Files
bitchat/bitchat/Services/MeshTopologyTracker.swift
T
9964710de2 Improve BLE mesh reliability for large transfers (#964)
* Improve BLE mesh reliability for large transfers

Major reliability improvements for fragment-based transfers (photos, files):

**Notification Queue Fixes**
- Fix silent packet loss when notification queue is full - now queues for retry
- Fix retry queue bug where remaining items were lost when one retry failed
- Add periodic drain mechanism as backup (every 5 seconds)

**Write Queue Fixes**
- Fix drainPendingWrites to use atomic take-send-requeue pattern
- Add logging when peripheral is ready for more writes
- Add periodic drain for pending writes as backup

**Fragment Pacing**
- Increase fragment spacing from 4-5ms to 25-30ms to prevent buffer overflow
- Conservative pacing prevents packet loss on congested BLE connections

**Thread Safety**
- Fix race conditions in stopServices() and emergencyDisconnectAll()
- Synchronize access to peripherals/centrals dictionaries during cleanup
- Clear pending message queues in emergencyDisconnectAll()

**Error Recovery**
- Add handlers for all BLE state transitions (poweredOff, unauthorized, etc.)
- Clear Noise session and re-initiate handshake on decryption failure
- Queue ACKs/receipts for delivery after handshake instead of dropping
- Re-queue failed pending messages for retry

**Other Improvements**
- Add route freshness validation in MeshTopologyTracker (60s threshold)
- Add TTL (24h) and size limits (100 per peer) for MessageRouter outbox
- Fix connection timeout to check peripheral.state before canceling
- Add NoiseEncryptionService.clearSession(for:) method

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* Fix race condition and increase test timeouts

- Fix race in sendNoisePayload: use sync barrier instead of async
  to ensure payload is queued before initiating handshake
  (addresses Codex review feedback)

- Increase BLEServiceTests sleep from 0.5s to 1.0s for CI reliability

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

---------

Co-authored-by: jack <jackjackbits@users.noreply.github.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-17 07:39:31 -10:00

131 lines
5.0 KiB
Swift

import Foundation
/// Tracks observed mesh topology and computes hop-by-hop routes.
final class MeshTopologyTracker {
private typealias RoutingID = Data
private let queue = DispatchQueue(label: "mesh.topology", attributes: .concurrent)
private let hopSize = 8
// Directed claims: Key claims to see Value (neighbors)
private var claims: [RoutingID: Set<RoutingID>] = [:]
// Last time we received an update from a node
private var lastSeen: [RoutingID: Date] = [:]
// Maximum age for topology claims to be considered fresh for routing
// Routes computed using stale topology can fail when the network has changed
private static let routeFreshnessThreshold: TimeInterval = 60 // 60 seconds
func reset() {
queue.sync(flags: .barrier) {
self.claims.removeAll()
self.lastSeen.removeAll()
}
}
/// Update the topology with a node's self-reported neighbor list
func updateNeighbors(for sourceData: Data?, neighbors: [Data]) {
guard let source = sanitize(sourceData) else { return }
// Sanitize neighbors and exclude self-loops
let validNeighbors = Set(neighbors.compactMap { sanitize($0) }).subtracting([source])
queue.sync(flags: .barrier) {
self.claims[source] = validNeighbors
self.lastSeen[source] = Date()
}
}
func removePeer(_ data: Data?) {
guard let peer = sanitize(data) else { return }
queue.sync(flags: .barrier) {
self.claims.removeValue(forKey: peer)
self.lastSeen.removeValue(forKey: peer)
}
}
/// Prune nodes that haven't updated their topology in `age` seconds
func prune(olderThan age: TimeInterval) {
let deadline = Date().addingTimeInterval(-age)
queue.sync(flags: .barrier) {
let stale = self.lastSeen.filter { $0.value < deadline }
for (peer, _) in stale {
self.claims.removeValue(forKey: peer)
self.lastSeen.removeValue(forKey: peer)
}
}
}
func computeRoute(from start: Data?, to goal: Data?, maxHops: Int = 10) -> [Data]? {
guard let source = sanitize(start), let target = sanitize(goal) else { return nil }
if source == target { return [] } // Direct connection, no intermediate hops
return queue.sync {
let now = Date()
let freshnessDeadline = now.addingTimeInterval(-Self.routeFreshnessThreshold)
// BFS
var visited: Set<RoutingID> = [source]
// Queue stores paths: [Start, Hop1, Hop2, ..., Current]
var queuePaths: [[RoutingID]] = [[source]]
while !queuePaths.isEmpty {
let path = queuePaths.removeFirst()
// Limit path length (path contains source + maxHops + target) -> maxHops intermediate
// If maxHops = 10, max edges = 11, max nodes = 12.
if path.count > maxHops + 1 { continue }
guard let last = path.last else { continue }
// Get neighbors that 'last' claims to see
guard let neighbors = claims[last] else { continue }
// Check if 'last' node's topology info is fresh
guard let lastSeenTime = lastSeen[last], lastSeenTime > freshnessDeadline else {
continue // Skip stale nodes
}
for neighbor in neighbors {
if visited.contains(neighbor) { continue }
// CONFIRMED EDGE CHECK:
// 'last' claims 'neighbor' (checked above)
// Does 'neighbor' claim 'last'?
guard let neighborClaims = claims[neighbor],
neighborClaims.contains(last) else {
continue
}
// Check if 'neighbor' node's topology info is fresh
guard let neighborSeenTime = lastSeen[neighbor], neighborSeenTime > freshnessDeadline else {
continue // Skip edges to stale nodes
}
var nextPath = path
nextPath.append(neighbor)
if neighbor == target {
// Return only intermediate hops
// Path: [Source, I1, I2, Target] -> [I1, I2]
return Array(nextPath.dropFirst().dropLast())
}
visited.insert(neighbor)
queuePaths.append(nextPath)
}
}
return nil
}
}
// MARK: - Helpers
private func sanitize(_ data: Data?) -> Data? {
guard var value = data, !value.isEmpty else { return nil }
if value.count > hopSize {
value = Data(value.prefix(hopSize))
} else if value.count < hopSize {
value.append(Data(repeating: 0, count: hopSize - value.count))
}
return value
}
}