* 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>
* 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
* Remove tokio-codec dependency from multistream-select.
In preparation for the eventual switch from tokio to std futures.
Includes some initial refactoring in preparation for further work
in the context of https://github.com/libp2p/rust-libp2p/issues/659.
* Reduce default buffer sizes.
* Allow more than one frame to be buffered for sending.
* Doc tweaks.
* Remove superfluous (duplicated) Message types.
* Reduce roundtrips in multistream-select negotiation.
1. Enable 0-RTT: If the dialer only supports a single protocol, it can send
protocol data (e.g. the actual application request) together with
the multistream-select header and protocol proposal. Similarly,
if the listener supports a proposed protocol, it can send protocol
data (e.g. the actual application response) together with the
multistream-select header and protocol confirmation.
2. In general, the dialer "settles on" an expected protocol as soon
as it runs out of alternatives. Furthermore, both dialer and listener
do not immediately flush the final protocol confirmation, allowing it
to be sent together with application protocol data. Attempts to read
from the negotiated I/O stream implicitly flushes any pending data.
3. A clean / graceful shutdown of an I/O stream always completes protocol
negotiation.
The publich API of multistream-select changed slightly, requiring both
AsyncRead and AsyncWrite bounds for async reading and writing due to
the implicit buffering and "lazy" negotiation. The error types have
also been changed, but they were not previously fully exported.
Includes some general refactoring with simplifications and some more tests,
e.g. there was an edge case relating to a possible ambiguity when parsing
multistream-select protocol messages.
* Further missing commentary.
* Remove unused test dependency.
* Adjust commentary.
* Cleanup NegotiatedComplete::poll()
* Fix deflate protocol tests.
* Stabilise network_simult test.
The test implicitly relied on "slow" connection establishment
in order to have a sufficient probability of passing.
With the removal of roundtrips in multistream-select, it is now
more likely that within the up to 50ms duration between swarm1
and swarm2 dialing, the connection is already established, causing
the expectation of step == 1 to fail when receiving a Connected event,
since the step may then still be 0.
This commit aims to avoid these spurious errors by detecting runs
during which a connection is established "too quickly", repeating
the test run.
It still seems theoretically possible that, if connections are always
established "too quickly", the test runs forever. However, given that
the delta between swarm1 and swarm2 dialing is 0-50ms and that the
TCP transport is used, that seems probabilistically unlikely.
Nevertheless, the purpose of the artificial dialing delay between
swarm1 and swarm2 should be re-evaluated and possibly at least
the maximum delay further reduced.
* Complete negotiation between upgrades in libp2p-core.
While multistream-select, as a standalone library and providing
an API at the granularity of a single negotiation, supports
lazy negotiation (and in particular 0-RTT negotiation), in the
context of libp2p-core where any number of negotiations are
composed generically within the concept of composable "upgrades",
it is necessary to wait for protocol negotiation between upgrades
to complete.
* Clarify docs. Simplify listener upgrades.
Since reading from a Negotiated I/O stream implicitly flushes any pending
negotiation data, there is no pitfall involved in not waiting for completion.
* Somewhat complete the implementation of Kademlia records.
This commit relates to [libp2p-146] and [libp2p-1089].
* All records expire (by default, configurable).
* Provider records are also stored in the RecordStore, and the RecordStore
API extended.
* Background jobs for periodic (re-)replication and (re-)publication
of records. Regular (value-)records are subject to re-replication and
re-publication as per standard Kademlia. Provider records are only
subject to re-publication.
* For standard Kademlia value lookups (quorum = 1), the record is cached
at the closest peer to the key that did not return the value, as per
standard Kademlia.
* Expiration times of regular (value-)records is computed exponentially
inversely proportional to the number of nodes between the local node
and the closest node known to the key (beyond the k closest), as per
standard Kademlia.
The protobuf messages are extended with two fields: `ttl` and `publisher`
in order to implement the different semantics of re-replication (by any
of the k closest peers to the key, not affecting expiry) and re-publication
(by the original publisher, resetting the expiry). This is not done yet in
other libp2p Kademlia implementations, see e.g. [libp2p-go-323]. The new protobuf fields
have been given somewhat unique identifiers to prevent future collision.
Similarly, periodic re-publication of provider records does not seem to
be done yet in other implementations, see e.g. [libp2p-js-98].
[libp2p-146]: https://github.com/libp2p/rust-libp2p/issues/146
[libp2p-1089]: https://github.com/libp2p/rust-libp2p/issues/1089
[libp2p-go-323]: https://github.com/libp2p/go-libp2p-kad-dht/issues/323
[libp2p-js-98]: https://github.com/libp2p/js-libp2p-kad-dht/issues/98
* Tweak kad-ipfs example.
* Add missing files.
* Ensure new delays are polled immediately.
To ensure task notification, since `NotReady` is returned right after.
* Fix ipfs-kad example and use wasm_timer.
* Small cleanup.
* Incorporate some feedback.
* Adjustments after rebase.
* Distinguish events further.
In order for a user to easily distinguish the result of e.g.
a `put_record` operation from the result of a later republication,
different event constructors are used. Furthermore, for now,
re-replication and "caching" of records (at the closest peer to
the key that did not return a value during a successful lookup)
do not yield events for now as they are less interesting.
* Speed up tests for CI.
* Small refinements and more documentation.
* Guard a node against overriding records for which it considers
itself to be the publisher.
* Document the jobs module more extensively.
* More inline docs around removal of "unreachable" addresses.
* Remove wildcard re-exports.
* Use NonZeroUsize for the constants.
* Re-add method lost on merge.
* Add missing 'pub'.
* Further increase the timeout in the ipfs-kad example.
* Readd log dependency to libp2p-kad.
* Simplify RecordStore API slightly.
* Some more commentary.
* Change Addresses::remove to return Result<(),()>.
Change the semantics of `Addresses::remove` so that the error case
is unambiguous, instead of the success case. Use the `Result` for
clearer semantics to that effect.
* Add some documentation to .
* Address some TODOs, refactor queries and public API.
The following left-over issues are addressed:
* The key for FIND_NODE requests is generalised to any Multihash,
instead of just peer IDs.
* All queries get a (configurable) timeout.
* Finishing queries as soon as enough results have been received is simplified
to avoid code duplication.
* No more panics in provider-API-related code paths. The provider API is
however still untested and (I think) still incomplete (e.g. expiration
of provider records).
* Numerous smaller TODOs encountered in the code.
The following public API changes / additions are made:
* Introduce a `KademliaConfig` with new configuration options for
the replication factor and query timeouts.
* Rename `find_node` to `get_closest_peers`.
* Rename `get_value` to `get_record` and `put_value` to `put_record`,
introducing a `Quorum` parameter for both functions, replacing the
existing `num_results` parameter with clearer semantics.
* Rename `add_providing` to `start_providing` and `remove_providing`
to `stop_providing`.
* Add a `bootstrap` function that implements a (almost) standard
Kademlia bootstrapping procedure.
* Rename `KademliaOut` to `KademliaEvent` with an updated list of
constructors (some renaming). All events that report query results
now report a `Result` to uniformly permit reporting of errors.
The following refactorings are made:
* Introduce some constants.
* Consolidate `query.rs` and `write.rs` behind a common query interface
to reduce duplication and facilitate better code reuse, introducing
the notion of a query peer iterator. `query/peers/closest.rs`
contains the code that was formerly in `query.rs`. `query/peers/fixed.rs` contains
a modified variant of `write.rs` (which is removed). The new `query.rs`
provides an interface for working with a collection of queries, taking
over some code from `behaviour.rs`.
* Reduce code duplication in tests and use the current_thread runtime for
polling swarms to avoid spurious errors in the test output due to aborted
connections when a test finishes prematurely (e.g. because a quorum of
results has been collected).
* Some additions / improvements to the existing tests.
* Fix test.
* Fix rebase.
* Tweak kad-ipfs example.
* Incorporate some feedback.
* Provide easy access and conversion to keys in error results.
* initial implementation of the records
* move to multihash keys
* correctly process query results
* comments and formatting
* correctly return closer_peers in query
* checking wrong peer id in test
* Apply suggestions from code review
Co-Authored-By: Roman Borschel <romanb@users.noreply.github.com>
* Fix changes from suggestions
* Send responses to PUT_VALUE requests
* Shortcut in get_value
* Update protocols/kad/src/behaviour.rs
Co-Authored-By: Roman Borschel <romanb@users.noreply.github.com>
* Revert "Update protocols/kad/src/behaviour.rs"
This reverts commit 579ce742a7f4c94587f1e1f0866d2a3a37418efb.
* Remove duplicate insertion
* Adds a record to a PUT_VALUE response
* Fix a racy put_value test
* Store value ourselves only if we are in K closest
* Abstract over storage
* Revert "Abstract over storage": bad take
This reverts commit eaebf5b6d915712eaf3b05929577fdf697f204d8.
* Abstract over records storage using hashmap as default
* Constructor for custom records
* New Record type and its traits
* Fix outdated storage name
* Fixes returning an event
* Change FindNodeReq key type to Multihash
* WriteState for a second stage of a PUT_VALUE request
* GET_VALUE should not have a record
* Refactor a match arm
* Add successes and failures counters to PutValueRes
* If value is found no need to return closer peers
* Remove a custo storage from tests
* Rename a test to get_value_not_found
* Adds a TODO to change FindNode request key to Multihash
Co-Authored-By: Roman Borschel <romanb@users.noreply.github.com>
* Move MemoryRecordStorage to record.rs
* Return a Cow-ed Record from get
* Fix incorrect GET_VALUE parsing
* Various fixes with review
* Fixes get_value_not_found
* Fix peerids names in test
* another fix
* PutValue correctly distributes values
* Simplify the test
* Check that results are actually the closest
* Reverts changes to tests
* Fix the test topology and checking the results
* Run put_value test ten times
* Adds a get_value test
* Apply suggestions from code review
Co-Authored-By: Roman Borschel <romanb@users.noreply.github.com>
* Make Record fields public
* Moves WriteState to write.rs
* A couple of minor fixes
* Another few fixes of review
* Simplify the put_value test
* Dont synchronously return an error from put_value
* Formatting fixes and comments
* Collect a bunch of results
* Take exactly as much elements as neede
* Check if the peer is still connected
* Adds a multiple GetValueResults results number test
* Unnecessary mut iterators in put_value
* Ask for num_results in get_value
* Dont allocate twice in get_value
* Dont count same errored peer multiple times
* Apply suggestions from code review
Co-Authored-By: Roman Borschel <romanb@users.noreply.github.com>
* Fix another review
* Apply suggestions from code review
Co-Authored-By: Pierre Krieger <pierre.krieger1708@gmail.com>
* Bring back FromIterator and improve a panic message
* Update protocols/kad/src/behaviour.rs
Co-Authored-By: Pierre Krieger <pierre.krieger1708@gmail.com>
* Fix self-dialing in Kademlia.
Addresses https://github.com/libp2p/rust-libp2p/issues/341 which is the cause
for one of the observations made in https://github.com/libp2p/rust-libp2p/issues/1053.
However, the latter is not assumed to be fully addressed by these changes and
needs further investigation.
Currently, whenever a search for a key yields a response containing the initiating
peer as one of the closest peers known to the remote, the local node
would attempt to dial itself. That attempt is ignored by the Swarm, but
the Kademlia behaviour now believes it still has a query ongoing which is
always doomed to time out. That timeout delays successful completion of the query.
Hence, any query where a remote responds with the ID of the local node takes at
least as long as the `rpc_timeout` to complete, which possibly affects almost
all queries in smaller clusters where every node knows about every other.
This problem is fixed here by ensuring that Kademlia never tries to dial the local node.
Furthermore, `Discovered` events are no longer emitted for the local node
and it is not inserted into the `untrusted_addresses` from discovery, as described
in #341.
This commit also includes a change to the condition for freezing / terminating
a Kademlia query upon receiving a response. Specifically, the condition is
tightened such that it only applies if in addition to `parallelism`
consecutive responses that failed to yield a peer closer to the target, the
last response must also either not have reported any new peer or the
number of collected peers has already reached the number of desired results.
In effect, a Kademlia query now tries harder to actually return `k`
closest peers.
Tests have been refactored and expanded.
* Add another comment.
* 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?
Update the protocols and transport subdirectories to the 2018 edition.
NB: The websocket transport cannot be moved to 2018 edition due to
websocket-rs's use of the keyword async as the name of a module.
* Rework Kademlia for the new design
* Minor work on protocol.rs
* More work
* Remove QueryTarget::FindValue
* Finish work on query
* Query timeout test
* Work on topology
* More work
* Update protocols/kad/src/topology.rs
Co-Authored-By: tomaka <pierre.krieger1708@gmail.com>
* Fix trailing whitespaces
* Use if let
