fix connection retry delay calculation logic
The delay d(n) for the nth retry was
d(1) = rand(initial_interval)
d(n+1) = d(n) + rand(d(n))
There are two problem with this:
1) The entire sequence is dominated by the random value for d(1). If
this is a small value, lots of retries at short interval ensue. In
extremis, if d(1) is 0, indefinite immediate retries would ensue.
2) The delay is not a true exponential backoff; the upper bound only
increases exponentially *probabilistically*.
The new algorithm calculates
d(n) = random_value in range [i-i/2,i+i/2],
where i = initial_interval * 1.5^(n-1).
Thus d(1) is at least initial_interval/2, and successive values are
independent of previous values, forming a true exponential sequence of
intervals bounds between which the retry delay is chosen randomly.
Due to the change in algorithm we reduce...
- the initial interval from 5s to 2s. Recall that previously d(1) was
in the range [0,initial_interval=5s]. It is now [2-2/2=1s,2+2/2=3s].
- the max interval from 10 minutes to 6. Previously, once that was
reached, it would stay exactly there. It is now randomly chosen in
the range [6-6/2=3m,6+6/2=9min].
Thus previously delays would range from 0 to 10 minutes, now they
range from 1s to 9 minutes.
Fixes #412.
This commit is contained in:
1 parent
d909a86fb0
commit
fe5102580d
2 files changed
+12
-10
No files matched your search
@@ -34,7 +34,7 @@ Router:
|
||||
the known locations of peers as they're discovered and is informed
|
||||
when connections we have made die. It proactively tries to create
|
||||
connections to remote peers we're not connected to using a random
|
||||
binary exponential backoff to regulate the period between connection
|
||||
exponential backoff to regulate the period between connection
|
||||
attempts.
|
||||
|
||||
- Local Peer
|
||||
|
||||
@@ -10,8 +10,8 @@ import (
|
||||
)
|
||||
|
||||
const (
|
||||
InitialInterval = 5 * time.Second
|
||||
MaxInterval = 10 * time.Minute
|
||||
InitialInterval = 2 * time.Second
|
||||
MaxInterval = 6 * time.Minute
|
||||
)
|
||||
|
||||
type peerAddrs map[string]*net.TCPAddr
|
||||
@@ -30,7 +30,7 @@ type Target struct {
|
||||
attempting bool // are we currently attempting to connect there?
|
||||
lastError error // reason for disconnection last time
|
||||
tryAfter time.Time // next time to try this address
|
||||
tryInterval time.Duration // backoff time on next failure
|
||||
tryInterval time.Duration // retry delay on next failure
|
||||
}
|
||||
|
||||
type ConnectionMakerAction func() bool
|
||||
@@ -304,14 +304,16 @@ func (cm *ConnectionMaker) attemptConnection(address string, acceptNewPeer bool)
|
||||
}
|
||||
|
||||
func tryImmediately() (time.Time, time.Duration) {
|
||||
interval := time.Duration(rand.Int63n(int64(InitialInterval)))
|
||||
return time.Now(), interval
|
||||
return time.Now(), InitialInterval
|
||||
}
|
||||
|
||||
// The delay at the nth retry is a random value in the range
|
||||
// [i-i/2,i+i/2], where i = InitialInterval * 1.5^(n-1).
|
||||
func tryAfter(interval time.Duration) (time.Time, time.Duration) {
|
||||
interval += time.Duration(rand.Int63n(int64(interval)))
|
||||
if interval > MaxInterval {
|
||||
interval = MaxInterval
|
||||
delay := interval/2 + time.Duration(rand.Int63n(int64(interval)))
|
||||
nextInterval := interval * 3 / 2
|
||||
if nextInterval > MaxInterval {
|
||||
nextInterval = MaxInterval
|
||||
}
|
||||
return time.Now().Add(interval), interval
|
||||
return time.Now().Add(delay), nextInterval
|
||||
}
|
||||
Reference in new issue
Block a user