bench: two routers exchanging their tables with ADD-PATH

The full-table benchmark measures one router taking in tables from its
peers. What two routers of one AS do with each other, each sending the
other every path it has (ADD-PATH both ways with all_paths, as a mesh
of routers that each hold the network's whole view is configured), was
measured nowhere: the exporter following the table's journal while the
sessions fill the table, at the size of the Internet. In production
that exchange took 70 seconds for a table that arrives from the
Internet in 20.

A new benchmark, mesh, starts two servers in one AS with distinct
router IDs, peers them over IPv6 loopback with ADD-PATH both ways and
all_paths, and feeds the first from four synthetic peers and the second
from two over IPv4 loopback (BENCH_PEERS, BENCH_PEERS_B,
BENCH_SCALE_DOWN). It prints how long each router takes to hold its
own peers' routes and then the other's, with the rate of the latter.
BENCH_DEADLINE prints the sessions' state if a router is not there in
time.

The benchmarks now allocate with jemalloc, as the daemon does, except
when memory is being counted: the C library's allocator put its own
locks in the profiles. Two routers on one host have each other's
addresses as next hops, loopback addresses, which the import check
refuses as it refuses a next hop that is this machine; the permissive
import policy, which only tests use and no configuration can ask for,
now takes them.

Testing: the next-hop test covers both policies; the benchmark runs on
macOS and in the Linux VM under perf.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

crates/bench/Cargo.toml

@@ -16,6 +16,9 @@ bytes.workspace = true
 flate2 = "1"
 stats_alloc = { version = "0.1.10", optional = true }
 
+[target.'cfg(not(target_env = "msvc"))'.dependencies]
+tikv-jemallocator.workspace = true
+
 [dev-dependencies]
 bgp-integration-tests.workspace = true
 bgp-rib.workspace = true
@@ -42,3 +45,7 @@ harness = false
 
 [lints]
 workspace = true
+
+[[bench]]
+name = "mesh"
+harness = false

crates/bench/benches/mesh.rs

@@ -0,0 +1,195 @@
+//! Two routers of one AS, each taking in full tables from its own peers
+//! and sending the other every path (ADD-PATH both ways, `all_paths`), as
+//! a mesh of routers that each hold the network's whole view do. How
+//! long until each router has the other's routes is what this measures:
+//! the exporter reading the table's journal while sessions fill the
+//! table, which nothing else exercises at this size.
+//!
+//! Run with `cargo bench -p bgp-bench --bench mesh`. `BENCH_PEERS`
+//! (default 4) feed the first router and `BENCH_PEERS_B` (default 2) the
+//! second; `BENCH_SCALE_DOWN` shrinks the table. The routers peer over
+//! IPv6 loopback and the feeders come over IPv4 loopback.
+
+use std::net::{Ipv4Addr, Ipv6Addr, SocketAddr};
+use std::sync::Arc;
+use std::time::{Duration, Instant};
+
+use bgp_bench::{Prefixes, Shape, announcements, encoded, env};
+use bgp_integration_tests::peer_config;
+use bgp_integration_tests::test_peer::TestPeer;
+use bgp_integration_tests::test_server::TestServer;
+use bgp_packet::open::SendReceive;
+use bgp_server::config::PeerConfig;
+use bgp_server::policy::{ExportPolicy, ImportPolicy};
+
+/// An AS number that is in none of the synthetic paths.
+const ASN: u32 = 4_200_000_000;
+
+fn free_port() -> u16 {
+    std::net::TcpListener::bind((Ipv6Addr::LOCALHOST, 0))
+        .expect("a port")
+        .local_addr()
+        .expect("an address")
+        .port()
+}
+
+/// A router of the mesh, listening for feeders on IPv4 loopback and for
+/// the other router on IPv6 loopback at `port`, which it dials at
+/// `other`.
+async fn router(name: &'static str, id: u8, port: u16, other: u16) -> TestServer {
+    TestServer::start_with(ASN, |c| {
+        // Two routers of one AS must not share a BGP identifier.
+        c.router_id = Ipv4Addr::new(192, 0, 2, id);
+        c.cluster_id = c.router_id;
+        c.listen_endpoints = vec![
+            SocketAddr::new(Ipv4Addr::LOCALHOST.into(), 0),
+            SocketAddr::new(Ipv6Addr::LOCALHOST.into(), port),
+        ];
+        c.peers = vec![PeerConfig {
+            add_path: Some(SendReceive::Both),
+            import: ImportPolicy::permissive(),
+            export: Arc::new(ExportPolicy {
+                learned_routes: true,
+                all_paths: true,
+                ..ExportPolicy::default()
+            }),
+            ..peer_config(
+                name,
+                SocketAddr::new(Ipv6Addr::LOCALHOST.into(), other),
+                ASN,
+            )
+        }];
+        c.connect_retry = Duration::from_millis(200);
+    })
+    .await
+    .expect("a router")
+}
+
+/// Connects `count` feeders to `router`, numbered from `first`, and
+/// returns their sessions with the bytes each is to send.
+async fn feeders(
+    router: &TestServer,
+    prefixes: &Prefixes,
+    shape: Shape,
+    first: u32,
+    count: u32,
+) -> Vec<(TestPeer, Vec<u8>)> {
+    let mut sessions = Vec::new();
+    for peer in first..first + count {
+        let stream: Vec<u8> = encoded(&announcements(prefixes, shape, peer))
+            .iter()
+            .flat_map(|m| m.iter().copied())
+            .collect();
+        let mut session = TestPeer::connect(router.addr).await.expect("a connection");
+        session
+            .handshake(64512 + peer, Ipv4Addr::new(10, 0, 0, peer as u8), 90)
+            .await
+            .expect("a session");
+        sessions.push((session, stream));
+    }
+    sessions
+}
+
+fn main() {
+    let peers_a = env("BENCH_PEERS", 4) as u32;
+    let peers_b = env("BENCH_PEERS_B", 2) as u32;
+    let shape = Shape::INTERNET.scaled_down(env("BENCH_SCALE_DOWN", 1));
+    let per_peer = shape.prefixes();
+    println!(
+        "== Two routers of AS{ASN}, every path both ways: A fed by {peers_a} peers, B by {peers_b}, {} prefixes each",
+        per_peer
+    );
+    let prefixes = Prefixes::generate(shape);
+
+    let runtime = tokio::runtime::Builder::new_multi_thread()
+        .enable_all()
+        .build()
+        .expect("a runtime");
+    runtime.block_on(async {
+        let (port_a, port_b) = (free_port(), free_port());
+        let a = router("b", 1, port_a, port_b).await;
+        let b = router("a", 2, port_b, port_a).await;
+        a.wait_for_sessions(1).await.expect("the mesh session at A");
+        b.wait_for_sessions(1).await.expect("the mesh session at B");
+
+        let feed_a = feeders(&a, &prefixes, shape, 1, peers_a).await;
+        let feed_b = feeders(&b, &prefixes, shape, 1 + peers_a, peers_b).await;
+        let own_a = per_peer * peers_a as usize;
+        let own_b = per_peer * peers_b as usize;
+
+        let started = Instant::now();
+        let mut sending = Vec::new();
+        for (mut session, stream) in feed_a.into_iter().chain(feed_b) {
+            sending.push(tokio::spawn(async move {
+                session.send_raw(&stream).await.expect("the router reads");
+                session
+            }));
+        }
+        let mut a_own = None;
+        let mut b_own = None;
+        let mut a_all = None;
+        let mut b_all = None;
+        while a_all.is_none() || b_all.is_none() {
+            tokio::time::sleep(Duration::from_millis(5)).await;
+            let (at_a, at_b) = (a.rib.len(), b.rib.len());
+            let now = started.elapsed();
+            if a_own.is_none() && at_a >= own_a {
+                a_own = Some(now);
+            }
+            if b_own.is_none() && at_b >= own_b {
+                b_own = Some(now);
+            }
+            if a_all.is_none() && at_a >= own_a + own_b {
+                a_all = Some(now);
+            }
+            if b_all.is_none() && at_b >= own_a + own_b {
+                b_all = Some(now);
+            }
+            if now > Duration::from_secs(env("BENCH_DEADLINE", 600) as u64) {
+                let sessions = |router: &TestServer| -> Vec<String> {
+                    router
+                        .registry
+                        .list()
+                        .iter()
+                        .map(|s| {
+                            format!(
+                                "{} routes {} rejected {}",
+                                s.peer,
+                                s.counters.routes(),
+                                s.counters.rejected()
+                            )
+                        })
+                        .collect()
+                };
+                panic!(
+                    "not all routes arrived: A has {at_a} {:?}, B has {at_b} {:?}",
+                    sessions(&a),
+                    sessions(&b)
+                );
+            }
+        }
+        let row = |what: &str, when: Option<Duration>, routes: usize| {
+            let when = when.unwrap_or_default();
+            println!(
+                "{what:<52} {:>8.3} s   {:.2} M routes/s",
+                when.as_secs_f64(),
+                routes as f64 / when.as_secs_f64() / 1e6
+            );
+        };
+        row("A has its own peers' routes", a_own, own_a);
+        row("B has its own peers' routes", b_own, own_b);
+        row(
+            "A has B's routes too (B's exporter, A's session)",
+            a_all,
+            own_b,
+        );
+        row(
+            "B has A's routes too (A's exporter, B's session)",
+            b_all,
+            own_a,
+        );
+        for session in sending {
+            drop(session.await);
+        }
+    });
+}

crates/bench/src/lib.rs

@@ -17,6 +17,13 @@
 pub mod memory;
 pub mod mrt;
 
+// The benchmarks allocate as the daemon does (bin/bgp/src/main.rs), with
+// jemalloc; the C library's allocator would put its own locks in the
+// profile. Not when memory is counted: that needs the counting one.
+#[cfg(all(not(feature = "count-memory"), not(target_env = "msvc")))]
+#[global_allocator]
+static ALLOCATOR: tikv_jemallocator::Jemalloc = tikv_jemallocator::Jemalloc;
+
 use std::collections::HashSet;
 use std::net::{Ipv4Addr, Ipv6Addr};
 

crates/server/src/config.rs

@@ -646,6 +646,7 @@ fn parse_import(import: &proto::ImportPolicy) -> Result<ImportPolicy, ImportProb
         accept_aspa_invalid: import.accept_aspa_invalid,
         accept_as_sets: import.accept_as_sets,
         accept_third_party_next_hop: import.accept_third_party_next_hop,
+        accept_loopback_next_hop: false,
         accept_blackholes: import.accept_blackholes,
         own_prefixes: Arc::default(),
         originated: Arc::default(),

crates/server/src/policy.rs

@@ -91,6 +91,10 @@ pub struct ImportPolicy {
     /// who never asked for it. A route server's routes always have its
     /// clients as next hops, and are taken either way.
     pub accept_third_party_next_hop: bool,
+    /// Take a next hop that is a loopback address, or one of our own: for
+    /// routers that share a host, as those of a test do. Not a setting;
+    /// only [`ImportPolicy::permissive`] has it.
+    pub accept_loopback_next_hop: bool,
     /// Take routes with the BLACKHOLE community for single addresses, and
     /// have the kernel drop the traffic to them (RFC 7999).
     pub accept_blackholes: bool,
@@ -199,6 +203,7 @@ impl Default for ImportPolicy {
             accept_aspa_invalid: false,
             accept_as_sets: false,
             accept_third_party_next_hop: false,
+            accept_loopback_next_hop: false,
             accept_blackholes: false,
             own_prefixes: Arc::default(),
             originated: Arc::default(),
@@ -228,6 +233,7 @@ impl ImportPolicy {
             accept_aspa_invalid: true,
             accept_as_sets: true,
             accept_third_party_next_hop: true,
+            accept_loopback_next_hop: true,
             accept_blackholes: false,
             ..Self::default()
         }
@@ -727,10 +733,10 @@ impl ImportPolicy {
         let mut is_peer = false;
         for address in named {
             let usable = !address.is_unspecified()
-                && !address.is_loopback()
                 && !address.is_multicast()
                 && address != IpAddr::V4(Ipv4Addr::BROADCAST)
-                && address != from.local_address;
+                && (self.accept_loopback_next_hop
+                    || (!address.is_loopback() && address != from.local_address));
             if !usable {
                 return Err(Rejection::NextHopUnusable);
             }
@@ -1548,13 +1554,7 @@ mod tests {
         );
         // Nowhere at all, whatever the policy.
         let lenient = ImportPolicy::permissive();
-        for nowhere in [
-            "0.0.0.0",
-            "127.0.0.1",
-            "224.0.0.5",
-            "255.255.255.255",
-            "192.0.2.1",
-        ] {
+        for nowhere in ["0.0.0.0", "224.0.0.5", "255.255.255.255"] {
             for policy in [&policy, &lenient] {
                 assert_eq!(
                     check(policy, &v4(nowhere), &EXTERNAL),
@@ -1563,6 +1563,20 @@ mod tests {
                 );
             }
         }
+        // This machine: nowhere for traffic to go, unless the policy is
+        // the permissive one, for routers that share a host.
+        for ourselves in ["127.0.0.1", "192.0.2.1"] {
+            assert_eq!(
+                check(&policy, &v4(ourselves), &EXTERNAL),
+                Err(Rejection::NextHopUnusable),
+                "{ourselves}"
+            );
+            assert_eq!(
+                check(&lenient, &v4(ourselves), &EXTERNAL),
+                Ok(()),
+                "{ourselves}"
+            );
+        }
         // Where it may be someone else: said so, a route server, our own AS.
         assert_eq!(check(&lenient, &v4("192.0.2.3"), &EXTERNAL), Ok(()));
         for from in [