---
title: "VPP with Maglev Loadbalancing"
url: https://daily.dev/posts/vpp-with-maglev-loadbalancing-jysrcegoj
source_url: https://ipng.ch/s/articles/2026/04/30/vpp-with-maglev-loadbalancing-part-1
type: article
source: "IPng Networks"
published: 2026-04-30T08:49:03.795Z
updated: 2026-04-30T08:51:02.721Z
reading_time: 18
upvotes: 1
comments: 0
language: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# VPP with Maglev Loadbalancing

**[IPng Networks](https://daily.dev/sources/ipngch)** · 18 min read · 1 upvotes · 0 comments

## Summary

A deep dive into VPP's load balancer plugin using Google's Maglev consistent hashing algorithm. Covers how Maglev works (pre-computed lookup table + per-CPU flow hash LRU cache), the plugin's internal data structures (VIPs, Application Servers, new-flow table, flow hash table), and a collection of API bugs fixed in Gerrit. Two new features are introduced: per-AS weights (0–100) enabling lameduck draining and gradual canary rollouts without disrupting existing TCP sessions, and a 'punt' flag for port-based VIPs that routes non-matching traffic (ICMP, traceroute) to the local IP stack instead of dropping it. New API calls (lb_as_add_del_v2, lb_as_set_weight, lb_add_del_vip_v3, etc.) are added to expose these capabilities without breaking existing API contracts.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://ipng.ch/s/articles/2026/04/30/vpp-with-maglev-loadbalancing-part-1>

## Similar posts on daily.dev

- [VPP with Maglev Loadbalancing](https://daily.dev/posts/vpp-with-maglev-loadbalancing-ioidlcbrh) · IPng Networks · 18 upvotes · 0 comments
- [VPP with Maglev Loadbalancing](https://daily.dev/posts/vpp-with-maglev-loadbalancing-c9kdhygia) · IPng Networks · 1 upvotes · 0 comments
- [VPP and eVPN/VxLAN](https://daily.dev/posts/vpp-and-evpn-vxlan-me6ck7qp1) · IPng Networks · 7 upvotes · 0 comments
- [vLLM x Novita AI: PegaFlow for Production-Grade External KV Cache](https://daily.dev/posts/vllm-x-novita-ai-pegaflow-for-production-grade-external-kv-cache-sspklzd0k) · vLLM · 0 upvotes · 0 comments
- [Client-Side Load Balancing at a Million Requests Per Second](https://daily.dev/posts/client-side-load-balancing-at-a-million-requests-per-second-bvi2j48ww) · Zalando · 20 upvotes · 1 comments

---

[View this post on daily.dev](https://daily.dev/posts/vpp-with-maglev-loadbalancing-jysrcegoj)