7 Commits

Author SHA1 Message Date
Roman Borschel
8337687b3a
Multiple connections per peer (#1440)
* 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>
2020-03-04 13:49:25 +01:00
Roman Borschel
b872bd9030
Temporary canonical multihash in peer ID. (#1449)
* Temporary canonical multihash in peer ID.

* Reduce code duplication.

* Remove unnecessary impls.

Co-authored-by: Pierre Krieger <pierre.krieger1708@gmail.com>
2020-02-13 10:36:14 +01:00
Pierre Krieger
fc4dec581e
Check documentation intra-link (#1432)
* 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>
2020-02-10 15:17:07 +01:00
Pierre Krieger
1eff4b9823
Simplify trait bounds on NetworkBehaviour (#1405)
* 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
2020-02-07 16:29:30 +01:00
Shotaro Yamada
b200728443
Fix copy-paste error in doc string (#1428)
Co-authored-by: Pierre Krieger <pierre.krieger1708@gmail.com>
2020-02-06 11:17:05 +01:00
Max Inden
2b7c015aa5
protocols/gossipsub: Do not close connection when inbound fails (#1424)
Instead of closing the connection on an error on the inbound substream
(both on `poll_next` as well as `poll_close`), one can set it to None
and depend on the remote to open an new one in case they have more data
to send.

Co-authored-by: Pierre Krieger <pierre.krieger1708@gmail.com>
2020-02-05 15:31:50 +01:00
Age Manning
37c7d73b11 Gossipsub Protocol (#898)
* Create gossipsub crate - Basic template, borrowed from floodsub

* Add a GossipsubConfig struct and set up basic structures in the Gossipsub struct

* Begin implementation of join. Adds get_random_peers helper function and adds tests

* Implements gossipsub leave()

* Update publishMany to incorporate gossipsub mesh and fanout logic

* Use the gossipsub mesh for determining peer subscription

* Remove subscribed_topics field from the Gossipsub struct

* Rename gossipsubconfig to ProtocolConfig

* Implement the gossipsub control messages into the Codec's Encode/Decode and modifies GossipsubRpc

* Modify GossipsubActions to enums for succinctness.

* Modify the memcache to store Gossipsub messages

* Implement control message handling.

* Update control message handling to handle multiple messages.

* Handle received gossipsub messages using pre-built handlers.

* Remove excess connected peer hashmap

* Add extra peer mapping and consistent topic naming.

* Implement heartbeat, emit_gossip and send_graft_prune.

* Group logic in forwarding messages. Add messages to memcache.

* Add heartbeat timer and move location of helper function.

* Add gossipsub the libp2p workspace, makes layer structs public

* Add logging to gossipsub

- Adds the log crate and implements logging macros
- Specifies versions for external crates

* Add example chat for debugging purposes

* Implement #868 for gossipsub.

* Add rust documentation to gossipsub crate.

- Adds basic documentation, overview and examples to the gossipsub
crate.

* Re-introduce the initial heartbeat time config.

This commit also adds the inject_connected test.

* Add subscribe tests.

- Modifies `handle_received_subscriptions` to take a reference of
subscriptions
- Adds `test_subscribe`
- Adds `test_handle_received_subscriptions`
- Adds tests for the filter in `get_random_peers`

* Add Bug fixes and further testing for gossipsub.

- Corrects the tuple use of topic_hashes
- Corrects JOIN logic around fanout and adding peers to the mesh
- Adds test_unsubscribe
- Adds test_join

* Rename GossipsubMessage::msg_id -> id

* Add bug fix for handling disconnected peers.

* Implements (partially) #889 for Gossipsub.

* handle_iwant event count tests

* handle_ihave event count tests

* Move layer.rs tests into separate file.

* Implement clippy suggestions for gossipsub.

* Modify control message tests for specific types.

* Implement builder pattern for GossipsubConfig.

As suggested by @twittner - The builder pattern for building
GossipsubConfig struct is implemented.

* Package version updates as suggested by @twittner.

* Correct line lengths in gossipsub.

* Correct braces in  found by @twittner.

* Implement @twittner's suggestions.

- Uses `HashSet` where applicable
- Update `FnvHashMap` to standard `HashMap`
- Uses `min` function in code simplification.

* Add NodeList struct to clarify topic_peers.

* Cleaner handling of messagelist

Co-Authored-By: AgeManning <Age@AgeManning.com>

* Cleaner handling of added peers.

Co-Authored-By: AgeManning <Age@AgeManning.com>

* handle_prune peer removed test

* basic grafting tests

* multiple topic grafting test

* Convert &vec to slice.

Co-Authored-By: AgeManning <Age@AgeManning.com>

* Convert to lazy insert.

Co-Authored-By: AgeManning <Age@AgeManning.com>

* Cleaner topic handling.

Co-Authored-By: AgeManning <Age@AgeManning.com>

* control pool piggybacking

using HashMap.drain() in control_pool_flush

going to squash this

* Add Debug derives to gossipsub and correct tests.

* changes from PR

squash this

all tests passing, but still some that need to be reconsidered

test reform

* Implements Arc for GossipsubRpc events

* Remove support for floodsub nodes

* Reconnected to disconnected peers, to mitigate timeout

* Use ReadOne WriteOne with configurable max gossip sizes

* Remove length delimination from RPC encoding

* Prevent peer duplication in mesh

* Allow oneshot handler's inactivity_timeout to be configurable

* Correct peer duplication in mesh bug

* Remove auto-reconnect to allow for user-level disconnects

* Single long-lived inbound/outbound streams to match go implementation

* Allow gossipsub topics to be optionally hashable

* Improves gossipsub stream handling

- Corrects the handler's keep alive.
- Correct the chat example.
- Instantly add peers to the mesh on subscription if the mesh is low.

* Allows message validation in gossipsub

* Replaces Cuckoofilter with LRUCache

The false positive rate was unacceptable for rejecting messages.

* Renames configuration parameter and corrects logic

* Removes peer from fanout on disconnection

* Add publish and fanout tests

* Apply @mxinden suggestions

* Resend message if outbound stream negotiated

- Downgrades log warnings

* Implement further reviewer suggestions

- Created associated functions to avoid unnecessary cloning
- Messages are rejected if their sequence numbers are not u64
- `GossipsbuConfigBuilder` has the same defaults as `GossipsubConfig`
- Miscellaneous typos

* Add MessageId type and remove unnecessary comments

* Add a return value to propagate_message function

* Adds user-customised gossipsub message ids

* Adds the message id to GossipsubEvent

* Implement Debug for GossipsubConfig

* protocols/gossipsub: Add basic smoke test

Implement a basic smoke test that:

1. Builds a fully connected graph of size N.

2. Subscribes each node to the same topic.

3. Publishes a single message.

4. Waits for all nodes to receive the above message.

N and the structure of the graph are reproducibly randomized via
Quickcheck.

* Corrections pointed out by @mxinden

* Add option to remove source id publishing

* protocols/gossipsub/tests/smoke: Remove unused variable

* Merge latest master

* protocols/gossipsub: Move to stable futures

* examples/gossipsub-chat.rs: Move to stable futures

* protocols/gossipsub/src/behaviour/tests: Update to stable futures

* protocols/gossipsub/tests: Update to stable futures

* protocols/gossipsub: Log substream errors

* protocols/gossipsub: Log outbound substream errors

* Remove rust-fmt formatting

* Shift to prost for protobuf compiling

* Use wasm_timer for wasm compatibility

Co-authored-by: Grant Wuerker <gwuerker@gmail.com>
Co-authored-by: Toralf Wittner <tw@dtex.org>
Co-authored-by: Pawan Dhananjay <pawandhananjay@gmail.com>
Co-authored-by: Max Inden <mail@max-inden.de>
Co-authored-by: Pierre Krieger <pierre.krieger1708@gmail.com>
2020-01-24 16:16:02 +01:00