meshtastic/Meshtastic-Android
1
0
Fork 0
mirror of https://github.com/meshtastic/Meshtastic-Android.git synced 2026-04-20 22:23:37 +00:00
Code Issues Projects Releases Packages Wiki Activity

fix(handshake): use 60 s stall guard for Stage 2 to match SDK behavior

Browse source 
Stage 2 of the handshake drains the full node database, which on meshes
with 50+ nodes can comfortably exceed the previous 30 s stall guard and
trigger a spurious want_config_id retry mid-drain. The meshtastic-client
KMP SDK uses a 60 s timeout for this stage for the same reason.

Split HANDSHAKE_TIMEOUT into HANDSHAKE_TIMEOUT_STAGE1 (30 s) and
HANDSHAKE_TIMEOUT_STAGE2 (60 s) and thread the duration through
startHandshakeStallGuard so each call site picks the right value.
This commit is contained in:
James Rich 2026-04-19 12:23:48 -05:00
parent 6135166ea5
commit 646858cc39
1 changed files with 13 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

18
core/data/src/commonMain/kotlin/org/meshtastic/core/data/manager/MeshConnectionManagerImpl.kt
View file

@ -60,6 +60,7 @@ import org.meshtastic.proto.AdminMessage
import org.meshtastic.proto.Config
import org.meshtastic.proto.Telemetry
import org.meshtastic.proto.ToRadio
import kotlin.time.Duration
import kotlin.time.Duration.Companion.milliseconds
import kotlin.time.Duration.Companion.seconds
import kotlin.time.DurationUnit
@ -211,11 +212,11 @@ class MeshConnectionManagerImpl(
}
}
private fun startHandshakeStallGuard(stage: Int, action: () -> Unit) {
private fun startHandshakeStallGuard(stage: Int, timeout: Duration, action: () -> Unit) {
handshakeTimeout?.cancel()
handshakeTimeout =
scope.handledLaunch {
delay(HANDSHAKE_TIMEOUT)
delay(timeout)
if (serviceRepository.connectionState.value is ConnectionState.Connecting) {
// Attempt one retry. Note: the firmware silently drops identical consecutive
// writes (per-connection dedup). If the first want_config_id was received and
@ -291,13 +292,13 @@ class MeshConnectionManagerImpl(
override fun startConfigOnly() {
val action = { packetHandler.sendToRadio(ToRadio(want_config_id = HandshakeConstants.CONFIG_NONCE)) }
startHandshakeStallGuard(1, action)
startHandshakeStallGuard(1, HANDSHAKE_TIMEOUT_STAGE1, action)
action()
}
override fun startNodeInfoOnly() {
val action = { packetHandler.sendToRadio(ToRadio(want_config_id = HandshakeConstants.NODE_INFO_NONCE)) }
startHandshakeStallGuard(2, action)
startHandshakeStallGuard(2, HANDSHAKE_TIMEOUT_STAGE2, action)
action()
}
@ -404,7 +405,14 @@ class MeshConnectionManagerImpl(
*/
private const val PRE_HANDSHAKE_SETTLE_MS = 100L
private val HANDSHAKE_TIMEOUT = 30.seconds
private val HANDSHAKE_TIMEOUT_STAGE1 = 30.seconds
/**
* Stage 2 drains the full node database, which can be significantly larger than Stage 1 config on big meshes.
* 60 s matches the meshtastic-client SDK timeout and avoids premature stall-guard triggers on meshes with 50+
* nodes.
*/
private val HANDSHAKE_TIMEOUT_STAGE2 = 60.seconds
// Shorter window for the retry attempt: if the device genuinely didn't receive the
// first want_config_id the retry completes within a few seconds. Waiting another 30s