Integrate litep2p into Polkadot SDK (#2944)

[litep2p](https://github.com/altonen/litep2p) is a libp2p-compatible P2P
networking library. It supports all of the features of `rust-libp2p`
that are currently being utilized by Polkadot SDK.

Compared to `rust-libp2p`, `litep2p` has a quite different architecture
which is why the new `litep2p` network backend is only able to use a
little of the existing code in `sc-network`. The design has been mainly
influenced by how we'd wish to structure our networking-related code in
Polkadot SDK: independent higher-levels protocols directly communicating
with the network over links that support bidirectional backpressure. A
good example would be `NotificationHandle`/`RequestResponseHandle`
abstractions which allow, e.g., `SyncingEngine` to directly communicate
with peers to announce/request blocks.

I've tried running `polkadot --network-backend litep2p` with a few
different peer configurations and there is a noticeable reduction in
networking CPU usage. For high load (`--out-peers 200`), networking CPU
usage goes down from ~110% to ~30% (80 pp) and for normal load
(`--out-peers 40`), the usage goes down from ~55% to ~18% (37 pp).

These should not be taken as final numbers because:

a) there are still some low-hanging optimization fruits, such as
enabling [receive window
auto-tuning](https://github.com/libp2p/rust-yamux/pull/176), integrating
`Peerset` more closely with `litep2p` or improving memory usage of the
WebSocket transport
b) fixing bugs/instabilities that incorrectly cause `litep2p` to do less
work will increase the networking CPU usage
c) verification in a more diverse set of tests/conditions is needed

Nevertheless, these numbers should give an early estimate for CPU usage
of the new networking backend.

This PR consists of three separate changes:
* introduce a generic `PeerId` (wrapper around `Multihash`) so that we
don't have use `NetworkService::PeerId` in every part of the code that
uses a `PeerId`
* introduce `NetworkBackend` trait, implement it for the libp2p network
stack and make Polkadot SDK generic over `NetworkBackend`
  * implement `NetworkBackend` for litep2p

The new library should be considered experimental which is why
`rust-libp2p` will remain as the default option for the time being. This
PR currently depends on the master branch of `litep2p` but I'll cut a
new release for the library once all review comments have been
addresses.

---------

Signed-off-by: Alexandru Vasile <alexandru.vasile@parity.io>
Co-authored-by: Dmitry Markin <dmitry@markin.tech>
Co-authored-by: Alexandru Vasile <60601340+lexnv@users.noreply.github.com>
Co-authored-by: Alexandru Vasile <alexandru.vasile@parity.io>
This commit is contained in:
Aaro Altonen
2024-04-08 19:44:13 +03:00
committed by GitHub
parent 9543d31474
commit 80616f6d03
181 changed files with 11055 additions and 1862 deletions
@@ -15,64 +15,56 @@
// along with Cumulus. If not, see <http://www.gnu.org/licenses/>.
use polkadot_core_primitives::{Block, Hash, Header};
use sp_runtime::traits::{Block as BlockT, NumberFor};
use sp_runtime::traits::NumberFor;
use sc_network::{
config::{
NetworkConfiguration, NonDefaultSetConfig, NonReservedPeerMode, NotificationHandshake,
ProtocolId, SetConfig,
NetworkConfiguration, NonReservedPeerMode, NotificationHandshake, PeerStore, ProtocolId,
SetConfig,
},
peer_store::PeerStore,
NetworkService,
peer_store::PeerStoreProvider,
service::traits::NetworkService,
NotificationMetrics,
};
use sc_network::{config::FullNetworkConfiguration, NotificationService};
use sc_network::{config::FullNetworkConfiguration, NetworkBackend, NotificationService};
use sc_network_common::{role::Roles, sync::message::BlockAnnouncesHandshake};
use sc_service::{error::Error, Configuration, NetworkStarter, SpawnTaskHandle};
use std::{iter, sync::Arc};
/// Build the network service, the network status sinks and an RPC sender.
pub(crate) fn build_collator_network(
pub(crate) fn build_collator_network<Network: NetworkBackend<Block, Hash>>(
config: &Configuration,
mut full_network_config: FullNetworkConfiguration,
mut network_config: FullNetworkConfiguration<Block, Hash, Network>,
spawn_handle: SpawnTaskHandle,
genesis_hash: Hash,
best_header: Header,
notification_metrics: NotificationMetrics,
) -> Result<
(
Arc<NetworkService<Block, Hash>>,
NetworkStarter,
Arc<dyn sp_consensus::SyncOracle + Send + Sync>,
),
(Arc<dyn NetworkService>, NetworkStarter, Arc<dyn sp_consensus::SyncOracle + Send + Sync>),
Error,
> {
let protocol_id = config.protocol_id();
let (block_announce_config, _notification_service) = get_block_announce_proto_config::<Block>(
let (block_announce_config, _notification_service) = get_block_announce_proto_config::<Network>(
protocol_id.clone(),
&None,
Roles::from(&config.role),
best_header.number,
best_header.hash(),
genesis_hash,
notification_metrics.clone(),
network_config.peer_store_handle(),
);
// Since this node has no syncing, we do not want light-clients to connect to it.
// Here we set any potential light-client slots to 0.
adjust_network_config_light_in_peers(&mut full_network_config.network_config);
adjust_network_config_light_in_peers(&mut network_config.network_config);
let peer_store = PeerStore::new(
full_network_config
.network_config
.boot_nodes
.iter()
.map(|bootnode| bootnode.peer_id)
.collect(),
);
let peer_store_handle = peer_store.handle();
let peer_store = network_config.take_peer_store();
spawn_handle.spawn("peer-store", Some("networking"), peer_store.run());
let network_params = sc_network::config::Params::<Block> {
let network_params = sc_network::config::Params::<Block, Hash, Network> {
role: config.role.clone(),
executor: {
let spawn_handle = Clone::clone(&spawn_handle);
@@ -81,16 +73,17 @@ pub(crate) fn build_collator_network(
})
},
fork_id: None,
network_config: full_network_config,
peer_store: peer_store_handle,
network_config,
genesis_hash,
protocol_id,
metrics_registry: config.prometheus_config.as_ref().map(|config| config.registry.clone()),
block_announce_config,
bitswap_config: None,
notification_metrics,
};
let network_worker = sc_network::NetworkWorker::new(network_params)?;
let network_service = network_worker.service().clone();
let network_worker = Network::new(network_params)?;
let network_service = network_worker.network_service();
let (network_start_tx, network_start_rx) = futures::channel::oneshot::channel();
@@ -143,14 +136,16 @@ impl sp_consensus::SyncOracle for SyncOracle {
}
}
fn get_block_announce_proto_config<B: BlockT>(
fn get_block_announce_proto_config<Network: NetworkBackend<Block, Hash>>(
protocol_id: ProtocolId,
fork_id: &Option<String>,
roles: Roles,
best_number: NumberFor<B>,
best_hash: B::Hash,
genesis_hash: B::Hash,
) -> (NonDefaultSetConfig, Box<dyn NotificationService>) {
best_number: NumberFor<Block>,
best_hash: Hash,
genesis_hash: Hash,
metrics: NotificationMetrics,
peer_store_handle: Arc<dyn PeerStoreProvider>,
) -> (Network::NotificationProtocolConfig, Box<dyn NotificationService>) {
let block_announces_protocol = {
let genesis_hash = genesis_hash.as_ref();
if let Some(ref fork_id) = fork_id {
@@ -160,11 +155,11 @@ fn get_block_announce_proto_config<B: BlockT>(
}
};
NonDefaultSetConfig::new(
Network::notification_config(
block_announces_protocol.into(),
iter::once(format!("/{}/block-announces/1", protocol_id.as_ref()).into()).collect(),
1024 * 1024,
Some(NotificationHandshake::new(BlockAnnouncesHandshake::<B>::build(
Some(NotificationHandshake::new(BlockAnnouncesHandshake::<Block>::build(
roles,
best_number,
best_hash,
@@ -178,5 +173,7 @@ fn get_block_announce_proto_config<B: BlockT>(
reserved_nodes: Vec::new(),
non_reserved_mode: NonReservedPeerMode::Deny,
},
metrics,
peer_store_handle,
)
}