* Allow multiple connections per peer in libp2p-core.
Instead of trying to enforce a single connection per peer,
which involves quite a bit of additional complexity e.g.
to prioritise simultaneously opened connections and can
have other undesirable consequences [1], we now
make multiple connections per peer a feature.
The gist of these changes is as follows:
The concept of a "node" with an implicit 1-1 correspondence
to a connection has been replaced with the "first-class"
concept of a "connection". The code from `src/nodes` has moved
(with varying degrees of modification) to `src/connection`.
A `HandledNode` has become a `Connection`, a `NodeHandler` a
`ConnectionHandler`, the `CollectionStream` was the basis for
the new `connection::Pool`, and so forth.
Conceptually, a `Network` contains a `connection::Pool` which
in turn internally employs the `connection::Manager` for
handling the background `connection::manager::Task`s, one
per connection, as before. These are all considered implementation
details. On the public API, `Peer`s are managed as before through
the `Network`, except now the API has changed with the shift of focus
to (potentially multiple) connections per peer. The `NetworkEvent`s have
accordingly also undergone changes.
The Swarm APIs remain largely unchanged, except for the fact that
`inject_replaced` is no longer called. It may now practically happen
that multiple `ProtocolsHandler`s are associated with a single
`NetworkBehaviour`, one per connection. If implementations of
`NetworkBehaviour` rely somehow on communicating with exactly
one `ProtocolsHandler`, this may cause issues, but it is unlikely.
[1]: https://github.com/paritytech/substrate/issues/4272
* Fix intra-rustdoc links.
* Update core/src/connection/pool.rs
Co-Authored-By: Max Inden <mail@max-inden.de>
* Address some review feedback and fix doc links.
* Allow responses to be sent on the same connection.
* Remove unnecessary remainders of inject_replaced.
* Update swarm/src/behaviour.rs
Co-Authored-By: Pierre Krieger <pierre.krieger1708@gmail.com>
* Update swarm/src/lib.rs
Co-Authored-By: Pierre Krieger <pierre.krieger1708@gmail.com>
* Update core/src/connection/manager.rs
Co-Authored-By: Pierre Krieger <pierre.krieger1708@gmail.com>
* Update core/src/connection/manager.rs
Co-Authored-By: Pierre Krieger <pierre.krieger1708@gmail.com>
* Update core/src/connection/pool.rs
Co-Authored-By: Pierre Krieger <pierre.krieger1708@gmail.com>
* Incorporate more review feedback.
* Move module declaration below imports.
* Update core/src/connection/manager.rs
Co-Authored-By: Toralf Wittner <tw@dtex.org>
* Update core/src/connection/manager.rs
Co-Authored-By: Toralf Wittner <tw@dtex.org>
* Simplify as per review.
* Fix rustoc link.
* Add try_notify_handler and simplify.
* Relocate DialingConnection and DialingAttempt.
For better visibility constraints.
* Small cleanup.
* Small cleanup. More robust EstablishedConnectionIter.
* Clarify semantics of `DialingPeer::connect`.
* Don't call inject_disconnected on InvalidPeerId.
To preserve the previous behavior and ensure calls to
`inject_disconnected` are always paired with calls to
`inject_connected`.
* Provide public ConnectionId constructor.
Mainly needed for testing purposes, e.g. in substrate.
* Move the established connection limit check to the right place.
* Clean up connection error handling.
Separate connection errors into those occuring during
connection setup or upon rejecting a newly established
connection (the `PendingConnectionError`) and those
errors occurring on previously established connections,
i.e. for which a `ConnectionEstablished` event has
been emitted by the connection pool earlier.
* Revert change in log level and clarify an invariant.
* Remove inject_replaced entirely.
* Allow notifying all connection handlers.
Thereby simplify by introducing a new enum `NotifyHandler`,
used with a single constructor `NetworkBehaviourAction::NotifyHandler`.
* Finishing touches.
Small API simplifications and code deduplication.
Some more useful debug logging.
Co-authored-by: Max Inden <mail@max-inden.de>
Co-authored-by: Pierre Krieger <pierre.krieger1708@gmail.com>
Co-authored-by: Toralf Wittner <tw@dtex.org>
* Fix broken links in rustdoc
This fixes all of the rustdoc warnings on nightly.
* Check documentation intra-link
* Fix config
* Fix bad indent
* Make nightly explicit
* More links fixes
* Fix link broken after master merge
Co-authored-by: Demi Obenour <48690212+DemiMarie-parity@users.noreply.github.com>
* Simplify trait bounds requirements
* More work
* Moar
* Finish
* Fix final tests
* More simplification
* Use separate traits for Inbound/Outbound
* Update gossipsub and remove warnings
* Add documentation to swarm
* Remove BoxSubstream
* Fix tests not compiling
* Fix stack overflow
* Address concerns
* For some reason my IDE ignored libp2p-kad
- Pin `futures_codec` to version 0.3.3 as later versions require
at least bytes-0.5 which he have not upgraded to yet.
- Replace `futures::executor::block_on` with `async_std::task::block_on`
where `async-std` is already a dependency to work around an issue with
`park`/`unpark` behaviour.
- Use the published version of `quicksink`.
* Implement Debug for (ed25519|secp256k1)::(Keypair|SecretKey) (#1285)
* Fix possible arithmetic overflow in libp2p-kad. (#1291)
When the number of active queries exceeds the (internal)
JOBS_MAX_QUERIES limit, which is only supposed to bound
the number of concurrent queries relating to background
jobs, an arithmetic overflow occurs. This is fixed by
using saturating subtraction.
* protocols/plaintext: Add example on how to upgrade with PlainTextConfig1 (#1286)
* [mdns] - Support for long mDNS names (Bug #1232) (#1287)
* Dead code -- commenting out with a note referencing future implementation
* Adding "std" feature so that cargo can build in other directories (notably `misc/mdns`, so that I could run these tests)
* Permitting `PeerID` to be built from an `Identity` multihash
* The length limit for DNS labels is 63 characters, as per RFC1035
* Allocates the vector with capacity for the service name plus additional QNAME encoding bytes
* Added support for encoding/decoding peer IDs with an encoded length greater than 63 characters
* Removing "std" from ring features
Co-Authored-By: Pierre Krieger <pierre.krieger1708@gmail.com>
* Retaining MAX_INLINE_KEY_LENGTH with comment about future usage
* `segment_peer_id` consumes `peer_id` ... plus an early return for IDs that don't need to be segmented
* Fixing logic
* Bump most dependencies (#1268)
* Bump most dependencies
This actually builds 😊.
* Bump all dependencies
Includes the excellent work of @rschulman in #1265.
* Remove use of ed25519-dalek fork
* Monomorphize more dependencies
* Add compatibility hack for rand
Cargo allows a crate to depend on multiple versions of another, but
`cargo-web` panics in that situation. Use a wrapper crate to work
around the panic.
* Use @tomaka’s idea for using a newer `rand`
instead of my own ugly hack.
* Switch to Parity master
as its dependency-bumping PR has been merged.
* Update some depenendencies again
* Remove unwraps and `#[allow(deprecated)]`.
* Remove spurious changes to dependencies
Bumping minor or patch versions is not needed, and increases likelyhood
of merge conflicts.
* Remove some redundant Cargo.toml changes
* Replace a retry loop with an expect
`ed25519::SecretKey::from_bytes` will never fail for 32-byte inputs.
* Revert changes that don’t belong in this PR
* Remove using void to bypass ICE (#1295)
* Publish 0.13.0 (#1294)
* Configurable multistream-select protocol. Add V1Lazy variant. (#1245)
Make the multistream-select protocol (version) configurable
on transport upgrades as well as for individual substreams.
Add a "lazy" variant of multistream-select 1.0 that delays
sending of negotiation protocol frames as much as possible
but is only safe to use under additional assumptions that
go beyond what is required by the multistream-select v1
specification.
* Improve the code readability of the chat example (#1253)
* Add bridged chats (#1252)
* Try fix CI (#1261)
* Print Rust version on CI
* Don't print where not appropriate
* Change caching strategy
* Remove win32 build
* Remove win32 from list
* Update libsecp256k1 dep to 0.3.0 (#1258)
* Update libsecp256k1 dep to 0.3.0
* Sign now cannot fail
* Upgrade url and percent-encoding deps to 2.1.0 (#1267)
* Upgrade percent-encoding dep to 2.1.0
* Upgrade url dep to 2.1.0
* Fix more conflicts
* Revert CIPHERS set to null (#1273)
* Rework the transport upgrade API.
ALthough transport upgrades must follow a specific pattern
in order fot the resulting transport to be usable with a
`Network` or `Swarm`, that pattern is currently not well
reflected in the transport upgrade API. Rather, transport
upgrades are rather laborious and involve non-trivial code
duplication.
This commit introduces a `transport::upgrade::Builder` that is
obtained from `Transport::upgrade`. The `Builder` encodes the
previously implicit rules for transport upgrades:
1. Authentication upgrades must happen first.
2. Any number of upgrades may follow.
3. A multiplexer upgrade must happen last.
Since multiplexing is the last (regular) transport upgrade (because
that upgrade yields a `StreamMuxer` which is no longer a `AsyncRead`
/ `AsyncWrite` resource, which the upgrade process is based on),
the upgrade starts with `Transport::upgrade` and ends with
`Builder::multiplex`, which drops back down to the `Transport`,
providing a fluent API.
Authentication and multiplexer upgrades must furthermore adhere
to a minimal contract w.r.t their outputs:
1. An authentication upgrade is given an (async) I/O resource `C`
and must produce a pair `(I, D)` where `I: ConnectionInfo` and
`D` is a new (async) I/O resource `D`.
2. A multiplexer upgrade is given an (async) I/O resource `C`
and must produce a `M: StreamMuxer`.
To that end, two changes to the `secio` and `noise` protocols have been
made:
1. The `secio` upgrade now outputs a pair of `(PeerId, SecioOutput)`.
The former implements `ConnectionInfo` and the latter `AsyncRead` /
`AsyncWrite`, fulfilling the `Builder` contract.
2. A new `NoiseAuthenticated` upgrade has been added that wraps around
any noise upgrade (i.e. `NoiseConfig`) and has an output of
`(PeerId, NoiseOutput)`, i.e. it checks if the `RemoteIdentity` from
the handshake output is an `IdentityKey`, failing if that is not the
case. This is the standard upgrade procedure one wants for integrating
noise with libp2p-core/swarm.
* Cleanup
* Add a new integration test.
* Add missing license.
* muxing: adds an error type to streammuxer
* Update examples/chat.rs
Co-Authored-By: montekki <fedor.sakharov@gmail.com>
* make the trait error type bound to io error
This is now a very simple option serving multiple purposes:
* It allows for stable (integration) tests involving a Swarm, which
are otherwise subject to race conditions due to the connection being
allowed to terminate at any time with `KeepAlive::No`
(which remains the default).
* It makes for a more entertaining ping example which continuously
sends pings.
* Maybe someone wants to use the ping protocol for application-layer
connection keep-alive after all.
* Bump to 0.7.0
* Update CHANGELOG.md
Co-Authored-By: tomaka <pierre.krieger1708@gmail.com>
* Update for #1078
* New version of multihash and multiaddr as well
* Fix connection & handler shutdown when using `KeepAlive::Now`.
Delay::new(Instant::now()) is never immediately ready, resulting in
`KeepAlive::Now` to have no effect, since the delay is re-created on
every execution of `poll()` in the `NodeHandlerWrapper`. It can also
send the node handler into a busy-loop, since every newly
created Delay will trigger a task wakeup, which creates a new Delay
with Instant::now(), and so forth.
The use of `Delay::new(Instant::now())` for "immediate" connection shutdown
is therefore removed here entirely. An important assumption is thereby
that as long as the node handler non-empty `negotiating_in` and `negotiating_out`,
the handler is not dependent on such a Delay for task wakeup.
* Correction to the libp2p-ping connection timeout.
The current connection timeout is always short of one `interval`,
because the "countdown" begins with the last received or sent pong
(depending on the policy). In effect, the current default config has
a connection timeout of 5 seconds (20 - 15) from the point when a ping is sent.
Instead, the "countdown" of the connection timeout should always begin
with the next scheduled ping. That also makes all configurations valid,
avoiding pitfalls.
The important properties of the ping handler are now checked to hold for all
configurations, in particular:
* The next ping must be scheduled no earlier than the ping interval
and no later than the connection timeout.
* The "countdown" for the connection timeout starts on the next ping,
i.e. the full connection timeout remains at the instant when the
next ping is sent.
* Do not keep connections alive.
The ping protocol is not supposed to keep otherwise idle connections
alive, only to add an additional condition for terminating them in
the form of a configurable number of consecutive failed ping requests.
In this context, the `PingPolicy` does not seem useful any longer.
* libp2p-ping improvements.
* re #950: Removes use of the `OneShotHandler`, but still sending each
ping over a new substream, as seems to be intentional since #828.
* re #842: Adds an integration test that exercises the ping behaviour through
a Swarm, requiring the RTT to be below a threshold. This requires disabling
Nagle's algorithm as it can interact badly with delayed ACKs (and has been
observed to do so in the context of the new ping example and integration test).
* re #864: Control of the inbound and outbound (sub)stream protocol upgrade
timeouts has been moved from the `NodeHandlerWrapperBuilder` to the
`ProtocolsHandler`. That may also alleviate the need for a custom timeout
on an `OutboundSubstreamRequest` as a `ProtocolsHandler` is now free to
adjust these timeouts over time.
Other changes:
* A new ping example.
* Documentation improvements.
* More documentation improvements.
* Add PingPolicy and ensure no event is dropped.
* Remove inbound_timeout/outbound_timeout.
As per review comment, the inbound timeout is now configured
as part of the `listen_protocol` and the outbound timeout as
part of the `OutboundSubstreamRequest`.
* Simplify and generalise.
Generalise `ListenProtocol` to `SubstreamProtocol`, reusing it in
the context of `ProtocolsHandlerEvent::OutboundSubstreamRequest`.
* Doc comments for SubstreamProtocol.
* Adapt to changes in master.
* Relax upper bound for ping integration test rtt.
For "slow" CI build machines?
