The Performance of Remote Display Mechanisms for Thin-Client Computing
S.Jae Yang, Jason Nieh, Matt Selsky, and Nikhil TiwariDepartment of Computer Science
Columbia University
Kim, Byeong GilSoftware & System Laboratory
@ kangwon Natl. Univ.
Introduction Background
shifted to the distributed model of desktop computing become unmanageble more centralized and easier-to-manage computing strate
gy Purpose
is to centralize computing resources. Maintain the same quality of service for the end user. Require less maintenance and less frequent upgrades. Can be shared server resources.
Introduction(con’t) Improvement
~ Graphical computing environment
What do we analyze? to assess the general feasibility of the
thin-client computing model to compare various thin-client platforms to determine the factors that govern
their performance
Thin-client platforms
Measurement Methodology Standard benchmarks
Benchmark applications are executed on the server
Benchmarks measure the server’s performance Benchmarks do not reflect the user’s experience
at the client-side slow-motion benchmarking
Use network packet traces to monitor the latency and data
Insert delays between the separate visual events
Slow-motion benchmark
Experimental Testbed Composition
Network emulator machine- ISDN(128Kbps), DSL(768Kbps), T1(1.5Mbps), 10BaseT(10Mbps), 100BaseT(100Mbps)
Packet monitor machine- obtain the measurements for slow-motion benchmarking
Thin client/server systems- used the same client/server hardware (except Sun Ray)- video resolution : 1024x768, 8-bit (Sun Ray : 24-bit)- compression and memory caching : ON- disk caching : OFF
Web server
Web Benchmark Modified i-Bench web benchmark
introduce delays of several seconds displayed each page completely was no temporal overlap used the packet monitor
Environment Netscape Navigator 4.72 Browser’s memory cache and disk cache were
enabled Netscape browser window was 1024x768
Video Benchmark Playback rates
1 fps- establish the reference data size
24 fps- playback performance - video quality
Video quality(VQ)
Experimental Results Default Configurations
default settings demonstrate the performance of a traditional
“fat” client system Underlying baseline remote display
encodings disabled configurable caching and compression
mechanisms measure for experiments at 100Mbps
Caching and compression mechanisms
Default Configuration
Web Performance
Default Configuration
Web Performance
Default Configuration
Video Performance
Default Configuration
Video Performance
Baseline Display Encoding primitives
Web Performance
Baseline Display Encoding primitives
Video Performance
Caching and Compression
Environment All caching and compression options
disabled All compression only options enabled All caching only options enabled All caching and compression options
enabled
Caching and Compression
Web Performance
Caching and Compression
Web Performance
Caching and Compression
Video Performance
Memory versus DiskCaching Memory caching
provide much faster access times to smaller caches. Disk caching
provide larger amounts of local cache with relatively slower access times
Environments Platform – Citrix MetaFrame (ICA) Disk cache size – 39MB Minimum cacheable bitmap size – 8KB Memory cache size – 8MB
Memory versus DiskCaching(con’t)
Memory versus DiskCaching(con’t)
Memory versus DiskCaching(con’t)
improves ICA performance at bandwidths below 768Kbps is much faster to fetch data from the client disk cache than going across the network to the server
Conclusions Higher-level graphics display primitives are
not always more bandwidth efficient than lower-level-display encoding primitives.
The timing in sending display updates. Display caching and compression are
techniques which should be used with care as they can help or hurt thin-client performance.
Thin-client design and implementation choices across environments.
References
Primary The Performance of Remote Display Mechanis
ms for Thin-Client Computing- S. Jae Yang, Jason Nieh, Matt Selsky, and Nikhil Tiwari (June 2002)
Additional Measuring Thin-Client Performance Using Slow-Motio
n Benchmarking- S.J. Yang, J.Nieh, and N. Novik (June 2001)