Skip to content

improve network resilience #286

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
orlandohohmeier merged 3 commits into from
Jan 5, 2026
Merged

improve network resilience #286

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
7a2d35a
fix: adjust request timeout
orlandohohmeier Jan 3, 2026
3eba5cb
fix: increase lease and offer timeouts
orlandohohmeier Jan 3, 2026
03e4b61
chore(network-sim) simulate RTT spikes and jitter
orlandohohmeier Jan 3, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion crates/data/src/network.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -87,7 +87,7 @@ impl Network {
let (action_sender, action_receiver) = mpsc::channel(64);
let meter = metrics::global::meter();
let request_timeout =
(Duration::from_millis(network_config.rtt_ms()) * 10).max(Duration::from_secs(10));
(Duration::from_millis(network_config.rtt_ms()) * 100).min(Duration::from_secs(30));

let swarm = SwarmBuilder::with_existing_identity(cert_chain, private_key, ca_certs, crls)
.with_tokio()
Expand Down
2 changes: 1 addition & 1 deletion crates/scheduler/src/network.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -113,7 +113,7 @@ impl Network {
let (action_sender, action_receiver) = mpsc::channel(512);
let meter = metrics::global::meter();
let request_timeout =
(Duration::from_millis(network_config.rtt_ms()) * 10).max(Duration::from_secs(10));
(Duration::from_millis(network_config.rtt_ms()) * 100).min(Duration::from_secs(30));

// Build libp2p Swarm using the derived identity and mTLS config
let swarm = SwarmBuilder::with_existing_identity(cert_chain, private_key, ca_certs, crls)
Expand Down
4 changes: 2 additions & 2 deletions crates/worker/src/arbiter.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,9 +25,9 @@ const WORKER_TOPIC: &str = "hypha/worker";
// This allows proper handling of multiple schedulers by batching advertisements
const WINDOW_LIMIT: usize = 100;
const WINDOW_WAIT: std::time::Duration = std::time::Duration::from_millis(200);
const OFFER_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(5);
const OFFER_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
const PRUNE_INTERVAL: std::time::Duration = std::time::Duration::from_millis(250);
const LEASE_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(60);
const LEASE_TIMEOUT: std::time::Duration = std::time::Duration::from_mins(3);

#[derive(Debug, Error)]
#[error("lease error")]
Expand Down
2 changes: 1 addition & 1 deletion crates/worker/src/network.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -107,7 +107,7 @@ impl Network {
let (action_sender, action_receiver) = mpsc::channel(512);
let meter = metrics::global::meter();
let request_timeout =
(Duration::from_millis(network_config.rtt_ms()) * 10).max(Duration::from_secs(10));
(Duration::from_millis(network_config.rtt_ms()) * 100).min(Duration::from_secs(30));

let swarm = SwarmBuilder::with_existing_identity(cert_chain, private_key, ca_certs, crls)
.with_tokio()
Expand Down
Loading