21
Performance Analysis of Home Streaming Video Using Orb Rabin Karki, Thangam Seenivasan, Mark Claypool and Robert Kinicki Worcester Polytechnic Institute Presented By: Rabin Karki 27 May, 2010

Performance Analysis of Home Streaming Video Using Orb Rabin Karki, Thangam Seenivasan, Mark Claypool and Robert Kinicki Worcester Polytechnic Institute

Embed Size (px)

Citation preview

Page 1: Performance Analysis of Home Streaming Video Using Orb Rabin Karki, Thangam Seenivasan, Mark Claypool and Robert Kinicki Worcester Polytechnic Institute

Performance Analysis of Home Streaming Video Using Orb

Rabin Karki, Thangam Seenivasan, Mark Claypool and Robert Kinicki

Worcester Polytechnic Institute

Presented By:Rabin Karki27 May, 2010

Page 2: Performance Analysis of Home Streaming Video Using Orb Rabin Karki, Thangam Seenivasan, Mark Claypool and Robert Kinicki Worcester Polytechnic Institute

2

Introduction

• Video streaming largest fraction of Web-based traffic to homes [cite]

• New trend - users streaming video from home to Internet

• Needs:

–Understand how available bandwidth determined

–Measure bandwidth use of new systems

–Ascertain video quality

Page 3: Performance Analysis of Home Streaming Video Using Orb Rabin Karki, Thangam Seenivasan, Mark Claypool and Robert Kinicki Worcester Polytechnic Institute

3

Introduction

• Orb – free video streaming system from home to the Internet

• Features– MyCast service– Instant access to photos, music, videos,

television, and other digital content on PC– Access anytime and from any Internet-

connected device

• Launched in 2005, now 7+ million users

Page 4: Performance Analysis of Home Streaming Video Using Orb Rabin Karki, Thangam Seenivasan, Mark Claypool and Robert Kinicki Worcester Polytechnic Institute

4

Overview

• Introduction• Goals• Experiments• Results• Conclusions

Page 5: Performance Analysis of Home Streaming Video Using Orb Rabin Karki, Thangam Seenivasan, Mark Claypool and Robert Kinicki Worcester Polytechnic Institute

5

Goals

• Ascertain how Orb determines bandwidth available for streaming

• Measure Orb network traffic under different bandwidth constraints

• Investigate video performance at streaming client

• Understand resource usage at streaming host

Page 6: Performance Analysis of Home Streaming Video Using Orb Rabin Karki, Thangam Seenivasan, Mark Claypool and Robert Kinicki Worcester Polytechnic Institute

6

Overview

• Introduction• Goals• Experiments• Results• Conclusions

Page 7: Performance Analysis of Home Streaming Video Using Orb Rabin Karki, Thangam Seenivasan, Mark Claypool and Robert Kinicki Worcester Polytechnic Institute

7

Orb – Streaming Modes

Page 8: Performance Analysis of Home Streaming Video Using Orb Rabin Karki, Thangam Seenivasan, Mark Claypool and Robert Kinicki Worcester Polytechnic Institute

8

Experiments – Setup

Orb Server

WPI LAN

Host PC Router Client PC

Internet

Direct streaming

Uplink Bandwidth estimation

Downlink Bandwidth estimation

Direct streaming

Host and Client PC• Windows XP running Orb

Router • Linux with Netem

Network• Direct streaming

Tools• Wireshark and MediaTracker

Page 9: Performance Analysis of Home Streaming Video Using Orb Rabin Karki, Thangam Seenivasan, Mark Claypool and Robert Kinicki Worcester Polytechnic Institute

9

Experiments – Videos Used

Encode:• Windows Streaming Media, low quality

320x240, 768 kbps, 25 fps• Windows Streaming Media, high quality

1280x720, 1546 kbps, 25 fps• Flash Video

320x214, 320 kbps

Source:• Documentary, High def,

.mov video, 150 seconds

Page 10: Performance Analysis of Home Streaming Video Using Orb Rabin Karki, Thangam Seenivasan, Mark Claypool and Robert Kinicki Worcester Polytechnic Institute

10

Overview

• Introduction• Goals• Experiments• Results• Conclusions

Page 11: Performance Analysis of Home Streaming Video Using Orb Rabin Karki, Thangam Seenivasan, Mark Claypool and Robert Kinicki Worcester Polytechnic Institute

11

Low Quality Video: Frame Rate

• Lower frame rate suggests coarse scaling

• 250 ends later

Page 12: Performance Analysis of Home Streaming Video Using Orb Rabin Karki, Thangam Seenivasan, Mark Claypool and Robert Kinicki Worcester Polytechnic Institute

12

Low Quality Video: Bit rate

• Different encoding levels suggest quality scaling.

• Extremely low bitrate at 250 kbps

Page 13: Performance Analysis of Home Streaming Video Using Orb Rabin Karki, Thangam Seenivasan, Mark Claypool and Robert Kinicki Worcester Polytechnic Institute

13

Low Quality Video: Bandwidth

• Video streamed just below available b/w (except 250 kbps)

Page 14: Performance Analysis of Home Streaming Video Using Orb Rabin Karki, Thangam Seenivasan, Mark Claypool and Robert Kinicki Worcester Polytechnic Institute

14

High Quality Video: Frame rate

• Frame rates similar to low quality video.

Page 15: Performance Analysis of Home Streaming Video Using Orb Rabin Karki, Thangam Seenivasan, Mark Claypool and Robert Kinicki Worcester Polytechnic Institute

15

High Quality Video: Bit rate

• Bitrates different than low quality

• When buffer progress is 100% for some time, bit rate is doubled.

• If buffer progress doesn’t improve, bit rate is reduced.

Page 16: Performance Analysis of Home Streaming Video Using Orb Rabin Karki, Thangam Seenivasan, Mark Claypool and Robert Kinicki Worcester Polytechnic Institute

16

High Quality Video: Bandwidth

•Bandwidth used more closely follows the bandwidth settings than do the encoded bitrates.

Page 17: Performance Analysis of Home Streaming Video Using Orb Rabin Karki, Thangam Seenivasan, Mark Claypool and Robert Kinicki Worcester Polytechnic Institute

17

Host Load

To FLV To WMV0

20

40

60

80

100

120

140

160

180

FLVWMVWMV (HQ)

CP

U L

oad

(%

) Source Format

Page 18: Performance Analysis of Home Streaming Video Using Orb Rabin Karki, Thangam Seenivasan, Mark Claypool and Robert Kinicki Worcester Polytechnic Institute

18

Overview

• Introduction• Goals• Experiments• Results• Conclusions

Page 19: Performance Analysis of Home Streaming Video Using Orb Rabin Karki, Thangam Seenivasan, Mark Claypool and Robert Kinicki Worcester Polytechnic Institute

19

Conclusions

• Bit rate adapts to capacity constraints using TCP

• Temporal and quality scaling

– Temporal scaling coarse

– Quality scaling smoother for low-quality video

• Transcoding in real-time

– Resource intensive for streaming host

Page 20: Performance Analysis of Home Streaming Video Using Orb Rabin Karki, Thangam Seenivasan, Mark Claypool and Robert Kinicki Worcester Polytechnic Institute

20

Future work

• Other devices• Indirect streaming• Other network settings

Page 21: Performance Analysis of Home Streaming Video Using Orb Rabin Karki, Thangam Seenivasan, Mark Claypool and Robert Kinicki Worcester Polytechnic Institute

21

Thank you!

Questions?