Trafficshifting: Avoiding Disasters & Improving Performance at Scale
0 likes248 views
LinkedIn uses traffic shifting techniques to avoid disasters and improve performance. They shift traffic between their datacenter fabrics and point of presence (PoP) locations using sticky routing and DNS steering. This allows them to perform disaster recovery testing and mitigate outages. Specifically for the Asia Pacific region, they overcame challenges such as fiber cuts by failing traffic out of affected PoP locations. Their techniques improved performance and user experience for both IPv4 and IPv6 users.
Trafficshifting: Avoiding Disasters & Improving Performance at Scale
- 2. Trafficshifting: Avoiding Disasters & Improving Performance at Scale Michael Kehoe Staff Site Reliability Engineer LinkedIn
- 3. 3 Overview • Problem Statement • Solution – How LinkedIn trafficshift’s • Datacenter shifting • PoP steering • Challenges of APAC region • IPv4 vs IPv6 • Questions
- 4. $ whoami 4 Michael Kehoe • Staff Site Reliability Engineer (SRE) @ LinkedIn • Production-SRE team • Funny accent = Australian + 3 years American
- 5. $ whatis SRE 5 Michael Kehoe • Site Reliability Engineering • Operations for the production application environment • Responsibilities include • Architecture design • Capacity planning • Operations • Tooling • Responsibilities include DNS/ CDN management & Traffic infrastructure
- 6. 6 Terminology • PoP - Where LinkedIn terminates incoming requests. • Fabric – Datacenter with full LinkedIn production stack deployed • Loadtest – Stress test of a Fabric – to simulate a disaster scenario
- 7. Disaster Recovery 7 Problem Statement • Fail between Fabrics • Performance of applications is degraded • Validate disaster recovery (DR) scenario • Expose bugs and suboptimal configurations via loadtest • Planned maintenance • Fail between PoP’s • Mitigate impact of a 3rd party provider maintenance/ failure (e.g. transport links) • Software/ Configuration Bugs
- 8. Performance 8 Problem Statement • Fabric Assignment • Assign preferred and secondary fabric to all members based on: • Member location • Capacity • PoP/ CDN steering • Use GeoDNS to steer user to ‘best’ PoP • Use RUM DNS to steer users to ’best’ CDN
- 9. United States Performance (Global) 9 Problem Statement
- 10. APAC Performance (APAC cities) 10 Problem Statement
- 11. Delta US & APAC 11 Problem Statement
- 12. Site Speed 12 Problem Statement • Site Speed affects User Engagement • User Engagement affects page-views & transactions • Bottom Line: Site Speed has an impact on revenue
- 13. • Site Speed affects User Engagement 13 Problem Statement
- 16. Fabric shifting 16 Solution • Stickyrouting • Using a Hadoop job, we calculate a primary and secondary datacenter for the user based on location • This data is stored in a Key-Value store (Espresso) • Stickyrouting serves this information over a RESTful interface to our Edge PoP’s
- 17. Fabric shifting 17 Solution • Different traffic types are partitioned and controlled separately • Logged-In vs Logged-out • CDN’s • Monitoring • Microsites • Logged-in users are placed into ‘buckets’ • Buckets are marked online/ offline to move site traffic
- 18. Fabric shifting 18 Solution • Stickyrouting – Benefits • Ensure we serve the request as close to the user as possible • Capacity management for datacenters • We can assign a percentage of users to a datacenter • Enables personal data routing (PDR) • Only store data where we need it
- 22. Fabric Shifting Load tests 22 Solution
- 26. LinkedIn’s PoP Architecture 26 Solution • Using IPVS - Each PoP announces a unicast address and a regional anycast address • APAC, EU and NAMER anycast regions • Use GeoDNS to steer users to the ‘best’ PoP • DNS will either provide users with an anycast or unicast address for www.linkedin.com • US and EU members is nearly all anycast • APAC is all unicast
- 27. LinkedIn’s PoP DR 27 Solution • Sometimes need to fail out of PoP’s • 3rd party provider issues (e.g. transit links going down) • Infrastructure maintenance • Withdraw anycast route announcements • Fail healthchecks on proxy to drain unicast traffic
- 28. LinkedIn’s PoP Performance 28 Solution • PoP DNS Steering • LinkedIn currently uses GeoDNS for routing • Piloting RumDNS • Pick the best PoP based on network, not country • CDN Steering • Mix CDN’s to get best performance • Constantly evaluate performance/ availability • Automatically adjust CDN weighting
- 29. LinkedIn’s PoP Performance 29 Solution US CDN request time 50th percentile 24 hours
- 30. Working around fiber cuts 30 APAC Challenges • Case Study: Fail out of India PoP due to fiber cuts Connection Time for Indian members (90th percentile)
- 31. ASN 15802 ASN 5384 GeoDNS Suboptimal PoP’s 31 APAC Challenges Source: http://www.submarinecablemap.com/#/submarine-cable/bay-of-bengal-gateway-bbg SingaporeMumbai 45 ms 220 ms 70 ms ASN 15802 RTT to Singapore is (220+70) 290ms (all at 50th percentile)
- 32. GeoDNS Suboptimal PoP’s 32 APAC Challenges London Dublin SingaporeMumbai 160 ms 45 ms ASN 15802 ASN 5384 70 ms 35 ms 350 ms Hong Kong160 ms
- 33. GeoDNS Suboptimal PoP’s 33 APAC Challenges 600 700 800 900 1000 1100 1200
- 34. Performance & Adoption 34 IPv4 vs IPv6 • IPv6 performs better for our members • Less request time-outs on IPv6 for mobile users • Mobile carriers are adopting IPv6 faster • Win for LinkedIn and our members! • In July 2014 (IPv6 launch): 3% of traffic was IPv6 • Today: ~12% of traffic is IPv6
- 35. Key Takeaways 35 Conclusion • Application level traffic engineering is extremely important for content providers • RUM data is extremely useful for finding anomalies • Route traffic based on performance, not just location • IPv6 performs better for LinkedIn users
- 36. 36 Questions?