loxilb is an open source cloud-native load-balancer based on GoLang/eBPF with the goal of achieving cross-compatibility across a wide range of on-prem, public-cloud or hybrid K8s environments.

Kubernetes defines many service constructs like cluster-ip, node-port, load-balancer, ingress etc for pod to pod, pod to service and outside-world to service communication.

All these services are provided by load-balancers/proxies operating at Layer4/Layer7. Since Kubernetes's is highly modular, these services can be provided by different software modules. For example, kube-proxy is used by default to provide cluster-ip and node-port services. For some services like LB and Ingress, no default is usually provided.

Service type load-balancer is usually provided by public cloud-provider(s) as a managed entity. But for on-prem and self-managed clusters, there are only a few good options available. Even for provider-managed K8s like EKS, there are many who would want to bring their own LB to clusters running anywhere. loxilb provides service type load-balancer as its main use-case. loxilb can be run in-cluster or ext-to-cluster as per user need.

loxilb works as a L4 load-balancer/service-proxy by default. Although L4 load-balancing provides great performance and functionality, an equally performant L7 load-balancer is also necessary in K8s for various use-cases. loxilb also supports L7 load-balancing in the form of Kubernetes Ingress implementation which is enhanced with eBPF sockmap helpers. This also benefit users who need L4 and L7 load-balancing under the same hood.

Additionally, loxilb also supports:

• kube-proxy replacement with eBPF(full cluster-mesh implementation for Kubernetes)
• Ingress Support
• Kubernetes Gateway API
• Kubernetes Network Policies

For deploying telco-cloud with cloud-native functions, loxilb can be used as a SCP(service communication proxy). SCP is a communication proxy defined by 3GPP and aimed at telco micro-services running in cloud-native environment. Read more in this blog

Telco-cloud requires load-balancing and communication across various interfaces/standards like N2, N4, E2(ORAN), S6x, 5GLAN, GTP etc. Each of these present its own unique challenges which loxilb aims to solve e.g.:

• N4 requires PFCP level session-intelligence
• N2 requires NGAP parsing capability(Related Blogs - Blog-1, Blog-2, Blog-3)
• S6x requires Diameter/SCTP multi-homing LB support(Related Blog)
• MEC use-cases might require UL-CL understanding(Related Blog)
• Hitless failover support might be essential for mission-critical applications
• E2 might require SCTP-LB with OpenVPN bundled together
• SIP support is needed to enable cloud-native VOIP

• Performs much better compared to its competitors across various architectures
  • Single-Node Performance
  • Multi-Node Performance
  • Performance on ARM
  • Short Demo on Performance
• Utitlizes ebpf which makes it flexible as well as customizable
• Advanced quality of service for workloads (per LB, per end-point or per client)
• Works with any Kubernetes distribution/CNI - k8s/k3s/k0s/kind/OpenShift + Calico/Flannel/Cilium/Weave/Multus etc
• Kube-proxy replacement with loxilb allows simple plug-in with any existing/deployed pod-networking software
• Extensive support for SCTP workloads (with multi-homing) on K8s
• Dual stack with NAT66, NAT64 support for K8s
• K8s multi-cluster support (planned 🚧)
• Runs in any cloud (public cloud/on-prem) or standalone environments

• L4/NAT stateful loadbalancer
  • NAT44, NAT66, NAT64 with One-ARM, FullNAT, DSR etc
  • Support for TCP, UDP, SCTP (w/ multi-homing), QUIC, FTP, TFTP etc
• High-availability support with BFD detection for hitless/maglev/cgnat clustering
• Extensive and scalable end-point liveness probes for cloud-native environments
• Stateful firewalling and IPSEC/Wireguard support
• Optimized implementation for features like Conntrack, QoS etc
• Full compatibility for ipvs (ipvs policies can be auto inherited)
• Policy oriented L7 proxy support - HTTP1.0, 1.1, 2.0, 3.0

• GoLang based control plane components
• A scalable/efficient eBPF based data-path implementation
• Integrated goBGP based routing stack
• A kubernetes operator kube-loxilb written in Go
• A kubernetes ingress implementation

• Understanding loxilb modes and deployment in K8s with kube-loxilb
• Understanding High-availability with loxilb

• K3s : loxilb with default flannel
• K3s : loxilb with calico
• K3s : loxilb with cilium
• K0s : loxilb with default kube-router networking
• EKS : loxilb ext-mode

• K3s : loxilb in-cluster mode
• K0s : loxilb in-cluster mode
• MicroK8s : loxilb in-cluster mode
• EKS : loxilb in-cluster mode

• K3s : loxilb service-proxy with flannel
• K3s : loxilb service-proxy with calico

• K3s: How to run loxilb-ingress

• Run loxilb standalone

• How-To : Service-group zones with loxilb
• How-To : Access end-points outside K8s
• How-To : Deploy multi-server K3s HA with loxilb
• How-To : Deploy loxilb with multi-AZ HA support in AWS
• How-To : Deploy loxilb with ingress-nginx

• What is eBPF
• What is k8s service - load-balancer
• Architecture in brief
• Code organization
• eBPF internals of loxilb
• What are loxilb NAT Modes
• loxilb load-balancer algorithms
• Manual steps to build/run
• Debugging loxilb
• loxicmd command-line tool usage
• Developer's guide to loxicmd
• Developer's guide to loxilb API
• API Reference - loxilb web-Api
• Performance Reports
• Development Roadmap
• Contribute
• System Requirements
• Frequenctly Asked Questions- FAQs
• Blogs
• Demo Videos

Join the loxilb Slack channel to chat with loxilb developers and other loxilb users. This is a good place to learn about loxilb, ask questions, and work collaboratively.

Feel free to post your queries in github discussion. If you find any issue/bugs, please raise an issue in github and members from loxilb community will be happy to help.

Features(Ubuntu20.04)	Features(Ubuntu22.04)	Features(RedHat9)

K3s Tests	K8s Cluster Tests	EKS Test