~/talk

Low Latency Multi-cluster Kubernetes Networking in AWS

on YouTube 34m
Talkat KubeCon + CloudNativeCon North America 2019 · on Tuesday, 2019-11-19· at 10:55· Room 28ABCDE - San Diego Convention Center, Upper Level· [networking, cloud-infrastructure]

speaker

name:Paul Fisher
links:none on file

resources

video:https://youtu.be/Mj5zgbC6YDI
slides:none on file

summary

Lyft migrates hundreds of microservices to Kubernetes on AWS using an open source CNI that assigns real VPC IPs to pods, ties clusters into a flat network, and keeps Envoy sidecars part of a single mesh. Implementation uses lightweight Go daemons, IPVLAN for near-native performance, an unnumbered p2p interface for host egress, and multi-AZ deployment across five core clusters. Production runs two years with p95/p99 latency matching legacy.

AI-written summary · about

chapters (15)

  1. 0:00Intro
  2. 0:58Lyft's Scale
  3. 3:13Lyft Kubernetes Timeline
  4. 5:08Lyft Kubernetes Environment
  5. 7:14Kubernetes Networking 101
  6. 8:23Kubernetes AWS Network Options
  7. 10:01Overlay Networks
  8. 11:52VPC Native Networks
  9. 14:54VPC Elastic Network Interface (ENI)
  10. 16:34Lyft Network Interfaces within a Pod
  11. 18:53Lyft Pod Internet Egress
  12. 20:50Lyft Envoy Control Plane
  13. 22:10Lyft Envoy Mesh Sidecar Startup
  14. 24:07Lyft Service Migration Takeaways
  15. 27:58Lyft Happy Hour Tonight!

related talks

~/search
type to search 6,249 conferences, 138,987 speakers and 185,172 talks
~/help
cmdctrl k
search every conference, speaker and series
/
focus the filter search
h
home
c
conferences
s
speakers
e
series
t
light / dark — the status bar button does the same
?
this help
esc
close this, then clear every filter — or just the search, while you are typing in it

Ignored while you are typing. Pages without a filter rail have no search to focus.