When first request fails, try alternative peers in staggered parallel.

Author: deuszx

CLI.md

@@ -201,6 +201,9 @@ Client implementation and command-line tool for the Linera blockchain
 * `--alpha <ALPHA>` — Smoothing factor for Exponential Moving Averages (0 < alpha < 1). Higher values give more weight to recent observations. Typical values are between 0.01 and 0.5. A value of 0.1 means that 10% of the new observation is considered and 90% of the previous average is retained
 
   Default value: `0.1`
+* `--alternative-peers-retry-delay-ms <ALTERNATIVE_PEERS_RETRY_DELAY_MS>` — Delay in milliseconds between starting requests to different peers. This helps to stagger requests and avoid overwhelming the network
+
+  Default value: `75`
 * `--storage <STORAGE_CONFIG>` — Storage configuration for the blockchain history
 * `--storage-max-concurrent-queries <STORAGE_MAX_CONCURRENT_QUERIES>` — The maximal number of simultaneous queries to the database
 * `--storage-max-stream-queries <STORAGE_MAX_STREAM_QUERIES>` — The maximal number of simultaneous stream queries to the database

linera-client/src/client_options.rs

@@ -230,6 +230,15 @@ pub struct ClientContextOptions {
         env = "LINERA_REQUESTS_SCHEDULER_ALPHA"
     )]
     pub alpha: f64,
+
+    /// Delay in milliseconds between starting requests to different peers.
+    /// This helps to stagger requests and avoid overwhelming the network.
+    #[arg(
+        long,
+        default_value_t = linera_core::client::requests_scheduler::STAGGERED_DELAY_MS,
+        env = "LINERA_REQUESTS_SCHEDULER_ALTERNATIVE_PEERS_RETRY_DELAY_MS"
+    )]
+    pub alternative_peers_retry_delay_ms: u64,
 }
 
 impl ClientContextOptions {
@@ -273,6 +282,7 @@ impl ClientContextOptions {
             cache_max_size: self.cache_max_size,
             max_request_ttl_ms: self.max_request_ttl_ms,
             alpha: self.alpha,
+            retry_delay_ms: self.alternative_peers_retry_delay_ms,
         }
     }
 }

linera-core/src/client/requests_scheduler/in_flight_tracker.rs

@@ -173,6 +173,21 @@ impl<N: Clone> InFlightTracker<N> {
         let peers = entry.alternative_peers.read().await;
         Some(peers.clone())
     }
+
+    /// Removes a specific peer from the alternative peers list.
+    ///
+    /// # Arguments
+    /// - `key`: The request key to look up
+    /// - `peer`: The peer to remove from alternatives
+    pub(super) async fn remove_alternative_peer(&self, key: &RequestKey, peer: &N)
+    where
+        N: PartialEq + Eq,
+    {
+        if let Some(entry) = self.entries.read().await.get(key) {
+            let mut alt_peers = entry.alternative_peers.write().await;
+            alt_peers.retain(|p| p != peer);
+        }
+    }
 }
 
 /// Type of in-flight request match found.

linera-core/src/client/requests_scheduler/mod.rs

@@ -21,6 +21,7 @@ pub const CACHE_TTL_MS: u64 = 2000;
 pub const CACHE_MAX_SIZE: usize = 1000;
 pub const MAX_REQUEST_TTL_MS: u64 = 200;
 pub const ALPHA_SMOOTHING_FACTOR: f64 = 0.1;
+pub const STAGGERED_DELAY_MS: u64 = 75;
 
 /// Configuration for the `RequestsScheduler`.
 #[derive(Debug, Clone)]
@@ -35,6 +36,8 @@ pub struct RequestsSchedulerConfig {
     pub max_request_ttl_ms: u64,
     /// Smoothing factor for Exponential Moving Averages (0 < alpha < 1)
     pub alpha: f64,
+    /// Delay in milliseconds between starting requests to different peers.
+    pub retry_delay_ms: u64,
 }
 
 impl Default for RequestsSchedulerConfig {
@@ -45,6 +48,7 @@ impl Default for RequestsSchedulerConfig {
             cache_max_size: CACHE_MAX_SIZE,
             max_request_ttl_ms: MAX_REQUEST_TTL_MS,
             alpha: ALPHA_SMOOTHING_FACTOR,
+            retry_delay_ms: STAGGERED_DELAY_MS,
         }
     }
 }