Recommended Free Tools
If a pod can reach destinations on its own SR-IOV rail but not across rails, first check whether the intended interface and address exist, then inspect the pod’s route table, and only then investigate gateways and external return routing. A missing route is a symptom to diagnose—not a reason to add a second default route blindly. In Multus pods, the default route typically remains on eth0, the cluster-wide default network, unless the pod’s network configuration changes it, as the Multus CNI documentation explains.
Understand which part of the network path is failing
SR-IOV networking in Kubernetes involves separate components: the device plugin exposes virtual functions (VFs) as node resources, SR-IOV CNI configures an assigned VF, and Multus coordinates attaching the secondary network to the pod. An Oracle OKE tutorial illustrates those roles in an OKE deployment; its implementation details are specific to that environment.
A secondary interface being attached does not by itself mean traffic for every destination will use it. The pod’s routes determine the outbound interface and next hop, while the surrounding network must carry traffic onward and route replies back. The Multus documentation says: “Typically, the default route for a pod will route traffic over the eth0 and therefore over the cluster-wide default network.”
Check the pod from attachment to route table
Run the checks below against the affected pod and its node. Adapt namespaces, labels, and access commands to your cluster: the Multus log command shown here is an example, not a universal selector.
The Tool Desk
Outbyte PC Repair FREEClear out junk files and repair common Windows errorsFree Scan →Outbyte Driver Updater FREEFix the driver behind crashes, sound loss and screen glitchesFind Drivers →#1 Best Overall
- Equipped with Intel’s X710 Ethernet Controller
- Dual 10GbE (10G/5G/2.5G/1G/100M) ports allows connecting to multiple high speed networking devices
- PCIe Gen 3 x4 (compatible with PCIe x4, x1, up to x4 slots are recommended)
- Supports Port Trunking to combine both ports to achieve up to 20 Gbps transfer speeds for accelerating file sharing and intensive data transfer
- Supports SR-IOV and iSCSI to greatly boosts network efficiency and is ideal for I/O-intensive and latency-sensitive virtualization applications and data centers
- Check pod events and node resources:
kubectl describe pod <pod>andkubectl describe node <node>. Look for attachment errors and whether the node advertises the expected allocatable SR-IOV resource. - Inspect Multus logs if attachment failed:
kubectl logs -l app=multus -n kube-system. Use the actual namespace and labels for your installation. The SR-IOV Network Operator troubleshooting guide recommends checking pod events, Multus logs, node resources, and the NetworkAttachmentDefinition (NAD) configuration. - Confirm interfaces and addresses inside the pod:
kubectl exec <pod> -- ip link showandkubectl exec <pod> -- ip addr show. Identify the interface and address expected for the rail in question. - Inspect route selection:
kubectl exec <pod> -- ip route. Record the matching destination prefix, next hop, and outgoing interface for the failed destination. Compare them with the source and destination addresses of the failing flow.
A successful pod start alone does not confirm that the intended IPAM route was installed.
Use the observed symptom to choose the next check
| What you find | Where to investigate next |
|---|---|
| The SR-IOV interface or its address is absent. | Check VF allocation and node resources, pod events, Multus logs, and the NAD attachment and IPAM configuration. |
| The interface and address exist, but the route for the destination is absent. | Inspect the NAD’s .spec.config, especially its IPAM type and route and gateway fields. Confirm that the selected IPAM plugin supports the configuration. |
| The expected route exists, but packets still fail. | Check whether the next-hop gateway is reachable on that rail, whether the VLAN and VF connectivity match the deployment, and whether routers have a return path to the pod subnet. |
This is a troubleshooting distinction based on the roles of the components and the documented configuration model, not a guarantee about every cluster topology. The operator troubleshooting guide is useful for attachment and resource failures; external network reachability must also be verified in the target environment.
Rank #2
- 【Controller】: 25GbE PCI-E NIC with Original Mellanox ConnectX-4 Lx controller, which provide true hardware-based I/O isolation with unmatched scalability and efficiency, achieving the most cost-effective and flexible solution for Web 2.0, cloud, data analytics, database, and storage platforms.
- 【Data Rate】:Dual SFP28 Ports(1GbE/10GbE/25GbE) let you connect to network cable for meeting the demands of data center environments.PCIe v3.0 (8.0GT/s) x8(Compatible with 2.0/1.1); X8/X16 Lane.
- 【Technical Support】:iPXE, DPDK, iSCSI, TCP/IP, UDP/IP, Jumbo Frames, RDMA（RoCE v1, RoCE V2）,ASAP², VMDq, SR-IOV, RSS, IPsec.
- 【Supported Operating Systems】:Windows; Windows Server; Linux Stable Kernel version; Ubuntu; Vmware ESXi; Citrix XenServer; Deepin; RHEL/CENTOS; Freebsd; OFED AND WINOF-2; Mikrotik; Debian; BCLINUX; ALIOS; Euler; KYLIN; etc.
- 【I/O virtualization, multi-VM support】：SR-IOV technology enables efficient management of I/O resources of virtual machines by sharing physical resources. And Infiniband technology fully meets the needs of high bandwidth and low latency in big data, its aggregation on virtual I/O and flat network architecture provide a huge pipeline that can be dynamically distributed on demand to improve availability and load balancing.
Check the NAD’s IPAM route and gateway
When the interface and address are present but the relevant route is not, inspect the NAD’s .spec.config and verify that the configured route and gateway are inside the IPAM object. The SR-IOV CNI documentation shows this illustrative configuration:
{
"type": "sriov",
"cniVersion": "0.3.1",
"name": "sriov-network",
"ipam": {
"type": "host-local",
"subnet": "10.56.217.0/24",
"routes": [{ "dst": "0.0.0.0/0" }],
"gateway": "10.56.217.1"
}
}The subnet, gateway, and default route above are documentation examples—not production values or a recommended multi-rail design. Use the address plan for your network and check the syntax supported by the IPAM plugin actually configured in the NAD. A configured route only selects an outbound path; it does not establish that the gateway, rail, or remote return path works.
Crashes, No Sound, or Screen Glitches?
Random freezes, missing sound and display glitches usually trace back to one bad driver. Find and replace yours safely.Free scan · under a minutePC Slower Than It Used to Be?
A free scan shows the junk files, broken settings and background clutter dragging Windows down - then fixes them in one click.Free scan · Windows 10 & 11Rank #3
- 【Controller】:10GbE PCI-E NIC with Original Intel ELX550AT2 controller, which supports single-root I/O virtualization and improves server stability.
- 【Data Rate】:Dual copper RJ45 ports(100MbE/1GbE/2.5GbE/5GbE/10GbE) let you connect to network cable for meeting the demands of data center environments.PCIe v3.0 (8.0GT/s) x4; (Compatible with 1.1/2.0), X4/X8/X16 Lane.⭐If the X550 NIC cannot negotiate to 2.5G/5G automatically, please try configuring it to 2.5G/5G manually, or seek assistance from customer support.⭐
- 【Technical Support】:On-chip QoS and Traffic management; FPP; Load balancing on multiple CPUs; VMDq; PCI-SIG* SR-IOV; Intel Data Directl/O Technology; TCP checksum offloading capabilities; iSCSI,FCoE,NFS; Jumbo Frames;PXE;DPDK;DCB;Auto-MDIX.
- 【Supported OS Online NVM Firmware Update】：Equipped with Intel official NVM Update Utility, this X550-T2 card enables in-system firmware refresh under Windows, Linux, VMware ESXi without entering BIOS or bootable USB drive. You can batch upgrade multiple adapters remotely, minimize business downtime and cut manual maintenance workload for data center servers.
- 【Supported Operating Systems】: Windows, Windows Server, Linux*RHEL, SUSE, Ubuntu, FreeBSD, Vmware ESX/ESXi, UEFI, WinPE, etc.
Choose a route that matches the intended traffic
Do not copy the example’s 0.0.0.0/0 route onto every rail without checking the design. A default route covers all destinations that do not have a more-specific match, and competing defaults or overlapping prefixes can change which interface carries traffic. The appropriate route depends on the destination ranges, intended gateway, and how cluster traffic should use the primary network. Confirm the behavior in your deployed IPAM and CNI versions; the cited examples do not prescribe a universal multi-rail policy.
- Destination coverage: Check that the route covers the failing destination and does not unintentionally overlap another rail’s prefix.
- Gateway reachability: Confirm that the next-hop address is reachable on the interface and rail where the route sends traffic.
- Default-network behavior: Account for traffic that should continue to use the primary
eth0network, including cluster services and egress. - Forward and return paths: Verify that the external network can route replies back to the pod subnet, rather than assuming a pod-side route is sufficient.
- Configuration support: Confirm the route and gateway syntax against the actual IPAM plugin and Kubernetes/CNI release in use.
Apply the narrowest fix supported by the evidence
- If the interface or address is missing, investigate VF allocation, device-plugin resources, Multus events and logs, and the NAD before changing routes.
- If the interface and address exist but the destination route is missing, correct the relevant IPAM route or gateway in the NAD, using syntax supported by the selected IPAM plugin.
- If the route exists but traffic fails, test next-hop reachability and ask the network team to verify VLAN or rail connectivity and return routing.
Workload recreation or restart requirements depend on the cluster’s CNI and operator workflow; there is no universal rollout procedure established by the cited documentation.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
