Merge branch 'rc-2024.12.1-hotfix6' into stable

maidsafe · Jan 20, 2025 · 92ed942 · 92ed942
2 parents 26eee3a + 2ef95c4
commit 92ed942
Show file tree

Hide file tree

Showing 20 changed files with 79 additions and 90 deletions.
diff --git a/.github/workflows/memcheck.yml b/.github/workflows/memcheck.yml
@@ -164,6 +164,22 @@ jobs:
         run: pgrep antnode | wc -l
         if: always()
 
+      - name: confirm opened FDs
+        shell: bash
+        timeout-minutes: 1
+        run: |
+          fd_cap="30"
+          pids=$(pgrep antnode)
+          for pid in $pids; do
+            fd_count=$(ls /proc/$pid/fd | wc -l)
+            echo "Process $pid - File Descriptors: $fd_count"
+            if (( $(echo "$fd_count > $fd_cap" | bc -l) )); then
+              echo "Process $pid holding FD exceeded threshold: $fd_cap"
+              exit 1
+            fi
+          done
+        if: always()
+
       - name: Stop the local network and upload logs
         if: always()
         uses: maidsafe/ant-local-testnet-action@main

diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -7,6 +7,35 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 *When editing this file, please respect a line length of 100.*
 
+## 2025-01-20
+
+### Client
+
+#### Fixed
+
+- Remove unallocated static IP from the bootstrap mechanism. We have five static IP addresses
+  allocated to five hosts, each of which run nodes and a minimal web server. The web server makes a
+  list of peers available to nodes and clients to enable them to join the network. These static IP
+  addresses are hard-coded in the `antnode` and `ant` binaries. It was discovered we had accidentally
+  added six IPs and one of those was unallocated. Removing the unallocated IP should reduce the time
+  to connect to the network.
+
+### Network
+
+#### Changed
+
+- Reduce the frequency of metrics collection in the node's metrics server, from fifteen to sixty
+  seconds. This should reduce resource usage and improve performance.
+- Do not refresh all CPU information in the metrics collection process in the node's metrics server.
+  Again, this should reduce resource usage and improve performance.
+- Remove the 50% CPU usage safety measure. We added a safety measure to the node to cause the
+  process to terminate if the system's CPU usage exceeded 50% for five consecutive minutes. This was
+  to prevent cascading failures resulting from too much churn when a large node operator pulled the
+  plug on tens of thousands of nodes in a very short period of time. If other operators had
+  provisioned to max capacity and not left some buffer room for their own nodes, many other node
+  processes could die from the resulting churn. After an internal discussion, the decision was taken
+  to remove the safety measure.
+
 ## 2025-01-14
 
 ### Client

diff --git a/Cargo.lock b/Cargo.lock
diff --git a/ant-bootstrap/Cargo.toml b/ant-bootstrap/Cargo.toml
@@ -7,13 +7,13 @@ license = "GPL-3.0"
 name = "ant-bootstrap"
 readme = "README.md"
 repository = "https://github.com/maidsafe/autonomi"
-version = "0.1.3"
+version = "0.1.4"
 
 [features]
 local = []
 
 [dependencies]
-ant-logging = { path = "../ant-logging", version = "0.2.44" }
+ant-logging = { path = "../ant-logging", version = "0.2.45" }
 ant-protocol = { path = "../ant-protocol", version = "0.3.3" }
 atomic-write-file = "0.2.2"
 chrono = { version = "0.4", features = ["serde"] }

diff --git a/ant-bootstrap/src/contacts.rs b/ant-bootstrap/src/contacts.rs
@@ -20,7 +20,6 @@ const MAINNET_CONTACTS: &[&str] = &[
     "http://159.223.246.45/bootstrap_cache.json",
     "http://139.59.201.153/bootstrap_cache.json",
     "http://139.59.200.27/bootstrap_cache.json",
-    "http://139.59.198.251/bootstrap_cache.json",
 ];
 
 /// The client fetch timeout

diff --git a/ant-build-info/src/release_info.rs b/ant-build-info/src/release_info.rs
@@ -1,4 +1,4 @@
 pub const RELEASE_YEAR: &str = "2024";
 pub const RELEASE_MONTH: &str = "12";
 pub const RELEASE_CYCLE: &str = "1";
-pub const RELEASE_CYCLE_COUNTER: &str = "9";
+pub const RELEASE_CYCLE_COUNTER: &str = "10";
diff --git a/ant-cli/Cargo.toml b/ant-cli/Cargo.toml
@@ -3,7 +3,7 @@ authors = ["MaidSafe Developers <[email protected]>"]
 name = "ant-cli"
 description = "CLI client for the Autonomi network"
 license = "GPL-3.0"
-version = "0.3.4"
+version = "0.3.5"
 edition = "2021"
 homepage = "https://maidsafe.net"
 readme = "README.md"
@@ -24,9 +24,9 @@ name = "files"
 harness = false
 
 [dependencies]
-ant-bootstrap = { path = "../ant-bootstrap", version = "0.1.3" }
+ant-bootstrap = { path = "../ant-bootstrap", version = "0.1.4" }
 ant-build-info = { path = "../ant-build-info", version = "0.1.23" }
-ant-logging = { path = "../ant-logging", version = "0.2.44" }
+ant-logging = { path = "../ant-logging", version = "0.2.45" }
 ant-protocol = { path = "../ant-protocol", version = "0.3.3" }
 autonomi = { path = "../autonomi", version = "0.3.4", features = [
     "fs",

diff --git a/ant-logging/Cargo.toml b/ant-logging/Cargo.toml
@@ -7,7 +7,7 @@ license = "GPL-3.0"
 name = "ant-logging"
 readme = "README.md"
 repository = "https://github.com/maidsafe/autonomi"
-version = "0.2.44"
+version = "0.2.45"
 
 [dependencies]
 chrono = "~0.4.19"

diff --git a/ant-logging/src/metrics.rs b/ant-logging/src/metrics.rs
@@ -11,7 +11,7 @@ use std::time::Duration;
 use sysinfo::{self, Networks, Pid, System};
 use tracing::{debug, error};
 
-const UPDATE_INTERVAL: Duration = Duration::from_secs(15);
+const UPDATE_INTERVAL: Duration = Duration::from_secs(60);
 const TO_MB: u64 = 1_000_000;
 
 // The following Metrics are collected and logged
@@ -44,7 +44,7 @@ struct ProcessMetrics {
 // Obtains the system metrics every UPDATE_INTERVAL and logs it.
 // The function should be spawned as a task and should be re-run if our main process is restarted.
 pub async fn init_metrics(pid: u32) {
-    let mut sys = System::new_all();
+    let mut sys = System::new();
     let mut networks = Networks::new_with_refreshed_list();
     let pid = Pid::from_u32(pid);
 

diff --git a/ant-networking/Cargo.toml b/ant-networking/Cargo.toml
@@ -7,7 +7,7 @@ license = "GPL-3.0"
 name = "ant-networking"
 readme = "README.md"
 repository = "https://github.com/maidsafe/autonomi"
-version = "0.3.3"
+version = "0.3.4"
 
 [features]
 default = []
@@ -20,7 +20,7 @@ upnp = ["libp2p/upnp"]
 
 [dependencies]
 aes-gcm-siv = "0.11.1"
-ant-bootstrap = { path = "../ant-bootstrap", version = "0.1.3" }
+ant-bootstrap = { path = "../ant-bootstrap", version = "0.1.4" }
 ant-build-info = { path = "../ant-build-info", version = "0.1.23" }
 ant-evm = { path = "../ant-evm", version = "0.1.8" }
 ant-protocol = { path = "../ant-protocol", version = "0.3.3" }

diff --git a/ant-networking/src/metrics/mod.rs b/ant-networking/src/metrics/mod.rs
@@ -28,7 +28,7 @@ use prometheus_client::{
 use sysinfo::{Pid, ProcessRefreshKind, System};
 use tokio::time::Duration;
 
-const UPDATE_INTERVAL: Duration = Duration::from_secs(15);
+const UPDATE_INTERVAL: Duration = Duration::from_secs(60);
 const TO_MB: u64 = 1_000_000;
 
 /// The shared recorders that are used to record metrics.
@@ -246,7 +246,7 @@ impl NetworkMetricsRecorder {
 
         let pid = Pid::from_u32(std::process::id());
         let process_refresh_kind = ProcessRefreshKind::everything().without_disk_usage();
-        let mut system = System::new_all();
+        let mut system = System::new();
         let physical_core_count = system.physical_core_count();
 
         tokio::spawn(async move {

diff --git a/ant-node-manager/Cargo.toml b/ant-node-manager/Cargo.toml
@@ -30,10 +30,10 @@ tcp = []
 websockets = []
 
 [dependencies]
-ant-bootstrap = { path = "../ant-bootstrap", version = "0.1.3" }
+ant-bootstrap = { path = "../ant-bootstrap", version = "0.1.4" }
 ant-build-info = { path = "../ant-build-info", version = "0.1.23" }
 ant-evm = { path = "../ant-evm", version = "0.1.8" }
-ant-logging = { path = "../ant-logging", version = "0.2.44" }
+ant-logging = { path = "../ant-logging", version = "0.2.45" }
 ant-protocol = { path = "../ant-protocol", version = "0.3.3" }
 ant-releases = { version = "0.4.0" }
 ant-service-management = { path = "../ant-service-management", version = "0.4.7" }

diff --git a/ant-node-rpc-client/Cargo.toml b/ant-node-rpc-client/Cargo.toml
@@ -18,9 +18,9 @@ nightly = []
 
 [dependencies]
 ant-build-info = { path = "../ant-build-info", version = "0.1.23" }
-ant-logging = { path = "../ant-logging", version = "0.2.44" }
+ant-logging = { path = "../ant-logging", version = "0.2.45" }
 ant-protocol = { path = "../ant-protocol", version = "0.3.3", features=["rpc"] }
-ant-node = { path = "../ant-node", version = "0.3.4" }
+ant-node = { path = "../ant-node", version = "0.3.5" }
 ant-service-management = { path = "../ant-service-management", version = "0.4.7" }
 async-trait = "0.1"
 bls = { package = "blsttc", version = "8.0.1" }

diff --git a/ant-node/Cargo.toml b/ant-node/Cargo.toml
@@ -2,7 +2,7 @@
 authors = ["MaidSafe Developers <[email protected]>"]
 description = "The Autonomi node binary"
 name = "ant-node"
-version = "0.3.4"
+version = "0.3.5"
 edition = "2021"
 license = "GPL-3.0"
 homepage = "https://maidsafe.net"
@@ -26,11 +26,11 @@ otlp = ["ant-logging/otlp"]
 upnp = ["ant-networking/upnp"]
 
 [dependencies]
-ant-bootstrap = { path = "../ant-bootstrap", version = "0.1.3" }
+ant-bootstrap = { path = "../ant-bootstrap", version = "0.1.4" }
 ant-build-info = { path = "../ant-build-info", version = "0.1.23" }
 ant-evm = { path = "../ant-evm", version = "0.1.8" }
-ant-logging = { path = "../ant-logging", version = "0.2.44" }
-ant-networking = { path = "../ant-networking", version = "0.3.3" }
+ant-logging = { path = "../ant-logging", version = "0.2.45" }
+ant-networking = { path = "../ant-networking", version = "0.3.4" }
 ant-protocol = { path = "../ant-protocol", version = "0.3.3" }
 ant-registers = { path = "../ant-registers", version = "0.4.7" }
 ant-service-management = { path = "../ant-service-management", version = "0.4.7" }
@@ -62,7 +62,6 @@ rayon = "1.8.0"
 self_encryption = "~0.30.0"
 serde = { version = "1.0.133", features = ["derive", "rc"] }
 strum = { version = "0.26.2", features = ["derive"] }
-sysinfo = { version = "0.30.8", default-features = false }
 thiserror = "1.0.23"
 tokio = { version = "1.32.0", features = [
     "io-util",

diff --git a/ant-node/src/bin/antnode/main.rs b/ant-node/src/bin/antnode/main.rs
@@ -36,7 +36,6 @@ use std::{
     process::Command,
     time::Duration,
 };
-use sysinfo::{self, System};
 use tokio::{
     runtime::Runtime,
     sync::{broadcast::error::RecvError, mpsc},
@@ -412,58 +411,6 @@ You can check your reward balance by running:
             error!("Failed to send node control msg to antnode bin main thread: {err}");
         }
     });
-    let ctrl_tx_clone_cpu = ctrl_tx.clone();
-    // Monitor host CPU usage
-    tokio::spawn(async move {
-        use rand::{thread_rng, Rng};
-
-        const CPU_CHECK_INTERVAL: Duration = Duration::from_secs(60);
-        const CPU_USAGE_THRESHOLD: f32 = 50.0;
-        const HIGH_CPU_CONSECUTIVE_LIMIT: u8 = 5;
-        const NODE_STOP_DELAY: Duration = Duration::from_secs(1);
-        const INITIAL_DELAY_MIN_S: u64 = 10;
-        const INITIAL_DELAY_MAX_S: u64 =
-            HIGH_CPU_CONSECUTIVE_LIMIT as u64 * CPU_CHECK_INTERVAL.as_secs();
-        const JITTER_MIN_S: u64 = 1;
-        const JITTER_MAX_S: u64 = 15;
-
-        let mut sys = System::new_all();
-
-        let mut high_cpu_count: u8 = 0;
-
-        // Random initial delay between 1 and 5 minutes
-        let initial_delay =
-            Duration::from_secs(thread_rng().gen_range(INITIAL_DELAY_MIN_S..=INITIAL_DELAY_MAX_S));
-        tokio::time::sleep(initial_delay).await;
-
-        loop {
-            sys.refresh_cpu();
-            let cpu_usage = sys.global_cpu_info().cpu_usage();
-
-            if cpu_usage > CPU_USAGE_THRESHOLD {
-                high_cpu_count += 1;
-            } else {
-                high_cpu_count = 0;
-            }
-
-            if high_cpu_count >= HIGH_CPU_CONSECUTIVE_LIMIT {
-                if let Err(err) = ctrl_tx_clone_cpu
-                    .send(NodeCtrl::Stop {
-                        delay: NODE_STOP_DELAY,
-                        result: StopResult::Success(format!("Excess host CPU %{CPU_USAGE_THRESHOLD} detected for {HIGH_CPU_CONSECUTIVE_LIMIT} consecutive minutes!")),
-                    })
-                    .await
-                {
-                    error!("Failed to send node control msg to antnode bin main thread: {err}");
-                }
-                break;
-            }
-
-            // Add jitter to the interval
-            let jitter = Duration::from_secs(thread_rng().gen_range(JITTER_MIN_S..=JITTER_MAX_S));
-            tokio::time::sleep(CPU_CHECK_INTERVAL + jitter).await;
-        }
-    });
 
     // Start up gRPC interface if enabled by user
     if let Some(addr) = rpc {

diff --git a/ant-service-management/Cargo.toml b/ant-service-management/Cargo.toml
@@ -10,9 +10,9 @@ repository = "https://github.com/maidsafe/autonomi"
 version = "0.4.7"
 
 [dependencies]
-ant-bootstrap = { path = "../ant-bootstrap", version = "0.1.3" }
+ant-bootstrap = { path = "../ant-bootstrap", version = "0.1.4" }
 ant-evm = { path = "../ant-evm", version = "0.1.8" }
-ant-logging = { path = "../ant-logging", version = "0.2.44" }
+ant-logging = { path = "../ant-logging", version = "0.2.45" }
 ant-protocol = { path = "../ant-protocol", version = "0.3.3", features = ["rpc"] }
 async-trait = "0.1"
 dirs-next = "2.0.0"

diff --git a/autonomi/Cargo.toml b/autonomi/Cargo.toml
@@ -33,9 +33,9 @@ registers = []
 vault = ["registers"]
 
 [dependencies]
-ant-bootstrap = { path = "../ant-bootstrap", version = "0.1.3" }
+ant-bootstrap = { path = "../ant-bootstrap", version = "0.1.4" }
 ant-evm = { path = "../ant-evm", version = "0.1.8" }
-ant-networking = { path = "../ant-networking", version = "0.3.3" }
+ant-networking = { path = "../ant-networking", version = "0.3.4" }
 ant-protocol = { path = "../ant-protocol", version = "0.3.3" }
 ant-registers = { path = "../ant-registers", version = "0.4.7" }
 bip39 = "2.0.0"
@@ -68,7 +68,7 @@ xor_name = "5.0.0"
 
 [dev-dependencies]
 alloy = { version = "0.7.3", default-features = false, features = ["contract", "json-rpc", "network", "node-bindings", "provider-http", "reqwest-rustls-tls", "rpc-client", "rpc-types", "signer-local", "std"] }
-ant-logging = { path = "../ant-logging", version = "0.2.44" }
+ant-logging = { path = "../ant-logging", version = "0.2.45" }
 eyre = "0.6.5"
 sha2 = "0.10.6"
 # Do not specify the version field. Release process expects even the local dev deps to be published.

diff --git a/nat-detection/Cargo.toml b/nat-detection/Cargo.toml
@@ -18,7 +18,7 @@ nightly = []
 
 [dependencies]
 ant-build-info = { path = "../ant-build-info", version = "0.1.23" }
-ant-networking = { path = "../ant-networking", version = "0.3.3" }
+ant-networking = { path = "../ant-networking", version = "0.3.4" }
 ant-protocol = { path = "../ant-protocol", version = "0.3.3" }
 clap = { version = "4.5.4", features = ["derive"] }
 clap-verbosity-flag = "2.2.0"