Req/res optimization for statement distribution (#2803)

* Wip

* Increase proposer timeout.

* WIP.

* Better timeout values now that we are going to be connected to all nodes. (#2778)

* Better timeout values.

* Fix typo.

* Fix validator bandwidth.

* Fix compilation.

* Better and more consistent sizes.

Most importantly code size is now 5 Meg, which is the limit we currently
want to support in statement distribution.

* Introduce statement fetching request.

* WIP

* Statement cache retrieval logic.

* Review remarks by @rphmeier

* Fixes.

* Better requester logic.

* WIP: Handle requester messages.

* Missing dep.

* Fix request launching logic.

* Finish fetching logic.

* Sending logic.

* Redo code size calculations.

Now that max code size is compressed size.

* Update Cargo.lock (new dep)

* Get request receiver to statement distribution.

* Expose new functionality for responding to requests.

* Cleanup.

* Responder logic.

* Fixes + Cleanup.

* Cargo.lock

* Whitespace.

* Add lost copyright.

* Launch responder task.

* Typo.

* info -> warn

* Typo.

* Fix.

* Fix.

* Update comment.

* Doc fix.

* Better large statement heuristics.

* Fix tests.

* Fix network bridge tests.

* Add test for size estimate.

* Very simple tests that checks we get LargeStatement.

* Basic check, that fetching of large candidates is performed.

* More tests.

* Basic metrics for responder.

* More metrics.

* Use Encode::encoded_size().

* Some useful spans.

* Get rid of redundant metrics.

* Don't add peer on duplicate.

* Properly check hash

instead of relying on signatures alone.

* Preserve ordering + better flood protection.

* Get rid of redundant clone.

* Don't shutdown responder on failed query.

And add test for this.

* Smaller fixes.

* Quotes.

* Better queue size calculation.

* A bit saner response sizes.

* Fixes.

polkadot/node/network/protocol/src/lib.rs

@@ -291,10 +291,7 @@ pub mod v1 {
 	use parity_scale_codec::{Encode, Decode};
 	use std::convert::TryFrom;
 
-	use polkadot_primitives::v1::{
-		CandidateIndex, CollatorId, Hash, Id as ParaId, SignedAvailabilityBitfield,
-		CollatorSignature,
-	};
+	use polkadot_primitives::v1::{CandidateHash, CandidateIndex, CollatorId, CollatorSignature, CompactStatement, Hash, Id as ParaId, SignedAvailabilityBitfield, ValidatorIndex, ValidatorSignature};
 	use polkadot_node_primitives::{
 		approval::{IndirectAssignmentCert, IndirectSignedApprovalVote},
 		SignedFullStatement,
@@ -313,7 +310,68 @@ pub mod v1 {
 	pub enum StatementDistributionMessage {
 		/// A signed full statement under a given relay-parent.
 		#[codec(index = 0)]
-		Statement(Hash, SignedFullStatement)
+		Statement(Hash, SignedFullStatement),
+		/// Seconded statement with large payload (e.g. containing a runtime upgrade).
+		///
+		/// We only gossip the hash in that case, actual payloads can be fetched from sending node
+		/// via req/response.
+		#[codec(index = 1)]
+		LargeStatement(StatementMetadata),
+	}
+
+	/// Data that maes a statement unique.
+	#[derive(Debug, Clone, Encode, Decode, PartialEq, Eq, Hash)]
+	pub struct StatementMetadata {
+		/// Relayt parent this statement is relevant under.
+		pub relay_parent: Hash,
+		/// Hash of the candidate that got validated.
+		pub candidate_hash: CandidateHash,
+		/// Validator that attested the valididty.
+		pub signed_by: ValidatorIndex,
+		/// Signature of seconding validator.
+		pub signature: ValidatorSignature,
+	}
+
+	impl StatementDistributionMessage {
+		/// Get meta data of the given `StatementDistributionMessage`.
+		pub fn get_metadata(&self) -> StatementMetadata {
+			match self {
+				Self::Statement(relay_parent, statement) => StatementMetadata {
+					relay_parent: *relay_parent,
+					candidate_hash: statement.payload().candidate_hash(),
+					signed_by: statement.validator_index(),
+					signature: statement.signature().clone(),
+				},
+				Self::LargeStatement(metadata) => metadata.clone(),
+			}
+		}
+
+		/// Get fingerprint describing the contained statement uniquely.
+		pub fn get_fingerprint(&self) -> (CompactStatement, ValidatorIndex) {
+			match self {
+				Self::Statement(_, statement) =>
+					(statement.payload().to_compact(), statement.validator_index()),
+				Self::LargeStatement(meta) =>
+					(CompactStatement::Seconded(meta.candidate_hash), meta.signed_by),
+			}
+		}
+
+		/// Get contained relay parent.
+		pub fn get_relay_parent(&self) -> Hash {
+			match self {
+				Self::Statement(r, _) => *r,
+				Self::LargeStatement(meta) => meta.relay_parent,
+			}
+		}
+
+		/// Whether or not this message contains a large statement.
+		pub fn is_large_statement(&self) -> bool {
+			if let Self::LargeStatement(_) = self {
+				true
+			} else {
+				false
+			}
+		}
 	}
 
 	/// Network messages used by the approval distribution subsystem.

polkadot/node/network/protocol/src/request_response/mod.rs

@@ -32,11 +32,12 @@
 //!
 //!  Versioned (v1 module): The actual requests and responses as sent over the network.
 
-use std::borrow::Cow;
+use std::{borrow::Cow, u64};
 use std::time::Duration;
 
 use futures::channel::mpsc;
 use polkadot_node_primitives::MAX_POV_SIZE;
+use polkadot_primitives::v1::MAX_CODE_SIZE;
 use strum::EnumIter;
 
 pub use sc_network::config as network;
@@ -64,8 +65,15 @@ pub enum Protocol {
 	PoVFetching,
 	/// Protocol for fetching available data.
 	AvailableDataFetching,
+	/// Fetching of statements that are too large for gossip.
+	StatementFetching,
 }
 
+
+/// Minimum bandwidth we expect for validators - 500Mbit/s is the recommendation, so approximately
+/// 50Meg bytes per second:
+const MIN_BANDWIDTH_BYTES: u64  = 50 * 1024 * 1024;
+
 /// Default request timeout in seconds.
 ///
 /// When decreasing this value, take into account that the very first request might need to open a
@@ -78,14 +86,22 @@ const DEFAULT_REQUEST_TIMEOUT: Duration = Duration::from_secs(3);
 /// peer set as well).
 const DEFAULT_REQUEST_TIMEOUT_CONNECTED: Duration = Duration::from_secs(1);
 
-/// Minimum bandwidth we expect for validators - 500Mbit/s is the recommendation, so approximately
-/// 50Meg bytes per second:
-const MIN_BANDWIDTH_BYTES: u64  = 50 * 1024 * 1024;
 /// Timeout for PoV like data, 2 times what it should take, assuming we can fully utilize the
 /// bandwidth. This amounts to two seconds right now.
 const POV_REQUEST_TIMEOUT_CONNECTED: Duration =
 	Duration::from_millis(2 * 1000 * (MAX_POV_SIZE as u64)  / MIN_BANDWIDTH_BYTES);
 
+/// We want timeout statement requests fast, so we don't waste time on slow nodes. Responders will
+/// try their best to either serve within that timeout or return an error immediately. (We need to
+/// fit statement distribution within a block of 6 seconds.)
+const STATEMENTS_TIMEOUT: Duration = Duration::from_secs(1);
+
+/// We don't want a slow peer to slow down all the others, at the same time we want to get out the
+/// data quickly in full to at least some peers (as this will reduce load on us as they then can
+/// start serving the data). So this value is a tradeoff. 3 seems to be sensible. So we would need
+/// to have 3 slow noded connected, to delay transfer for others by `STATEMENTS_TIMEOUT`.
+pub const MAX_PARALLEL_STATEMENT_REQUESTS: u32 = 3;
+
 impl Protocol {
 	/// Get a configuration for a given Request response protocol.
 	///
@@ -105,16 +121,16 @@ impl Protocol {
 		let cfg = match self {
 			Protocol::ChunkFetching => RequestResponseConfig {
 				name: p_name,
-				max_request_size: 10_000,
-				max_response_size: 10_000_000,
+				max_request_size: 1_000,
+				max_response_size: MAX_POV_SIZE as u64 / 10,
 				// We are connected to all validators:
 				request_timeout: DEFAULT_REQUEST_TIMEOUT_CONNECTED,
 				inbound_queue: Some(tx),
 			},
 			Protocol::CollationFetching => RequestResponseConfig {
 				name: p_name,
-				max_request_size: 10_000,
-				max_response_size: MAX_POV_SIZE as u64,
+				max_request_size: 1_000,
+				max_response_size: MAX_POV_SIZE as u64 + 1000,
 				// Taken from initial implementation in collator protocol:
 				request_timeout: POV_REQUEST_TIMEOUT_CONNECTED,
 				inbound_queue: Some(tx),
@@ -130,10 +146,28 @@ impl Protocol {
 				name: p_name,
 				max_request_size: 1_000,
 				// Available data size is dominated by the PoV size.
-				max_response_size: MAX_POV_SIZE as u64,
+				max_response_size: MAX_POV_SIZE as u64 + 1000,
 				request_timeout: POV_REQUEST_TIMEOUT_CONNECTED,
 				inbound_queue: Some(tx),
 			},
+			Protocol::StatementFetching => RequestResponseConfig {
+				name: p_name,
+				max_request_size: 1_000,
+				// Available data size is dominated code size.
+                // + 1000 to account for protocol overhead (should be way less).
+				max_response_size: MAX_CODE_SIZE as u64 + 1000,
+				// We need statement fetching to be fast and will try our best at the responding
+				// side to answer requests within that timeout, assuming a bandwidth of 500Mbit/s
+				// - which is the recommended minimum bandwidth for nodes on Kusama as of April
+				// 2021.
+				// Responders will reject requests, if it is unlikely they can serve them within
+				// the timeout, so the requester can immediately try another node, instead of
+				// waiting for timeout on an overloaded node.  Fetches from slow nodes will likely
+				// fail, but this is desired, so we can quickly move on to a faster one - we should
+				// also decrease its reputation.
+				request_timeout: Duration::from_secs(1),
+				inbound_queue: Some(tx),
+			},
 		};
 		(rx, cfg)
 	}
@@ -154,6 +188,26 @@ impl Protocol {
 			// Validators are constantly self-selecting to request available data which may lead
 			// to constant load and occasional burstiness.
 			Protocol::AvailableDataFetching => 100,
+			// Our queue size approximation is how many blocks of the size of
+			// a runtime we can transfer within a statements timeout, minus the requests we handle
+			// in parallel.
+			Protocol::StatementFetching => {
+				// We assume we can utilize up to 70% of the available bandwidth for statements.
+				// This is just a guess/estimate, with the following considerations: If we are
+				// faster than that, queue size will stay low anyway, even if not - requesters will
+				// get an immediate error, but if we are slower, requesters will run in a timeout -
+				// waisting precious time.
+				let available_bandwidth = 7 * MIN_BANDWIDTH_BYTES / 10;
+				let size = u64::saturating_sub(
+                    STATEMENTS_TIMEOUT.as_millis() as u64 * available_bandwidth / (1000 * MAX_CODE_SIZE as u64),
+					MAX_PARALLEL_STATEMENT_REQUESTS as u64
+				);
+				debug_assert!(
+					size > 0,
+					"We should have a channel size greater zero, otherwise we won't accept any requests."
+				);
+				size as usize
+			}
 		}
 	}
 
@@ -169,6 +223,7 @@ impl Protocol {
 			Protocol::CollationFetching => "/polkadot/req_collation/1",
 			Protocol::PoVFetching => "/polkadot/req_pov/1",
 			Protocol::AvailableDataFetching => "/polkadot/req_available_data/1",
+			Protocol::StatementFetching => "/polkadot/req_statement/1",
 		}
 	}
 }

polkadot/node/network/protocol/src/request_response/request.rs

@@ -25,6 +25,8 @@ use sc_network::PeerId;
 
 use polkadot_primitives::v1::AuthorityDiscoveryId;
 
+use crate::UnifiedReputationChange;
+
 use super::{v1, Protocol};
 
 /// Common properties of any `Request`.
@@ -47,6 +49,8 @@ pub enum Requests {
 	PoVFetching(OutgoingRequest<v1::PoVFetchingRequest>),
 	/// Request full available data from a node.
 	AvailableDataFetching(OutgoingRequest<v1::AvailableDataFetchingRequest>),
+	/// Requests for fetching large statements as part of statement distribution.
+	StatementFetching(OutgoingRequest<v1::StatementFetchingRequest>),
 }
 
 impl Requests {
@@ -57,6 +61,7 @@ impl Requests {
 			Self::CollationFetching(_) => Protocol::CollationFetching,
 			Self::PoVFetching(_) => Protocol::PoVFetching,
 			Self::AvailableDataFetching(_) => Protocol::AvailableDataFetching,
+			Self::StatementFetching(_) => Protocol::StatementFetching,
 		}
 	}
 
@@ -73,6 +78,7 @@ impl Requests {
 			Self::CollationFetching(r) => r.encode_request(),
 			Self::PoVFetching(r) => r.encode_request(),
 			Self::AvailableDataFetching(r) => r.encode_request(),
+			Self::StatementFetching(r) => r.encode_request(),
 		}
 	}
 }
@@ -199,6 +205,22 @@ pub struct IncomingRequest<Req> {
 	pending_response: oneshot::Sender<netconfig::OutgoingResponse>,
 }
 
+/// Typed variant of [`netconfig::OutgoingResponse`].
+///
+/// Responses to `IncomingRequest`s.
+pub struct OutgoingResponse<Response> {
+	/// The payload of the response.
+	pub result: Result<Response, ()>,
+
+	/// Reputation changes accrued while handling the request. To be applied to the reputation of
+	/// the peer sending the request.
+	pub reputation_changes: Vec<UnifiedReputationChange>,
+
+	/// If provided, the `oneshot::Sender` will be notified when the request has been sent to the
+	/// peer.
+	pub sent_feedback: Option<oneshot::Sender<()>>,
+}
+
 impl<Req> IncomingRequest<Req>
 where
 	Req: IsRequest,
@@ -232,6 +254,31 @@ where
 			})
 			.map_err(|_| resp)
 	}
+
+	/// Send response with additional options.
+	///
+	/// This variant allows for waiting for the response to be sent out, allows for changing peer's
+	/// reputation and allows for not sending a response at all (for only changing the peer's
+	/// reputation).
+	pub fn send_outgoing_response(self, resp: OutgoingResponse<<Req as IsRequest>::Response>)
+		-> Result<(), ()> {
+		let OutgoingResponse {
+			result,
+			reputation_changes,
+			sent_feedback,
+		} = resp;
+
+		let response = netconfig::OutgoingResponse {
+			result: result.map(|v| v.encode()),
+			reputation_changes: reputation_changes
+				.into_iter()
+				.map(|c| c.into_base_rep())
+				.collect(),
+			sent_feedback,
+		};
+
+		self.pending_response.send(response).map_err(|_| ())
+	}
 }
 
 /// Future for actually receiving a typed response for an OutgoingRequest.

polkadot/node/network/protocol/src/request_response/v1.rs

@@ -18,10 +18,7 @@
 
 use parity_scale_codec::{Decode, Encode};
 
-use polkadot_primitives::v1::{
-	CandidateHash, CandidateReceipt, ValidatorIndex,
-	Hash,
-};
+use polkadot_primitives::v1::{CandidateHash, CandidateReceipt, CommittedCandidateReceipt, Hash, ValidatorIndex};
 use polkadot_primitives::v1::Id as ParaId;
 use polkadot_node_primitives::{AvailableData, PoV, ErasureChunk};
 
@@ -169,3 +166,29 @@ impl IsRequest for AvailableDataFetchingRequest {
 	type Response = AvailableDataFetchingResponse;
 	const PROTOCOL: Protocol = Protocol::AvailableDataFetching;
 }
+
+/// Request for fetching a large statement via request/response.
+#[derive(Debug, Clone, Encode, Decode)]
+pub struct StatementFetchingRequest {
+	/// Data needed to locate and identify the needed statement.
+	pub relay_parent: Hash,
+	/// Hash of candidate that was used create the CommitedCandidateRecept.
+	pub candidate_hash: CandidateHash,
+}
+
+/// Respond with found full statement.
+///
+/// In this protocol the requester will only request data it was previously notified about,
+/// therefore not having the data is not really an option and would just result in a
+/// `RequestFailure`.
+#[derive(Debug, Clone, Encode, Decode)]
+pub enum StatementFetchingResponse {
+	/// Data missing to reconstruct the full signed statement.
+	#[codec(index = 0)]
+	Statement(CommittedCandidateReceipt),
+}
+
+impl IsRequest for StatementFetchingRequest {
+	type Response = StatementFetchingResponse;
+	const PROTOCOL: Protocol = Protocol::StatementFetching;
+}