1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
|
//! Prometheus Metrics for Proactive Sync (GRASP-02)
//!
//! This module provides comprehensive sync monitoring metrics including:
//! - Connection status and attempts per relay
//! - Health state tracking (Healthy/Degraded/Dead)
//! - Event sync tracking by source (live/startup/reconnect/daily catchup)
//! - Gap events filled during catchup operations
//!
//! All metrics follow the `ngit_sync_` prefix convention.
use prometheus::{IntCounterVec, IntGauge, IntGaugeVec, Opts, Registry};
use super::health::HealthState;
/// Prometheus metrics for the proactive sync system.
///
/// Tracks relay connections, sync progress, health states, and operational statistics.
/// Designed for comprehensive monitoring of GRASP-02 proactive sync operations.
#[derive(Clone)]
pub struct SyncMetrics {
// === Connection metrics ===
/// Per-relay connection status (1=connected, 0=disconnected)
relay_connected: IntGaugeVec,
/// Connection attempts by relay and result (success/failure)
connection_attempts_total: IntCounterVec,
// === Health metrics ===
/// Per-relay health status (healthy=1, degraded=2, dead=3)
relay_status: IntGaugeVec,
/// Per-relay consecutive failure count
relay_failures: IntGaugeVec,
// === Event metrics ===
/// Events synced by source (live/startup/reconnect/daily)
events_total: IntCounterVec,
/// Gap events filled during catchup, by relay
gap_events_total: IntCounterVec,
// === Summary metrics ===
/// Total relays discovered and tracked
relays_tracked_total: IntGauge,
/// Currently connected relay count
relays_connected_total: IntGauge,
/// Relays marked as dead
relays_dead_total: IntGauge,
}
impl SyncMetrics {
/// Register all sync metrics with the provided Prometheus registry.
///
/// # Errors
///
/// Returns an error if metrics are already registered (e.g., in tests).
pub fn register(registry: &Registry) -> Result<Self, prometheus::Error> {
// Connection metrics
let relay_connected = IntGaugeVec::new(
Opts::new(
"ngit_sync_relay_connected",
"Relay connection status (1=connected, 0=disconnected)",
),
&["relay"],
)?;
registry.register(Box::new(relay_connected.clone()))?;
let connection_attempts_total = IntCounterVec::new(
Opts::new(
"ngit_sync_connection_attempts_total",
"Total connection attempts by relay and result",
),
&["relay", "result"],
)?;
registry.register(Box::new(connection_attempts_total.clone()))?;
// Health metrics
let relay_status = IntGaugeVec::new(
Opts::new(
"ngit_sync_relay_status",
"Relay health status (1=healthy, 2=degraded, 3=dead)",
),
&["relay"],
)?;
registry.register(Box::new(relay_status.clone()))?;
let relay_failures = IntGaugeVec::new(
Opts::new(
"ngit_sync_relay_failures",
"Consecutive failure count per relay",
),
&["relay"],
)?;
registry.register(Box::new(relay_failures.clone()))?;
// Event metrics
let events_total = IntCounterVec::new(
Opts::new(
"ngit_sync_events_total",
"Total events synced by source type",
),
&["source"],
)?;
registry.register(Box::new(events_total.clone()))?;
let gap_events_total = IntCounterVec::new(
Opts::new(
"ngit_sync_gap_events_total",
"Gap events filled during catchup by relay",
),
&["relay"],
)?;
registry.register(Box::new(gap_events_total.clone()))?;
// Summary metrics
let relays_tracked_total = IntGauge::with_opts(Opts::new(
"ngit_sync_relays_tracked_total",
"Total number of relays discovered and tracked",
))?;
registry.register(Box::new(relays_tracked_total.clone()))?;
let relays_connected_total = IntGauge::with_opts(Opts::new(
"ngit_sync_relays_connected_total",
"Number of currently connected relays",
))?;
registry.register(Box::new(relays_connected_total.clone()))?;
let relays_dead_total = IntGauge::with_opts(Opts::new(
"ngit_sync_relays_dead_total",
"Number of relays marked as dead",
))?;
registry.register(Box::new(relays_dead_total.clone()))?;
Ok(Self {
relay_connected,
connection_attempts_total,
relay_status,
relay_failures,
events_total,
gap_events_total,
relays_tracked_total,
relays_connected_total,
relays_dead_total,
})
}
// === Connection Recording Methods ===
/// Record a connection attempt (success or failure).
///
/// # Arguments
///
/// * `relay` - The relay URL
/// * `success` - Whether the connection attempt succeeded
pub fn record_connection_attempt(&self, relay: &str, success: bool) {
let result = if success { "success" } else { "failure" };
self.connection_attempts_total
.with_label_values(&[relay, result])
.inc();
self.set_relay_connected(relay, success);
}
/// Set relay connection status.
///
/// # Arguments
///
/// * `relay` - The relay URL
/// * `connected` - Whether the relay is currently connected
pub fn set_relay_connected(&self, relay: &str, connected: bool) {
self.relay_connected
.with_label_values(&[relay])
.set(if connected { 1 } else { 0 });
// Note: Connected count should be updated via update_connected_count() for accuracy
}
/// Update the total connected relay count.
///
/// This directly sets the count rather than deriving it from individual relay states,
/// which is more accurate when relay connection states are managed elsewhere.
pub fn update_connected_count(&self, count: i64) {
self.relays_connected_total.set(count);
}
/// Increment connected count by one.
pub fn inc_connected_count(&self) {
self.relays_connected_total.inc();
}
/// Decrement connected count by one.
pub fn dec_connected_count(&self) {
self.relays_connected_total.dec();
}
// === Health Recording Methods ===
/// Record relay health state change.
///
/// Maps health states to numeric values for Prometheus:
/// - Healthy = 1
/// - Degraded = 2
/// - Dead = 3
///
/// # Arguments
///
/// * `relay` - The relay URL
/// * `state` - The current health state
pub fn record_health_state(&self, relay: &str, state: HealthState) {
let state_value = match state {
HealthState::Healthy => 1,
HealthState::Degraded => 2,
HealthState::Dead => 3,
};
self.relay_status
.with_label_values(&[relay])
.set(state_value);
}
/// Record relay failure count.
///
/// # Arguments
///
/// * `relay` - The relay URL
/// * `count` - The number of consecutive failures
pub fn record_failure_count(&self, relay: &str, count: u32) {
self.relay_failures
.with_label_values(&[relay])
.set(count as i64);
}
/// Update dead relay count.
pub fn update_dead_count(&self, count: i64) {
self.relays_dead_total.set(count);
}
/// Increment dead relay count by one.
pub fn inc_dead_count(&self) {
self.relays_dead_total.inc();
}
/// Decrement dead relay count by one.
pub fn dec_dead_count(&self) {
self.relays_dead_total.dec();
}
// === Event Recording Methods ===
/// Record a synced event by source type.
///
/// # Arguments
///
/// * `source` - The event source type. Use constants from [`event_source`]:
/// - [`event_source::LIVE`] - Real-time subscription events
/// - [`event_source::STARTUP`] - Events from startup catchup
/// - [`event_source::RECONNECT`] - Events from reconnection catchup
/// - [`event_source::DAILY`] - Events from daily catchup
pub fn record_event(&self, source: &str) {
self.events_total.with_label_values(&[source]).inc();
}
/// Record multiple events synced by source type.
///
/// # Arguments
///
/// * `source` - The event source type (see [`record_event`](Self::record_event))
/// * `count` - Number of events to record
pub fn record_events(&self, source: &str, count: u64) {
self.events_total.with_label_values(&[source]).inc_by(count);
}
/// Record a gap event filled during catchup.
///
/// Gap events are historical events discovered during catchup that weren't
/// received during live sync.
///
/// # Arguments
///
/// * `relay` - The relay URL from which the gap event was received
pub fn record_gap_event(&self, relay: &str) {
self.gap_events_total.with_label_values(&[relay]).inc();
}
/// Record multiple gap events filled during catchup.
///
/// # Arguments
///
/// * `relay` - The relay URL from which the gap events were received
/// * `count` - Number of gap events to record
pub fn record_gap_events(&self, relay: &str, count: u64) {
self.gap_events_total
.with_label_values(&[relay])
.inc_by(count);
}
// === Summary Recording Methods ===
/// Set the total tracked relay count.
pub fn set_tracked_count(&self, count: i64) {
self.relays_tracked_total.set(count);
}
/// Increment tracked relay count by one.
pub fn inc_tracked_count(&self) {
self.relays_tracked_total.inc();
}
/// Get current tracked relay count.
pub fn get_tracked_count(&self) -> i64 {
self.relays_tracked_total.get()
}
/// Get current connected relay count.
pub fn get_connected_count(&self) -> i64 {
self.relays_connected_total.get()
}
/// Get current dead relay count.
pub fn get_dead_count(&self) -> i64 {
self.relays_dead_total.get()
}
}
/// Event source types for metrics tracking.
///
/// These constants are used as labels for the `ngit_sync_events_total` metric
/// to categorize events by how they were discovered.
pub mod event_source {
/// Real-time subscription events received during live sync.
pub const LIVE: &str = "live";
/// Events from startup catchup when the relay first starts.
pub const STARTUP: &str = "startup";
/// Events from reconnection catchup after a relay reconnects.
pub const RECONNECT: &str = "reconnect";
/// Events from daily catchup for drift detection.
pub const DAILY: &str = "daily";
}
#[cfg(test)]
mod tests {
use super::*;
fn create_test_registry() -> Registry {
Registry::new()
}
#[test]
fn test_metrics_registration() {
let registry = create_test_registry();
let metrics = SyncMetrics::register(®istry);
assert!(metrics.is_ok());
}
#[test]
fn test_connection_metrics() {
let registry = create_test_registry();
let metrics = SyncMetrics::register(®istry).unwrap();
// Record connection attempts
metrics.record_connection_attempt("wss://relay1.example.com", true);
metrics.record_connection_attempt("wss://relay1.example.com", false);
metrics.record_connection_attempt("wss://relay2.example.com", true);
// Set relay connection status
metrics.set_relay_connected("wss://relay1.example.com", true);
metrics.inc_connected_count();
assert_eq!(metrics.get_connected_count(), 1);
// Test decrement
metrics.dec_connected_count();
assert_eq!(metrics.get_connected_count(), 0);
}
#[test]
fn test_health_metrics() {
let registry = create_test_registry();
let metrics = SyncMetrics::register(®istry).unwrap();
// Record health states
metrics.record_health_state("wss://relay1.example.com", HealthState::Healthy);
metrics.record_health_state("wss://relay2.example.com", HealthState::Degraded);
metrics.record_health_state("wss://relay3.example.com", HealthState::Dead);
// Record failure count
metrics.record_failure_count("wss://relay2.example.com", 5);
// Test dead count tracking
metrics.update_dead_count(1);
assert_eq!(metrics.get_dead_count(), 1);
metrics.inc_dead_count();
assert_eq!(metrics.get_dead_count(), 2);
metrics.dec_dead_count();
assert_eq!(metrics.get_dead_count(), 1);
}
#[test]
fn test_event_metrics() {
let registry = create_test_registry();
let metrics = SyncMetrics::register(®istry).unwrap();
// Record single events
metrics.record_event(event_source::LIVE);
metrics.record_event(event_source::STARTUP);
metrics.record_event(event_source::RECONNECT);
metrics.record_event(event_source::DAILY);
// Record multiple events
metrics.record_events(event_source::STARTUP, 10);
// Record gap events
metrics.record_gap_event("wss://relay1.example.com");
metrics.record_gap_events("wss://relay2.example.com", 5);
}
#[test]
fn test_summary_metrics() {
let registry = create_test_registry();
let metrics = SyncMetrics::register(®istry).unwrap();
// Test tracked count
metrics.set_tracked_count(5);
assert_eq!(metrics.get_tracked_count(), 5);
metrics.inc_tracked_count();
assert_eq!(metrics.get_tracked_count(), 6);
// Test connected count
metrics.update_connected_count(3);
assert_eq!(metrics.get_connected_count(), 3);
}
#[test]
fn test_event_source_constants() {
// Verify constants have expected values
assert_eq!(event_source::LIVE, "live");
assert_eq!(event_source::STARTUP, "startup");
assert_eq!(event_source::RECONNECT, "reconnect");
assert_eq!(event_source::DAILY, "daily");
}
#[test]
fn test_duplicate_registration_fails() {
let registry = create_test_registry();
// First registration should succeed
let metrics1 = SyncMetrics::register(®istry);
assert!(metrics1.is_ok());
// Second registration should fail (metrics already registered)
let metrics2 = SyncMetrics::register(®istry);
assert!(metrics2.is_err());
}
}
|