optimizing network calculus for switched ethernet network...
TRANSCRIPT
Optimizing Network Calculus for SwitchedEthernet Network with DRR Scheduler
Aakash SONI 1,2 Xiaoting LI 2
Jean-Luc SCHARBARG 1 Christian FRABOUL 1
1IRIT Toulouse 2ECE Paris
RTSS - 2018
December 13, 2018
Context : Evolution of Avionic Network
Traditional aircraft network ARINC 429. (Airbus A320)Mono-transmitter buses with limited performances (100Kbits/s).
Avionics Full DupleX (AFDX) network.Switched Ethernet ARINC 664. (Airbus A380)A backbone network for the avionics platform.100 Mbps.FIFO/SP queues.
Aakash SONI Optimizing NC for Avionic Network with DRR 1/42
Context : The Problem
Non intrinsic determinism of resource access in traditionalEthernet.
Collisions on the point-to-point links levelSolution : ARINC 664
Full Duplex Links.No collision frame losses.
ARINC 664 : Indeterminism at Switch level.Competition for the use of the resources.
Congestion = frame lossesFrame storage in queues = Latency andjitter.
Switch
. . .
Input flow traffic
CogestionLatencyJitter
Need of guaranteed bounds for certification.(Motivation)
Aakash SONI Optimizing NC for Avionic Network with DRR 2/42
Context : The Problem
Inefficient use of available bandwidth.[1]
Lightly loaded network (up to 10 % only).
Possibility to share bandwidth among critical(avionic) and non-critical flow.Example:> Audio message from cockpit to cabin.> Parking video.
Solution : Quality of Service (QoS) mechanism.(Motivation)
[1] ] H. Charara, J-L.Scharbarg, J. Ermont and C.Fraboul, ”Methods for bounding end-to-end
delays on an AFDX network,” ECRTS 2006.
Aakash SONI Optimizing NC for Avionic Network with DRR 3/42
Context: Objective 1
How to make better use of available bandwidth?
QoS : Share bandwidth using Round Robin Scheduler.Deficit Round Robin (DRR) scheduling.Weighted Round Robin (WRR) scheduling.[1]
DRR
Priority 1
Priority 2
Priority 3
FIFO BuffersTraffic class
C1
C2
C3
[1] ] A. Soni, X. Li, J-L.Scharbarg, and C.Fraboul, ”WCTT analysis of avionics Switched Ethernet
Network with WRR Scheduling,” RTNS 2018.
Aakash SONI Optimizing NC for Avionic Network with DRR 4/42
Context: Objective 2
Performance analysis of DRR and WRR scheduler in AFDXnetwork.
Worst-case end-to-end delay.
Fairness.
DRR / WRR
Aakash SONI Optimizing NC for Avionic Network with DRR 5/42
Context: Objective 3
Improve delay bound computation.
Reduce pessimism in analysis approach.
Worst-casedelay
Sure upper bound ofworst-case delay
Pessimism
E2EDelay
NC approach
Optimizeddelay bound
Optimization
Aakash SONI Optimizing NC for Avionic Network with DRR 6/42
Table of Contents
1 Context
2 Switched Ethernet Network
3 DRR Algorithm
4 Network Calculus
5 Optimization
6 Evaluation
7 DRR vs WRR
8 Conclusion
Aakash SONI Optimizing NC for Avionic Network with DRR 7/42
Table of Contents
1 Context
2 Switched Ethernet Network
3 DRR Algorithm
4 Network Calculus
5 Optimization
6 Evaluation
7 DRR vs WRR
8 Conclusion
Aakash SONI Optimizing NC for Avionic Network with DRR 8/42
Switched Ethernet Network : AFDX Network Model
AFDX network model
End-Systems (ex)
Switches (Sx)
FIFO output ports
Statically defined flows.
e1
e2 e3
e4S1 S2
DRR
DRR
DRR
DRR
DRRDRR
Perspective
AFDX
e1
e2 e3
e4S1 S2
FIFO
FIFO
FIFO
FIFO
FIFOFIFO
ExistingAFDXModel
Aakash SONI Optimizing NC for Avionic Network with DRR 9/42
Switched Ethernet Network : AFDX Flow Model
Avionic flows are characterized as virtual links;
Statically defined : predictable deterministic behavior.
Maximum frame length: Smax
Minimum delay between two consecutive frames: BAG(Bandwidth Allocation Gap)
Multi-cast routing
E1E4S1 S2
v1 v1 v1
S3 E5v3
v1E2
v2
v2v3v4
v1v2v4E3
BAG BAG BAG
Aakash SONI Optimizing NC for Avionic Network with DRR 10/42
Table of Contents
1 Context
2 Switched Ethernet Network
3 DRR Algorithm
4 Network Calculus
5 Optimization
6 Evaluation
7 DRR vs WRR
8 Conclusion
Aakash SONI Optimizing NC for Avionic Network with DRR 11/42
DRR Algorithm
DRR
C2C1
Active flow
v4
v3
v2
v1
v7
v6
v5
10
20
30
40
0
Q = 20
∆ : Deficit
Credit = Q+ ∆
QC1 ∆C1 QC2 ∆C2
buffers
bytes
Aakash SONI Optimizing NC for Avionic Network with DRR 12/42
DRR Algorithm
DRR
C2C1
Active flow
v4
v3
v2
v1
v7
v6
v5
10
20
30
40
0
Q = 20
∆ : Deficit
Credit = Q+ ∆
QC1 ∆C1 QC2 ∆C2
buffers
bytes
20
Aakash SONI Optimizing NC for Avionic Network with DRR 13/42
DRR Algorithm
DRR
C2C1
Active flow
v4
v3
v2
v1
v7
v6
v5
10
20
30
40
0
Q = 20
∆ : Deficit
Credit = Q+ ∆
QC1 ∆C1 QC2 ∆C2
buffers
bytes
20
v4v3
v2
v1
0
Aakash SONI Optimizing NC for Avionic Network with DRR 14/42
DRR Algorithm
DRR
C2C1
Active flow
v4
v3
v2
v1
v7
v6
v5
10
20
30
40
0
Q = 20
∆ : Deficit
Credit = Q+ ∆
QC1 ∆C1 QC2 ∆C2
buffers
bytes
20
v4v3
v2
v1
0 20
Aakash SONI Optimizing NC for Avionic Network with DRR 15/42
DRR Algorithm
DRR
C2C1
Active flow
v4
v3
v2
v1
v7
v6
v5
10
20
30
40
0
Q = 20
∆ : Deficit
Credit = Q+ ∆
QC1 ∆C1 QC2 ∆C2
buffers
bytes
20
v4v3
v2
v1
0 20
v7
v6
v5
10
Aakash SONI Optimizing NC for Avionic Network with DRR 16/42
DRR Algorithm
DRR
C2C1
Active flow
v4
v3
v2
v1
v7
v6
v5
10
20
30
40
0
Q = 20
∆ : Deficit
Credit = Q+ ∆
QC1 ∆C1 QC2 ∆C2
buffers
bytes
20
v4v3
v2
v1
0 20
v7
v6
v5
10
20
Aakash SONI Optimizing NC for Avionic Network with DRR 17/42
DRR Algorithm
DRR
C2C1
Active flow
v4
v3
v2
v1
v7
v6
v5
10
20
30
40
0
Q = 20
∆ : Deficit
Credit = Q+ ∆
QC1 ∆C1 QC2 ∆C2
buffers
bytes
20
v4v3
v2
v1
0 20
v7
v6
v5
10
20
v2v1
0
Aakash SONI Optimizing NC for Avionic Network with DRR 18/42
DRR Algorithm
DRR
C2C1
Active flow
v4
v3
v2
v1
v7
v6
v5
10
20
30
40
0
Q = 20
∆ : Deficit
Credit = Q+ ∆
QC1 ∆C1 QC2 ∆C2
buffers
bytes
20
v4v3
v2
v1
0 20
v7
v6
v5
10
20
v2v1
0 20
Aakash SONI Optimizing NC for Avionic Network with DRR 19/42
DRR Algorithm
DRR
C2C1
Active flow
v4
v3
v2
v1
v7
v6
v5
10
20
30
40
0
Q = 20
∆ : Deficit
Credit = Q+ ∆
QC1 ∆C1 QC2 ∆C2
buffers
bytes
20
v4v3
v2
v1
0 20
v7
v6
v5
10
20
v2v1
0 20
v6v5
0
Aakash SONI Optimizing NC for Avionic Network with DRR 20/42
Table of Contents
1 Context
2 Switched Ethernet Network
3 DRR Algorithm
4 Network Calculus
5 Optimization
6 Evaluation
7 DRR vs WRR
8 Conclusion
Aakash SONI Optimizing NC for Avionic Network with DRR 21/42
Network Calculus
Network calculus
Computes upper bounds on:
End-to-end delay.Jitter.
Pessimism: models network based on traffic envelops.
Overestimated flow traffic.Underestimated network service.
Aakash SONI Optimizing NC for Avionic Network with DRR 22/42
Network Calculus: Traffic Envelops
System
Network
(DRR)
End
System
End
Aakash SONI Optimizing NC for Avionic Network with DRR 23/42
Network Calculus: Traffic Envelops : Arrival Traffic
System
Network
(DRR)
End
System
End
Actual Arrival Flow
t(µsec)
bits
Smax
f1 f2
BAG
Aakash SONI Optimizing NC for Avionic Network with DRR 24/42
Network Calculus: Traffic Envelops : Arrival Curve
System
Network
(DRR)
End
System
End
t(µsec)
bits
Smax
f1 f2
BAG
αhC1
Smax
f1 f2
BAG
Aakash SONI Optimizing NC for Avionic Network with DRR 25/42
Network Calculus: Traffic Envelops : Network Service
System
Network
(DRR)
End
System
End
Actual Network Service
t(µsec)
bits
Smax
f1 f2
BAG
αhC1
Smax
f1 f2
BAG
Aakash SONI Optimizing NC for Avionic Network with DRR 26/42
Network Calculus: Traffic Envelops : Service Curve
System
Network
(DRR)
End
System
End
t(µsec)
bits
Smax
f1 f2
BAG
αhC1
Smax
f1 f2
BAG
ρhC1
βhC1
ΘhC1
Aakash SONI Optimizing NC for Avionic Network with DRR 27/42
Network Calculus: Traffic Envelops : Delay
System
Network
(DRR)
End
System
End
t(µsec)
bits
Smax
f1 f2
BAG
αhC1
Smax
f1 f2
BAG
ρhC1
βhC1
ΘhC1
delay
Aakash SONI Optimizing NC for Avionic Network with DRR 28/42
Network Calculus: Traffic Envelops : Optimization
System
Network
(DRR)
End
System
End
t(µsec)
bits
Smax
f1 f2
BAG
αhC1
Smax
f1 f2
BAG
ρhC1
βhC1
ΘhC1
delay
β‘hC1
ρhC1
βhC1
Aakash SONI Optimizing NC for Avionic Network with DRR 29/42
Network Calculus: Traffic Envelops : Optimization
System
Network
(DRR)
End
System
End
t(µsec)
bits
Smax
f1 f2
BAG
αhC1
Smax
f1 f2
BAG
ρhC1
βhC1
ΘhC1
delay
β‘hC1
ρhC1
βhC1
α‘hC1
delay
αhC1
delay‘
Aakash SONI Optimizing NC for Avionic Network with DRR 30/42
Table of Contents
1 Context
2 Switched Ethernet Network
3 DRR Algorithm
4 Network Calculus
5 Optimization
6 Evaluation
7 DRR vs WRR
8 Conclusion
Aakash SONI Optimizing NC for Avionic Network with DRR 31/42
Pessimism in computed network service
DRR
v1v2
v7
v3v4
v8v9v10
C1 v5v6
C2 v11v12
v13v14v15v16C3 v17v18
v7 v13v14v8
v9 v15v16v10
v11 v17v18v12
v1
v2, v3
v4, v5, v6
βhC1
ΘhC1 Dh
C1
αhC1
t(µsec)
bits
Aakash SONI Optimizing NC for Avionic Network with DRR 32/42
Pessimism in computed network service
DRR
v1v2
v7
v3v4
v8v9v10
C1 v5v6
C2 v11v12
v13v14v15v16C3 v17v18
v7 v13v14v8
v9 v15v16v10
v11 v17v18v12
v1
v2, v3
v4, v5, v6
DRR
v1v2
v7
v3v4
v8v9v10
C1 v5v6
C2 v11
v13v14v15C3
v7 v13v14v8
v9 v15v10
v11
v1
v2, v3
v4, v5, v6
βhC1
ΘhC1 Dh
C1
βhC1
ΘhC1 D‘hC1
DhC1
Pessimism
αhC1
αhC1
t(µsec)
bits
t(µsec)
bits
Aakash SONI Optimizing NC for Avionic Network with DRR 33/42
Upper bound on interfering traffic
DRR
v1v2
v7
v3v4
v8v9v10
C1 v5v6
C2 v11v12
v13v14v15v16C3 v17v18
v7 v13v14v8
v9 v15v16v10
v11 v17v18v12
v1
v2, v3
v4, v5, v6
DRR
v1v2
v7
v3v4
v8v9v10
C1 v5v6
C2 v11
v13v14v15C3
v7 v13v14v8
v9 v15v10
v11
v1
v2, v3
v4, v5, v6
βhC1
ΘhC1 Dh
C1
βhC1
ΘhC1 D‘hC1
DhC1
Pessimism
αhC1
αhC1
t(µsec)
bits
t(µsec)
bits
(αhC2
(DC1))
(αhC3
(DC1))
− = ExtraloadC2Actual traffic from C2 before DhC1
C2 Flow traffic in βhC1
− = ExtraloadC3Actual traffic from C3 before DhC1
C3 Flow traffic in βhC1
Aakash SONI Optimizing NC for Avionic Network with DRR 34/42
More accurate delay computation
DRR
v1v2
v7
v3v4
v8v9v10
C1 v5v6
C2 v11v12
v13v14v15v16C3 v17v18
v7 v13v14v8
v9 v15v16v10
v11 v17v18v12
v1
v2, v3
v4, v5, v6
DRR
v1v2
v7
v3v4
v8v9v10
C1 v5v6
C2 v11
v13v14v15C3
v7 v13v14v8
v9 v15v10
v11
v1
v2, v3
v4, v5, v6
βhC1
ΘhC1 Dh
C1
βhC1
ΘhC1 D‘hC1
DhC1
Pessimism
αhC1
αhC1
t(µsec)
bits
t(µsec)
bits
(αhC2
(DC1))
(αhC3
(DC1))
− = ExtraloadC2Actual traffic from C2 before DhC1
C2 Flow traffic in βhC1
− = ExtraloadC3Actual traffic from C3 before DhC1
C3 Flow traffic in βhC1
Dopt,hC1
= DhC1− tr{ExtraloadC2 + ExtraloadC3}
Dopt,hC1
Aakash SONI Optimizing NC for Avionic Network with DRR 35/42
Table of Contents
1 Context
2 Switched Ethernet Network
3 DRR Algorithm
4 Network Calculus
5 Optimization
6 Evaluation
7 DRR vs WRR
8 Conclusion
Aakash SONI Optimizing NC for Avionic Network with DRR 36/42
Evaluation
Airbus A350 configuration
984 flows, 96 end systems, 8 switches, 6412 paths
0
20
40
60
80
100
0 1000 2000 3000 4000 5000 6000 7000
flow paths
DRR_SER normalized to 100DRR_SER_OPT compared to DRR_SER
Average gain:48%.
Max gain 75%.
Class Flows Smax (byte) Qx CategoryC1 718 475 2×Lmax CriticalC2 194 971 Lmax MultimediaC3 72 1535 Lmax Best-effort
Aakash SONI Optimizing NC for Avionic Network with DRR 37/42
Table of Contents
1 Context
2 Switched Ethernet Network
3 DRR Algorithm
4 Network Calculus
5 Optimization
6 Evaluation
7 DRR vs WRR
8 Conclusion
Aakash SONI Optimizing NC for Avionic Network with DRR 38/42
Performance Analysis
classNo. of DRR WRR weight frame sizeflows Quantum (bytes) (no. of packets) range
C1 718 4 x lmax 4 415-475C2 194 2 x lmax 2 911-971C3 72 1 x lmax 1 1475-1535
classDRR vs WRR
avg difference (%) max difference (%)
C1 29.16 52.7C2 29.6 52.3C3 -35.4 -68.8
Aakash SONI Optimizing NC for Avionic Network with DRR 39/42
Table of Contents
1 Context
2 Switched Ethernet Network
3 DRR Algorithm
4 Network Calculus
5 Optimization
6 Evaluation
7 DRR vs WRR
8 Conclusion
Aakash SONI Optimizing NC for Avionic Network with DRR 40/42
Conclusion
NC on AFDX network with mixed criticality
QoS: DRR scheduling.
Evaluation of improved NC approach.
Performance comparison of DRR and WRR schedulers.
What’s next?
Exact worst case delay using model checking approach.Evaluation of pessimism of NC for avionic network withDRR and WRR scheduler.Weight/Quantum allocation in Round Robin scheduler(WRR/DRR)
Aakash SONI Optimizing NC for Avionic Network with DRR 41/42
Questions
Thank you for your attention!
Aakash SONI - [email protected]
Aakash SONI Optimizing NC for Avionic Network with DRR 42/42