Transcript
Performance and Robustness Testing of Wireless Web Servers Guangwei Bai Kehinde Oladosu Carey Williamson
November 26, 2002
TeleSim Research Group
1
1. Introduction and Motivation Observation: the same wireless technology
that allows a Web client to be mobile also allows Web servers to be mobile Idea: portable, short-lived, ad hoc networks Possible applications: o classroom area networks, seminars o press conferences, media events o sporting events, gaming, exhibitions o conferences and trade shows o disaster recovery sites, field work, etc. November 26, 2002
TeleSim Research Group
2
Background: Portable Networks Assumptions: the characteristics of a
portable short-lived network are: o set it up when needed; tear down after o only needed for minutes or hours o when may not be known a priori o where may not be known a priori o no existing infrastructure of any kind o general Internet access not available o general Internet access not required o pre-defined content; target audience o 1-100 users; mobile; limited bw needed November 26, 2002
TeleSim Research Group
3
2. Objectives to assess feasibility of portable networks
to benchmark the performance capabilities and limitations of an Apache Web server in a wireless ad hoc network to identify the performance bottlenecks to understand impacts of different factors o number of clients o Web object size o persistent connections o transmit power (energy consumption) o wireless channel conditions November 26, 2002
TeleSim Research Group
4
3. Experimental Setup
• Compaq Notebooks (1.2GHz Pentium III, 128MB RAM, 512 KB L2 cache, Cisco Aironet 350 network cards) • RedHat Linux 7.3, httperf, Apache 1.3.23, SnifferPro 4.6 • Network: 11 Mbps IEEE 802.11b wireless LAN, ad hoc mode November 26, 2002
TeleSim Research Group
5
Experimental Setup (Cont’d) • IEEE 802.11b: a standard for wireless LANs Carrier Sense Multiple Access with Collision Avoidance (CSMA/CA), up to 11 Mbps data rate at physical layer
• ad hoc mode frames are addressed directly from sender to receiver
• httperf Web benchmarking software tool developed at HP Labs
• Web server: Apache (version 1.3.23) Process-based, flexible, powerful, HTTP/1.1-compliant
• SnifferPro 4.6 real-time capture, recording all wireless channel activity, enabling protocol analysis at MAC, IP, TCP and HTTP layers November 26, 2002
TeleSim Research Group
6
4. Experimental Design • Impacts of different factors on wireless Web server performance (one-factor-at-a-time) Experimental Factors and Levels
Factor
Number of Clients HTTP Transaction Rate (per-client)
Levels 1, 2, 4 10, 20, 30, …, 160
HTTP Transfer Size (KB) Persistent Connections HTTP Requests per Connection Transmit Power (mW)
1, 2, 4, 8, …, 100 no, yes 1, 5, 10, 15, …, 60 1, 5, 20, 30, 50, 100
Client-Server Distance (m)
1, 10, 100
• Performance metrics – HTTP transaction rate, throughput, response time, error rate at Application Layer, – TCP connection duration at Network Layer – Transmit queue behaviour at Link Layer,
7
5. Measurement Results and Analyses - Expt 1: Request Rate - Expt 2: Transfer Size - Expt 3: Number of Clients - Expt 4: Persistent Connections - Expt 5: Transmit Power - Expt 6: Wireless Channel
November 26, 2002
TeleSim Research Group
8
Experiment 1: Request Rate Purpose: to determine the range of feasible and sustainable loads for the wireless Web server
Design: • Number of Clients: 1 • HTTP transaction rate: 10, 20, …, 160 req/sec • HTTP transfer size: 1 KB (fixed) • Persistent connections: no • Transmit power: 100 mW • Client-server distance: 1 meter (on same desk)
November 26, 2002
TeleSim Research Group
9
Wireless Web Performance at Application Layer
Main observation: • As the offered load increases: linear increase instability lower plateau
• Peak throughput < 1 Mbps for 1 KB transfers November 26, 2002
TeleSim Research Group
10
Transmit Queue Behaviour for Experiment 1
Main observation: Wireless LAN is the bottleneck • Packet drops occur from link-layer queue (client side) • Even before they get on the wireless LAN!!! Reason: • No flow control / backpressure mechanism • Note: default queue size is 100 in the Linux kernel November 26, 2002
TeleSim Research Group
11
Wireless Web Performance at Application Layer (Cont’d)
Main observation: • the response time is about 9 ms at low load, increase significantly to over 2 sec at high load (>85 req/sec) • failures occur frequently under overload November 26, 2002
TeleSim Research Group
12
Measurement at Network Layer
Low load: 10 req/sec Stable performance Mean: 9.7ms Medium load: 50 req/sec Greater variation, 2 spikes Mean: 10ms High load: 80 req/sec More variability, some spikes, slight skew Overload: 100 req/sec Queue buildup,Packet drops, Retransmissions,TCP resets November 26, 2002
TeleSim Research Group
13
Experiment 2: Transfer Size Purpose: to study impact of HTTP response size
Design: • Number of Clients: 1 • HTTP transaction rate: 10 req/sec (fixed) • HTTP transfer size (KB): 1, 2, 4, 8, … • Persistent connections: no • Transmit power: 100 mW • Client-server distance: 1 meter (on same desk)
November 26, 2002
TeleSim Research Group
14
Measurement at Network Layer
General observation: as HTTP transfer size increases, mean TCP connection duration increases, as does the variance of distribution.
November 26, 2002
TeleSim Research Group
15
Measurement at Network Layer Light load: 8 KB Duration: 24 msec Throughput: 2.8 Mbps
Medium load: 32 KB Duration: 67 msec Throughput: 3.9 Mbps
Overload: 64 KB Duration: >100 msec Throughput: 4.1 Mbps November 26, 2002
TeleSim Research Group
16
Experiment 3: Number of Clients Purpose: to study impact of high load generated by multiple clients
Design: • Number of Clients: 2, 3, 4 • HTTP transaction rate: 10, 20, …, 160 req/sec • HTTP transfer size: 1 KB (fixed) • Persistent connections: no • Transmit power: 100 mW • Client-server distance: 1 meter (on same desk)
November 26, 2002
TeleSim Research Group
17
Wireless Web Performance at Application Layer (4 Clients)
18
Wireless Web Performance at Application Layer (4 Clients)
Main observation: • 4 clients share network and server resources equally • 30% higher aggregate throughput (110 conns/sec) • bottleneck is now at server network card (drops!!) November 26, 2002
TeleSim Research Group
19
Wireless Web Performance at Application Layer (2 or 3 Clients)
November 26, 2002
TeleSim Research Group
20
Wireless Web Performance at Application Layer (2 or 3 Clients)
Main observation: unfairness problem at high loads: one client obtained a higher proportion of the throughput at expense of another (don’t know why?) November 26, 2002
TeleSim Research Group
21
Experiment 4: Persistent Connections Persistent Connections: • Multiple HTTP transactions can be sent on the same TCP connection. • amortize overhead of TCP connection processing • reduce memory consumption for TCP state Purpose of this experiment: to study impact of persistent connection on wireless Web performance
Design: • Number of Clients: 1 and 2 • HTTP transaction rate: 10 req/sec (fixed) • HTTP transfer size: 1 KB (fixed) • Persistent connections: yes • Transmit power: 100 mW • Client-server distance: 1 meter (on same desk) November 26, 2002
TeleSim Research Group
22
Achieved Throughput for Experiment with Persistent Connections
Main observation: • Peak throughput: 3.22 Mbps, 3.5x improvement over non-persistent connections (0.9 Mbps), • two clients share the server and network resources equally November 26, 2002
TeleSim Research Group
23
Experiment 5: Transmit Power Energy consumption- an important issue for mobile Clients and Server. Purpose: to see what transmit power is required for acceptable performance in classroom setting
Design: • Number of Clients: 1 • HTTP transaction rate: 10 req/sec (fixed) • HTTP transfer size: 1 KB (fixed) • Persistent connections: no • Transmit power: 1, 5, 20, 100 mW • Client-server distance: 10 meter (same floor) November 26, 2002
TeleSim Research Group
24
Measurement at Network Layer
General observation: If transmit power<10 mW: • MAC-layer retransmits • rightward skew • unacceptable perf. If transmit power20 mW: • acceptable performance
November 26, 2002
TeleSim Research Group
25
Experiment 6: Wireless Channel Characteristics Wireless Internet is characterized by limited bandwidth, high error rates, and interference. Purpose: to study the impact of the wireless channel characteristics on wireless Web performance
Design: • Number of Clients: 1 • HTTP transaction rate: 10 req/sec (fixed) • HTTP transfer size: 1 KB (fixed) • Persistent connection: no • Transmit power: 100 mW • Client-server distance: 1m, 10m, 100m November 26, 2002
TeleSim Research Group
26
Measurement at Network Layer (100m scenario) Low load: 10 req/sec Significant skew to the tail of the distribution, Some periodicity (why?)
Medium load: 50 req/sec Significant skew to the tail of the distribution
November 26, 2002
TeleSim Research Group
27
6. Summary and Conclusions What we did: wireless Web server, portable nw • Application-layer measurements (httperf) • Network-layer measurements (Wireless Sniffer)
Our results show: • Server capability: 100 conn/sec for non-persistent HTTP with throughputs up to 4 Mbps (adequate?) • Bottleneck: at wireless network interface • Some “network thrashing” for large HTTP transfers when the network utilization is high (aborts, resets) • Effect of wireless channel on performance at TCP and HTTP-level (MAC-layer retransmits) • Power consumption issue for mobile client and server November 26, 2002
TeleSim Research Group
28
7. Future Work Explaining the anomalies (fairness, periodicity) Better system instrumentation (Linux) More realistic Web workloads Larger WLAN testing (classroom scenario) Repeat experiments with IEEE 802.11a (55 Mbps) Kenny’s M.Sc. Thesis... Another paper?
November 26, 2002
TeleSim Research Group
29