[PPT] - Traversal time for weakly synchronized CAN bus Hugo Daigmorte, Marc PowerPoint Presentation

SLIDE 1

Context and goal Computing an upper bound on network delay Experimental results Conclusion

Traversal time for weakly synchronized CAN bus

Hugo Daigmorte, Marc Boyer

ONERA – The French aerospace lab 24th International Conference on Real-Time Networks and Systems RTNS’2016 19th October 2016

C

n

s i s t e n t * C

m

p l e t e * W e l l d

c

u m e n t e d * E a s y t

r

e u s e *

*

E v a l u a t e d

* R T N S *

A r t i f a c t

H. Daigmorte, M. Boyer

Traversal time for weakly synchronized CAN bus 1 / 24

SLIDE 2

Context and goal Computing an upper bound on network delay Experimental results Conclusion Context and goal Global clock Local clock Bounded phases

Context

Context Real-time networked system Bus network: CAN Periodic flows with Offsets

reduces contentions ⇒ reduces delays requires synchronization

CAN Node n°N CAN Node n°2 CAN Node n°1

H. Daigmorte, M. Boyer

Traversal time for weakly synchronized CAN bus 3 / 24

SLIDE 4

Context and goal Computing an upper bound on network delay Experimental results Conclusion Context and goal Global clock Local clock Bounded phases

Model and Goal

Model Flows Fi: Pi, Si, Oi N nodes, each node j has a clock: cj(t) Sending frame k: cj(t) = Oi + kPi Goal Accurate bound on network traversal time aka Worst Case Traversal Time (WCTT)

H. Daigmorte, M. Boyer

Traversal time for weakly synchronized CAN bus 4 / 24

SLIDE 5

Context and goal Computing an upper bound on network delay Experimental results Conclusion Context and goal Global clock Local clock Bounded phases

Global clock

∀j, j′ : cj(t) = cj′(t) Advantage: efficient schedule ⇒ no contention Drawback: perfect synchronization (HW/SW cost)

A,1 B,1 A,2 C,3 C,1 C,2 A,1 B,1 A,2 C,1 C,2 C,3 BUS N1 N2 BUS

H. Daigmorte, M. Boyer

Traversal time for weakly synchronized CAN bus 5 / 24

SLIDE 6

Context and goal Computing an upper bound on network delay Experimental results Conclusion Context and goal Global clock Local clock Bounded phases

Local clock

Advantage: efficient schedule ⇒ no contention intra-nodes efficient schedule ⇒ workload spread over time

N1 N2 BUS BUS A,1 B,1 A,2 C,3 C,1 C,2 A,1 B,1 A,2 C,1 C,2 C,3

H. Daigmorte, M. Boyer

Traversal time for weakly synchronized CAN bus 6 / 24

SLIDE 7

Context and goal Computing an upper bound on network delay Experimental results Conclusion Context and goal Global clock Local clock Bounded phases

Bounded phases

∀j, j′ : cj(t) − cj′(t) ≤ Φj,j′ Objectives: affordable synchronization reduces delays wrt no sync/local clock

N1 N2 BUS BUS A,1 B,1 A,2 C,3 C,1 C,2 A,1 B,1 A,2 C,1 C,2 C,3

H. Daigmorte, M. Boyer

Traversal time for weakly synchronized CAN bus 7 / 24

SLIDE 8

Context and goal Computing an upper bound on network delay Experimental results Conclusion Network Calculus Methodology

Reality modeling

Network Calculus is a theory designed to compute memory and delay bounds in networks. A αA+A′ Flow : Cumulative curve A

A(t) : amount of data sent up to time t Properties: null at 0 (and before), non decreasing

Server: simple arrival/departure relation:

Property: departure produced after arrival: A

S

− → D = ⇒ A ≥ D

Worst delay: d(A, S) = sup

t∈R+{inf{d ∈ R+|A(t) ≤ D(t + d)}}

H. Daigmorte, M. Boyer

Traversal time for weakly synchronized CAN bus 9 / 24

SLIDE 10

Context and goal Computing an upper bound on network delay Experimental results Conclusion Network Calculus Methodology

Arrival curve and services

Real behaviors are unknown at design time ⇒ use of contracts Traffic contract: arrival curve A flow A has arrival curve α iff: ∀t, d ∈ R+ : A(t + d) − A(t) ≤ α(d) Server contract: service curve For t, s in the same busy/backlogged period, a server S offers a strict minimal service of curve β iff: D(t) − D(s) ≥ β(t − s)

H. Daigmorte, M. Boyer

Traversal time for weakly synchronized CAN bus 10 / 24

SLIDE 11

Context and goal Computing an upper bound on network delay Experimental results Conclusion Network Calculus Methodology

A common period

Problem transformation

H. Daigmorte, M. Boyer

Traversal time for weakly synchronized CAN bus 11 / 24

SLIDE 12

Context and goal Computing an upper bound on network delay Experimental results Conclusion Network Calculus Methodology

A common period

Problem transformation Initial problem: Flow : Fi =< Ti, Oi, Si >, F = {F1, .., Fn}

1 source periodic messages Size, Period, Offset Priority

H. Daigmorte, M. Boyer

Traversal time for weakly synchronized CAN bus 11 / 24

SLIDE 13

Context and goal Computing an upper bound on network delay Experimental results Conclusion Network Calculus Methodology

A common period

Problem transformation Initial problem: Flow : Fi =< Ti, Oi, Si >, F = {F1, .., Fn}

1 source periodic messages Size, Period, Offset Priority

Transformed problem: A = {A1, .., Am}

Period T = ppcm(Ti) Offset Oj Size Sj

Donner un exemple (avec figure)

H. Daigmorte, M. Boyer

Traversal time for weakly synchronized CAN bus 11 / 24

SLIDE 14

Context and goal Computing an upper bound on network delay Experimental results Conclusion Network Calculus Methodology

Arrival curve

Arrival curve α1..k (Theorem 5) Capture the synchronization Efficient algorithm Required common period

H. Daigmorte, M. Boyer

Traversal time for weakly synchronized CAN bus 12 / 24

SLIDE 15

Context and goal Computing an upper bound on network delay Experimental results Conclusion Network Calculus Methodology

A O P α A′ O′ P α A + A′ 2α αA+A′

H. Daigmorte, M. Boyer

Traversal time for weakly synchronized CAN bus 13 / 24

SLIDE 16

Context and goal Computing an upper bound on network delay Experimental results Conclusion Network Calculus Methodology

State of the art: hDev(Ai, Di) ≤ hDev(αi, β −

j<i

αj − L)

1 Method 1: hDev(Ai, Di) ≤ hDev(αi, β − α1..i−1 − L)

Taking into account synchronization between flows A1..Ai−1

αi β − α1..i−1 − L

hDev(αi, βi − α1..i−1)

H. Daigmorte, M. Boyer

Traversal time for weakly synchronized CAN bus 14 / 24

SLIDE 17

Context and goal Computing an upper bound on network delay Experimental results Conclusion Network Calculus Methodology 2 Method 2: hDev(Ai, Di) ≤ (β − α1..i − L)−1(0)

Bound busy period for high priority flows (1..i) Pessimistic if several messages of the same flow are in the same busy period

(

β

α1

. . i

L

)

1

( )

i,1 i,2 i,1 i,2

8,6cm

H. Daigmorte, M. Boyer

Traversal time for weakly synchronized CAN bus 15 / 24

SLIDE 18

Context and goal Computing an upper bound on network delay Experimental results Conclusion Network Calculus Methodology 3 Method 3 (Theorem 3): hDev(Ai, Di) ≤ hDev(Ai, Di)

Requires good knowledge of Ai

Ai Di Di

hDev(Ai, Di) hDev(Ai, Di)

H. Daigmorte, M. Boyer

Traversal time for weakly synchronized CAN bus 16 / 24

SLIDE 19

Context and goal Computing an upper bound on network delay Experimental results Conclusion Phases bounded by 0ms Phases bounded by ±1ms Phases bounded by ±5ms Phases bounded by ±10ms

Traversal time for weakly synchronized CAN bus

Hugo Daigmorte, Marc Boyer

ONERA – The French aerospace lab 24th International Conference on Real-Time Networks and Systems RTNS’2016 19th October 2016

Table of Contents

1

Context and goal Context and goal Global clock Local clock Bounded phases

2

Computing an upper bound on network delay

3

Experimental results

4

Conclusion

Context

Context Real-time networked system Bus network: CAN Periodic flows with Offsets

reduces contentions ⇒ reduces delays requires synchronization

Model and Goal

Model Flows Fi: Pi, Si, Oi N nodes, each node j has a clock: cj(t) Sending frame k: cj(t) = Oi + kPi Goal Accurate bound on network traversal time aka Worst Case Traversal Time (WCTT)

Global clock

∀j, j′ : cj(t) = cj′(t) Advantage: efficient schedule ⇒ no contention Drawback: perfect synchronization (HW/SW cost)

Local clock

Advantage: efficient schedule ⇒ no contention intra-nodes efficient schedule ⇒ workload spread over time

Bounded phases

∀j, j′ : cj(t) − cj′(t) ≤ Φj,j′ Objectives: affordable synchronization reduces delays wrt no sync/local clock

Table of Contents

1

Context and goal

2

Computing an upper bound on network delay Network Calculus Methodology

3

Experimental results

4

Conclusion

Reality modeling

Network Calculus is a theory designed to compute memory and delay bounds in networks. A αA+A′ Flow : Cumulative curve A

A(t) : amount of data sent up to time t Properties: null at 0 (and before), non decreasing

Server: simple arrival/departure relation:

Property: departure produced after arrival: A

− → D = ⇒ A ≥ D

Worst delay: d(A, S) = sup

t∈R+{inf{d ∈ R+|A(t) ≤ D(t + d)}}

Arrival curve and services

A common period

Problem transformation

A common period

Problem transformation Initial problem: Flow : Fi =< Ti, Oi, Si >, F = {F1, .., Fn}

1 source periodic messages Size, Period, Offset Priority

A common period

Problem transformation Initial problem: Flow : Fi =< Ti, Oi, Si >, F = {F1, .., Fn}

1 source periodic messages Size, Period, Offset Priority

Transformed problem: A = {A1, .., Am}

Period T = ppcm(Ti) Offset Oj Size Sj

Donner un exemple (avec figure)

Arrival curve

Arrival curve α1..k (Theorem 5) Capture the synchronization Efficient algorithm Required common period

A O P α A′ O′ P α A + A′ 2α αA+A′

State of the art: hDev(Ai, Di) ≤ hDev(αi, β −

j<i

αj − L)

Taking into account synchronization between flows A1..Ai−1

αi β − α1..i−1 − L

hDev(αi, βi − α1..i−1)

Bound busy period for high priority flows (1..i) Pessimistic if several messages of the same flow are in the same busy period

(

α1

)

( )

i,1 i,2 i,1 i,2

8,6cm

Requires good knowledge of Ai

Ai Di Di

hDev(Ai, Di) hDev(Ai, Di)

Table of Contents

1

Context and goal

2

Computing an upper bound on network delay

3

Experimental results Phases bounded by 0ms Phases bounded by ±1ms Phases bounded by ±5ms Phases bounded by ±10ms

4

Conclusion