libn/networkdb: prevent spurious rejoins in tests

corhere · corhere · commit 1e1be54d3e7c · 2025-07-07T14:09:01.000-04:00
The rejoinClusterBootStrap periodic task rejoins with the bootstrap
nodes if none of them are members of the cluster. It correlates the
cluster nodes with the bootstrap list by comparing IP addresses,
ignoring ports. In normal operation this works out fine as every node
has a unique IP address, but in unit tests every node listens on a
distinct port of 127.0.0.1. This situation causes the check to
incorrectly filter out all nodes from the list, mistaking them for the
local node.

Filter out the local node using pointer equality of the *node to avoid
any ambiguity. Correlate the remote nodes by IP:port so that the check
behaves the same in tests and in production.

Signed-off-by: Cory Snider &lt;csnider@mirantis.com&gt;
diff --git a/libnetwork/networkdb/cluster.go b/libnetwork/networkdb/cluster.go
@@ -10,6 +10,7 @@ import (
 	"math/big"
 	rnd "math/rand"
 	"net"
+	"net/netip"
 	"strings"
 	"time"
 
@@ -296,17 +297,22 @@ func (nDB *NetworkDB) rejoinClusterBootStrap() {
 	bootStrapIPs := make([]string, 0, len(nDB.bootStrapIP))
 	for _, bootIP := range nDB.bootStrapIP {
 		// bootstrap IPs are usually IP:port from the Join
-		var bootstrapIP net.IP
-		ipStr, _, err := net.SplitHostPort(bootIP)
+		bootstrapIP, err := netip.ParseAddrPort(bootIP)
 		if err != nil {
-			// try to parse it as an IP with port
+			// try to parse it as an IP without port
 			// Note this seems to be the case for swarm that do not specify any port
-			ipStr = bootIP
+			addr, err := netip.ParseAddr(bootIP)
+			if err == nil {
+				bootstrapIP = netip.AddrPortFrom(addr, uint16(nDB.config.BindPort))
+			}
 		}
-		bootstrapIP = net.ParseIP(ipStr)
-		if bootstrapIP != nil {
+		if bootstrapIP.IsValid() {
 			for _, node := range nDB.nodes {
-				if node.Addr.Equal(bootstrapIP) && !node.Addr.Equal(myself.Addr) {
+				if node == myself {
+					continue
+				}
+				nodeIP, _ := netip.AddrFromSlice(node.Addr)
+				if bootstrapIP == netip.AddrPortFrom(nodeIP, node.Port) {
 					// One of the bootstrap nodes (and not myself) is part of the cluster, return
 					nDB.RUnlock()
 					return
