Use same MTU as uplink for bridge port

In bridging mode (on Linux), when moving the physical adapter to the bridge, we explictly set the MTU for the bridge port to the same value as for the physical adapter. Without this change, the MTU may default to a different (lower) value if some existing container ports have a lower MTU value. For example, this occurs when first installing Antrea in encap mode, then re-installing Antrea in noEncap mode with bridging mode enabled. We also do some minor documentation updates to indicate to users that they should consider restarting existing workloads when updating the Antrea datapath configuration. Fixes #6456 Signed-off-by: Antonin Bas <antonin.bas@broadcom.com>
antrea-io · Aug 2, 2024 · 0182d3f · 0182d3f
1 parent f5a9a2b
commit 0182d3f
Show file tree

Hide file tree

Showing 12 changed files with 39 additions and 12 deletions.
diff --git a/build/charts/antrea/README.md b/build/charts/antrea/README.md
@@ -84,7 +84,7 @@ Kubernetes: `>= 1.19.0-0`
 | controller.selfSignedCert | bool | `true` | Indicates whether to use auto-generated self-signed TLS certificates. If false, a Secret named "antrea-controller-tls" must be provided with the following keys: ca.crt, tls.crt, tls.key. |
 | controller.tolerations | list | `[{"key":"CriticalAddonsOnly","operator":"Exists"},{"effect":"NoSchedule","key":"node-role.kubernetes.io/master"},{"effect":"NoSchedule","key":"node-role.kubernetes.io/control-plane"},{"effect":"NoExecute","key":"node.kubernetes.io/unreachable","operator":"Exists","tolerationSeconds":0}]` | Tolerations for the antrea-controller Pod. |
 | controllerImage | object | `{"pullPolicy":"IfNotPresent","repository":"antrea/antrea-controller-ubuntu","tag":""}` | Container image to use for the antrea-controller component. |
-| defaultMTU | int | `0` | Default MTU to use for the host gateway interface and the network interface of each Pod. By default, antrea-agent will discover the MTU of the Node's primary interface and adjust it to accommodate for tunnel encapsulation overhead if applicable. |
+| defaultMTU | int | `0` | Default MTU to use for the host gateway interface and the network interface of each Pod. By default, antrea-agent will discover the MTU of the Node's primary interface and adjust it to accommodate for tunnel encapsulation overhead if applicable. If the MTU is updated, the new value will only be applied to new workloads. |
 | disableTXChecksumOffload | bool | `false` | Disable TX checksum offloading for container network interfaces. It's supposed to be set to true when the datapath doesn't support TX checksum offloading, which causes packets to be dropped due to bad checksum. It affects Pods running on Linux Nodes only. |
 | dnsServerOverride | string | `""` | Address of DNS server, to override the kube-dns Service. It's used to resolve hostnames in a FQDN policy. |
 | egress.exceptCIDRs | list | `[]` | CIDR ranges to which outbound Pod traffic will not be SNAT'd by Egresses. |

diff --git a/build/charts/antrea/conf/antrea-agent.conf b/build/charts/antrea/conf/antrea-agent.conf
@@ -175,6 +175,7 @@ disableTXChecksumOffload: {{ .Values.disableTXChecksumOffload }}
 # Default MTU to use for the host gateway interface and the network interface of each Pod.
 # If omitted, antrea-agent will discover the MTU of the Node's primary interface and
 # also adjust MTU to accommodate for tunnel encapsulation overhead (if applicable).
+# If the MTU is updated, the new value will only be applied to new workloads.
 defaultMTU: {{ .Values.defaultMTU }}
 
 # packetInRate defines the OVS controller packet rate limits for different

diff --git a/build/charts/antrea/values.yaml b/build/charts/antrea/values.yaml
@@ -71,7 +71,8 @@ multicast:
 # -- Default MTU to use for the host gateway interface and the network interface
 # of each Pod. By default, antrea-agent will discover the MTU of the Node's
 # primary interface and adjust it to accommodate for tunnel encapsulation
-# overhead if applicable.
+# overhead if applicable. If the MTU is updated, the new value will only be
+# applied to new workloads.
 defaultMTU: 0
 
 # -- packetInRate defines the OVS controller packet rate limits for different

diff --git a/build/yamls/antrea-aks.yml b/build/yamls/antrea-aks.yml
@@ -3891,6 +3891,7 @@ data:
     # Default MTU to use for the host gateway interface and the network interface of each Pod.
     # If omitted, antrea-agent will discover the MTU of the Node's primary interface and
     # also adjust MTU to accommodate for tunnel encapsulation overhead (if applicable).
+    # If the MTU is updated, the new value will only be applied to new workloads.
     defaultMTU: 0
 
     # packetInRate defines the OVS controller packet rate limits for different
@@ -5125,7 +5126,7 @@ spec:
         kubectl.kubernetes.io/default-container: antrea-agent
         # Automatically restart Pods with a RollingUpdate if the ConfigMap changes
         # See https://helm.sh/docs/howto/charts_tips_and_tricks/#automatically-roll-deployments
-        checksum/config: cce7d6644fb552607ebeda9bf30a5fafa871dd4382afc609500fcb493b61768c
+        checksum/config: f950d38c3e5f05b4e6290aae92fc46eeda9126a68a0ed6b88eee7f5c4c6fb491
       labels:
         app: antrea
         component: antrea-agent
@@ -5363,7 +5364,7 @@ spec:
       annotations:
         # Automatically restart Pod if the ConfigMap changes
         # See https://helm.sh/docs/howto/charts_tips_and_tricks/#automatically-roll-deployments
-        checksum/config: cce7d6644fb552607ebeda9bf30a5fafa871dd4382afc609500fcb493b61768c
+        checksum/config: f950d38c3e5f05b4e6290aae92fc46eeda9126a68a0ed6b88eee7f5c4c6fb491
       labels:
         app: antrea
         component: antrea-controller

diff --git a/build/yamls/antrea-eks.yml b/build/yamls/antrea-eks.yml
@@ -3891,6 +3891,7 @@ data:
     # Default MTU to use for the host gateway interface and the network interface of each Pod.
     # If omitted, antrea-agent will discover the MTU of the Node's primary interface and
     # also adjust MTU to accommodate for tunnel encapsulation overhead (if applicable).
+    # If the MTU is updated, the new value will only be applied to new workloads.
     defaultMTU: 0
 
     # packetInRate defines the OVS controller packet rate limits for different
@@ -5125,7 +5126,7 @@ spec:
         kubectl.kubernetes.io/default-container: antrea-agent
         # Automatically restart Pods with a RollingUpdate if the ConfigMap changes
         # See https://helm.sh/docs/howto/charts_tips_and_tricks/#automatically-roll-deployments
-        checksum/config: cce7d6644fb552607ebeda9bf30a5fafa871dd4382afc609500fcb493b61768c
+        checksum/config: f950d38c3e5f05b4e6290aae92fc46eeda9126a68a0ed6b88eee7f5c4c6fb491
       labels:
         app: antrea
         component: antrea-agent
@@ -5364,7 +5365,7 @@ spec:
       annotations:
         # Automatically restart Pod if the ConfigMap changes
         # See https://helm.sh/docs/howto/charts_tips_and_tricks/#automatically-roll-deployments
-        checksum/config: cce7d6644fb552607ebeda9bf30a5fafa871dd4382afc609500fcb493b61768c
+        checksum/config: f950d38c3e5f05b4e6290aae92fc46eeda9126a68a0ed6b88eee7f5c4c6fb491
       labels:
         app: antrea
         component: antrea-controller

diff --git a/build/yamls/antrea-gke.yml b/build/yamls/antrea-gke.yml
@@ -3891,6 +3891,7 @@ data:
     # Default MTU to use for the host gateway interface and the network interface of each Pod.
     # If omitted, antrea-agent will discover the MTU of the Node's primary interface and
     # also adjust MTU to accommodate for tunnel encapsulation overhead (if applicable).
+    # If the MTU is updated, the new value will only be applied to new workloads.
     defaultMTU: 0
 
     # packetInRate defines the OVS controller packet rate limits for different
@@ -5125,7 +5126,7 @@ spec:
         kubectl.kubernetes.io/default-container: antrea-agent
         # Automatically restart Pods with a RollingUpdate if the ConfigMap changes
         # See https://helm.sh/docs/howto/charts_tips_and_tricks/#automatically-roll-deployments
-        checksum/config: e30c52c9fcb04d362d018e846cf72dc633c5e891e02b3ebb87fab4d7ee08e15a
+        checksum/config: 5bab13c466e83f8a14191bfb9aad49229945c442808ea135f80cafe5e21be5f3
       labels:
         app: antrea
         component: antrea-agent
@@ -5361,7 +5362,7 @@ spec:
       annotations:
         # Automatically restart Pod if the ConfigMap changes
         # See https://helm.sh/docs/howto/charts_tips_and_tricks/#automatically-roll-deployments
-        checksum/config: e30c52c9fcb04d362d018e846cf72dc633c5e891e02b3ebb87fab4d7ee08e15a
+        checksum/config: 5bab13c466e83f8a14191bfb9aad49229945c442808ea135f80cafe5e21be5f3
       labels:
         app: antrea
         component: antrea-controller

diff --git a/build/yamls/antrea-ipsec.yml b/build/yamls/antrea-ipsec.yml
@@ -3904,6 +3904,7 @@ data:
     # Default MTU to use for the host gateway interface and the network interface of each Pod.
     # If omitted, antrea-agent will discover the MTU of the Node's primary interface and
     # also adjust MTU to accommodate for tunnel encapsulation overhead (if applicable).
+    # If the MTU is updated, the new value will only be applied to new workloads.
     defaultMTU: 0
 
     # packetInRate defines the OVS controller packet rate limits for different
@@ -5138,7 +5139,7 @@ spec:
         kubectl.kubernetes.io/default-container: antrea-agent
         # Automatically restart Pods with a RollingUpdate if the ConfigMap changes
         # See https://helm.sh/docs/howto/charts_tips_and_tricks/#automatically-roll-deployments
-        checksum/config: 73a49a9a8508cc8fb94eb2c770bb3589e68d9623327231943cba60a48716568a
+        checksum/config: 7212fbcdde8fe4be00f31ebbbcd7b03a7335666b4af245eed7dac1ba9e99118c
         checksum/ipsec-secret: d0eb9c52d0cd4311b6d252a951126bf9bea27ec05590bed8a394f0f792dcb2a4
       labels:
         app: antrea
@@ -5420,7 +5421,7 @@ spec:
       annotations:
         # Automatically restart Pod if the ConfigMap changes
         # See https://helm.sh/docs/howto/charts_tips_and_tricks/#automatically-roll-deployments
-        checksum/config: 73a49a9a8508cc8fb94eb2c770bb3589e68d9623327231943cba60a48716568a
+        checksum/config: 7212fbcdde8fe4be00f31ebbbcd7b03a7335666b4af245eed7dac1ba9e99118c
       labels:
         app: antrea
         component: antrea-controller

diff --git a/build/yamls/antrea.yml b/build/yamls/antrea.yml
@@ -3891,6 +3891,7 @@ data:
     # Default MTU to use for the host gateway interface and the network interface of each Pod.
     # If omitted, antrea-agent will discover the MTU of the Node's primary interface and
     # also adjust MTU to accommodate for tunnel encapsulation overhead (if applicable).
+    # If the MTU is updated, the new value will only be applied to new workloads.
     defaultMTU: 0
 
     # packetInRate defines the OVS controller packet rate limits for different
@@ -5125,7 +5126,7 @@ spec:
         kubectl.kubernetes.io/default-container: antrea-agent
         # Automatically restart Pods with a RollingUpdate if the ConfigMap changes
         # See https://helm.sh/docs/howto/charts_tips_and_tricks/#automatically-roll-deployments
-        checksum/config: 20130c4a5dbfeec75182bc3053288f64c06d0350b34c86675ac88d5961c47853
+        checksum/config: 616b79b8deedba740ff992ca870b346c64c1dde5e3381436dc2cb24c0bd98ead
       labels:
         app: antrea
         component: antrea-agent
@@ -5361,7 +5362,7 @@ spec:
       annotations:
         # Automatically restart Pod if the ConfigMap changes
         # See https://helm.sh/docs/howto/charts_tips_and_tricks/#automatically-roll-deployments
-        checksum/config: 20130c4a5dbfeec75182bc3053288f64c06d0350b34c86675ac88d5961c47853
+        checksum/config: 616b79b8deedba740ff992ca870b346c64c1dde5e3381436dc2cb24c0bd98ead
       labels:
         app: antrea
         component: antrea-controller

diff --git a/docs/noencap-hybrid-modes.md b/docs/noencap-hybrid-modes.md
@@ -34,6 +34,13 @@ spec:
               value: "true"
 ```
 
+Note that changing the traffic mode in an existing cluster, where Antrea is
+currently installed or was previously installed, may require restarting existing
+workloads. In particular, the choice of traffic mode has an impact on the MTU
+value used for Pod network interfaces. When changing the traffic mode from
+`NoEncap` to `Encap`, existing workloads should be restarted, so that new
+network interfaces with a lower MTU value can be created.
+
 ## Hybrid Mode
 
 Let us start from `Hybrid` mode which is simpler to configure. `Hybrid` mode

diff --git a/pkg/agent/agent_linux.go b/pkg/agent/agent_linux.go
@@ -129,11 +129,16 @@ func (i *Initializer) ConnectUplinkToOVSBridge() error {
 	externalIDs := map[string]interface{}{
 		interfacestore.AntreaInterfaceTypeKey: interfacestore.AntreaHost,
 	}
+	// We request the same MTU for the bridge interface as for the uplink adapter. If we don't,
+	// OVS will default to the lowest MTU among all existing bridge ports, including container
+	// ports. There may be some existing workloads with a lower MTU, and using that lower value
+	// may impact host connectivity.
 	bridgedUplinkName, exists, err := util.PrepareHostInterfaceConnection(
 		i.ovsBridgeClient,
 		uplinkNetConfig.Name,
 		int32(i.nodeConfig.HostInterfaceOFPort),
 		externalIDs,
+		i.nodeConfig.NodeTransportInterfaceMTU,
 	)
 	if err != nil {
 		return err

diff --git a/pkg/agent/secondarynetwork/init_linux.go b/pkg/agent/secondarynetwork/init_linux.go
@@ -48,6 +48,7 @@ func (c *Controller) Initialize() error {
 				map[string]interface{}{
 					interfacestore.AntreaInterfaceTypeKey: interfacestore.AntreaHost,
 				},
+				0, // do not request a specific MTU
 			)
 			if err != nil {
 				return err

diff --git a/pkg/agent/util/net_linux.go b/pkg/agent/util/net_linux.go
@@ -412,6 +412,7 @@ func PrepareHostInterfaceConnection(
 	ifaceName string,
 	ifaceOFPort int32,
 	externalIDs map[string]interface{},
+	mtu int,
 ) (string, bool, error) {
 	bridgedName := GenerateUplinkInterfaceName(ifaceName)
 	// If the port already exists, just return.
@@ -453,6 +454,12 @@ func PrepareHostInterfaceConnection(
 		return "", false, fmt.Errorf("failed to set link up: %v", err)
 	}
 
+	if mtu > 0 {
+		if err := bridge.SetInterfaceMTU(ifaceName, mtu); err != nil {
+			return "", false, fmt.Errorf("failed to set bridge interface MTU: %w", err)
+		}
+	}
+
 	// Check if interface is configured with an IPv6 address: if it is, we need to ensure that IPv6
 	// is enabled on the OVS internal port as we need to move all IP addresses over.
 	for _, ip := range ifaceIPs {