Given the following scenario:
1. Remote peer X connects and is added to `connected_peers`.
2. Remote peer X opens a Kademlia substream and thus confirms that it supports
the Kademlia protocol.
3. Remote peer X is added to the routing table as `Connected`.
4. Remote peer X disconnects and is thus marked as `Disconnected` in the routing
table.
5. Remote peer Y connects and is added to `connected_peers`.
6. Remote peer X re-connects and is added to `connected_peers`.
7. Remote peer Y opens a Kademlia substream and thus confirms that it supports
the Kademlia protocol.
8. Remote peer Y is added to the routing table. Given that the bucket is already
full the call to `entry.insert` returns `kbucket::InsertResult::Pending {
disconnected }` where disconnected is peer X.
While peer X is in `connected_peers` it has not yet (re-) confirmed that it
supports the Kademlia routing protocol and thus is still tracked as
`Disconnected` in the routing table. The `debug_assert` removed in this pull
request does not capture this scenario.
1. Deprecating the `write_one` function
Semantically, this function is a composition of `write_with_len_prefix` and
`io.close()`. This represents a footgun because the `close` functionality is
not obvious and only mentioned in the docs. Using this function multiple times
on a single substream will produces hard to debug behaviour.
2. Deprecating `read_one` and `write_with_len_prefix` functions
3. Introducing `write_length_prefixed` and `read_length_prefixed`
- These functions are symmetric and do exactly what you would expect, just
writing to the socket without closing
- They also have a symmetric interface (no more custom errors, just `io::Error`)
Co-authored-by: Max Inden <mail@max-inden.de>
Add `ExpandedSwarm::disconnect_peer_id` and
`NetworkBehaviourAction::CloseConnection` to close connections to a specific
peer via an `ExpandedSwarm` or `NetworkBehaviour`.
Co-authored-by: Max Inden <mail@max-inden.de>
Change `Stream` implementation of `ExpandedSwarm` to return all
`SwarmEvents` instead of only the `NetworkBehaviour`'s events.
Remove `ExpandedSwarm::next_event`. Users can use `<ExpandedSwarm as
StreamExt>::next` instead.
Remove `ExpandedSwarm::next`. Users can use `<ExpandedSwarm as
StreamExt>::filter_map` instead.
Add instructions on how to run a three node example where a listening
relay client listens via a relay server and a dialing relay client dials
the listening relay client via the relay server.
mdns keeps rediscovering nodes. this PR changes that to only emit events for new
nodes it discovered. In addition we make sure to only send a query if it is
really needed. Some logging is added for debugging purposes.
If you start listening after mdns joined a multicast group, the peers may not
discover eachother until the 5min timeout expires.
Co-authored-by: Max Inden <mail@max-inden.de>
Remove `Deref` and `DerefMut` implementations previously dereferencing
to the `NetworkBehaviour` on `Swarm`. Instead one can access the
`NetworkBehaviour` via `Swarm::behaviour` and `Swarm::behaviour_mut`.
Methods on `Swarm` can now be accessed directly, e.g. via
`my_swarm.local_peer_id()`.
Reasoning: Accessing the `NetworkBehaviour` of a `Swarm` through `Deref`
and `DerefMut` instead of a method call is an unnecessary complication,
especially for newcomers. In addition, `Swarm` is not a smart-pointer
and should thus not make use of `Deref` and `DerefMut`, see documentation
from the standard library below.
> Deref should only be implemented for smart pointers to avoid
confusion.
https://doc.rust-lang.org/std/ops/trait.Deref.html
* Implement /ipfs/id/push/1.0.0 alongside some refactoring.
* Implement /ipfs/id/push/1.0.0, i.e. the ability to actively
push information of the local peer to specific remotes.
* Make the initial delay as well as the recurring delay
for the periodic identification requests configurable,
introducing `IdentifyConfig`.
* Fix test.
* Fix example.
* Update protocols/identify/src/identify.rs
Co-authored-by: Max Inden <mail@max-inden.de>
* Update protocols/identify/src/identify.rs
Co-authored-by: Max Inden <mail@max-inden.de>
* Update versions and changelogs.
Co-authored-by: Max Inden <mail@max-inden.de>
* Implement `/dnsaddr` support on `libp2p-dns`.
To that end, since resolving `/dnsaddr` addresses needs
"fully qualified" multiaddresses when dialing, i.e. those
that end with the `/p2p/...` protocol, we make sure that
dialing always uses such fully qualified addresses by
appending the `/p2p` protocol as necessary. As a side-effect,
this adds support for dialing peers via "fully qualified"
addresses, as an alternative to using a `PeerId` together
with a `Multiaddr` with or without the `/p2p` protocol.
* Adapt libp2p-relay.
* Update versions, changelogs and small cleanups.
This commit implements the [libp2p circuit
relay](https://github.com/libp2p/specs/tree/master/relay) specification. It is
based on previous work from https://github.com/libp2p/rust-libp2p/pull/1134.
Instead of altering the `Transport` trait, the approach taken in this commit
is to wrap an existing implementation of `Transport` allowing one to:
- Intercept `dial` requests with a relayed address.
- Inject incoming relayed connections with the local node being the destination.
- Intercept `listen_on` requests pointing to a relay, ensuring to keep a
constant connection to the relay, waiting for incoming requests with the local
node being the destination.
More concretely one would wrap an existing `Transport` implementation as seen
below, allowing the `Relay` behaviour and the `RelayTransport` to communicate
via channels.
### Example
```rust
let (relay_transport, relay_behaviour) = new_transport_and_behaviour(
RelayConfig::default(),
MemoryTransport::default(),
);
let transport = relay_transport
.upgrade(upgrade::Version::V1)
.authenticate(plaintext)
.multiplex(YamuxConfig::default())
.boxed();
let mut swarm = Swarm::new(transport, relay_behaviour, local_peer_id);
let relay_addr = Multiaddr::from_str("/memory/1234").unwrap()
.with(Protocol::P2p(PeerId::random().into()))
.with(Protocol::P2pCircuit);
let dst_addr = relay_addr.clone().with(Protocol::Memory(5678));
// Listen for incoming connections via relay node (1234).
Swarm::listen_on(&mut swarm, relay_addr).unwrap();
// Dial node (5678) via relay node (1234).
Swarm::dial_addr(&mut swarm, dst_addr).unwrap();
```
Co-authored-by: Pierre Krieger <pierre.krieger1708@gmail.com>
Co-authored-by: Roman Borschel <romanb@users.noreply.github.com>
Co-authored-by: David Craven <david@craven.ch>
* Add `Kademlia::put_record_to` for storing a record at specific nodes,
e.g. for write-back caching after a successful read. In that context,
peers that were queried in a successful `Kademlia::get_record` operation but
did not return a record are now returned in the `GetRecordOk::no_record`
list of peer IDs.
Closes https://github.com/libp2p/rust-libp2p/issues/1577.
* Update protocols/kad/src/behaviour.rs
Co-authored-by: Max Inden <mail@max-inden.de>
* Refine implementation.
Rather than returning the peers that are cache candidates
in a `Vec` in an arbitrary order, use a `BTreeMap`. Furthermore,
make the caching configurable, being enabled by default with
`max_peers` of 1. By configuring it with `max_peers` > 1 it is
now also possible to control at how many nodes the record is cached
automatically after a lookup with quorum 1. When enabled,
successful lookups will always return `cache_candidates`, which
can be used explicitly with `Kademlia::put_record_to` after
lookups with a quorum > 1.
* Re-export KademliaCaching
* Update protocols/kad/CHANGELOG.md
Co-authored-by: Max Inden <mail@max-inden.de>
* Clarify changelog.
Co-authored-by: Max Inden <mail@max-inden.de>
* Remove substream-specific protocol negotiation version.
Remove the option for a substream-specific multistream select protocol override.
The override at this granularity is no longer deemed useful, in particular because
it can usually not be configured for existing protocols like `libp2p-kad` and others.
There is a `Swarm`-scoped configuration for this version available since
[1858](https://github.com/libp2p/rust-libp2p/pull/1858).
* Update protocol crate versions and changelogs.
* Clean up documentation.
* Make clippy "happy".
Address all clippy complaints that are not purely stylistic (or even
have corner cases with false positives). Ignore all "style" and "pedantic" lints.
* Fix tests.
* Undo unnecessary API change.
