* Store addresses of provider records.
So far, provider records are stored without their
addresses and the addresses of provider records are
obtained from the routing table on demand. This has
two shortcomings:
1. We can only return provider records whose provider
peers happen to currently be in the local routing table.
2. The local node never returns itself as a provider for
a key, even if it is indeed a provider.
These issues are addressed here by storing the addresses
together with the provider records, falling back to
addresses from the routing table only for backward-compatibility
with existing implementations of `RecordStore` using persistent
storage.
Resolves https://github.com/libp2p/rust-libp2p/issues/1526.
* Update protocols/kad/src/behaviour.rs
Co-authored-by: Max Inden <mail@max-inden.de>
* Remove negligible use of with_capacity.
* Update changelog.
Co-authored-by: Max Inden <mail@max-inden.de>
With 826f513 a `StreamMuxer` can notify that the address of a remote
peer changed. This is needed to support the transport protocol QUIC as
remotes can change their IP addresses within the lifetime of a single
connection.
This commit implements the `NetworkBehaviour::inject_address_change`
handler to update the Kademlia routing table accordingly.
* Emit events for active connection close and fix `disconnect()`.
The `Network` does currently not emit events for actively
closed connections, e.g. via `EstablishedConnection::close`
or `ConnectedPeer::disconnect()`. As a result, when actively
closing connections, there will be `ConnectionEstablished`
events emitted without eventually a matching `ConnectionClosed`
event. This seems undesirable and has the consequence that
the `Swarm::ban_peer_id` feature in `libp2p-swarm` does not
result in appropriate calls to `NetworkBehaviour::inject_connection_closed`
and `NetworkBehaviour::inject_disconnected`. Furthermore,
the `disconnect()` functionality in `libp2p-core` is currently
broken as it leaves the `Pool` in an inconsistent state.
This commit does the following:
1. When connection background tasks are dropped
(i.e. removed from the `Manager`), they
always terminate immediately, without attempting
an orderly close of the connection.
2. An orderly close is sent to the background task
of a connection as a regular command. The
background task emits a `Closed` event
before terminating.
3. `Pool::disconnect()` removes all connection
tasks for the affected peer from the `Manager`,
i.e. without an orderly close, thereby also
fixing the discovered state inconsistency
due to not removing the corresponding entries
in the `Pool` itself after removing them from
the `Manager`.
4. A new test is added to `libp2p-swarm` that
exercises the ban/unban functionality and
places assertions on the number and order
of calls to the `NetworkBehaviour`. In that
context some new testing utilities have
been added to `libp2p-swarm`.
This addresses https://github.com/libp2p/rust-libp2p/issues/1584.
* Update swarm/src/lib.rs
Co-authored-by: Toralf Wittner <tw@dtex.org>
* Incorporate some review feedback.
* Adapt to changes in master.
* More verbose panic messages.
* Simplify
There is no need for a `StartClose` future.
* Fix doc links.
* Further small cleanup.
* Update CHANGELOGs and versions.
Co-authored-by: Toralf Wittner <tw@dtex.org>
* More control & insight for k-buckets.
1) More control: It is now possible to disable automatic
insertions of peers into the routing table via a new
`KademliaBucketInserts` configuration option. The
default is `OnConnected`, but it can be set to `Manual`,
in which case `add_address` must be called explicitly.
In order to communicate all situations in which a user
of `Kademlia` may want to manually update the routing
table, two new events are introduced:
* `KademliaEvent::RoutablePeer`: When a connection to
a peer with a known listen address is established
which may be added to the routing table. This is
also emitted when automatic inserts are allowed but
the corresponding k-bucket is full.
* `KademliaEvent::PendingRoutablePeer`: When a connection
to a peer with a known listen address is established
which is pending insertion into the routing table
(but may not make it). This is only emitted when
`OnConnected` (i.e. automatic inserts) are used.
These complement the existing `UnroutablePeer` and
`RoutingUpdated` events. It is now also possible to
explicitly remove peers and addresses from the
routing table.
2) More insight: `Kademlia::kbuckets` now gives an
iterator over `KBucketRef`s and `Kademlia::bucket`
a particular `KBucketRef`. A `KBucketRef` in turn
allows iteration over its entries. In this way,
the full contents of the routing table can be
inspected, e.g. in order to decide which peer(s)
to remove.
* Update protocols/kad/src/behaviour.rs
* Update protocols/kad/src/behaviour.rs
Co-authored-by: Max Inden <mail@max-inden.de>
* Update CHANGELOG.
Co-authored-by: Max Inden <mail@max-inden.de>
- Update `libp2p-kad` CHANGELOG and increment version to 0.20.1.
- Update `libp2p` version to 0.20.1.
- Fix some linter warning in `libp2p-gossipsub` and increment
version to 0.19.3 and update CHANGELOG.
The extension paper S-Kademlia includes a proposal for lookups over
disjoint paths. Within vanilla Kademlia, queries keep track of the
closest nodes in a single bucket. Any adversary along the path can thus
influence all future paths, in case they can come up with the
next-closest (not overall closest) hops. S-Kademlia tries to solve the
attack above by querying over disjoint paths using multiple buckets.
To adjust the libp2p Kademlia implementation accordingly this change-set
introduces an additional peers iterator: `ClosestDisjointPeersIter`.
This new iterator wraps around a set of `ClosestPeersIter`
`ClosestDisjointPeersIter` enforces that each of the `ClosestPeersIter`
explore disjoint paths by having each peer instantly return that was
queried by a different iterator before.
* [libp2p-kad] Provide more insight and control into Kademlia queries.
More insight: The API allows iterating over the active queries and
inspecting their state and execution statistics.
More control: The API allows aborting queries prematurely
at any time.
To that end, API operations that initiate new queries return the query ID
and multi-phase queries such as `put_record` retain the query ID across all
phases, each phase being executed by a new (internal) query.
* Cleanup
* Cleanup
* Update examples and re-exports.
* Incorporate review feedback.
* Update CHANGELOG
* Update CHANGELOG
Co-authored-by: Max Inden <mail@max-inden.de>
`FixedPeersIter` requires the initial set of peers to be passed as
`PeerId`s and not as `Key<PeerId>`s. This commit removes the unnecessary
conversion.
Instead of creating unconstrained random number generators in quickcheck
tests to generate test data, have quickcheck provide a `Seed` to seed
those random number generators and thus make the test execution
deterministic / reproducible.
Make sure to decrease `num_waiting` when being notified of a peer
failure to allow an additional peer to be queried.
Given that `FixedPeersIter` is initialized with `replication_factor` by
`QueryPool` this bug will not surface today.
* protocols/kad/query/peers/closest: Consider K_VALUE nodes at init
By considering `K_VALUE` at `ClosestPeersIter` initialization, the initial peer
set length is independent of `num_results` and thus of the `replication_factor`.
* protocols/kad/src/behaviour/test: Enable building single nodes
Introduces the `build_node` function to build a single not connected
node. Along the way replace the notion of a `port_base` with returning
the actual `Multiaddr` of the node.
* protocols/kad/behaviour/test: Fix bootstrap test initialization
When looking for the closest node to a key, Kademlia considers
ALPHA_VALUE nodes to query at initialization. If `num_groups` is larger
than ALPHA_VALUE the remaining locally known nodes will not be
considered. Given that no other node is aware of them other than node 1,
they would be lost entirely. To prevent the above restrict `num_groups`
to be equal or smaller than ALPHA_VALUE.
* protocols/kad/behaviour/test: Fix put_record and get_provider
In the past, when trying to find the closest nodes to a key, Kademlia
would consider `num_result` amount of nodes to query out of all the
nodes it is aware of.
Both the `put_record` and the `get_provider` tests initialized their
swarms in the same way. The tests took the replication factor to use as
an input. The number of results to get was equal to the replication
factor. The amount of swarms to start was twice the replication factor.
Nodes would be grouped in two groups a replication factor nodes. The
first node would be aware of all of the nodes in the first group. The
last node of the first group would be aware of all the nodes in the
second group.
By coincidence (I assume) these numbers played together very well. At
initialization the first node would consider `num_results` amount of
peers (see first paragraph). It would then contact each of them. As the
first node is aware of the last node of the first group which in turn is
aware of all nodes in the second group, the first node would eventually
discover all nodes.
Recently the amount of nodes Kademlia considers at initialization when
looking for the nodes closest to a key was changed to only consider
ALPHA nodes.
With this in mind playing through the test setup above again would
result in (1) `replication_factor - ALPHA` nodes being entirely lost as
the first node would never consider them and (2) the first node probably
never contacting the last node out of the first group and thus not
discovering any nodes of the second group.
To keep the multi hop discovery in place while not basing ones test
setup on the lucky assumption of Kademlia considering replication factor
amount of nodes at initialization, this patch alters the two tests:
Build a fully connected set of nodes and one addition node (the first
node). Connect the first node to a single node of the fully connected
set (simulating a boot node). Continue as done previously.
Co-authored-by: Roman Borschel <romanb@users.noreply.github.com>
When not making progress for `parallelism` time a `ClosestPeersIter`
becomes `State::Stalled`. When stalled an iterator is allowed to make
more parallel requests up to `num_results`. If `num_results` is smaller
than `parallelism` make sure to still allow up to `parallelism` requests
in-flight.
Co-Authored-By: Roman Borschel <romanb@users.noreply.github.com>
A node receiving a `GetRecord` request first checks whether it has the
given record. If it does have the record it does not return closer
nodes.
A node that knows the record for the given key is likely within a
neighborhood of nodes that know the record as well. In addition the node
likely knows its neighboorhood well.
When querying for a key with a quorum of 1 the above behavior of only
returning the record but not any close peers is fine. Once one queries
with a higher quorum having a node respond with the record as well as
close nodes is likely going to speed up the query, given that the
returned peers probably know the record as well.
* [libp2p-swarm] Make the multiple connections per peer first-class.
This commit makes the notion of multiple connections per peer
first-class in the API of libp2p-swarm, introducing the new
callbacks `inject_connection_established` and
`inject_connection_closed`. The `endpoint` parameter from
`inject_connected` and `inject_disconnected` is removed,
since the first connection to open may not be the last
connection to close, i.e. it cannot be guaranteed,
as was previously the case, that the endpoints passed
to these callbacks match up.
* Have identify track all addresses.
So that identify requests can be answered with the correct
observed address of the connection on which the request
arrives.
* Cleanup
* Cleanup
* Improve the `Peer` state API.
* Remove connection ID from `SwarmEvent::Dialing`.
* Mark `DialPeerCondition` non-exhaustive.
* Re-encapsulate `NetworkConfig`.
To retain the possibility of not re-exposing all
network configuration choices, thereby providing
a more convenient API on the \`SwarmBuilder\`.
* Rework Swarm::dial API.
* Update CHANGELOG.
* Doc formatting tweaks.
Given that the order of `PeerId`s within the `GetProvidersOk.providers`
set is irrelevant but duplication is at best confusing this commit makes
use of a `HashSet` instead of a `Vec` to return unique `PeerId`s only.
* protocols/kad: Do not attempt to store expired record in record store
`Kademlia::record_received` calculates the expiration time of a record
before inserting it into the record store. Instead of inserting the
record into the record store in any case, with this patch the record is
only inserted if it is not expired. If the record is expired a
`KademliaHandlerIn::Reset` for the given (sub) stream is triggered.
This would serve as a tiny defense mechanism against an attacker trying
to fill a node's record store with expired records before the record
store's clean up procedure removes the records.
* protocols/kad: Send regular ack when record discarded due to expiration
With this commit the remote receives a
[`KademliaHandlerIn::PutRecordRes`] even in the case where the record is
discarded due to being expired. Given that the remote sent the local
node a [`KademliaHandlerEvent::PutRecord`] request, the remote perceives
the local node as one node among the k closest nodes to the target.
Returning a [`KademliaHandlerIn::Reset`] instead of an
[`KademliaHandlerIn::PutRecordRes`] to have the remote try another node
would only result in the remote node to contact an even more distant
node. In addition returning [`KademliaHandlerIn::PutRecordRes`] does not
reveal any internal information to a possibly malicious remote node.
* protocols/kad/src/behaviour: Use `now` and reword expiration comment
Co-authored-by: Roman Borschel <romanb@users.noreply.github.com>
* protocols/kad: Add test to reproduce right shift overflow panic
* protocols/kad: Fix right shift overflow panic in record_received
Within `Behaviour::record_received` the exponentially decreasing
expiration based on the distance to the target for a record is
calculated as following:
1. Calculate the amount of nodes between us and the record key beyond
the k replication constant as `n`.
2. Shift the configured record time-to-live `n` times to the right to
calculate an exponentially decreasing expiration.
The configured record time-to-live is a u64. If `n` is larger or equal
to 64 the right shift will lead to an overflow which panics in debug
mode.
This patch uses a checked right shift instead, defaulting to 0 (`now +
0`) for the expiration on overflow.
* protocols/kad: Put attribute below comment
* protocols/kad: Extract shifting logic and rework test
Extract right shift into isolated function and replace complex
regression test with small isolated one.
* protocols/kad/src/behaviour: Refactor exp_decr_expiration
Co-authored-by: Roman Borschel <romanb@users.noreply.github.com>
* 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>
The `QueryId` type should be exported as it is used in the
`NetworkBehaviour::ProtocolsHandler` type of `Kademlia`.
`Kademlia::protocol_name` is added for convenience.
* Replace some remaining `AsRef` constraints for DHT keys with `Borrow`.
* Add a bit of debug/trace logging.
* Tiny refactoring and a debug assertion for the `bucket` module.
* 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
