; for (; i + 15 < user_input.size(); i += 16) { __m128i word = _mm_loadu_si128(user_input.data() + i); running = _mm_or_si128( _mm_or_si128(running, _mm_or_si128( _mm_cmpeq_epi8(word, mask1), _mm_cmpeq_epi8(word, mask2))), _mm_cmpeq_epi8(word, mask3)); } return _mm_movemask_epi8(running) != 0; } D 15
  13. JavaScript Benchmark bench(filename, () => { for (let i =

    0; i < lines.length; i++) { try { length += new URL(lines[i]).href.length; good_url++; } catch (e) { bad_url++; } } return length; }); https://github.com/ada-url/js_url_benchmark/ Y 17
  14. The Ada C++ library is safe and efficient Modern C++

    Sanitizers Fuzzing Unit tests A few minor bugs were reported, mostly related to the standard. Quickly fixed. D 19
  15. Ada is available in the language of your choice JavaScript

    with Node.js C bindings at https://github.com/ada-url/ada Rust bindings at https://github.com/ada-url/rust Go bindings at https://github.com/ada-url/goada Python bindings at https://github.com/ada-url/ada-python R bindings at https://github.com/schochastics/adaR Often the only way to get WHATWG URL support! Y 20