fluencelabs/rust-libp2p
1
0
Fork 0
mirror of https://github.com/fluencelabs/rust-libp2p synced 2025-06-18 04:21:22 +00:00
Code Issues Projects Releases Wiki Activity

refactor(swarm)!: don't share event buffer for established connections (#3188)

Browse Source 
Currently, we only have a single channel for all established connections. This requires us to construct the channel ahead of time, before we even have a connection. As it turns out, sharing this buffer across all connections actually has downsides. In particular, this means a single, very busy connection can starve others by filling up this buffer, forcing other connections to wait until they can emit an event.
This commit is contained in:
Thomas Eizinger
2023-01-20 09:49:11 +11:00
committed by GitHub
parent a34411c528
commit b5a3f81c3d
3 changed files with 45 additions and 37 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
swarm/src/lib.rs
View File

@ -1489,31 +1489,19 @@ where
self
}
/// Configures the number of extra events from the [`ConnectionHandler`] in
/// destination to the [`NetworkBehaviour`] that can be buffered before
/// the [`ConnectionHandler`] has to go to sleep.
/// Configures the size of the buffer for events sent by a [`ConnectionHandler`] to the
/// [`NetworkBehaviour`].
///
/// There exists a buffer of events received from [`ConnectionHandler`]s
/// that the [`NetworkBehaviour`] has yet to process. This buffer is
/// shared between all instances of [`ConnectionHandler`]. Each instance of
/// [`ConnectionHandler`] is guaranteed one slot in this buffer, meaning
/// that delivering an event for the first time is guaranteed to be
/// instantaneous. Any extra event delivery, however, must wait for that
/// first event to be delivered or for an "extra slot" to be available.
/// Each connection has its own buffer.
///
/// This option configures the number of such "extra slots" in this
/// shared buffer. These extra slots are assigned in a first-come,
/// first-served basis.
///
/// The ideal value depends on the executor used, the CPU speed, the
/// average number of connections, and the volume of events. If this value
/// is too low, then the [`ConnectionHandler`]s will be sleeping more often
/// The ideal value depends on the executor used, the CPU speed and the volume of events.
/// If this value is too low, then the [`ConnectionHandler`]s will be sleeping more often
/// than necessary. Increasing this value increases the overall memory
/// usage, and more importantly the latency between the moment when an
/// event is emitted and the moment when it is received by the
/// [`NetworkBehaviour`].
pub fn connection_event_buffer_size(mut self, n: usize) -> Self {
self.pool_config = self.pool_config.with_connection_event_buffer_size(n);
pub fn per_connection_event_buffer_size(mut self, n: usize) -> Self {
self.pool_config = self.pool_config.with_per_connection_event_buffer_size(n);
self
}