Download presentation
Presentation is loading. Please wait.
Published byAbigail Evans Modified over 11 years ago
1
THIS TEXT WILL NOT BE SHOWN DURING PRESENTATION! Design by Jon Angelo Gjetting www.gjetting.com ndgf@gjetting.com Reproducability not allowed without explicit written consent from Jon Angelo Gjetting. The development in Network Performance And its impact on the computing model of tomorrow
3
The GRiD Named after the power-grid Sometimes referred to as the information power grid Like the power-grid GRID should be powered by large installations –not individual generators
4
Philosophy Current Internet only allows access to information The GRiD should provide access to any desired resource –CPU/SuperComputers –Storage –Applications
5
Performance Improvement since 1988
6
Rules of the Game Copenhagen-Stockholm 1988 –Latency 40 ms –Bandwidth 64 kb/s 2005 –Latency 10 ms –Bandwidth 10Gb/s Networking is much better
7
Is There an Improvement? Whether we have an improvement depend on our watch!
8
CPU Whether we have an improvement depend on our watch! Is There an Improvement?
9
CPU Outer Clock Inner Clock Whether we have an improvement depend on our watch! Is There an Improvement?
10
Rules of the Game Copenhagen-Stockholm Using the inner clock 1988 –1B: 0.8M CPU cycles –1GB: 2T CPU cycles 2005 –1B: 39M CPU cycles –1GB: 3G CPU cycles Latency is much worse But bandwidth is much better
11
Rules of the Game Harddrive-Memory Using the inner clock 1988 –1B: 1M CPU cycles –1GB: 1G CPU cycles 2005 –1B: 13M CPU cycles –1GB: 38G CPU cycles Hard-drives are also much worse
12
Development as seen from the CPU
13
Why is GRID? Network bandwidth is now here
15
Transparent Remote File Access Huge input files incur a number of problems: –Download time vs. total execution time –Job execution on the resource is delayed –Storage requirements on resources Often only small scattered fragments of input files are needed How about automatic on-demand download of needed data?
16
int fd = open(inputfile, O_RDONLY); while ((i=read(fd, &buffer, 2000)) >0){ /* process buffer */ } Example User applications need not be recompiled or rewritten!
17
Communication Protocol HTTP supports a range parameter in get request: GET /inputfile HTTP/1.1 HOST: MiG_server.imada.sdu.dk Range: bytes=2000-3000 No range support in put requests –In order to support writing to remote files, a custom web server is developed
18
Overriding file-access Override a subset of file manipulating routines: –open, close, read, write, seek, dup, sync, etc. Preload this library using the LD_PRELOAD environment variable –Requires user apps to be dynamically linked Forward local file access to the native file system using the dlfcn library
19
Efficient Access Simple solution: general purpose block size based on n/2-analysis Advanced solution: depends on the user application: –The nature of the application (sequential vs non- sequential file access) –The block size used in the application Introduce prefetching (1 block read-ahead) Adjust the block size dynamically based on the prefetching and the time taken to transfer a block
20
Experiments 4 experiments: – Overhead: read a one byte file – I/O intensive application: Checksum a 1 GB file – I/O balanced application: Process a 1 GB file – Partial file traversal: Search a 360 MB B+ tree for a random key 3 test setups: – Local execution – Copy model – Remote access model
21
Baseline Performance 100Mb net ExperimentLocalCopyRemote 1B file0.0020.1520.008 Checksum50.11130.1114.3 Balanced632.83721.22600.72 B+ Tree0.00230.6920.0186
22
Latency tests
23
Checksum
24
Balanced
25
B+ Tree
27
True End of the PC? If we can eliminate the disk we eliminate >60% of the errors in the PC But perhaps we dont need the PC –The average PC utilizes less that 5% of its capacity (Source: Intel) Reality is that the PC is –Much too powerful most of the time –Not nearly powerful enough the rest of the time So we eliminate the PC?
28
Bandwidth for Remote users A graphics intensive user –Screen size: 1600x1400 –Frequency: 50Hz –Color depth: 32b –Compression 1:10 Required bandwidth: 0.33 Gb/s Translates into 30 users per 10Gb line
29
Bandwidth for Remote users A typical user –Screen size: 1280x1024 –Frequency: 30Hz –Color depth: 24b –Compression 1:100 Required bandwidth: 0.008 Gb/s Translates into 1138 users per 10Gb line
30
World of Tomorrow? GRID User Resource GRID Dis k
31
The Grid Terminal
32
Grid terminal
33
But we have seen this before? Is this not just another thin client? No! –Thin clients work against dedicated servers –Grid has no single point of failure –And Grid has competition
35
Distributed Shared Memory
36
DSM Test – the problem… PointsLatency (us)Bandwidth (MB/s) SDU-SDU13063.0 NBI-NBI25095.3 SDU-NBI175576.3 SDU-DIKU176764.7 NBI-DIKU342258.1
37
The Results
39
Conclusion and Predictions No reason to expect any change in the development of performance Networks will be increasingly slower But bandwidth is limited only by demand Grid will allow users to ignore computer maintenance and backups Even individual home-users will join Grid
40
THIS TEXT WILL NOT BE SHOWN DURING PRESENTATION! Design by Jon Angelo Gjetting www.gjetting.com ndgf@gjetting.com Reproducability not allowed without explicit written consent from Jon Angelo Gjetting.
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.