An Efficient Packet Scheduling Algorithm in Network Processors

1
An Efficient Packet Scheduling Algorithm in
Network Processors

• CS260
• ---November 2004---

2
Packet Scheduling in Network Processors

• Design Goals
• The input load is well balanced among the worker
  processors
• Flow order is maintained at the output port

3
Channel Stripping

• N channels
• Sender strip incoming traffic across the N
  channels
• Receiver combine the traffic into a single stream

4
Surplus Round Robin
5
Desired Load Distribution Pattern

D-Step Packet Dispatching P-Step Packet
Processing T-Step Packet Transmission
Dynamic Batch CoScheduling (DBCS)
6
Problems to Be Addressed

• Q How much workload should be scheduled to each
  processor?
• A Divisible load scheduling Processing unit
  bytes or packets?
• Q What if the packets are of variable lengths?
• A Packetized DBCS! Packets ? Bytes
• Q Go for Batches?
• A To improve performance. Applicable to a
  dynamic non-backlogged system.
• Q How much workload should be scheduled in a
  batch? When to initiate the next batch?
• A Batch Size Determination Scheduling Time
  Determination
• Q What if there are multiple flows?
• A Fair scheduling among multiple flows with
  different reservations?

7
Load Scheduling Model

• Known Zr,i wi Zs,i N
• To determine ai B Time

8
Load Distribution in A Single Batch
9
Optimal Load Fractions in A Single Batch
10
Load Distribution in Batches
11
Batch Size Determination

• Minimal schedulable batch size
• I C L (L maximal possible length of a
  packet)
• At least one packet should be dispatched to each
  processor mini(aiCL) gt L
• Batch size multiple of I
• B m I

12
Scheduling Time Determination
13
For a Homogeneous Sytem

• zs,i zr,i z wi w ? ai 1/N

14
N 8 GaprGapdGapi0
15
N 4 GaprGapdgt0 Gapi0
16
N 10 GaprGapd0 Gapigt0
17
Best Scheduling Time (N, m, L)
18
Scalability of the Throughput
19
Packetized DBCS Dispatch Decision

• If (PacketSize lt Balancewhich ) Dispatch
• Else if
• (PacketSize Balancewhich lt Balancewhich)
• (Balancewhich gt PacketSize/2) Dispatch
• Else Do not dispatch. Move on to next processor.

20
Packetized DBCS
21
Throughput Verification of P-DBCS
22
Out of Order Rate Verification of P-DBCS
23
Throughput Comparison
24
Out of Order Rate Comparison
25
Fair Scheduling Among Multiple Flows
26
Fair Scheduling Among Multiple Flows

• Minimal schedulable batch size
• I C L (L maximal possible length of a
  packet)
• At least one packet should be dispatched to each
  processor mini(aiCL) gt L
• At least one packet should be selected from each
  flow mini(riCL) gt L
• Batch size multiple of I
• B m I
• Load fraction for each flow
• Fi ri B

27
Select Decision

• (F1, F2, , FM) (F1, F2, , FM)

• If (PacketSize lt FBalancewhich ) Select
• Else if
• (PacketSize FBalancewhich lt FBalancewhich)
• (FBalancewhich gt PacketSize/2) Select
• Else Do not select. Move on to next flow.

28
Fair Scheduling Among Multiple Flows
29
Fair Scheduling Among Multiple Flows
30
Throughput of Multiple Flows

• Reservations (0.3, 0.3, 0.1, 0.1, 0.1, 0.1)

31
Out of Order Rate of Multiple Flows