mirror of
https://github.com/netbirdio/netbird.git
synced 2026-08-24 16:41:30 +02:00
Three pieces, each verified on Android across WiFi/cellular switches: - A sweep-aware backoff wrapper: the first retry after a disconnect that follows a recent network-change mark comes after 200ms instead of the randomized [0..1.6s] interval. Any other failure keeps the unchanged spread, so the clients of a restarted server still scatter their reconnects. - The retry sleep wakes on OS network availability transitions (nbgrpc.Retry): a disconnect that precedes the offline flag by a few milliseconds no longer sleeps blindly through the recovery - the loop parks on the netstate gate and resumes the moment the network returns. - The connection state is re-checked after WaitForStateChange: a dial settling in Ready proceeds immediately instead of burning another backoff round on an already-usable channel. Measured after a network switch: management and signal recover in 270-470ms deterministically, down from a 312-1593ms lottery.
40 lines
767 B
Go
40 lines
767 B
Go
package netsweep
|
|
|
|
import (
|
|
"time"
|
|
|
|
"github.com/cenkalti/backoff/v4"
|
|
|
|
"github.com/netbirdio/netbird/client/netstate"
|
|
)
|
|
|
|
const quickRetryDelay = 200 * time.Millisecond
|
|
|
|
type quickRetryBackoff struct {
|
|
backoff.BackOff
|
|
sweeper *Sweeper
|
|
netState *netstate.State
|
|
used bool
|
|
}
|
|
|
|
func newQuickRetryBackoff(bo backoff.BackOff, sweeper *Sweeper, netState *netstate.State) *quickRetryBackoff {
|
|
return &quickRetryBackoff{
|
|
BackOff: bo,
|
|
sweeper: sweeper,
|
|
netState: netState,
|
|
}
|
|
}
|
|
|
|
func (b *quickRetryBackoff) NextBackOff() time.Duration {
|
|
if !b.used && b.sweeper.markedRecently() && b.netState.IsOnline() {
|
|
b.used = true
|
|
return quickRetryDelay
|
|
}
|
|
return b.BackOff.NextBackOff()
|
|
}
|
|
|
|
func (b *quickRetryBackoff) Reset() {
|
|
b.used = false
|
|
b.BackOff.Reset()
|
|
}
|