Christoffer Martinsson 374b126446 Reduce all command timeouts to 2-3 seconds max
With 10-second host heartbeat timeout, all command timeouts must be significantly lower to ensure total collection time stays under 10 seconds.

Changed timeouts:
- smartctl: 10s → 3s (critical: multiple drives queried sequentially)
- du: 5s → 2s
- lsblk: 5s → 2s
- systemctl list commands: 5s → 3s
- systemctl show/is-active: 3s → 2s
- docker commands: 5s → 3s
- df, ip commands: 3s → 2s

Total worst-case collection time now capped at more reasonable levels, preventing false host offline alerts from blocking operations.
2025-11-27 16:38:54 +01:00

225 lines
9.3 KiB
Rust

use async_trait::async_trait;
use cm_dashboard_shared::{AgentData, NetworkInterfaceData, Status};
use std::process::Command;
use tracing::debug;
use super::{Collector, CollectorError};
use crate::config::NetworkConfig;
/// Network interface collector with physical/virtual classification and link status
pub struct NetworkCollector {
_config: NetworkConfig,
}
impl NetworkCollector {
pub fn new(config: NetworkConfig) -> Self {
Self { _config: config }
}
/// Check if interface is physical (not virtual)
fn is_physical_interface(name: &str) -> bool {
// Physical interface patterns
matches!(
&name[..],
s if s.starts_with("eth")
|| s.starts_with("ens")
|| s.starts_with("enp")
|| s.starts_with("wlan")
|| s.starts_with("wlp")
|| s.starts_with("eno")
|| s.starts_with("enx")
)
}
/// Get link status for an interface
fn get_link_status(interface: &str) -> Status {
let operstate_path = format!("/sys/class/net/{}/operstate", interface);
match std::fs::read_to_string(&operstate_path) {
Ok(state) => {
let state = state.trim();
match state {
"up" => Status::Ok,
"down" => Status::Inactive,
"unknown" => Status::Warning,
_ => Status::Unknown,
}
}
Err(_) => Status::Unknown,
}
}
/// Get the primary physical interface (the one with default route)
fn get_primary_physical_interface() -> Option<String> {
match Command::new("timeout").args(["2", "ip", "route", "show", "default"]).output() {
Ok(output) if output.status.success() => {
let output_str = String::from_utf8_lossy(&output.stdout);
// Parse: "default via 192.168.1.1 dev eno1 ..."
for line in output_str.lines() {
if line.starts_with("default") {
if let Some(dev_pos) = line.find(" dev ") {
let after_dev = &line[dev_pos + 5..];
if let Some(space_pos) = after_dev.find(' ') {
let interface = &after_dev[..space_pos];
// Only return if it's a physical interface
if Self::is_physical_interface(interface) {
return Some(interface.to_string());
}
} else {
// No space after interface name (end of line)
let interface = after_dev.trim();
if Self::is_physical_interface(interface) {
return Some(interface.to_string());
}
}
}
}
}
None
}
_ => None,
}
}
/// Parse VLAN configuration from /proc/net/vlan/config
/// Returns a map of interface name -> VLAN ID
fn parse_vlan_config() -> std::collections::HashMap<String, u16> {
let mut vlan_map = std::collections::HashMap::new();
if let Ok(contents) = std::fs::read_to_string("/proc/net/vlan/config") {
for line in contents.lines().skip(2) { // Skip header lines
let parts: Vec<&str> = line.split('|').collect();
if parts.len() >= 2 {
let interface_name = parts[0].trim();
let vlan_id_str = parts[1].trim();
if let Ok(vlan_id) = vlan_id_str.parse::<u16>() {
vlan_map.insert(interface_name.to_string(), vlan_id);
}
}
}
}
vlan_map
}
/// Collect network interfaces using ip command
async fn collect_interfaces(&self) -> Vec<NetworkInterfaceData> {
let mut interfaces = Vec::new();
// Parse VLAN configuration
let vlan_map = Self::parse_vlan_config();
match Command::new("timeout").args(["2", "ip", "-j", "addr"]).output() {
Ok(output) if output.status.success() => {
let json_str = String::from_utf8_lossy(&output.stdout);
if let Ok(json_data) = serde_json::from_str::<serde_json::Value>(&json_str) {
if let Some(ifaces) = json_data.as_array() {
for iface in ifaces {
let name = iface["ifname"].as_str().unwrap_or("").to_string();
// Skip loopback, empty names, and ifb* interfaces
if name.is_empty() || name == "lo" || name.starts_with("ifb") {
continue;
}
// Parse parent interface from @parent notation (e.g., lan@enp0s31f6)
let (interface_name, parent_interface) = if let Some(at_pos) = name.find('@') {
let (child, parent) = name.split_at(at_pos);
(child.to_string(), Some(parent[1..].to_string()))
} else {
(name.clone(), None)
};
let mut ipv4_addresses = Vec::new();
let mut ipv6_addresses = Vec::new();
// Extract IP addresses
if let Some(addr_info) = iface["addr_info"].as_array() {
for addr in addr_info {
if let Some(family) = addr["family"].as_str() {
if let Some(local) = addr["local"].as_str() {
match family {
"inet" => ipv4_addresses.push(local.to_string()),
"inet6" => {
// Skip link-local IPv6 addresses (fe80::)
if !local.starts_with("fe80:") {
ipv6_addresses.push(local.to_string());
}
}
_ => {}
}
}
}
}
}
// Determine if physical and get status
let is_physical = Self::is_physical_interface(&interface_name);
// Only filter out virtual interfaces without IPs
// Physical interfaces should always be shown even if down/no IPs
if !is_physical && ipv4_addresses.is_empty() && ipv6_addresses.is_empty() {
continue;
}
let link_status = if is_physical {
Self::get_link_status(&name)
} else {
Status::Unknown // Virtual interfaces don't have meaningful link status
};
// Look up VLAN ID from the map (use original name before @ parsing)
let vlan_id = vlan_map.get(&name).copied();
interfaces.push(NetworkInterfaceData {
name: interface_name,
ipv4_addresses,
ipv6_addresses,
is_physical,
link_status,
parent_interface,
vlan_id,
});
}
}
}
}
Err(e) => {
debug!("Failed to execute ip command: {}", e);
}
Ok(output) => {
debug!("ip command failed with status: {}", output.status);
}
}
// Assign primary physical interface as parent to virtual interfaces without explicit parent
let primary_interface = Self::get_primary_physical_interface();
if let Some(primary) = primary_interface {
for interface in interfaces.iter_mut() {
// Only assign parent to virtual interfaces that don't already have one
if !interface.is_physical && interface.parent_interface.is_none() {
interface.parent_interface = Some(primary.clone());
}
}
}
interfaces
}
}
#[async_trait]
impl Collector for NetworkCollector {
async fn collect_structured(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> {
debug!("Collecting network interface data");
// Collect all network interfaces
let interfaces = self.collect_interfaces().await;
agent_data.system.network.interfaces = interfaces;
Ok(())
}
}