Anja Feldmann Bala Chandrasekaran, Emilia Weyulu, Seif Fathalli - - PowerPoint PPT Presentation

P4-enabled Network-assisted Congestion Feedback: A Case for NACKs

Anja Feldmann

Bala Chandrasekaran, Emilia Weyulu, Seif Fathalli

Motivation – some observations

• Buffers
• Are getting shallow (relative to link speed)
• Should be shallow to ensure short, deterministic delays
• Traffic
• Mice vs. Elephants
• Elephants contribute most traffic

– React to congestion signal

• Mice contribute most flows

– Not subject to congestion control

• Separating mice from elephants can be beneficial
• Today’s switches

2

MPI INF | Anja Feldmann

Background – Buffer Occupancy

• NS2 simulations results
• Mice can fill any queue as they

are not subject to congestion control

3

MPI INF | Anja Feldmann

Server Clients Used to limit capacity 1.5 Mbits to 3 Mbits Used to vary delay 640 ms or 40 ms 40-100 Kbits/second Used to measure before bottleneck

Infinite sources Web like sources

Motivation – some observations

• Buffers
• Are getting shallow (relative to link speed)
• Should be shallow to ensure short, deterministic delays
• Traffic
• Mice vs. Elephants
• Elephants contribute most traffic

– React to congestion signal

• Mice contribute most flows

– Not subject to congestion control

• Separating mice from elephants can be beneficial
• Today’s switches
• Enable gathering of fine-grain statistics –

The P4 advantage

• Enable use of multiple queues

– The QoS leftover

4

MPI INF | Anja Feldmann

Today‘s Congestion Inference

• Left to the end-systems

5

MPI INF | Anja Feldmann

Source Destination Implicit (delay, discard) Explicit (binary, rate) Policing Choke Packet Back Pressure

Today Today Archaic Archaic

Tomorrow‘s Congestion Inference

• Network-assisted
• Network-assisted Congestion Notification (NCF)

6

MPI INF | Anja Feldmann

Source Destination

NCF

NCF – Insights

• Network (switches/routers) can initiate NACKs with P4
• Trim packets in data plane
• Reflect packet as NACK back to source
• Address elephants and mice
• Detect elephants in data plane
• Use separate queues
• Three queues suffice
• Dynamically allocate memory (to keep buffers where needed)
• Congestion signals independent of queue usage

7

MPI INF | Anja Feldmann

Network-assisted Congestion Feedback (NCF)

• Rolling Sketches (Counters)
• How
• Rolling: Multiple time windows
• Counters: Per flow per time window
• Mice:

Sum of counters < threshold

• Elephant: Sum of counters > threshold
• Advantages
• Small memory foot-print
• Efficient and flexible
• Feasible: Due to skewed flow distributions

8

MPI INF | Anja Feldmann

Advantages NCF

• Fast direct feedback directly to source

(includes lost packet info)

• Separation of Mice and Elephants
• Flexible allocation of buffer memory
• Design
• Is work-conserving
• Is scalable
• Shares resources fairly
• Ensures short queues
• Can handle TCP Incast challenge
• Incrementally deployable

9

MPI INF | Anja Feldmann

Source

Destination

NCF

Status

• Prototype implementations
• P4
• NS3
• First results look promising
• Needed: NCF enabled congestion control algorithm

10

MPI INF | Anja Feldmann

NCF – Insights

• Network (switches/routers) can initiate NACKs with P4
• Trim packets in data plane
• Reflect packet as NACK back to source => Fast congestion feedback
• Separate elephants and mice
• Detect elephants in data plane
• Use separate queues
• Three queues suffice
• Dynamically allocate memory (to keep buffers where needed)
• Congestion signals independent of queue usage

11

MPI INF | Anja Feldmann