Automated and Scalable QoS Control - For Network Convergence Wonho - - PowerPoint PPT Presentation

▶
automated and scalable qos control
SMART_READER_LITE
LIVE PREVIEW

Automated and Scalable QoS Control - For Network Convergence Wonho - - PowerPoint PPT Presentation

Jun 10, 2023 48 likes •411 views

Automated and Scalable QoS Control - For Network Convergence Wonho Kim (Princeton Univ.) Puneet Sharma, Jeongkeun Lee, Sujata Banerjee, Jean Tourrilhes, Sung-Ju Lee, and Praveen Yalagandula (HP Labs) 1 Motivation Why do we care about QoS

slide-1
SLIDE 1

Automated and Scalable QoS Control

  • For Network Convergence

Wonho Kim (Princeton Univ.) Puneet Sharma, Jeongkeun Lee, Sujata Banerjee, Jean Tourrilhes, Sung-Ju Lee, and Praveen Yalagandula (HP Labs)

1

slide-2
SLIDE 2

Motivation

  • Why do we care about QoS control?

− Network convergence − Multi-tenancy networks

  • Automated QoS control is needed

2 29 April 2010

slide-3
SLIDE 3

Network convergence

Map- Reduce Storage

Fibre Channel Ethernet

3 29 April 2010

HPC …

Different protocols, adapters, switches, and configuration

Infiniband …

slide-4
SLIDE 4

Network convergence

Map- Reduce Storage

4 29 April 2010

  • Cost reduction (single network infrastructure)
  • Unified management (single management infrastructure)

HPC

…

Converged Enhanced Ethernet (CEE) Data Center Ethernet (DCE) Data Center Bridging (DCB) Fibre Channel over Ethernet (FCoE) Fibre Channel over CEE (FCoCEE) Fewer switches, ports, adapters, cables Reduced power, equipment, cooling cost Simpler topology I/O consolidation Unified resource management

slide-5
SLIDE 5

Multi-tenancy networks

Customer A Customer C

  • Serve multiple customers with a single fabric
  • Better utilization of network infrastructure

5 29 April 2010

Customer B

slide-6
SLIDE 6

Map- Reduce Storage

Performance isolation

HPC

…

6 29 April 2010

slide-7
SLIDE 7

Map- Reduce Storage

Performance isolation

HPC

…

7 29 April 2010

slide-8
SLIDE 8

Performance isolation

Map- Reduce Storage

8 29 April 2010

HPC

…

slide-9
SLIDE 9

Performance isolation

Map- Reduce Storage

Customer A Customer C Virtualized Servers Variable Workloads

9 29 April 2010

  • Need virtual network slices
  • Need fine-grained performance isolation

HPC

…

Customer B Bugs, malicious attack

slide-10
SLIDE 10

Goal

  • Enables performance isolation with QoS control

Slice 1

…

Slice n

10 29 April 2010

Physical network fabric QoS configuration High-level Specifications

slide-11
SLIDE 11

Good news

  • Most commodity switches have QoS knobs

− rate limiter − priority queues − schedulers

  • Single network domain

− datacenters, enterprise networks, … − free from Layer-8 issues (billing, collaborations, …) − fine-grained control becomes feasible

11 29 April 2010

slide-12
SLIDE 12

Challenges

  • Coarse-grained QoS knobs

− designed for distributed management − class-based − no e2e performance

  • Manual configuration

− no standards for classifiers − error-prone − static (not adaptive)

12 29 April 2010

Storage Traffic CEO/CTO Managers Interns VoIP Fibre Channel Email Web

slide-13
SLIDE 13

Our Solution: OpenFlow QoS Controller

Physical network fabric

Virtual Slice 1

…

Virtual Slice n

13 29 April 2010

QoS configuration High-level Specifications (rate limiter, priority queues, …) Manual & Static setting QoS Controller

  • Automated configuration
  • Fine-grained flow management
  • Adaptive to dynamic workloads

Problem

slide-14
SLIDE 14

Overview of OpenFlow QoS controller

OpenFlow APIs Flow

Src Dest prio prio prio prio rate limit

14 14 29 April 2010

QoS Controller Topology, Nodes, Resource, Flows, … Rate limiters Queue mappings End-to-End performance models Adaptive Aggregator Network-wide Optimization

Shortest Span First …

slide-15
SLIDE 15

Adaptive aggregation

Slice specs Flow specs

flow 1 flow 2 flow 3

Storage

Peak rate: 400 Mbps Delay bound: 10 ms Aggregate: False

Customer DB

src IP: X.X.X.X, port: 9551 Type: IP (UDP), …

15 29 April 2010

flow 3 flow 4

Video Backup

Peak rate: 100 Mbps Delay bound: 100 ms Aggregate: False Aggregate: True

Employee DB VoD

System backup

Log Archive

flow 5 flow 6 flow 7 flow 8

slide-16
SLIDE 16

Available QoS Knobs (Priority queue)

highest Output port short delay

16 29 April 2010

lowest long delay

slide-17
SLIDE 17

Available QoS Knobs (Rate limiter)

highest Output port Peak rate

17 29 April 2010

lowest

slide-18
SLIDE 18

OpenFlow QoS APIs

Rate limiter

Flow 1 Flow 2 Flow 3 Flow 4 H/W rate limiter 1 H/W rate limiter 2

18 18 29 April 2010

Priority queue mapping

Switch 1 Switch 2 Switch 3

  • Extension of OpenFlow specification
  • Expose QoS capability in switches
slide-19
SLIDE 19

OpenFlow QoS APIs

  • With OpenFlow flow control

− fine-grained control of flows − automated flow management

  • With OpenFlow QoS APIs

− uniform control of QoS knobs − configure QoS for individual (or aggregate) flows

19 29 April 2010

slide-20
SLIDE 20

Admission Control

  • Input

− new flow arrival event − performance requirements (peak rate, e2e delay) − database for the current network state − end-to-end performance model − end-to-end performance model

  • Output

− admission control result (accept/reject) − priority queue assignment, rate limiter settings − path selection

20 29 April 2010

slide-21
SLIDE 21

Admission Control

  • Two conditions should be satisfied

− satisfy f ’s performance requirement − not violate existing flows in the networks

21 29 April 2010

slide-22
SLIDE 22

Difficulties in queue assignment

highest (8/10) (10/10) f2 (8/10) (10/10) f1

22 29 April 2010

lowest

f

Switch A Switch B Switch C

We should consider interactions between

  • flows in a switch
  • flows in multiple switches
slide-23
SLIDE 23

Admission control heuristic

  • Goal

− increase the ratio of admitted flows − lower the complexities in queue allocation

  • Shortest Span First (SSF)
  • Basic ideas

− estimate affordable options for a flow − try first switches more likely to reject flow

23 29 April 2010

slide-24
SLIDE 24

Highest level & Lowest level

high Shorter delay bound More likely to violate other flows

f

Highest level for f

  • Highest level: not violate existing flows
  • Lowest level: not violate the new flow
  • Span: available options for f

24 29 April 2010

low Switch Longer delay bound More likely to violate flow f Lowest level for f

slide-25
SLIDE 25

Shortest Span First (SSF)

high

src dest

f

  • Step 1: compute highest & lowest levels independently

25 29 April 2010

low Switch A Switch B Switch C

slide-26
SLIDE 26

Shortest Span First (SSF)

high

src dest

f

  • Step 2: sort switches in order of the span

26 29 April 2010

low Switch A Switch B Switch C

slide-27
SLIDE 27

Shortest Span First (SSF)

high

src dest

f

  • Step 2: sort switches in order of the span

27 29 April 2010

low Switch C Switch A Switch B

slide-28
SLIDE 28

Shortest Span First (SSF)

high

src dest

f

  • Step 3: try highest level at each hop

− try first a switch more likely to reject flow

28 29 April 2010

low Switch C Switch A Switch B

slide-29
SLIDE 29

Implementataion

  • QoS APIs implemented on

− hardware switch (HP ProCurve 5406zl) − software switch (Open vSwitch)

  • QoS Controller implemented on top of NOX

− open-source OpenFlow controller − http://noxrepo.org

  • QoS Controller web interface

29 29 April 2010

slide-30
SLIDE 30

Prototype

Switch A

Host A Host B

QoS Controller

HTTP OpenFlow OpenFlow OpenFlow Output 14 Priority 7

30 29 April 2010

Host C Host D

Switch B Switch C Output 21 Priority 7

Peak rate 400 Mbps Delay bound 10 ms

400

slide-31
SLIDE 31

Evaluation

  • Traffic generation

− generate 3 guaranteed flows from emulated services (UDP) − generate cross traffic (UDP, TCP)

  • Disable/Enable QoS controller
  • Measured throughput and packet loss in testbeds

31 29 April 2010

slide-32
SLIDE 32

Throughput with UDP cross traffic

Generate cross traffic

32 29 April 2010

Enable QoS Controller

Flow name Route (queue assignment) Customer DB H3 – S3(8) – S1(8) – H1 Employee DB H4 – S3(8) – S1(8) – H2 VoD H3 – S3(7) – S1(7) – H1 System Backup H4 – S3(1) – S1(1) – H2

QoS controller protects guaranteed flows in congestion

slide-33
SLIDE 33

Packet loss with TCP cross traffic

10 TCP 30 TCP

QoS control is needed even when most traffic in network is TCP

33 29 April 2010

1 TCP Enable QoS Controller

slide-34
SLIDE 34

Future works

  • Evaluations

− effectiveness of admission control heuristics (ratio of admitted flows) − compare with offline optimal assignment − simulations on a variety of datacenter networks (e.g., − simulations on a variety of datacenter networks (e.g., Hierarchical, FatTree, …)

  • Deployment

− extend deployment to large networks − test with mixture of services

34 29 April 2010

slide-35
SLIDE 35

Conclusion

  • Single integrated network fabric is desirable
  • We need fine-grained automated QoS control
  • Contributions

− Design & Implement OpenFlow QoS APIs − QoS controller: automated QoS control for network slicing

35 29 April 2010

slide-36
SLIDE 36

Thank you

36 29 April 2010