diff --git a/deploy/bootstrap/onboard-node.sh b/deploy/bootstrap/onboard-node.sh
index 5fbc27d..00c0264 100755
--- a/deploy/bootstrap/onboard-node.sh
+++ b/deploy/bootstrap/onboard-node.sh
@@ -226,6 +226,10 @@ ExecStart=/usr/local/bin/llmgw agent --config /etc/llmgw/agent.yaml
 KillMode=process
 Restart=on-failure
 RestartSec=2s
+# RDMA pins the buffers it registers, and NCCL registers a great deal: with
+# systemd's default 8 MB lock limit, an engine that drops the capability that
+# lets root ignore it fails its first collective over InfiniBand.
+LimitMEMLOCK=infinity
 StateDirectory=llmgw-agent
 
 [Install]
diff --git a/deploy/systemd/llmgw-agent.service b/deploy/systemd/llmgw-agent.service
index fd52957..75cadfa 100644
--- a/deploy/systemd/llmgw-agent.service
+++ b/deploy/systemd/llmgw-agent.service
@@ -11,6 +11,10 @@ ExecStart=/usr/local/bin/llmgw agent --config /etc/llmgw/agent.yaml
 KillMode=process
 Restart=on-failure
 RestartSec=2s
+# RDMA pins the buffers it registers, and NCCL registers a great deal: with
+# systemd's default 8 MB lock limit, an engine that drops the capability that
+# lets root ignore it fails its first collective over InfiniBand.
+LimitMEMLOCK=infinity
 StateDirectory=llmgw-agent
 
 [Install]
diff --git a/internal/agent/agent.go b/internal/agent/agent.go
index a0f4bdb..4755291 100644
--- a/internal/agent/agent.go
+++ b/internal/agent/agent.go
@@ -118,8 +118,11 @@ type Config struct {
 
 // DefaultConfig returns sensible defaults.
 func DefaultConfig() Config {
+	// No MgmtInterface: normalize finds the one holding the management
+	// address, and falls back to eth0 only when it cannot. Defaulted here, it
+	// was never found — every node said eth0 unless told otherwise, and a node
+	// on ens3 or bond0 had NCCL bootstrap over an interface it does not have.
 	return Config{
-		MgmtInterface:     "eth0",
 		HeartbeatInterval: 5 * time.Second,
 		ReconnectBase:     time.Second,
 		ReconnectMax:      30 * time.Second,
@@ -159,7 +162,7 @@ func (c *Config) normalize() error {
 		c.MgmtInterface = interfaceOf(c.MgmtAddr)
 	}
 	if c.MgmtInterface == "" {
-		c.MgmtInterface = d.MgmtInterface
+		c.MgmtInterface = "eth0"
 	}
 	// The directory downloads land in is always one that is looked in. When
 	// they were two settings, a node could fill its disk with fetched weights
diff --git a/internal/agent/agent_test.go b/internal/agent/agent_test.go
index 9ca6a39..e3bcdd4 100644
--- a/internal/agent/agent_test.go
+++ b/internal/agent/agent_test.go
@@ -813,3 +813,18 @@ func TestAShardUsesThisNodesInterfaceAndRoCEIndex(t *testing.T) {
 		t.Error("an InfiniBand shard was given a GID index")
 	}
 }
+
+func TestTheManagementInterfaceIsFoundNotAssumed(t *testing.T) {
+	// It was defaulted to eth0 before it could be looked for, so it never
+	// was: a node on ens3 or bond0 had NCCL bootstrap over nothing.
+	cfg := DefaultConfig()
+	cfg.Server = "http://127.0.0.1:7443"
+	cfg.NodeID = "n1"
+	cfg.MgmtAddr = "127.0.0.1"
+	if err := cfg.normalize(); err != nil {
+		t.Fatal(err)
+	}
+	if cfg.MgmtInterface == "" || cfg.MgmtInterface == "eth0" {
+		t.Errorf("interface = %q, want the loopback interface holding 127.0.0.1", cfg.MgmtInterface)
+	}
+}
diff --git a/internal/cli/serverinit_cluster.go b/internal/cli/serverinit_cluster.go
index d7046e1..39fa441 100644
--- a/internal/cli/serverinit_cluster.go
+++ b/internal/cli/serverinit_cluster.go
@@ -62,6 +62,10 @@ ExecStart=/usr/local/bin/llmgw agent --config /etc/llmgw/agent.yaml
 KillMode=process
 Restart=on-failure
 RestartSec=2s
+# RDMA pins the buffers it registers, and NCCL registers a great deal: with
+# systemd's default 8 MB lock limit, an engine that drops the capability that
+# lets root ignore it fails its first collective over InfiniBand.
+LimitMEMLOCK=infinity
 StateDirectory=llmgw-agent
 
 [Install]