Routine-local conntrack cache (#391)

Previously, every packet we see gets a lock on the conntrack table and updates it. When running with multiple routines, this can cause heavy lock contention and limit our ability for the threads to run independently. This change caches reads from the conntrack table for a very short period of time to reduce this lock contention. This cache will currently default to disabled unless you are running with multiple routines, in which case the default cache delay will be 1 second. This means that entries in the conntrack table may be up to 1 second out of date and remain in a routine local cache for up to 1 second longer than the global table.

Instead of calling time.Now() for every packet, this cache system relies on a tick thread that updates the current cache "version" each tick. Every packet we check if the cache version is out of date, and reset the cache if so.

firewall.go

@@ -12,6 +12,7 @@ import (
 	"strconv"
 	"strings"
 	"sync"
+	"sync/atomic"
 	"time"
 
 	"github.com/rcrowley/go-metrics"
@@ -372,9 +373,9 @@ var ErrNoMatchingRule = errors.New("no matching rule in firewall table")
 
 // Drop returns an error if the packet should be dropped, explaining why. It
 // returns nil if the packet should not be dropped.
-func (f *Firewall) Drop(packet []byte, fp FirewallPacket, incoming bool, h *HostInfo, caPool *cert.NebulaCAPool) error {
+func (f *Firewall) Drop(packet []byte, fp FirewallPacket, incoming bool, h *HostInfo, caPool *cert.NebulaCAPool, localCache ConntrackCache) error {
 	// Check if we spoke to this tuple, if we did then allow this packet
-	if f.inConns(packet, fp, incoming, h, caPool) {
+	if f.inConns(packet, fp, incoming, h, caPool, localCache) {
 		return nil
 	}
 
@@ -426,7 +427,12 @@ func (f *Firewall) EmitStats() {
 	metrics.GetOrRegisterGauge("firewall.rules.version", nil).Update(int64(f.rulesVersion))
 }
 
-func (f *Firewall) inConns(packet []byte, fp FirewallPacket, incoming bool, h *HostInfo, caPool *cert.NebulaCAPool) bool {
+func (f *Firewall) inConns(packet []byte, fp FirewallPacket, incoming bool, h *HostInfo, caPool *cert.NebulaCAPool, localCache ConntrackCache) bool {
+	if localCache != nil {
+		if _, ok := localCache[fp]; ok {
+			return true
+		}
+	}
 	conntrack := f.Conntrack
 	conntrack.Lock()
 
@@ -494,6 +500,10 @@ func (f *Firewall) inConns(packet []byte, fp FirewallPacket, incoming bool, h *H
 
 	conntrack.Unlock()
 
+	if localCache != nil {
+		localCache[fp] = struct{}{}
+	}
+
 	return true
 }
 
@@ -923,3 +933,54 @@ func (f *Firewall) checkTCPRTT(c *conn, p []byte) bool {
 	c.Seq = 0
 	return true
 }
+
+// ConntrackCache is used as a local routine cache to know if a given flow
+// has been seen in the conntrack table.
+type ConntrackCache map[FirewallPacket]struct{}
+
+type ConntrackCacheTicker struct {
+	cacheV    uint64
+	cacheTick uint64
+
+	cache ConntrackCache
+}
+
+func NewConntrackCacheTicker(d time.Duration) *ConntrackCacheTicker {
+	if d == 0 {
+		return nil
+	}
+
+	c := &ConntrackCacheTicker{
+		cache: ConntrackCache{},
+	}
+
+	go c.tick(d)
+
+	return c
+}
+
+func (c *ConntrackCacheTicker) tick(d time.Duration) {
+	for {
+		time.Sleep(d)
+		atomic.AddUint64(&c.cacheTick, 1)
+	}
+}
+
+// Get checks if the cache ticker has moved to the next version before returning
+// the map. If it has moved, we reset the map.
+func (c *ConntrackCacheTicker) Get() ConntrackCache {
+	if c == nil {
+		return nil
+	}
+	if tick := atomic.LoadUint64(&c.cacheTick); tick != c.cacheV {
+		c.cacheV = tick
+		if ll := len(c.cache); ll > 0 {
+			if l.GetLevel() == logrus.DebugLevel {
+				l.WithField("len", ll).Debug("resetting conntrack cache")
+			}
+			c.cache = make(ConntrackCache, ll)
+		}
+	}
+
+	return c.cache
+}