Download UDL Mesh Network over DVB-S

Survey
yes no Was this document useful for you?
   Thank you for your participation!

* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project

Document related concepts

IEEE 802.1aq wikipedia , lookup

Zero-configuration networking wikipedia , lookup

RapidIO wikipedia , lookup

Network tap wikipedia , lookup

IEEE 1355 wikipedia , lookup

Piggybacking (Internet access) wikipedia , lookup

Computer network wikipedia , lookup

Net bias wikipedia , lookup

Airborne Networking wikipedia , lookup

Wake-on-LAN wikipedia , lookup

Deep packet inspection wikipedia , lookup

Recursive InterNetwork Architecture (RINA) wikipedia , lookup

Cracking of wireless networks wikipedia , lookup

Internet protocol suite wikipedia , lookup

Throughput wikipedia , lookup

TCP congestion control wikipedia , lookup

Transcript
Implementation of IP
Mesh Network using ULE
Protocol over DVB-S
Links
Ang Way Chuang ([email protected])
Wan Tat Chee ([email protected])
Network Research Group
School Of Computer Sciences
Universiti Sains Malaysia
11800 USM, Penang, Malaysia.
Introduction

Satellite-based Internet connectivity
• Provides access to rural / underserved
communities
• Able to operate in areas without existing
telecommunications infrastructure
• Quick setup for disaster relief and
recovery efforts (e.g., earthquakes,
tsunami, etc.)
April 12
(c) 2006 TC Wan
2
Issues






Existing satellite-link based Internet access
equipment is expensive
Existing technology has inefficient spectrum
usage
Existing hub-based network averages two hops
among nodes (high latency)
DVB-S is a cost-effective method used in satellite
TV broadcast (e.g., Astro)
However, It is unidirectional in nature
Unidirectional Link Mesh Network implements
bidirectional network access using DVB-S
technology
April 12
(c) 2006 TC Wan
3
Existing Point-to-Point
Satellite Links
April 12
(c) 2006 TC Wan
4
UniDirectional Link Mesh
Networking Approach
April 12
(c) 2006 TC Wan
5
Hardware Requirements



An ASI (Asynchronous Serial Interface)
card to transmit MPEG2-TS packet (Linear
Systems’ DVB Master FD).
(N – 1) DVB receiver cards where N is the
number of nodes in the UDL mesh
network. List of supported DVB receiver
cards:
http://www.linuxtv.org/wiki/index.php/DV
B-S_cards.
A DVB-S modulator (Newtec NTC2177).
April 12
(c) 2006 TC Wan
6
Node Configuration
(for 3-Node WAN network)
April 12
(c) 2006 TC Wan
7
Configuration for 3 Nodes Test Bed
April 12
(c) 2006 TC Wan
8
Bidirectional DVB-S
ULE Architecture
April 12
(c) 2006 TC Wan
9
Experiment and Result
April 12
(c) 2006 TC Wan
10
Experiment and Result (cont)
Throughput for TCP Unicast v.s. TCP Window Size
2000
1800
TCP WS
216KBytes
Throughput (kbps)
1600
1400
TCP WS
180KBytes
1200
1000
Log. (TCP
WS
216KBytes)
800
600
Log. (TCP
WS
180KBytes)
400
200
0
1
14 27 40 53 66 79 92 105 118 131 144 157 170 183 196
Time (s)
April 12
(c) 2006 TC Wan
11
Experiment and Result (cont)
Throughput Comparison for TCP Unicast on 8Mbps DVB-Mesh v.s.
Benchmark on 10Mbps Wired LAN
Benchmark
10Mbps Wired
LAN TCP WS
216KBytes
10000
9000
Throughput(kbps)
8000
8Mbps UDLMesh TCP WS
216KBytes
7000
6000
5000
4000
3000
2000
1000
0
1
15 29 43 57 71 85 99 113 127 141 155 169 183 197
Time (s)
April 12
(c) 2006 TC Wan
Log.
(Benchmark
10Mbps Wired
LAN TCP WS
216KBytes)
Log. (8Mbps
UDL-Mesh TCP
WS
216KBytes)
12
Experiment and Result (cont)
Throughput for UDP Unicast v.s. Offered Load
7000
6000
Throughput (kbps)
1Mbps
5000
2Mbps
3Mbps
4000
4Mbps
5Mbps
3000
6Mbps
2000
7Mbps
8Mbps
1000
0
1
2
3
4
5
6
7
8
9
Time (s)
April 12
(c) 2006 TC Wan
13
Experiment and Result (cont)
Average Packet Loss for UDP Unicast
8Mbps
40%
45%
40%
Packet Loss (%)
35%
6Mbps
29%
30%
1Mbps
2Mbps
3Mbps
25%
4Mbps
5Mbps
16%
20%
15%
5Mbps
6Mbps
7Mbps
10%
5%
7Mbps
32%
8Mbps
1Mbps
0%
2Mbps
0%
3Mbps
0%
4Mbps
0.18%
0%
Bandwidth Type
April 12
(c) 2006 TC Wan
14
Experiment and Result (cont)
Throughput Comparison for TCP Unicast and UDP
Unicast
4500
4000
TCP (Window
Size
216KBytes)
Throughput(kbps)
3500
3000
UDP
(Bandwidth
4Mbps)
2500
2000
Log. (UDP
(Bandwidth
4Mbps))
1500
1000
Log. (TCP
(Window Size
216KBytes))
500
0
1
13
25 37 49
61 73 85
97 109 121 133 145 157 169 181 193
Time (s)
April 12
(c) 2006 TC Wan
15
Analysis of Result



All UDL nodes are allocated 8Mbps of
bandwidth for the tests.
The throughputs of TCP and UDP traffic
are about 1/2 and 1/8 of allocated
bandwidth respectively.
ASI card buffer queue affects the latency
of packet sending. Less buffer queue
decreases latency, but increases CPU
usage due to more interrupts and context
switches.
April 12
(c) 2006 TC Wan
16
Analysis of Result (cont)



Faulty ASI card firmware disables
automatic null packets insertion. Thus
bidirectional module need to insert null
packets manually.
Consequently, real data packets have to
compete with null packets for resources.
Thus the performance is less than ideal.
Due to high latency, bigger TCP window
size results in better throughput.
April 12
(c) 2006 TC Wan
17
Future Work
Reimplemention of bidirectional
module as a kernel space module to
cut the cost of context switches and
improve performance.
 Try to obtain an ASI card that
properly insert null packets
automatically.

April 12
(c) 2006 TC Wan
18
Links & Contacts
IP over DVB-S via ULE research page:
http://nrg.cs.usm.my/satellite_ule.htm
 Bidirectional module research page:
http://nrg.cs.usm.my/ule.htm
 Coordinator: [email protected]
 Developers: [email protected],
[email protected],
[email protected].

April 12
(c) 2006 TC Wan
19