diff --git a/Cargo.lock b/Cargo.lock index bd15955..a8563e2 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -17,6 +17,12 @@ dependencies = [ "memchr", ] +[[package]] +name = "anes" +version = "0.1.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "4b46cbb362ab8752921c97e041f5e366ee6297bd428a31275b9fcf1e380f7299" + [[package]] name = "anstream" version = "0.6.21" @@ -237,6 +243,12 @@ version = "1.11.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "1e748733b7cbc798e1434b6ac524f0c1ff2ab456fe201501e6497c8417a4fc33" +[[package]] +name = "cast" +version = "0.3.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "37b2a672a2cb129a2e41c10b1224bb368f9f37a2b16b612598138befd7b37eb5" + [[package]] name = "cc" version = "1.2.57" @@ -261,6 +273,58 @@ version = "0.2.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "613afe47fcd5fac7ccf1db93babcb082c5994d996f20b8b159f2ad1658eb5724" +[[package]] +name = "ciborium" +version = "0.2.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "42e69ffd6f0917f5c029256a24d0161db17cea3997d185db0d35926308770f0e" +dependencies = [ + "ciborium-io", + "ciborium-ll", + "serde", +] + +[[package]] +name = "ciborium-io" +version = "0.2.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "05afea1e0a06c9be33d539b876f1ce3692f4afea2cb41f740e7743225ed1c757" + +[[package]] +name = "ciborium-ll" +version = "0.2.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "57663b653d948a338bfb3eeba9bb2fd5fcfaecb9e199e87e1eda4d9e8b240fd9" +dependencies = [ + "ciborium-io", + "half", +] + +[[package]] +name = "clap" +version = "4.6.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b193af5b67834b676abd72466a96c1024e6a6ad978a1f484bd90b85c94041351" +dependencies = [ + "clap_builder", +] + +[[package]] +name = "clap_builder" +version = "4.6.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "714a53001bf66416adb0e2ef5ac857140e7dc3a0c48fb28b2f10762fc4b5069f" +dependencies = [ + "anstyle", + "clap_lex", +] + +[[package]] +name = "clap_lex" +version = "1.1.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c8d4a3bb8b1e0c1050499d1815f5ab16d04f0959b233085fb31653fbfc9d98f9" + [[package]] name = "cmake" version = "0.1.57" @@ -302,6 +366,73 @@ dependencies = [ "cfg-if", ] +[[package]] +name = "criterion" +version = "0.5.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f2b12d017a929603d80db1831cd3a24082f8137ce19c69e6447f54f5fc8d692f" +dependencies = [ + "anes", + "cast", + "ciborium", + "clap", + "criterion-plot", + "is-terminal", + "itertools", + "num-traits", + "once_cell", + "oorandom", + "plotters", + "rayon", + "regex", + "serde", + "serde_derive", + "serde_json", + "tinytemplate", + "walkdir", +] + +[[package]] +name = "criterion-plot" +version = "0.5.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6b50826342786a51a89e2da3a28f1c32b06e387201bc2d19791f622c673706b1" +dependencies = [ + "cast", + "itertools", +] + +[[package]] +name = "crossbeam-deque" +version = "0.8.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9dd111b7b7f7d55b72c0a6ae361660ee5853c9af73f70c3c2ef6858b950e2e51" +dependencies = [ + "crossbeam-epoch", + "crossbeam-utils", +] + +[[package]] +name = "crossbeam-epoch" +version = "0.9.18" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5b82ac4a3c2ca9c3460964f020e1402edd5753411d7737aa39c3714ad1b5420e" +dependencies = [ + "crossbeam-utils", +] + +[[package]] +name = "crossbeam-utils" +version = "0.8.21" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d0a5c400df2834b80a4c3327b3aad3a4c4cd4de0629063962b03235697506a28" + +[[package]] +name = "crunchy" +version = "0.2.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "460fbee9c2c2f33933d720630a6a0bac33ba7053db5344fac858d4b8952d77d5" + [[package]] name = "data-encoding" version = "2.10.0" @@ -348,6 +479,12 @@ version = "1.0.5" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "92773504d58c093f6de2459af4af33faa518c13451eb8f2b5698ed3d36e7c813" +[[package]] +name = "either" +version = "1.15.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "48c757948c5ede0e46177b7add2e67155f70e33c07fea8284df6576da70b3719" + [[package]] name = "env_filter" version = "1.0.0" @@ -548,12 +685,29 @@ dependencies = [ "tracing", ] +[[package]] +name = "half" +version = "2.7.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6ea2d84b969582b4b1864a92dc5d27cd2b77b622a8d79306834f1be5ba20d84b" +dependencies = [ + "cfg-if", + "crunchy", + "zerocopy", +] + [[package]] name = "hashbrown" version = "0.16.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "841d1cc9bed7f9236f321df977030373f4a4163ae1a7dbfe1a51a2c1a51d9100" +[[package]] +name = "hermit-abi" +version = "0.5.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "fc0fef456e4baa96da950455cd02c081ca953b141298e41db3fc7e36b1da849c" + [[package]] name = "http" version = "1.4.0" @@ -790,12 +944,32 @@ dependencies = [ "serde", ] +[[package]] +name = "is-terminal" +version = "0.4.17" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3640c1c38b8e4e43584d8df18be5fc6b0aa314ce6ebf51b53313d4306cca8e46" +dependencies = [ + "hermit-abi", + "libc", + "windows-sys 0.61.2", +] + [[package]] name = "is_terminal_polyfill" version = "1.70.2" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "a6cb138bb79a146c1bd460005623e142ef0181e3d0219cb493e02f7d08a35695" +[[package]] +name = "itertools" +version = "0.10.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b0fd2260e829bddf4cb6ea802289de2f86d6a7a690192fbe91b3f46e0f2c8473" +dependencies = [ + "either", +] + [[package]] name = "itoa" version = "1.0.17" @@ -971,6 +1145,7 @@ version = "0.5.0" dependencies = [ "arc-swap", "axum", + "criterion", "env_logger", "futures", "http-body-util", @@ -1010,6 +1185,12 @@ version = "1.70.2" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "384b8ab6d37215f3c5301a95a4accb5d64aa607f1fcb26a11b5303878451b4fe" +[[package]] +name = "oorandom" +version = "11.1.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d6790f58c7ff633d8771f42965289203411a5e5c68388703c06e14f24770b41e" + [[package]] name = "pem" version = "3.0.6" @@ -1038,6 +1219,34 @@ version = "0.1.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "8b870d8c151b6f2fb93e84a13146138f05d02ed11c7e7c54f8826aaaf7c9f184" +[[package]] +name = "plotters" +version = "0.3.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5aeb6f403d7a4911efb1e33402027fc44f29b5bf6def3effcc22d7bb75f2b747" +dependencies = [ + "num-traits", + "plotters-backend", + "plotters-svg", + "wasm-bindgen", + "web-sys", +] + +[[package]] +name = "plotters-backend" +version = "0.3.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "df42e13c12958a16b3f7f4386b9ab1f3e7933914ecea48da7139435263a4172a" + +[[package]] +name = "plotters-svg" +version = "0.3.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "51bae2ac328883f7acdfea3d66a7c35751187f870bc81f94563733a154d7a670" +dependencies = [ + "plotters-backend", +] + [[package]] name = "portable-atomic" version = "1.13.1" @@ -1185,6 +1394,26 @@ dependencies = [ "getrandom 0.3.4", ] +[[package]] +name = "rayon" +version = "1.11.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "368f01d005bf8fd9b1206fb6fa653e6c4a81ceb1466406b81792d87c5677a58f" +dependencies = [ + "either", + "rayon-core", +] + +[[package]] +name = "rayon-core" +version = "1.13.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "22e18b0f0062d30d4230b2e85ff77fdfe4326feb054b9783a3460d8435c8ab91" +dependencies = [ + "crossbeam-deque", + "crossbeam-utils", +] + [[package]] name = "rcgen" version = "0.13.2" @@ -1346,6 +1575,15 @@ version = "1.0.23" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "9774ba4a74de5f7b1c1451ed6cd5285a32eddb5cccb8cc655a4e50009e06477f" +[[package]] +name = "same-file" +version = "1.0.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "93fc1dc3aaa9bfed95e02e6eadabb4baf7e3078b0bd1b4d7b6b0b68378900502" +dependencies = [ + "winapi-util", +] + [[package]] name = "serde" version = "1.0.228" @@ -1589,6 +1827,16 @@ dependencies = [ "zerovec", ] +[[package]] +name = "tinytemplate" +version = "1.2.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "be4d6b5f19ff7664e8c98d03e2139cb510db9b0a60b55f8e8709b689d939b6bc" +dependencies = [ + "serde", + "serde_json", +] + [[package]] name = "tinyvec" version = "1.11.0" @@ -1807,6 +2055,16 @@ version = "0.2.2" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "06abde3611657adf66d383f00b093d7faecc7fa57071cce2578660c9f1010821" +[[package]] +name = "walkdir" +version = "2.5.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "29790946404f91d9c5d06f9874efddea1dc06c5efe94541a7d6863108e3a5e4b" +dependencies = [ + "same-file", + "winapi-util", +] + [[package]] name = "want" version = "0.3.1" @@ -1919,6 +2177,15 @@ dependencies = [ "rustls-pki-types", ] +[[package]] +name = "winapi-util" +version = "0.1.11" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c2a7b1c03c876122aa43f3020e6c3c3ee5c05081c9a00739faf7503aeba10d22" +dependencies = [ + "windows-sys 0.61.2", +] + [[package]] name = "windows-link" version = "0.2.1" diff --git a/Cargo.toml b/Cargo.toml index fa52afa..ea71da7 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -28,3 +28,14 @@ time = "0.3" rustls = "0.23" tokio-rustls = "0.26" arc-swap = "1" + +[dev-dependencies] +criterion = { version = "0.5", features = ["html_reports"] } + +[[bench]] +name = "hot_path" +harness = false + +[[bench]] +name = "throughput" +harness = false diff --git a/Makefile b/Makefile index d25d697..643c058 100644 --- a/Makefile +++ b/Makefile @@ -1,4 +1,4 @@ -.PHONY: all build lint fmt check audit test clean deploy +.PHONY: all build lint fmt check audit test bench clean deploy blog all: lint build @@ -19,6 +19,17 @@ audit: test: cargo test +bench: + cargo bench + +blog: + @mkdir -p site/blog + @for f in blog/*.md; do \ + name=$$(basename "$$f" .md); \ + pandoc "$$f" --template=site/blog-template.html -o "site/blog/$$name.html"; \ + echo " $$f → site/blog/$$name.html"; \ + done + clean: cargo clean diff --git a/bench/README.md b/bench/README.md new file mode 100644 index 0000000..7307369 --- /dev/null +++ b/bench/README.md @@ -0,0 +1,87 @@ +# Benchmarks + +Numa has two benchmark suites measuring different layers of performance. + +## Micro-benchmarks (`benches/`, criterion) + +Nanosecond-precision measurement of individual operations on the hot path. +No running server required — these are pure Rust unit-level benchmarks. + +```sh +cargo bench # run all +cargo bench --bench hot_path # parse, serialize, cache, clone +cargo bench --bench throughput # pipeline QPS, buffer alloc +``` + +### What's measured + +**hot_path** — individual operations: + +| Benchmark | What it measures | +|-----------|-----------------| +| `buffer_parse` | Wire bytes → DnsPacket (typical response with 4 records) | +| `buffer_serialize` | DnsPacket → wire bytes | +| `packet_clone` | Full DnsPacket clone (what cache hit costs) | +| `cache_lookup_hit` | Cache lookup on a single-entry cache | +| `cache_lookup_hit_populated` | Cache lookup with 1000 entries | +| `cache_lookup_miss` | HashMap miss (baseline) | +| `cache_insert` | Insert into cache with packet clone | +| `round_trip_cached` | Full cached path: parse query → cache hit → serialize response | + +**throughput** — pipeline capacity: + +| Benchmark | What it measures | +|-----------|-----------------| +| `pipeline_throughput/N` | N cached queries end-to-end (parse → lookup → serialize) | +| `buffer_alloc` | BytePacketBuffer 4KB zero-init cost | + +### Reading results + +Criterion auto-compares against the previous run: + +``` +round_trip_cached time: [710.5 ns 715.2 ns 720.1 ns] + change: [-2.48% -1.85% -1.21%] (p = 0.00 < 0.05) + Performance has improved. +``` + +- The three values are [lower bound, estimate, upper bound] of the mean +- `change` shows the delta vs the last saved baseline +- HTML reports with charts: `target/criterion/report/index.html` + +To save a named baseline for comparison: + +```sh +cargo bench -- --save-baseline before +# ... make changes ... +cargo bench -- --baseline before +``` + +## End-to-end benchmark (`bench/dns-bench.sh`) + +Real-world latency comparison using `dig` against a running Numa instance +and public resolvers. Measures millisecond-level latency including network I/O. + +```sh +# Start Numa first (default port 15353 for testing) +python3 bench/dns-bench.sh [port] [rounds] +python3 bench/dns-bench.sh 15353 20 # default +``` + +### What's measured + +- **Numa (cold)**: cache flushed before each query — measures upstream forwarding +- **Numa (cached)**: queries hit cache — measures local processing +- **System / Google / Cloudflare / Quad9**: public resolver comparison + +Results saved to `bench/results.json`. + +### When to use which + +| Question | Use | +|----------|-----| +| Did my code change make parsing faster? | `cargo bench --bench hot_path` | +| Is the cached path still sub-microsecond? | `cargo bench --bench hot_path` (round_trip_cached) | +| How many queries/sec can we handle? | `cargo bench --bench throughput` | +| Is Numa still competitive with system resolver? | `bench/dns-bench.sh` | +| Did upstream forwarding regress? | `bench/dns-bench.sh` | diff --git a/bench/results.json b/bench/results.json new file mode 100644 index 0000000..934835e --- /dev/null +++ b/bench/results.json @@ -0,0 +1,50 @@ +{ + "Numa(cold)": { + "avg": 9, + "p50": 9, + "p99": 18, + "min": 8, + "max": 18, + "count": 50 + }, + "Numa(cached)": { + "avg": 0, + "p50": 0, + "p99": 0, + "min": 0, + "max": 0, + "count": 50 + }, + "System": { + "avg": 9.1, + "p50": 8, + "p99": 44, + "min": 7, + "max": 44, + "count": 50 + }, + "Google": { + "avg": 22.4, + "p50": 17, + "p99": 37, + "min": 13, + "max": 37, + "count": 50 + }, + "Cloudflare": { + "avg": 18.7, + "p50": 14, + "p99": 132, + "min": 12, + "max": 132, + "count": 50 + }, + "Quad9": { + "avg": 14.5, + "p50": 13, + "p99": 43, + "min": 12, + "max": 43, + "count": 50 + } +} \ No newline at end of file diff --git a/benches/hot_path.rs b/benches/hot_path.rs new file mode 100644 index 0000000..accfcf2 --- /dev/null +++ b/benches/hot_path.rs @@ -0,0 +1,185 @@ +use criterion::{black_box, criterion_group, criterion_main, Criterion}; +use std::net::Ipv4Addr; + +use numa::buffer::BytePacketBuffer; +use numa::cache::DnsCache; +use numa::header::ResultCode; +use numa::packet::DnsPacket; +use numa::question::{DnsQuestion, QueryType}; +use numa::record::DnsRecord; + +fn make_response(domain: &str) -> DnsPacket { + let mut pkt = DnsPacket::new(); + pkt.header.id = 0x1234; + pkt.header.response = true; + pkt.header.recursion_desired = true; + pkt.header.recursion_available = true; + pkt.header.rescode = ResultCode::NOERROR; + pkt.questions + .push(DnsQuestion::new(domain.to_string(), QueryType::A)); + pkt.answers.push(DnsRecord::A { + domain: domain.to_string(), + addr: Ipv4Addr::new(93, 184, 216, 34), + ttl: 300, + }); + // Typical response includes authority + additional records + pkt.authorities.push(DnsRecord::NS { + domain: domain.to_string(), + host: format!("ns1.{domain}"), + ttl: 172800, + }); + pkt.authorities.push(DnsRecord::NS { + domain: domain.to_string(), + host: format!("ns2.{domain}"), + ttl: 172800, + }); + pkt.resources.push(DnsRecord::A { + domain: format!("ns1.{domain}"), + addr: Ipv4Addr::new(198, 51, 100, 1), + ttl: 172800, + }); + pkt +} + +fn to_wire(pkt: &DnsPacket) -> Vec { + let mut buf = BytePacketBuffer::new(); + pkt.write(&mut buf).unwrap(); + buf.filled().to_vec() +} + +fn bench_buffer_parse(c: &mut Criterion) { + let pkt = make_response("example.com"); + let wire = to_wire(&pkt); + + c.bench_function("buffer_parse", |b| { + b.iter(|| { + let mut buf = BytePacketBuffer::from_bytes(black_box(&wire)); + DnsPacket::from_buffer(&mut buf).unwrap() + }) + }); +} + +fn bench_buffer_serialize(c: &mut Criterion) { + let pkt = make_response("example.com"); + + c.bench_function("buffer_serialize", |b| { + b.iter(|| { + let mut buf = BytePacketBuffer::new(); + black_box(&pkt).write(&mut buf).unwrap(); + black_box(buf.pos()); + }) + }); +} + +fn bench_packet_clone(c: &mut Criterion) { + let pkt = make_response("example.com"); + + c.bench_function("packet_clone", |b| b.iter(|| black_box(&pkt).clone())); +} + +fn bench_cache_lookup_hit(c: &mut Criterion) { + let mut cache = DnsCache::new(10_000, 60, 86400); + let pkt = make_response("example.com"); + cache.insert("example.com", QueryType::A, &pkt); + + c.bench_function("cache_lookup_hit", |b| { + b.iter(|| { + cache + .lookup(black_box("example.com"), QueryType::A) + .unwrap() + }) + }); +} + +fn bench_cache_lookup_miss(c: &mut Criterion) { + let cache = DnsCache::new(10_000, 60, 86400); + + c.bench_function("cache_lookup_miss", |b| { + b.iter(|| cache.lookup(black_box("nonexistent.com"), QueryType::A)) + }); +} + +fn bench_cache_insert(c: &mut Criterion) { + let pkt = make_response("example.com"); + + c.bench_function("cache_insert", |b| { + let mut cache = DnsCache::new(10_000, 60, 86400); + let mut i = 0u64; + b.iter(|| { + let domain = format!("bench-{i}.example.com"); + cache.insert(&domain, QueryType::A, black_box(&pkt)); + i += 1; + // Reset cache periodically to avoid filling up + if i % 5000 == 0 { + cache.clear(); + } + }) + }); +} + +fn bench_round_trip(c: &mut Criterion) { + // Simulates the cached hot path: parse query → cache hit → serialize response + let query_pkt = { + let mut q = DnsPacket::new(); + q.header.id = 0xABCD; + q.header.recursion_desired = true; + q.questions + .push(DnsQuestion::new("example.com".to_string(), QueryType::A)); + q + }; + let query_wire = to_wire(&query_pkt); + + let response = make_response("example.com"); + let mut cache = DnsCache::new(10_000, 60, 86400); + cache.insert("example.com", QueryType::A, &response); + + c.bench_function("round_trip_cached", |b| { + b.iter(|| { + // 1. Parse incoming query + let mut buf = BytePacketBuffer::from_bytes(black_box(&query_wire)); + let query = DnsPacket::from_buffer(&mut buf).unwrap(); + let qname = &query.questions[0].name; + let qtype = query.questions[0].qtype; + + // 2. Cache lookup + let mut resp = cache.lookup(qname, qtype).unwrap(); + resp.header.id = query.header.id; + + // 3. Serialize response + let mut resp_buf = BytePacketBuffer::new(); + resp.write(&mut resp_buf).unwrap(); + black_box(resp_buf.pos()); + }) + }); +} + +fn bench_cache_populated_lookup(c: &mut Criterion) { + // Benchmark with a realistically populated cache (1000 entries) + let mut cache = DnsCache::new(10_000, 60, 86400); + for i in 0..1000 { + let domain = format!("domain-{i}.example.com"); + let pkt = make_response(&domain); + cache.insert(&domain, QueryType::A, &pkt); + } + + c.bench_function("cache_lookup_hit_populated", |b| { + b.iter(|| { + cache + .lookup(black_box("domain-500.example.com"), QueryType::A) + .unwrap() + }) + }); +} + +criterion_group!( + benches, + bench_buffer_parse, + bench_buffer_serialize, + bench_packet_clone, + bench_cache_lookup_hit, + bench_cache_lookup_miss, + bench_cache_insert, + bench_round_trip, + bench_cache_populated_lookup, +); +criterion_main!(benches); diff --git a/benches/throughput.rs b/benches/throughput.rs new file mode 100644 index 0000000..e01a25c --- /dev/null +++ b/benches/throughput.rs @@ -0,0 +1,94 @@ +use criterion::{criterion_group, criterion_main, BenchmarkId, Criterion, Throughput}; +use std::net::Ipv4Addr; + +use numa::buffer::BytePacketBuffer; +use numa::header::ResultCode; +use numa::packet::DnsPacket; +use numa::question::{DnsQuestion, QueryType}; +use numa::record::DnsRecord; + +fn make_query_wire(domain: &str) -> Vec { + let mut q = DnsPacket::new(); + q.header.id = 0xABCD; + q.header.recursion_desired = true; + q.questions + .push(DnsQuestion::new(domain.to_string(), QueryType::A)); + let mut buf = BytePacketBuffer::new(); + q.write(&mut buf).unwrap(); + buf.filled().to_vec() +} + +fn make_response(domain: &str) -> DnsPacket { + let mut pkt = DnsPacket::new(); + pkt.header.id = 0xABCD; + pkt.header.response = true; + pkt.header.recursion_desired = true; + pkt.header.recursion_available = true; + pkt.header.rescode = ResultCode::NOERROR; + pkt.questions + .push(DnsQuestion::new(domain.to_string(), QueryType::A)); + pkt.answers.push(DnsRecord::A { + domain: domain.to_string(), + addr: Ipv4Addr::new(93, 184, 216, 34), + ttl: 300, + }); + pkt +} + +/// Simulates the complete cached query pipeline (sans network I/O): +/// parse → cache lookup → TTL adjust → serialize response +fn simulate_cached_pipeline(query_wire: &[u8], cache: &numa::cache::DnsCache) -> usize { + let mut buf = BytePacketBuffer::from_bytes(query_wire); + let query = DnsPacket::from_buffer(&mut buf).unwrap(); + let q = &query.questions[0]; + + let mut resp = cache.lookup(&q.name, q.qtype).unwrap(); + resp.header.id = query.header.id; + + let mut resp_buf = BytePacketBuffer::new(); + resp.write(&mut resp_buf).unwrap(); + resp_buf.pos() +} + +fn bench_pipeline_throughput(c: &mut Criterion) { + let domains: Vec = (0..100) + .map(|i| format!("domain-{i}.example.com")) + .collect(); + + let mut cache = numa::cache::DnsCache::new(10_000, 60, 86400); + for d in &domains { + cache.insert(d, QueryType::A, &make_response(d)); + } + + let query_wires: Vec> = domains.iter().map(|d| make_query_wire(d)).collect(); + + let mut group = c.benchmark_group("pipeline_throughput"); + + for count in [1, 10, 100] { + group.throughput(Throughput::Elements(count)); + group.bench_with_input(BenchmarkId::from_parameter(count), &count, |b, &count| { + let mut idx = 0usize; + b.iter(|| { + for _ in 0..count { + let wire = &query_wires[idx % query_wires.len()]; + simulate_cached_pipeline(wire, &cache); + idx += 1; + } + }); + }); + } + group.finish(); +} + +/// Measures the overhead of BytePacketBuffer allocation + zero-init +fn bench_buffer_alloc(c: &mut Criterion) { + c.bench_function("buffer_alloc", |b| { + b.iter(|| { + let buf = BytePacketBuffer::new(); + criterion::black_box(buf.pos()); + }) + }); +} + +criterion_group!(benches, bench_pipeline_throughput, bench_buffer_alloc,); +criterion_main!(benches); diff --git a/blog/dns-from-scratch.md b/blog/dns-from-scratch.md new file mode 100644 index 0000000..0959fc7 --- /dev/null +++ b/blog/dns-from-scratch.md @@ -0,0 +1,328 @@ +--- +title: I Built a DNS Resolver from Scratch in Rust +description: How DNS actually works at the wire level — label compression, TTL tricks, DoH, and what surprised me building a resolver with zero DNS libraries. +date: March 2026 +--- + +I wanted to understand how DNS actually works. Not the "it translates domain names to IP addresses" explanation — the actual bytes on the wire. What does a DNS packet look like? How does label compression work? Why is everything crammed into 512 bytes? + +So I built one from scratch in Rust. No `hickory-dns`, no `trust-dns`, no `simple-dns`. The entire RFC 1035 wire protocol — headers, labels, compression pointers, record types — parsed and serialized by hand. It started as a weekend learning project, became a side project I kept coming back to over 6 years, and eventually turned into [Numa](https://github.com/razvandimescu/numa) — which I now use as my actual system DNS. + +A note on terminology before we go further: Numa is currently a *forwarding* resolver — it parses and caches DNS packets, but forwards queries to an upstream (Quad9, Cloudflare, or any DoH provider) rather than walking the delegation chain from root servers itself. Think of it as a smart proxy that does useful things with your DNS traffic locally (caching, ad blocking, overrides, local service domains) before forwarding what it can't answer. Full recursive resolution — where Numa talks directly to root and authoritative nameservers — is on the roadmap, along with DNSSEC validation. + +Here's what surprised me along the way. + +## What does a DNS packet actually look like? + +You can see a real one yourself. Run this: + +```bash +dig @127.0.0.1 example.com A +noedns +``` + +``` +;; ->>HEADER<<- opcode: QUERY, status: NOERROR, id: 15242 +;; flags: qr rd ra; QUERY: 1, ANSWER: 2, AUTHORITY: 0, ADDITIONAL: 0 + +;; QUESTION SECTION: +;example.com. IN A + +;; ANSWER SECTION: +example.com. 53 IN A 104.18.27.120 +example.com. 53 IN A 104.18.26.120 +``` + +That's the human-readable version. But what's actually on the wire? A DNS query for `example.com A` is just 29 bytes: + +``` + ID Flags QCount ACount NSCount ARCount + ┌────┐ ┌────┐ ┌────┐ ┌────┐ ┌────┐ ┌────┐ +Header: AB CD 01 00 00 01 00 00 00 00 00 00 + └────┘ └────┘ └────┘ └────┘ └────┘ └────┘ + ↑ ↑ ↑ + │ │ └─ 1 question, 0 answers, 0 authority, 0 additional + │ └─ Standard query, recursion desired + └─ Random ID (we'll match this in the response) + +Question: 07 65 78 61 6D 70 6C 65 03 63 6F 6D 00 00 01 00 01 + ── ───────────────────── ── ───────── ── ───── ───── + 7 e x a m p l e 3 c o m end A IN + ↑ ↑ ↑ + └─ length prefix └─ length └─ root label (end of name) +``` + +12 bytes of header + 17 bytes of question = 29 bytes to ask "what's the IP for example.com?" Compare that to an HTTP request for the same information — you'd need hundreds of bytes just for headers. + +We can send exactly those bytes and capture what comes back: + +```python +python3 -c " +import socket +# Hand-craft a DNS query: header (12 bytes) + question (17 bytes) +q = b'\xab\xcd\x01\x00\x00\x01\x00\x00\x00\x00\x00\x00' # header +q += b'\x07example\x03com\x00\x00\x01\x00\x01' # question +s = socket.socket(socket.AF_INET, socket.SOCK_DGRAM) +s.sendto(q, ('127.0.0.1', 53)) +resp = s.recv(512) +for i in range(0, len(resp), 16): + h = ' '.join(f'{b:02x}' for b in resp[i:i+16]) + a = ''.join(chr(b) if 32<=b<127 else '.' for b in resp[i:i+16]) + print(f'{i:08x} {h:<48s} {a}') +" +``` + +``` +00000000 ab cd 81 80 00 01 00 02 00 00 00 00 07 65 78 61 .............exa +00000010 6d 70 6c 65 03 63 6f 6d 00 00 01 00 01 07 65 78 mple.com......ex +00000020 61 6d 70 6c 65 03 63 6f 6d 00 00 01 00 01 00 00 ample.com....... +00000030 00 19 00 04 68 12 1b 78 07 65 78 61 6d 70 6c 65 ....h..x.example +00000040 03 63 6f 6d 00 00 01 00 01 00 00 00 19 00 04 68 .com...........h +00000050 12 1a 78 ..x +``` + +83 bytes back. Let's annotate the response: + +``` + ID Flags QCount ACount NSCount ARCount + ┌────┐ ┌────┐ ┌────┐ ┌────┐ ┌────┐ ┌────┐ +Header: AB CD 81 80 00 01 00 02 00 00 00 00 + └────┘ └────┘ └────┘ └────┘ └────┘ └────┘ + ↑ ↑ ↑ ↑ + │ │ │ └─ 2 answers + │ │ └─ 1 question (echoed back) + │ └─ Response flag set, recursion available + └─ Same ID as our query + +Question: 07 65 78 61 6D 70 6C 65 03 63 6F 6D 00 00 01 00 01 + (same as our query — echoed back) + +Answer 1: 07 65 78 61 6D 70 6C 65 03 63 6F 6D 00 00 01 00 01 + ───────────────────────────────────── ── ───── ───── + e x a m p l e . c o m end A IN + + 00 00 00 19 00 04 68 12 1B 78 + ─────────── ───── ─────────── + TTL: 25s len:4 104.18.27.120 + +Answer 2: (same domain repeated) 00 01 00 01 00 00 00 19 00 04 68 12 1A 78 + ─────────── + 104.18.26.120 +``` + +Notice something wasteful? The domain `example.com` appears *three times* — once in the question, twice in the answers. That's 39 bytes of repeated names in an 83-byte packet. DNS has a solution for this — but first, the overall structure. + +The whole thing fits in a single UDP datagram. The structure is: + +``` ++--+--+--+--+--+--+--+--+ +| Header | 12 bytes: ID, flags, counts ++--+--+--+--+--+--+--+--+ +| Questions | What you're asking ++--+--+--+--+--+--+--+--+ +| Answers | The response records ++--+--+--+--+--+--+--+--+ +| Authorities | NS records for the zone ++--+--+--+--+--+--+--+--+ +| Additional | Extra helpful records ++--+--+--+--+--+--+--+--+ +``` + +In Rust, parsing the header is just reading 12 bytes and unpacking the flags: + +```rust +pub fn read(buffer: &mut BytePacketBuffer) -> Result { + let id = buffer.read_u16()?; + let flags = buffer.read_u16()?; + // Flags pack 9 fields into 16 bits + let recursion_desired = (flags & (1 << 8)) > 0; + let truncated_message = (flags & (1 << 9)) > 0; + let authoritative_answer = (flags & (1 << 10)) > 0; + let opcode = (flags >> 11) & 0x0F; + let response = (flags & (1 << 15)) > 0; + // ... and so on +} +``` + +No padding, no alignment, no JSON overhead. DNS was designed in 1987 when every byte counted, and honestly? The wire format is kind of beautiful in its efficiency. + +## Label compression is the clever part + +Remember how `example.com` appeared three times in that 83-byte response? Domain names in DNS are stored as a sequence of **labels** — length-prefixed segments: + +``` +example.com → [7]example[3]com[0] +``` + +The `[7]` means "the next 7 bytes are a label." The `[0]` is the root label (end of name). That's 13 bytes per occurrence, 39 bytes for three repetitions. In a response with authority and additional records, domain names can account for half the packet. + +DNS solves this with **compression pointers** — if the top two bits of a length byte are `11`, the remaining 14 bits are an offset back into the packet where the rest of the name can be found. A well-compressed version of our response would replace the answer names with `C0 0C` — a 2-byte pointer to offset 12 where `example.com` first appears in the question section. That turns 39 bytes of names into 15 (13 + 2 + 2). Our upstream didn't bother compressing, but many do — especially when related domains appear: + +``` +Offset 0x20: [6]google[3]com[0] ← full name +Offset 0x40: [4]mail[0xC0][0x20] ← "mail" + pointer to offset 0x20 +Offset 0x50: [3]www[0xC0][0x20] ← "www" + pointer to offset 0x20 +``` + +Pointers can chain — a pointer can point to another pointer. Parsing this correctly requires tracking your position in the buffer and handling jumps: + +```rust +pub fn read_qname(&mut self, outstr: &mut String) -> Result<()> { + let mut pos = self.pos(); + let mut jumped = false; + let mut delim = ""; + + loop { + let len = self.get(pos)?; + + // Top two bits set = compression pointer + if (len & 0xC0) == 0xC0 { + if !jumped { + self.seek(pos + 2)?; // advance past the pointer + } + let offset = (((len as u16) ^ 0xC0) << 8) | self.get(pos + 1)? as u16; + pos = offset as usize; + jumped = true; + continue; + } + + pos += 1; + if len == 0 { break; } // root label + + outstr.push_str(delim); + outstr.push_str(&self.get_range(pos, len as usize)? + .iter().map(|&b| b as char).collect::()); + delim = "."; + pos += len as usize; + } + + if !jumped { + self.seek(pos)?; + } + Ok(()) +} +``` + +This one bit me: when you follow a pointer, you must *not* advance the buffer's read position past where you jumped from. The pointer is 2 bytes, so you advance by 2, but the actual label data lives elsewhere in the packet. If you follow the pointer and also advance past it, you'll skip over the next record entirely. I spent a fun evening debugging that one. + +## TTL adjustment on read, not write + +This is my favorite trick in the whole codebase. I initially stored the remaining TTL and decremented it, which meant I needed a background thread to sweep expired entries. It worked, but it felt wrong — too much machinery for something simple. + +The cleaner approach: store the original TTL and the timestamp when the record was cached. On read, compute `remaining = original_ttl - elapsed`. If it's zero or negative, the entry is stale — evict it lazily. + +```rust +pub fn lookup(&mut self, domain: &str, qtype: QueryType) -> Option { + let key = (domain.to_lowercase(), qtype); + let entry = self.entries.get(&key)?; + let elapsed = entry.cached_at.elapsed().as_secs() as u32; + + if elapsed >= entry.original_ttl { + self.entries.remove(&key); + return None; + } + + // Adjust TTLs in the response to reflect remaining time + let mut packet = entry.packet.clone(); + for answer in &mut packet.answers { + answer.set_ttl(entry.original_ttl.saturating_sub(elapsed)); + } + Some(packet) +} +``` + +No background thread. No timer. Entries expire lazily. The cache stays consistent because every consumer sees the adjusted TTL. + +## The resolution pipeline + +Each incoming UDP packet spawns a tokio task. Each task walks a deterministic pipeline — every step either answers or passes to the next: + +``` + ┌─────────────────────────────────────────────────────┐ + │ Numa Resolution Pipeline │ + └─────────────────────────────────────────────────────┘ + + Query ──→ Overrides ──→ .numa TLD ──→ Blocklist ──→ Zones ──→ Cache ──→ DoH + │ │ │ │ │ │ │ + │ │ match? │ match? │ blocked? │ match? │ hit? │ + │ ↓ ↓ ↓ ↓ ↓ ↓ + │ respond respond 0.0.0.0 respond respond forward + │ (auto-reverts (reverse (ad gone) (static (TTL to upstream + │ after N min) proxy+TLS) records) adjusted) (encrypted) + │ + └──→ Each step either answers or passes to the next. +``` + +This is where "from scratch" pays off. Want conditional forwarding for Tailscale? Insert a step before the upstream. Want to override `api.example.com` for 5 minutes while debugging? Add an entry in the overrides step — it auto-expires. A DNS library would have hidden this pipeline behind an opaque `resolve()` call. + +## DNS-over-HTTPS: the "wait, that's it?" moment + +The most recent addition, and honestly the one that surprised me with how little code it needed. DoH (RFC 8484) is conceptually simple: take the exact same DNS wire-format packet you'd send over UDP, POST it to an HTTPS endpoint with `Content-Type: application/dns-message`, and parse the response the same way. Same bytes, different transport. + +```rust +async fn forward_doh( + query: &DnsPacket, + url: &str, + client: &reqwest::Client, + timeout_duration: Duration, +) -> Result { + let mut send_buffer = BytePacketBuffer::new(); + query.write(&mut send_buffer)?; + + let resp = timeout(timeout_duration, client + .post(url) + .header("content-type", "application/dns-message") + .header("accept", "application/dns-message") + .body(send_buffer.filled().to_vec()) + .send()) + .await??.error_for_status()?; + + let bytes = resp.bytes().await?; + let mut recv_buffer = BytePacketBuffer::from_bytes(&bytes); + DnsPacket::from_buffer(&mut recv_buffer) +} +``` + +The one gotcha that cost me an hour: Quad9 and other DoH providers require HTTP/2. My first attempt used HTTP/1.1 and got a cryptic 400 Bad Request. Adding the `http2` feature to reqwest fixed it. The upside of HTTP/2? Connection multiplexing means subsequent queries reuse the TLS session — ~16ms vs ~50ms for the first query. Free performance. + +The `Upstream` enum dispatches between UDP and DoH based on the URL scheme: + +```rust +pub enum Upstream { + Udp(SocketAddr), + Doh { url: String, client: reqwest::Client }, +} +``` + +If the configured address starts with `https://`, it's DoH. Otherwise, plain UDP. Simple, no toggles. + +## "Why not just use dnsmasq + nginx + mkcert?" + +You absolutely can — those are mature, battle-tested tools. The difference is integration: with dnsmasq + nginx + mkcert, you're configuring three tools with three config formats. Numa puts the DNS record, reverse proxy, and TLS cert behind one API call: + +```bash +curl -X POST localhost:5380/services -d '{"name":"frontend","target_port":5173}' +``` + +That creates the DNS entry, generates a TLS certificate, and starts proxying — including WebSocket upgrade for Vite HMR. One command, no config files. Having full control over the resolution pipeline is what makes auto-revert overrides and LAN discovery possible. + +## What I learned + +**DNS is a 40-year-old protocol that works remarkably well.** The wire format is tight, the caching model is elegant, and the hierarchical delegation system has scaled to billions of queries per day. The things people complain about (DNSSEC complexity, lack of encryption) are extensions bolted on decades later, not flaws in the original design. + +**The hard parts aren't where you'd expect.** Parsing the wire protocol was straightforward (RFC 1035 is well-written). The hard parts were: browsers rejecting wildcard certs under single-label TLDs, macOS resolver quirks (`scutil` vs `/etc/resolv.conf`), and getting multiple processes to bind the same multicast port (`SO_REUSEPORT` on macOS, `SO_REUSEADDR` on Linux). + +**Learn the vocabulary before you show up.** I initially called Numa a "DNS resolver" and got corrected — it's a forwarding resolver. The distinction matters to people who work with DNS professionally, and being sloppy about it cost me credibility in my first community posts. + +## What's next + +Numa is at v0.5.0 with DNS forwarding, caching, ad blocking, DNS-over-HTTPS, .numa local domains with auto TLS, and LAN service discovery. + +On the roadmap: + +- **DoT (DNS-over-TLS)** — DoH was first because it passes through captive portals and corporate firewalls (port 443 vs 853). DoT has less framing overhead, so it's faster. Both will be available. +- **Recursive resolution** — walk the delegation chain from root servers instead of forwarding. Combined with DNSSEC validation, this removes the need to trust any upstream resolver. +- **[pkarr](https://github.com/pubky/pkarr) integration** — self-sovereign DNS via the Mainline BitTorrent DHT. Publish DNS records signed with your Ed25519 key, no registrar needed. + +But those are rabbit holes for future posts. + +[github.com/razvandimescu/numa](https://github.com/razvandimescu/numa) diff --git a/site/CNAME b/site/CNAME new file mode 100644 index 0000000..3004d18 --- /dev/null +++ b/site/CNAME @@ -0,0 +1 @@ +numa.rs \ No newline at end of file diff --git a/site/blog-template.html b/site/blog-template.html new file mode 100644 index 0000000..0275c1f --- /dev/null +++ b/site/blog-template.html @@ -0,0 +1,301 @@ + + + + + +$title$ — Numa + + + + + + + + + + + + + + diff --git a/site/blog/dns-from-scratch.html b/site/blog/dns-from-scratch.html new file mode 100644 index 0000000..39f857f --- /dev/null +++ b/site/blog/dns-from-scratch.html @@ -0,0 +1,651 @@ + + + + + +I Built a DNS Resolver from Scratch in Rust — Numa + + + + + + + + +
+
+

I Built a DNS Resolver from Scratch in Rust

+
+ March 2026 · Razvan Dimescu +
+
+ +

I wanted to understand how DNS actually works. Not the “it translates +domain names to IP addresses” explanation — the actual bytes on the +wire. What does a DNS packet look like? How does label compression work? +Why is everything crammed into 512 bytes?

+

So I built one from scratch in Rust. No hickory-dns, no +trust-dns, no simple-dns. The entire RFC 1035 +wire protocol — headers, labels, compression pointers, record types — +parsed and serialized by hand. It started as a weekend learning project, +became a side project I kept coming back to over 6 years, and eventually +turned into Numa — +which I now use as my actual system DNS.

+

A note on terminology before we go further: Numa is currently a +forwarding resolver — it parses and caches DNS packets, but +forwards queries to an upstream (Quad9, Cloudflare, or any DoH provider) +rather than walking the delegation chain from root servers itself. Think +of it as a smart proxy that does useful things with your DNS traffic +locally (caching, ad blocking, overrides, local service domains) before +forwarding what it can’t answer. Full recursive resolution — where Numa +talks directly to root and authoritative nameservers — is on the +roadmap, along with DNSSEC validation.

+

Here’s what surprised me along the way.

+

What does a DNS +packet actually look like?

+

You can see a real one yourself. Run this:

+
dig @127.0.0.1 example.com A +noedns
+
;; ->>HEADER<<- opcode: QUERY, status: NOERROR, id: 15242
+;; flags: qr rd ra; QUERY: 1, ANSWER: 2, AUTHORITY: 0, ADDITIONAL: 0
+
+;; QUESTION SECTION:
+;example.com.                   IN      A
+
+;; ANSWER SECTION:
+example.com.            53      IN      A       104.18.27.120
+example.com.            53      IN      A       104.18.26.120
+

That’s the human-readable version. But what’s actually on the wire? A +DNS query for example.com A is just 29 bytes:

+
         ID    Flags  QCount ACount NSCount ARCount
+        ┌────┐ ┌────┐ ┌────┐ ┌────┐ ┌────┐ ┌────┐
+Header: AB CD  01 00  00 01  00 00  00 00  00 00
+        └────┘ └────┘ └────┘ └────┘ └────┘ └────┘
+         ↑      ↑      ↑
+         │      │      └─ 1 question, 0 answers, 0 authority, 0 additional
+         │      └─ Standard query, recursion desired
+         └─ Random ID (we'll match this in the response)
+
+Question: 07 65 78 61 6D 70 6C 65  03 63 6F 6D  00  00 01  00 01
+          ── ─────────────────────  ── ─────────  ──  ─────  ─────
+          7  e  x  a  m  p  l  e   3  c  o  m   end  A      IN
+          ↑                        ↑             ↑
+          └─ length prefix         └─ length     └─ root label (end of name)
+

12 bytes of header + 17 bytes of question = 29 bytes to ask “what’s +the IP for example.com?” Compare that to an HTTP request for the same +information — you’d need hundreds of bytes just for headers.

+

We can send exactly those bytes and capture what comes back:

+
python3 -c "
+import socket
+# Hand-craft a DNS query: header (12 bytes) + question (17 bytes)
+q  = b'\xab\xcd\x01\x00\x00\x01\x00\x00\x00\x00\x00\x00'  # header
+q += b'\x07example\x03com\x00\x00\x01\x00\x01'              # question
+s = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
+s.sendto(q, ('127.0.0.1', 53))
+resp = s.recv(512)
+for i in range(0, len(resp), 16):
+    h = ' '.join(f'{b:02x}' for b in resp[i:i+16])
+    a = ''.join(chr(b) if 32<=b<127 else '.' for b in resp[i:i+16])
+    print(f'{i:08x}  {h:<48s}  {a}')
+"
+
00000000  ab cd 81 80 00 01 00 02 00 00 00 00 07 65 78 61   .............exa
+00000010  6d 70 6c 65 03 63 6f 6d 00 00 01 00 01 07 65 78   mple.com......ex
+00000020  61 6d 70 6c 65 03 63 6f 6d 00 00 01 00 01 00 00   ample.com.......
+00000030  00 19 00 04 68 12 1b 78 07 65 78 61 6d 70 6c 65   ....h..x.example
+00000040  03 63 6f 6d 00 00 01 00 01 00 00 00 19 00 04 68   .com...........h
+00000050  12 1a 78                                          ..x
+

83 bytes back. Let’s annotate the response:

+
         ID    Flags  QCount ACount NSCount ARCount
+        ┌────┐ ┌────┐ ┌────┐ ┌────┐ ┌────┐ ┌────┐
+Header: AB CD  81 80  00 01  00 02  00 00  00 00
+        └────┘ └────┘ └────┘ └────┘ └────┘ └────┘
+         ↑      ↑      ↑      ↑
+         │      │      │      └─ 2 answers
+         │      │      └─ 1 question (echoed back)
+         │      └─ Response flag set, recursion available
+         └─ Same ID as our query
+
+Question: 07 65 78 61 6D 70 6C 65  03 63 6F 6D  00  00 01  00 01
+          (same as our query — echoed back)
+
+Answer 1: 07 65 78 61 6D 70 6C 65  03 63 6F 6D  00  00 01  00 01
+          ─────────────────────────────────────  ──  ─────  ─────
+          e  x  a  m  p  l  e  .  c  o  m       end  A      IN
+
+          00 00 00 19  00 04  68 12 1B 78
+          ───────────  ─────  ───────────
+          TTL: 25s     len:4  104.18.27.120
+
+Answer 2: (same domain repeated)  00 01  00 01  00 00 00 19  00 04  68 12 1A 78
+                                                                    ───────────
+                                                                    104.18.26.120
+

Notice something wasteful? The domain example.com +appears three times — once in the question, twice in the +answers. That’s 39 bytes of repeated names in an 83-byte packet. DNS has +a solution for this — but first, the overall structure.

+

The whole thing fits in a single UDP datagram. The structure is:

+
+--+--+--+--+--+--+--+--+
+|         Header         |  12 bytes: ID, flags, counts
++--+--+--+--+--+--+--+--+
+|        Questions       |  What you're asking
++--+--+--+--+--+--+--+--+
+|         Answers        |  The response records
++--+--+--+--+--+--+--+--+
+|       Authorities      |  NS records for the zone
++--+--+--+--+--+--+--+--+
+|       Additional       |  Extra helpful records
++--+--+--+--+--+--+--+--+
+

In Rust, parsing the header is just reading 12 bytes and unpacking +the flags:

+
pub fn read(buffer: &mut BytePacketBuffer) -> Result<DnsHeader> {
+    let id = buffer.read_u16()?;
+    let flags = buffer.read_u16()?;
+    // Flags pack 9 fields into 16 bits
+    let recursion_desired = (flags & (1 << 8)) > 0;
+    let truncated_message = (flags & (1 << 9)) > 0;
+    let authoritative_answer = (flags & (1 << 10)) > 0;
+    let opcode = (flags >> 11) & 0x0F;
+    let response = (flags & (1 << 15)) > 0;
+    // ... and so on
+}
+

No padding, no alignment, no JSON overhead. DNS was designed in 1987 +when every byte counted, and honestly? The wire format is kind of +beautiful in its efficiency.

+

Label compression is the +clever part

+

Remember how example.com appeared three times in that +83-byte response? Domain names in DNS are stored as a sequence of +labels — length-prefixed segments:

+
example.com → [7]example[3]com[0]
+

The [7] means “the next 7 bytes are a label.” The +[0] is the root label (end of name). That’s 13 bytes per +occurrence, 39 bytes for three repetitions. In a response with authority +and additional records, domain names can account for half the +packet.

+

DNS solves this with compression pointers — if the +top two bits of a length byte are 11, the remaining 14 bits +are an offset back into the packet where the rest of the name can be +found. A well-compressed version of our response would replace the +answer names with C0 0C — a 2-byte pointer to offset 12 +where example.com first appears in the question section. +That turns 39 bytes of names into 15 (13 + 2 + 2). Our upstream didn’t +bother compressing, but many do — especially when related domains +appear:

+
Offset 0x20: [6]google[3]com[0]        ← full name
+Offset 0x40: [4]mail[0xC0][0x20]       ← "mail" + pointer to offset 0x20
+Offset 0x50: [3]www[0xC0][0x20]        ← "www" + pointer to offset 0x20
+

Pointers can chain — a pointer can point to another pointer. Parsing +this correctly requires tracking your position in the buffer and +handling jumps:

+
pub fn read_qname(&mut self, outstr: &mut String) -> Result<()> {
+    let mut pos = self.pos();
+    let mut jumped = false;
+    let mut delim = "";
+
+    loop {
+        let len = self.get(pos)?;
+
+        // Top two bits set = compression pointer
+        if (len & 0xC0) == 0xC0 {
+            if !jumped {
+                self.seek(pos + 2)?; // advance past the pointer
+            }
+            let offset = (((len as u16) ^ 0xC0) << 8) | self.get(pos + 1)? as u16;
+            pos = offset as usize;
+            jumped = true;
+            continue;
+        }
+
+        pos += 1;
+        if len == 0 { break; } // root label
+
+        outstr.push_str(delim);
+        outstr.push_str(&self.get_range(pos, len as usize)?
+            .iter().map(|&b| b as char).collect::<String>());
+        delim = ".";
+        pos += len as usize;
+    }
+
+    if !jumped {
+        self.seek(pos)?;
+    }
+    Ok(())
+}
+

This one bit me: when you follow a pointer, you must not +advance the buffer’s read position past where you jumped from. The +pointer is 2 bytes, so you advance by 2, but the actual label data lives +elsewhere in the packet. If you follow the pointer and also advance past +it, you’ll skip over the next record entirely. I spent a fun evening +debugging that one.

+

TTL adjustment on read, not +write

+

This is my favorite trick in the whole codebase. I initially stored +the remaining TTL and decremented it, which meant I needed a background +thread to sweep expired entries. It worked, but it felt wrong — too much +machinery for something simple.

+

The cleaner approach: store the original TTL and the timestamp when +the record was cached. On read, compute +remaining = original_ttl - elapsed. If it’s zero or +negative, the entry is stale — evict it lazily.

+
pub fn lookup(&mut self, domain: &str, qtype: QueryType) -> Option<DnsPacket> {
+    let key = (domain.to_lowercase(), qtype);
+    let entry = self.entries.get(&key)?;
+    let elapsed = entry.cached_at.elapsed().as_secs() as u32;
+
+    if elapsed >= entry.original_ttl {
+        self.entries.remove(&key);
+        return None;
+    }
+
+    // Adjust TTLs in the response to reflect remaining time
+    let mut packet = entry.packet.clone();
+    for answer in &mut packet.answers {
+        answer.set_ttl(entry.original_ttl.saturating_sub(elapsed));
+    }
+    Some(packet)
+}
+

No background thread. No timer. Entries expire lazily. The cache +stays consistent because every consumer sees the adjusted TTL.

+

The resolution pipeline

+

Each incoming UDP packet spawns a tokio task. Each task walks a +deterministic pipeline — every step either answers or passes to the +next:

+
                     ┌─────────────────────────────────────────────────────┐
+                     │              Numa Resolution Pipeline               │
+                     └─────────────────────────────────────────────────────┘
+
+  Query ──→ Overrides ──→ .numa TLD ──→ Blocklist ──→ Zones ──→ Cache ──→ DoH
+    │        │              │             │             │         │         │
+    │        │ match?       │ match?      │ blocked?    │ match?  │ hit?    │
+    │        ↓              ↓             ↓             ↓         ↓         ↓
+    │      respond        respond       0.0.0.0      respond   respond   forward
+    │      (auto-reverts  (reverse      (ad gone)    (static   (TTL      to upstream
+    │       after N min)   proxy+TLS)                 records)  adjusted) (encrypted)
+    │
+    └──→ Each step either answers or passes to the next.
+

This is where “from scratch” pays off. Want conditional forwarding +for Tailscale? Insert a step before the upstream. Want to override +api.example.com for 5 minutes while debugging? Add an entry +in the overrides step — it auto-expires. A DNS library would have hidden +this pipeline behind an opaque resolve() call.

+

DNS-over-HTTPS: the +“wait, that’s it?” moment

+

The most recent addition, and honestly the one that surprised me with +how little code it needed. DoH (RFC 8484) is conceptually simple: take +the exact same DNS wire-format packet you’d send over UDP, POST it to an +HTTPS endpoint with Content-Type: application/dns-message, +and parse the response the same way. Same bytes, different +transport.

+
async fn forward_doh(
+    query: &DnsPacket,
+    url: &str,
+    client: &reqwest::Client,
+    timeout_duration: Duration,
+) -> Result<DnsPacket> {
+    let mut send_buffer = BytePacketBuffer::new();
+    query.write(&mut send_buffer)?;
+
+    let resp = timeout(timeout_duration, client
+        .post(url)
+        .header("content-type", "application/dns-message")
+        .header("accept", "application/dns-message")
+        .body(send_buffer.filled().to_vec())
+        .send())
+    .await??.error_for_status()?;
+
+    let bytes = resp.bytes().await?;
+    let mut recv_buffer = BytePacketBuffer::from_bytes(&bytes);
+    DnsPacket::from_buffer(&mut recv_buffer)
+}
+

The one gotcha that cost me an hour: Quad9 and other DoH providers +require HTTP/2. My first attempt used HTTP/1.1 and got a cryptic 400 Bad +Request. Adding the http2 feature to reqwest fixed it. The +upside of HTTP/2? Connection multiplexing means subsequent queries reuse +the TLS session — ~16ms vs ~50ms for the first query. Free +performance.

+

The Upstream enum dispatches between UDP and DoH based +on the URL scheme:

+
pub enum Upstream {
+    Udp(SocketAddr),
+    Doh { url: String, client: reqwest::Client },
+}
+

If the configured address starts with https://, it’s +DoH. Otherwise, plain UDP. Simple, no toggles.

+

“Why not just use dnsmasq ++ nginx + mkcert?”

+

You absolutely can — those are mature, battle-tested tools. The +difference is integration: with dnsmasq + nginx + mkcert, you’re +configuring three tools with three config formats. Numa puts the DNS +record, reverse proxy, and TLS cert behind one API call:

+
curl -X POST localhost:5380/services -d '{"name":"frontend","target_port":5173}'
+

That creates the DNS entry, generates a TLS certificate, and starts +proxying — including WebSocket upgrade for Vite HMR. One command, no +config files. Having full control over the resolution pipeline is what +makes auto-revert overrides and LAN discovery possible.

+

What I learned

+

DNS is a 40-year-old protocol that works remarkably +well. The wire format is tight, the caching model is elegant, +and the hierarchical delegation system has scaled to billions of queries +per day. The things people complain about (DNSSEC complexity, lack of +encryption) are extensions bolted on decades later, not flaws in the +original design.

+

The hard parts aren’t where you’d expect. Parsing +the wire protocol was straightforward (RFC 1035 is well-written). The +hard parts were: browsers rejecting wildcard certs under single-label +TLDs, macOS resolver quirks (scutil vs +/etc/resolv.conf), and getting multiple processes to bind +the same multicast port (SO_REUSEPORT on macOS, +SO_REUSEADDR on Linux).

+

Learn the vocabulary before you show up. I initially +called Numa a “DNS resolver” and got corrected — it’s a forwarding +resolver. The distinction matters to people who work with DNS +professionally, and being sloppy about it cost me credibility in my +first community posts.

+

What’s next

+

Numa is at v0.5.0 with DNS forwarding, caching, ad blocking, +DNS-over-HTTPS, .numa local domains with auto TLS, and LAN service +discovery.

+

On the roadmap:

+
    +
  • DoT (DNS-over-TLS) — DoH was first because it +passes through captive portals and corporate firewalls (port 443 vs +853). DoT has less framing overhead, so it’s faster. Both will be +available.
    • +
  • Recursive resolution — walk the delegation chain +from root servers instead of forwarding. Combined with DNSSEC +validation, this removes the need to trust any upstream resolver.
    • +
  • pkarr +integration — self-sovereign DNS via the Mainline BitTorrent +DHT. Publish DNS records signed with your Ed25519 key, no registrar +needed.
    • +
+

But those are rabbit holes for future posts.

+

github.com/razvandimescu/numa

+
+ + + + + diff --git a/site/blog/index.html b/site/blog/index.html new file mode 100644 index 0000000..4034054 --- /dev/null +++ b/site/blog/index.html @@ -0,0 +1,186 @@ + + + + + +Blog — Numa + + + + + + + + +
+

Blog

+ +
+ + + + + diff --git a/site/dashboard.html b/site/dashboard.html index 348960c..005106e 100644 --- a/site/dashboard.html +++ b/site/dashboard.html @@ -4,9 +4,7 @@ Numa — Dashboard - - - +
-
404
+{body} +
+"## + ) +} + +fn extract_host(req: &Request) -> Option { + req.headers() + .get(hyper::header::HOST) + .and_then(|v| v.to_str().ok()) + .map(|h| h.split(':').next().unwrap_or(h).to_lowercase()) +} + +async fn proxy_handler(State(state): State, req: Request) -> axum::response::Response { + let hostname = match extract_host(&req) { + Some(h) => h, + None => { + return (StatusCode::BAD_REQUEST, "missing Host header").into_response(); + } + }; + + let service_name = match hostname.strip_suffix(state.ctx.proxy_tld_suffix.as_str()) { + Some(name) => name.to_string(), + None => { + // Check if this domain was blocked — show a helpful styled page + if state.ctx.blocklist.read().unwrap().is_blocked(&hostname) { + let body = format!( + r#"
🛡
+
Blocked by Numa
+
{0}
+

This domain is on the ad & tracker blocklist.
To allow it, use the dashboard or:

+ 
$ curl -X POST localhost:5380/blocking/allowlist \
+    -d '{{"domain":"{0}"}}'
"#, + hostname + ); + return ( + StatusCode::FORBIDDEN, + [(hyper::header::CONTENT_TYPE, "text/html; charset=utf-8")], + error_page(&format!("Blocked — {}", hostname), &body), + ) + .into_response(); + } + return ( + StatusCode::BAD_GATEWAY, + format!("not a {} domain: {}", state.ctx.proxy_tld_suffix, hostname), + ) + .into_response(); + } + }; + + let request_path = req.uri().path().to_string(); + + let (target_host, target_port, rewritten_path) = { + let store = state.ctx.services.lock().unwrap(); + if let Some(entry) = store.lookup(&service_name) { + let (port, path) = entry.resolve_route(&request_path); + ("localhost".to_string(), port, path) + } else { + let mut peers = state.ctx.lan_peers.lock().unwrap(); + match peers.lookup(&service_name) { + Some((ip, port)) => (ip.to_string(), port, request_path.clone()), + None => { + let body = format!( + r#"
404
{0}{1}

This service isn't registered yet.
Add it from the dashboard or:

$ curl -X POST numa.numa:5380/services \
     -H 'Content-Type: application/json' \
     -d '{{"name":"{0}","target_port":3000}}'
-
ma-ia hii, ma-ia huu, ma-ia haa, ma-ia ha-ha
- -"##, +
ma-ia hii, ma-ia huu, ma-ia haa, ma-ia ha-ha
"#, service_name, state.ctx.proxy_tld_suffix - ), - ) - .into_response() + ); + return ( + StatusCode::NOT_FOUND, + [(hyper::header::CONTENT_TYPE, "text/html; charset=utf-8")], + error_page( + &format!("404 — {}{}", service_name, state.ctx.proxy_tld_suffix), + &body, + ), + ) + .into_response(); } } } diff --git a/src/record.rs b/src/record.rs index f525cbb..b7522dc 100644 --- a/src/record.rs +++ b/src/record.rs @@ -70,7 +70,7 @@ impl DnsRecord { } pub fn read(buffer: &mut BytePacketBuffer) -> Result { - let mut domain = String::new(); + let mut domain = String::with_capacity(64); buffer.read_qname(&mut domain)?; let qtype_num = buffer.read_u16()?; @@ -110,7 +110,7 @@ impl DnsRecord { Ok(DnsRecord::AAAA { domain, addr, ttl }) } QueryType::NS => { - let mut ns = String::new(); + let mut ns = String::with_capacity(64); buffer.read_qname(&mut ns)?; Ok(DnsRecord::NS { @@ -120,7 +120,7 @@ impl DnsRecord { }) } QueryType::CNAME => { - let mut cname = String::new(); + let mut cname = String::with_capacity(64); buffer.read_qname(&mut cname)?; Ok(DnsRecord::CNAME { @@ -131,7 +131,7 @@ impl DnsRecord { } QueryType::MX => { let priority = buffer.read_u16()?; - let mut mx = String::new(); + let mut mx = String::with_capacity(64); buffer.read_qname(&mut mx)?; Ok(DnsRecord::MX { diff --git a/src/tls.rs b/src/tls.rs index 966b1f1..a4d91bf 100644 --- a/src/tls.rs +++ b/src/tls.rs @@ -112,8 +112,15 @@ fn generate_service_cert( .distinguished_name .push(DnType::CommonName, format!("Numa .{} services", tld)); - // Add each service as an explicit SAN: numa.numa, peekm.numa, api.numa, etc. + // Add a wildcard SAN so any .numa domain gets a valid cert (including + // unregistered services — lets the proxy show a styled 404 over HTTPS). + // Also add each service explicitly for clients that don't match wildcards. let mut sans = Vec::new(); + let wildcard = format!("*.{}", tld); + match wildcard.clone().try_into() { + Ok(ia5) => sans.push(SanType::DnsName(ia5)), + Err(e) => warn!("invalid wildcard SAN {}: {}", wildcard, e), + } for name in service_names { let fqdn = format!("{}.{}", name, tld); match fqdn.clone().try_into() {