* Small addendum to #1072.
* Missed two review comments related to documentation.
* Avoid creating new `Delay`s when possible, i.e. when the deadline
did not change, since they're not exactly cheap and returning
`KeepAlive::Until(t)` with the same instant `t` over a prolonged
period of time is common.
* Even better.
* 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.
* 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.
* Trigger CI.
The functionality is available through `Multiaddr::replace`.
What we currently call "nat_traversal" is merley a replacement of an IP
address prefix in a `Multiaddr`, hence it can be done directly on
`Multiaddr` values instead of having to go through a `Transport`.
In addition this PR consolidates changes made to `Multiaddr` in
previous commits which resulted in lots of deprecations. It adds some
more (see below for the complete list of API changes) and removes all
deprecated functionality, requiring a minor version bump.
Here are the changes to `multiaddr` compared to the currently published
version:
1. Removed `into_bytes` (use `to_vec` instead).
2. Renamed `to_bytes` to `to_vec`.
3. Removed `from_bytes` (use the `TryFrom` impl instead).
4. Added `with_capacity`.
5. Added `len`.
6. Removed `as_slice` (use `AsRef` impl instead).
7. Removed `encapsulate` (use `push` or `with` instead).
8. Removed `decapsulate` (use `pop` instead).
9. Renamed `append` to `push`.
10. Added `with`.
11. Added `replace`.
12. Removed `ToMultiaddr` trait (use `TryFrom` instead).
* 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?
Wildcard IP addresses (e.g. 0.0.0.0) are used to listen on all host
interfaces. To report those addresses such that clients know about them
and can actually make use of them we use the `get_if_addrs` crate and
maintain a collection of addresses. We report the whole expansion at the
very beginning of the listener stream with `ListenerEvent::NewAddress`
events and add new addresses should they come to our attention.
What remains to be done is to potentially allow users to filter IP
addresses, for example the local loopback one, and to detect expired
addresses not only if a new address is discovered.
Replace the listener and address pair returned from `Transport::listen_on` with just a listener that produces `ListenerEvent` values which include upgrades as well as address changes.
* Documentation updates:
* libp2p: Update the top-level module documentation, already including
intra-rustdoc links, removing outdated documentation, updating examples and
polishing the text.
* libp2p-core: Update the transport documentation to clarify that a `Transport`
is really an abstraction only for connection-oriented transports.
* More links
* Fix typo.
* Address review comments.
* More doc tweaks.
* Mention the necessity of creating an identity keypair.
* Remove another mention of the removed Topology trait.
* Consolidate keypairs in core.
Introduce the concept of a node's identity keypair in libp2p-core,
instead of only the public key:
* New module: libp2p_core::identity with submodules for the currently
supported key types. An identity::Keypair and identity::PublicKey
support the creation and verification of signatures. The public key
supports encoding/decoding according to the libp2p specs.
* The secio protocol is simplified as a result of moving code to libp2p-core.
* The noise protocol is slightly simplified by consolidating ed25519
keypairs in libp2p-core and using x25519-dalek for DH. Furthermore,
Ed25519 to X25519 keypair conversion is now complete and tested.
Generalise over the DH keys in the noise protocol.
Generalise over the DH keys and thus DH parameter in handshake patterns
of the Noise protocol, such that it is easy to support other DH schemes
in the future, e.g. X448.
* Address new review comments.
* Add Ord implementation for KeepAlive
* Fix import path
* Implement PartialOrd for KeepAlive
* remove Ord implementation
* Reimplement Ord for KeepAlive
* Add equality cases to KeepAlive Ord implementation
