Reduce network bandwidth, improve parablock times: optimize approval-distribution (#5164)

* gossip-support: be explicit about dimensions * some guide updates * update network-bridge to distinguish x and y dimensions * get everything to compile * beginnings * some TODOs * polkadot runtime: use relevant_authorities * make gossip topologies per-session * better formatting * gossip support: use current session validators * expand in comment * adjust tests and fix index bug * add past/present/future connection test and clean up code * fmt * network bridge: updated types * update protocols to new gossip topology message * guide updates * add session to BlockApprovalMeta * add session to block info * refactor knowledge and remove most unify logic * start replacing gossip_peers with new SessionTopologies * add routing information to message state * add some utilities to SessionTopology * implement new gossip topology logic * re-implement unify_with_peer * distribute assignments according to topology * finish grid topology implementation * refactor network bridge slightly * issue connection requests on all past/present/future * fmt * address grumbles * tighten invariants in unify_with_peer * implement random propagation * refactor: extract required routing adjustment logic * some block-age logic * aggressively propagate messages when finality is slow * overhaul aggression system to have 3 levels * add aggression metrics * remove aggression L3 * reduce random circulation * remove PeerData * get approval tests compiling * use btree_map in known_by to make deterministic * Revert "use btree_map in known_by to make deterministic" This reverts commit 330d65343a7bb6fe4dd0f24bd8dbc15c0cbdbd9d. * test XY grid propagation * remove stray println * test unshared dimension propagation * add random gossip check * test unify_with_peer better * test sending after getting gossip topology * test L1 aggression on originator * test L1 aggression for non-originators * test non-originator aggression L2 * fnt * ~spellcheck * fix statement-distribution tests * fix flaky test * fix metrics typo * re-send periodically * test resending * typo Co-authored-by: Bernhard Schuster <bernhard@ahoi.io> * add more metrics about apd messages * add back unify_with_peer logs * make Resend an enum * be more explicit when resending * fmt * fix error * add a TODO for refactoring * remove debug metrics * add some guide stuff * fmt * update runtime API in test-runtim Co-authored-by: Bernhard Schuster <bernhard@ahoi.io>
2026-04-30 21:17:56 +00:00 · 2022-04-19 13:26:55 -05:00
parent edfa24bbc5
commit 79ecc53801
25 changed files with 2563 additions and 499 deletions
@@ -31,10 +31,13 @@ use polkadot_node_network_protocol::{
 };
 use polkadot_node_subsystem_util::metrics::{self, prometheus};
 use polkadot_overseer::gen::{OverseerError, Subsystem};
-use polkadot_primitives::v2::{BlockNumber, Hash};
+use polkadot_primitives::v2::{AuthorityDiscoveryId, BlockNumber, Hash, ValidatorIndex};
 use polkadot_subsystem::{
 	errors::{SubsystemError, SubsystemResult},
-	messages::{AllMessages, CollatorProtocolMessage, NetworkBridgeEvent, NetworkBridgeMessage},
+	messages::{
+		network_bridge_event::{NewGossipTopology, TopologyPeerInfo},
+		AllMessages, CollatorProtocolMessage, NetworkBridgeEvent, NetworkBridgeMessage,
+	},
 	overseer, ActivatedLeaf, ActiveLeavesUpdate, FromOverseer, OverseerSignal, SpawnedSubsystem,
 	SubsystemContext, SubsystemSender,
 };
@@ -45,7 +48,8 @@ use polkadot_subsystem::{
 pub use polkadot_node_network_protocol::peer_set::{peer_sets_info, IsAuthority};

 use std::{
-	collections::{hash_map, HashMap, HashSet},
+	collections::{hash_map, HashMap},
+	iter::ExactSizeIterator,
 	sync::Arc,
 };

@@ -590,30 +594,36 @@ where
 						).await;
 					}
 					NetworkBridgeMessage::NewGossipTopology {
-						our_neighbors,
+						session,
+						our_neighbors_x,
+						our_neighbors_y,
 					} => {
 						gum::debug!(
 							target: LOG_TARGET,
 							action = "NewGossipTopology",
-							neighbors = our_neighbors.len(),
+							neighbors_x = our_neighbors_x.len(),
+							neighbors_y = our_neighbors_y.len(),
 							"Gossip topology has changed",
 						);

-						let ads = &mut authority_discovery_service;
-						let mut gossip_peers = HashSet::with_capacity(our_neighbors.len());
-						for authority in our_neighbors {
-							let addr = get_peer_id_by_authority_id(
-								ads,
-								authority.clone(),
-							).await;
+						let gossip_peers_x = update_gossip_peers_1d(
+							&mut authority_discovery_service,
+							our_neighbors_x,
+						).await;

-							if let Some(peer_id) = addr {
-								gossip_peers.insert(peer_id);
-							}
-						}
+						let gossip_peers_y = update_gossip_peers_1d(
+							&mut authority_discovery_service,
+							our_neighbors_y,
+						).await;

 						dispatch_validation_event_to_all_unbounded(
-							NetworkBridgeEvent::NewGossipTopology(gossip_peers),
+							NetworkBridgeEvent::NewGossipTopology(
+								NewGossipTopology {
+									session,
+									our_neighbors_x: gossip_peers_x,
+									our_neighbors_y: gossip_peers_y,
+								}
+							),
 							ctx.sender(),
 						);
 					}
@@ -624,6 +634,28 @@ where
 	}
 }

+async fn update_gossip_peers_1d<AD, N>(
+	ads: &mut AD,
+	neighbors: N,
+) -> HashMap<AuthorityDiscoveryId, TopologyPeerInfo>
+where
+	AD: validator_discovery::AuthorityDiscovery,
+	N: IntoIterator<Item = (AuthorityDiscoveryId, ValidatorIndex)>,
+	N::IntoIter: std::iter::ExactSizeIterator,
+{
+	let neighbors = neighbors.into_iter();
+	let mut peers = HashMap::with_capacity(neighbors.len());
+	for (authority, validator_index) in neighbors {
+		let addr = get_peer_id_by_authority_id(ads, authority.clone()).await;
+
+		if let Some(peer_id) = addr {
+			peers.insert(authority, TopologyPeerInfo { peer_ids: vec![peer_id], validator_index });
+		}
+	}
+
+	peers
+}
+
 async fn handle_network_messages<AD: validator_discovery::AuthorityDiscovery>(
 	mut sender: impl SubsystemSender,
 	mut network_service: impl Network,