Mountain/IPC/Common/
HealthStatus.rs

1//! # Health Status Monitoring
2//!
3//! Provides health monitoring and scoring for IPC components.
4//! Used to track the overall health of the IPC system.
5
6use std::time::Instant;
7
8use serde::{Deserialize, Serialize};
9
10/// Severity levels for health issues
11#[derive(Debug, Clone, Copy, PartialEq, Eq, PartialOrd, Ord, Serialize, Deserialize)]
12pub enum SeverityLevel {
13	/// Informational, no action needed
14	Low,
15	/// Monitor closely, may need attention
16	Medium,
17	/// Requires investigation and action
18	High,
19	/// Immediate attention required
20	Critical,
21}
22
23/// Types of health issues that can be detected
24#[derive(Debug, Clone, PartialEq, Eq, Hash, Serialize, Deserialize)]
25pub enum HealthIssue {
26	/// Response time exceeds threshold
27	HighLatency(String),
28	/// High memory usage detected
29	MemoryPressure(String),
30	/// IPC connection failure
31	ConnectionLoss(String),
32	/// Message queue capacity exceeded
33	QueueOverflow(String),
34	/// Unauthorized access or suspicious activity
35	SecurityViolation(String),
36	/// General performance decline
37	PerformanceDegradation(String),
38	/// Custom health issue
39	Custom(String),
40}
41
42impl HealthIssue {
43	/// Get the severity level for this health issue
44	pub fn severity(&self) -> SeverityLevel {
45		match self {
46			HealthIssue::HighLatency(_) => SeverityLevel::Medium,
47			HealthIssue::MemoryPressure(_) => SeverityLevel::Medium,
48			HealthIssue::ConnectionLoss(_) => SeverityLevel::High,
49			HealthIssue::QueueOverflow(_) => SeverityLevel::High,
50			HealthIssue::SecurityViolation(_) => SeverityLevel::Critical,
51			HealthIssue::PerformanceDegradation(_) => SeverityLevel::Medium,
52			HealthIssue::Custom(_) => SeverityLevel::Low,
53		}
54	}
55
56	/// Get the description of this health issue
57	pub fn description(&self) -> &str {
58		match self {
59			HealthIssue::HighLatency(desc) => desc,
60			HealthIssue::MemoryPressure(desc) => desc,
61			HealthIssue::ConnectionLoss(desc) => desc,
62			HealthIssue::QueueOverflow(desc) => desc,
63			HealthIssue::SecurityViolation(desc) => desc,
64			HealthIssue::PerformanceDegradation(desc) => desc,
65			HealthIssue::Custom(desc) => desc,
66		}
67	}
68}
69
70/// Health monitoring state
71#[derive(Debug, Clone, Serialize)]
72pub struct HealthMonitor {
73	/// Overall health score (0-100, where 100 is perfect health)
74	pub health_score:u8,
75	/// Detected health issues
76	pub issues:Vec<(HealthIssue, SeverityLevel)>,
77	/// Number of recovery attempts made
78	pub recovery_attempts:u32,
79	/// Timestamp of last health check (skipped for serialization as Instant is
80	/// not serializable)
81	#[serde(skip)]
82	pub last_check:Instant,
83}
84
85impl Default for HealthMonitor {
86	fn default() -> Self {
87		Self {
88			health_score:100,
89			issues:Vec::new(),
90			recovery_attempts:0,
91			last_check:Instant::now(),
92		}
93	}
94}
95
96impl HealthMonitor {
97	/// Create a new health monitor with perfect health
98	pub fn new() -> Self {
99		Self {
100			health_score:100,
101			issues:Vec::new(),
102			recovery_attempts:0,
103			last_check:Instant::now(),
104		}
105	}
106
107	/// Add a health issue and update the health score
108	pub fn add_issue(&mut self, issue:HealthIssue) {
109		let severity = issue.severity();
110		self.issues.push((issue.clone(), severity));
111		self.recalculate_score();
112	}
113
114	/// Remove a health issue and update the health score
115	pub fn remove_issue(&mut self, issue:&HealthIssue) {
116		self.issues.retain(|(i, _)| i != issue);
117		self.recalculate_score();
118	}
119
120	/// Clear all health issues and reset to perfect health
121	pub fn clear_issues(&mut self) {
122		self.issues.clear();
123		self.health_score = 100;
124		self.last_check = Instant::now();
125	}
126
127	/// Recalculate health score based on current issues
128	fn recalculate_score(&mut self) {
129		let mut score:i32 = 100;
130
131		for (_issue, severity) in &self.issues {
132			let penalty = match severity {
133				SeverityLevel::Low => 5,
134				SeverityLevel::Medium => 15,
135				SeverityLevel::High => 25,
136				SeverityLevel::Critical => 40,
137			};
138			score -= penalty;
139		}
140
141		self.health_score = score.max(0).min(100) as u8;
142		self.last_check = Instant::now();
143	}
144
145	/// Check if the system is healthy (score >= 70)
146	pub fn is_healthy(&self) -> bool { self.health_score >= 70 }
147
148	/// Check if the system is in critical state (score < 50)
149	pub fn is_critical(&self) -> bool { self.health_score < 50 }
150
151	/// Get issues by severity level
152	pub fn issues_by_severity(&self, severity:SeverityLevel) -> Vec<&HealthIssue> {
153		self.issues.iter().filter(|(_, s)| *s == severity).map(|(i, _)| i).collect()
154	}
155
156	/// Increment recovery attempt counter
157	pub fn increment_recovery_attempts(&mut self) { self.recovery_attempts += 1; }
158}
Mountain/IPC/Common/HealthStatus.rs

Mountain/IPC/Common/
HealthStatus.rs
