Merge pull request #18428 from ahrtr/improve_leaseRenew_20240809

Skip leadership check if the etcd instance is active processing heartbeats

server/etcdserver/raft.go

@@ -80,7 +80,9 @@ type toApply struct {
 type raftNode struct {
 	lg *zap.Logger
 
-	tickMu *sync.Mutex
+	tickMu *sync.RWMutex
+	// timestamp of the latest tick
+	latestTickTs time.Time
 	raftNodeConfig
 
 	// a chan to send/receive snapshot
@@ -132,8 +134,9 @@ func newRaftNode(cfg raftNodeConfig) *raftNode {
 	raft.SetLogger(lg)
 	r := &raftNode{
 		lg:             cfg.lg,
-		tickMu:         new(sync.Mutex),
+		tickMu:         new(sync.RWMutex),
 		raftNodeConfig: cfg,
+		latestTickTs:   time.Now(),
 		// set up contention detectors for raft heartbeat message.
 		// expect to send a heartbeat within 2 heartbeat intervals.
 		td:         contention.NewTimeoutDetector(2 * cfg.heartbeat),
@@ -155,9 +158,16 @@ func newRaftNode(cfg raftNodeConfig) *raftNode {
 func (r *raftNode) tick() {
 	r.tickMu.Lock()
 	r.Tick()
+	r.latestTickTs = time.Now()
 	r.tickMu.Unlock()
 }
 
+func (r *raftNode) getLatestTickTs() time.Time {
+	r.tickMu.RLock()
+	defer r.tickMu.RUnlock()
+	return r.latestTickTs
+}
+
 // start prepares and starts raftNode in a new goroutine. It is no longer safe
 // to modify the fields after it has been started.
 func (r *raftNode) start(rh *raftReadyHandler) {

server/etcdserver/server.go

@@ -904,10 +904,26 @@ func (s *EtcdServer) revokeExpiredLeases(leases []*lease.Lease) {
 	})
 }
 
+// isActive checks if the etcd instance is still actively processing the
+// heartbeat message (ticks). It returns false if no heartbeat has been
+// received within 3 * tickMs.
+func (s *EtcdServer) isActive() bool {
+	latestTickTs := s.r.getLatestTickTs()
+	threshold := 3 * time.Duration(s.Cfg.TickMs) * time.Millisecond
+	return latestTickTs.Add(threshold).After(time.Now())
+}
+
 // ensureLeadership checks whether current member is still the leader.
 func (s *EtcdServer) ensureLeadership() bool {
 	lg := s.Logger()
 
+	if s.isActive() {
+		lg.Debug("The member is active, skip checking leadership",
+			zap.Time("latestTickTs", s.r.getLatestTickTs()),
+			zap.Time("now", time.Now()))
+		return true
+	}
+
 	ctx, cancel := context.WithTimeout(s.ctx, s.Cfg.ReqTimeout())
 	defer cancel()
 	if err := s.linearizableReadNotify(ctx); err != nil {

server/etcdserver/server_test.go

@@ -29,6 +29,7 @@ import (
 
 	"github.com/coreos/go-semver/semver"
 	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
 	"go.uber.org/zap"
 	"go.uber.org/zap/zaptest"
 
@@ -1538,3 +1539,45 @@ func TestWaitAppliedIndex(t *testing.T) {
 		})
 	}
 }
+
+func TestIsActive(t *testing.T) {
+	cases := []struct {
+		name                  string
+		tickMs                uint
+		durationSinceLastTick time.Duration
+		expectActive          bool
+	}{
+		{
+			name:                  "1.5*tickMs,active",
+			tickMs:                100,
+			durationSinceLastTick: 150 * time.Millisecond,
+			expectActive:          true,
+		},
+		{
+			name:                  "2*tickMs,active",
+			tickMs:                200,
+			durationSinceLastTick: 400 * time.Millisecond,
+			expectActive:          true,
+		},
+		{
+			name:                  "4*tickMs,not active",
+			tickMs:                150,
+			durationSinceLastTick: 600 * time.Millisecond,
+			expectActive:          false,
+		},
+	}
+
+	for _, tc := range cases {
+		s := EtcdServer{
+			Cfg: config.ServerConfig{
+				TickMs: tc.tickMs,
+			},
+			r: raftNode{
+				tickMu:       new(sync.RWMutex),
+				latestTickTs: time.Now().Add(-tc.durationSinceLastTick),
+			},
+		}
+
+		require.Equal(t, tc.expectActive, s.isActive())
+	}
+}