Главная
Study mode:
on
1
Intro
2
L4 LB at datacenter boundary
3
Being stateful
4
Stateful L4 LB requirements
5
Existing solution: software-based LB
6
Existing solution: switch-based LB
7
Strawman solution: switch-server LB
8
Traffic at datacenter boundary
9
System goals
10
Tiara idea
11
Tiara three-tier architecture
12
Tiara architecture in details
13
Inbound traffic: the first packet
14
Inbound traffic: the rest packets
15
Outbound traffic
16
Optimizations
17
Prototype implementation T-switch: Barefoot Tofino switch
18
System performance
19
Latency-bounded throughput
20
Tiara vs. existing approaches
21
Conclusion
Description:
Explore a conference talk on Tiara, a scalable and efficient hardware acceleration architecture for stateful Layer-4 load balancing. Learn about the challenges of distributing terabits per second of Internet traffic at datacenter boundaries and how Tiara addresses these issues. Discover the innovative three-tier architecture that utilizes heterogeneous hardware, including programmable switches and FPGAs for the fast path and x86 servers for the slow path. Understand how Tiara divides the load balancing fast path into memory-intensive and throughput-intensive tasks, mapping them to the most suitable hardware. Gain insights into the implementation of a fully functional Tiara prototype and its impressive performance metrics, including 1.6 Tbps throughput, 80M concurrent flows, and 1.8M new connections per second. Delve into the system goals, architecture details, traffic handling, optimizations, and comparative advantages over existing approaches in this comprehensive presentation from NSDI '22. Read more

Tiara - A Scalable and Efficient Hardware Acceleration Architecture for Stateful Layer-4 Load Balancing

USENIX
Add to list