Previously we would increase a counter / gauge / histogram on each received identify information. These metrics are missleading, as e.g. they depend on the identify interval and don't represent the set of currently connected peers.
With this commit, identify information is tracked for the currently connected peers only. Instead of an increase on each received identify information, metrics represent the status quo (Gauge).
Example:
```
\# HELP libp2p_libp2p_identify_remote_protocols Number of connected nodes supporting a specific protocol, with "unrecognized" for each peer supporting one or more unrecognized protocols...
\# TYPE libp2p_libp2p_identify_remote_protocols gauge
libp2p_libp2p_identify_remote_protocols_total{protocol="/ipfs/id/push/1.0.0"} 1
libp2p_libp2p_identify_remote_protocols_total{protocol="/ipfs/id/1.0.0"} 1
libp2p_libp2p_identify_remote_protocols_total{protocol="/ipfs/ping/1.0.0"} 1
libp2p_libp2p_identify_remote_protocols_total{protocol="unrecognized"} 1
\# HELP libp2p_libp2p_identify_remote_listen_addresses Number of connected nodes advertising a specific listen address...
\# TYPE libp2p_libp2p_identify_remote_listen_addresses gauge
libp2p_libp2p_identify_remote_listen_addresses_total{listen_address="/ip4/tcp"} 1
libp2p_libp2p_identify_remote_listen_addresses_total{listen_address="/ip4/udp/quic"} 1
\# HELP libp2p_libp2p_identify_local_observed_addresses Number of connected nodes observing the local node at a specific address...
\# TYPE libp2p_libp2p_identify_local_observed_addresses gauge
libp2p_libp2p_identify_local_observed_addresses_total{observed_address="/ip4/tcp"} 1
```
Pull-Request: #3325.
This patch removes the 3 out of 4 deprecated public modules. I've left `store` for now because we made some mistakes in declaring that. The items within `store` still need to be publicly visible but I haven't yet figured out a good way of exporting / naming them. Thus, I've left that to a follow-up PR.
Related: #3647.
Pull-Request: #3896.
Users are encouraged to use `libp2p::connection_limit::Behaviour` which is a one-to-one replacement for this functionality but built as a `NetworkBehaviour`.
Related: #3647.
Pull-Request: #3885.
When an inbound stream upgrade fails, there isn't a whole lot we can do about that in the handler. In fact, for several errors, we wouldn't even know which specific handler to target, for example, `NegotiationFailed`. Similiarly, in case of an IO error during the upgrade, we don't know which handler the stream was eventually meant to be for.
Pull-Request: #3605.
Previously, a protocol could be any sequence of bytes as long as it started with `/`. Now, we directly parse a protocol as `String` which enforces it to be valid UTF8.
To notify users of this change, we delete the `ProtocolName` trait. The new requirement is that users need to provide a type that implements `AsRef<str>`.
We also add a `StreamProtocol` newtype in `libp2p-swarm` which provides an easy way for users to ensure their protocol strings are compliant. The newtype enforces that protocol strings start with `/`. `StreamProtocol` also implements `AsRef<str>`, meaning users can directly use it in their upgrades.
`multistream-select` by itself only changes marginally with this patch. The only thing we enforce in the type-system is that protocols must implement `AsRef<str>`.
Resolves: #2831.
Pull-Request: #3746.
Previously, we would specify the version and path of our workspace dependencies in each of our crates. This is error prone as https://github.com/libp2p/rust-libp2p/pull/3658#discussion_r1153278072 for example shows. Problems like these happened in the past too.
There is no need for us to ever depend on a earlier version than the most current one in our crates. It thus makes sense that we manage this version in a single place.
Cargo supports a feature called "workspace inheritance" which allows us to share a dependency declaration across a workspace and inherit it with `{ workspace = true }`.
We do this for all our workspace dependencies and for the MSRV.
Resolves#3787.
Pull-Request: #3715.
The `unreachable_pub` lint makes us aware of uses of `pub` that are not actually reachable from the crate root. This is considered good because it means reading a `pub` somewhere means it is actually public API. Some of our crates are quite large and keeping their entire API surface in your head is difficult.
We should strive for most items being `pub(crate)`. This lint helps us enforce that.
Pull-Request: #3735.
Currently, banning peers is a first-class feature of `Swarm`. With the new connection management capabilities of `NetworkBehaviour`, we can now implement allow and block lists as a separate module.
We introduce a new crate `libp2p-allow-block-list` and deprecate `Swarm::ban_peer_id` in favor of that.
Related #2824.
Pull-Request: #3590.
This patch deprecates the existing connection limits within `Swarm` and uses the new `NetworkBehaviour` APIs to implement it as a plugin instead.
Related #2824.
Pull-Request: #3386.
Mark constructors `Swarm::with_X_executor` as deprecated.
Move the deprecated functionality to `SwarmBuilder::with_X_executor`
Use `SwarmBuilder` throughout.
Resolves#3186.
Resolves#3107.
Pull-Request: #3588.
A large release with lots of changes I am looking forward to. Sorry for the long release cadence.
Anything folks would like to see included that is not yet in `master`? As usual I would like to only block on bug fixes.
Pull-Request: #3491.
Previously, a `ConnectionHandler` was immediately requested from the `NetworkBehaviour` as soon as a new dial was initiated or a new incoming connection accepted.
With this patch, we delay the creation of the handler until the connection is actually established and fully upgraded, i.e authenticated and multiplexed.
As a consequence, `NetworkBehaviour::new_handler` is now deprecated in favor of a new set of callbacks:
- `NetworkBehaviour::handle_pending_inbound_connection`
- `NetworkBehaviour::handle_pending_outbound_connection`
- `NetworkBehaviour::handle_established_inbound_connection`
- `NetworkBehaviour::handle_established_outbound_connection`
All callbacks are fallible, allowing the `NetworkBehaviour` to abort the connection either immediately or after it is fully established. All callbacks also receive a `ConnectionId` parameter which uniquely identifies the connection. For example, in case a `NetworkBehaviour` issues a dial via `NetworkBehaviourAction::Dial`, it can unambiguously detect this dial in these lifecycle callbacks via the `ConnectionId`.
Finally, `NetworkBehaviour::handle_pending_outbound_connection` also replaces `NetworkBehaviour::addresses_of_peer` by allowing the behaviour to return more addresses to be used for the dial.
Resolves#2824.
Pull-Request: #3254.
In case an error happens for an outgoing connection, `Pool` reports an `OutgoingConnectionError`. This one is mapped to a `DialError` and reported via `SwarmEvent::OutgoingConnectionError` and `FromSwarm::DialFailure`.
For incoming connections, we didn't quite do the same thing. For one, `SwarmEvent::IncomingConnectionError` directly contained a `PendingInboundConnectionError`. Two, `FromSwarm::ListenFailure` did not include an error at all.
With this patch, we now introduce a `ListenError` enum which we use in `SwarmEvent::IncomingConnectionError` and we pass a reference to it along in `FromSwarm::ListenFailure`.
Previously, inbound connections that happened to resolve to our own `PeerId` were reported as `WrongPeerId`. With this patch, we now report those in a dedicated `LocalPeerId` error.
Related: #3205.
Ever since we moved `Pool` into `libp2p-swarm`, we always use it with the same `Transport`: `Boxed`. It is thus unnecessary for us to be overly generic over what kind of `Transport` we are using. This allows us to remove a few type parameters from the implementation which overall simplifies things.
This is technically a breaking change because I am removing a type parameter from two exported type aliases:
- `PendingInboundConnectionError`
- `PendingOutboundConnectionError`
Those have always only be used with `std::io::Error` in our API but it is still a breaking change.
Previously, we applied a lifetime onto the entire `RecordStore` to workaround Rust not having GATs. With Rust 1.65.0 we now have GATs so we can remove this workaround.
Related https://github.com/libp2p/rust-libp2p/issues/3240. Without this change, we would have to specify HRTB in various places.
Currently the `libp2p_swarm_connections_establishment_duration` metric has the following buckets:
```
// exponential_buckets(1e-3, 2., 10)
[0.001, 0.002, 0.004, 0.008, 0.016, 0.032, 0.064, 0.128, 0.256, 0.512]
```
It is unlikely that a connection is established in 1ms, even within a datacenter. It is very likely that libp2p connection establishment takes longer than 512ms over the internet.
This commit proposes the following buckets:
```
// exponential_buckets(0.01, 1.5, 20)
[0.01, 0.015, 0.0225, 0.03375, 0.050625, 0.0759375, 0.11390625, 0.170859375, 0.2562890625,
0.38443359375, 0.576650390625, 0.8649755859375, 1.29746337890625, 1.946195068359375,
2.9192926025390626, 4.378938903808594, 6.568408355712891, 9.852612533569337, 14.778918800354004,
22.168378200531006]
```
- Buckets start at 10ms.
- Reasonably high resolution in the sub-second area.
- Largest bucket at 22s, e.g. for a relayed connection.
- Unfortunately rather obscure numbers.
We refactor our continuous integration workflow with the following goals in mind:
- Run as few jobs as possible
- Have the jobs finish as fast as possible
- Have the jobs redo as little work as possible
There are only so many jobs that GitHub Actions will run in parallel.
Thus, it makes sense to not create massive matrices but instead group
things together meaningfully.
The new `test` job will:
- Run once for each crate
- Ensure that the crate compiles on its specified MSRV
- Ensure that the tests pass
- Ensure that there are no semver violations
This is an improvement to before because we are running all of these
in parallel which speeds up execution and highlights more errors at
once. Previously, tests run later in the pipeline would not get run
at all until you make sure the "first" one passes.
We also previously did not verify the MSRV of each crate, making the
setting in the `Cargo.toml` rather pointless.
The new `cross` job supersedes the existing `wasm` job.
This is an improvement because we now also compile the crate for
windows and MacOS. Something that wasn't checked before.
We assume that checking MSRV and the tests under Linux is good enough.
Hence, this job only checks for compile-errors.
The new `feature_matrix` ensures we compile correctly with certain feature combinations.
`libp2p` exposes a fair few feature-flags. Some of the combinations
are worth checking independently. For the moment, this concerns only
the executor related transports together with the executor flags but
this list can easily be extended.
The new `clippy` job runs for `stable` and `beta` rust.
Clippy gets continuously extended with new lints. Up until now, we would only
learn about those as soon as a new version of Rust is released and CI would
run the new lints. This leads to unrelated failures in CI. Running clippy on with `beta`
Rust gives us a heads-up of 6 weeks before these lints land on stable.
Fixes#2951.
Previously, we would only track the metrics like the number of open connections. With this patch, we extend these metrics with a `protocols` label that contains a "protocol stack". A protocol stack is a multi-address with all variable parts removed. For example, `/ip4/127.0.0.1/tcp/1234` turns into `/ip4/tcp`.
Resolves https://github.com/libp2p/rust-libp2p/issues/2758.
Previously, the executor for connection tasks silently defaulted to a `futures::executor::ThreadPool`. This causes issues such as https://github.com/libp2p/rust-libp2p/issues/2230.
With this patch, we force the user to choose, which executor they want to run the connection tasks on which results in overall simpler API with less footguns.
Closes#3068.
Currently, our `NetworkBehaviour` derive macro depends on the `libp2p` crate to be in scope. This prevents standalone usage which forces us to depend on `libp2p` in all our tests where we want to derive a `NetworkBehaviour`.
This PR introduces a `prelude` option that - by default - points to `libp2p::swarm::derive_prelude`, a new module added to `libp2p_swarm`. With this config option, users of `libp2p_swarm` can now refer to the macro without depending on `libp2p`, breaking the circular dependency in our workspace. For consistency with the ecosystem, the macro is now also re-exported by `libp2p_swarm` instead of `libp2p` at the same position as the trait that it implements.
Lastly, we introduce an off-by-default `macros` feature flag that shrinks the dependency tree for users that don't need the derive macro.
Previously, the `DummyConnectionHandler` offered a "keep alive" functionality,
i.e. it allowed users to set the value of what is returned from
`ConnectionHandler::keep_alive`. This handler is primarily used in tests or
`NetworkBehaviour`s that don't open any connections (like mDNS). In all of these
cases, it is statically known whether we want to keep connections alive. As
such, this functionality is better represented by a static
`KeepAliveConnectionHandler` that always returns `KeepAlive::Yes` and a
`DummyConnectionHandler` that always returns `KeepAlive::No`.
To follow the naming conventions described in
https://github.com/libp2p/rust-libp2p/issues/2217, we introduce a top-level
`keep_alive` and `dummy` behaviour in `libp2p-swarm` that contains both the
`NetworkBehaviour` and `ConnectionHandler` implementation for either case.
