Upload
cory-mitchell
View
216
Download
2
Embed Size (px)
Citation preview
Developing the Web100 Based Network Diagnostic Tool (NDT)
E2EpiPEs/Web100 Joint Session
April 9, 2002
by
Rich Carlson
Argonne National Laboratory
4/8/03 2
Motivation for work
• Develop “single shot” diagnostic tool that doesn’t us historical data
• Measure performance to users desktop
• Combine numerous Web100 variables to analyze connection
• Develop network signatures for ‘typical’ network problems
4/8/03 3
NDT Benefits
• End-user based view of network
• Can be used to identify performance bottlenecks (could be host problem)
• Provides some ‘hard evidence’ to users and network administrators to reduce finger pointing
• Doesn’t rely on historical data
4/8/03 4
Network Signatures
• Duplex Mismatch Detection– Good results in Campus environment
• Faulty Hardware/Link– Few reports, needs more work
4/8/03 5
Network Signatures
• Bottleneck Link Type– New detection algorithm being developed
• Link Duplex setting– Needs more work
• Normal Congestion– Needs more work
4/8/03 6
Current Deployment• 3 servers at ANL
– Miranda Externally visible– Ophelia, Cordelia ANL Internal only
• Non-ANL Servers– Swiss Education and Research Network (SWITCH)– University of Michigan - Flint, MI– University of California - Santa Cruz, CA– Rochester Institute of Technology - Rochester, NY– StarLight peering point (coming soon)
4/8/03 7
Availability
• Tools available via anonymous ftp from: achilles.ctd.anl.gov/pub/web100 directory– Contains source code and executables
• Email discussion list <[email protected]>– Majordomo list <[email protected]>– subscribe ndt
4/8/03 8
Installation and Configuration
• Download and Build Web100 kernel/lib– grab base kernel from ftp.kernel.org– apply web100 patch– run favorite ‘kernel config’ command
• enable experimental code
• enable web100 specific code
– make and install web100lib{.a|.so}– reboot and you’re ready to rock & roll
4/8/03 9
Installation and Configuration
• Download web100-tools.tar{.gz} from ANL anonymous FTP server (achilles.ctd.anl.gov)– decide to run pre-compiled or ‘make’ your own
• grab java SDK from sun for javac compiler
– ensure web100srv program can access web100lib routines
• change LD_LIBRARY_PATH environment variable
• edit /etc/ld.so.conf and add /usr/local/lib, run ldconfig
– start fakewww & web100srv programs and you’re off to the races (start.ndt script provided)
4/8/03 10
Results and Observations
• Faulty Hardware identification
• New Link Detection algorithm & preliminary results
• Mathis et.al formula fails
• Usage statistics
• Demo
4/8/03 11
Effect of Faulty HW & Congestion
100 Mbps FD
Ave Rtt %loss loss/sec5.41 0.00 0.03
1.38 0.78 15.11
6.16 0.00 0.03
14.82 0.00 0.1010 Mbps
72.80 0.01 0.03
8.84 0.75 4.65
Speed94.09 Good
22.50 Bad NIC
82.66 Bad reverse
33.61 Congestion
6.99 Good
7.15 Bad NIC
4/8/03 12
New Link Detection Algorithm
• Uses Packet-Pair timing– Small Libpcap program captures data– Timing taken for each transmit/receive pair– Results quantized into unique bins– Statistical analysis on resulting bin counts
• Will compare results with Paxson’s “Receiver-Side Estimation Algorithm”
4/8/03 13
Comparison between old and new link type detection
010203040506070
80
Percent
Link type
old
new
4/8/03 14
Mathis et.al. Formula fails
• Estimate = (K * MSS) / (RTT * sqrt(loss))– old-loss = (Retrans - FastRetran) / (DataPktsOut - AckPktsOut)
– new-loss = CongestionSignals / PktsOut
• Estimate < Measured (K = 1)– old-loss 91/443 (20.54%)– new-loss 35/443 (7.90%)– old agrees with new 26/35 (74.29%)
4/8/03 15
Usage by Top Level Domain Name
NDT usage April 02 - March 03 20073 Tests from 70 unique domains
net 38%
com 27%
edu 8%
mil 0%
gov 4%
org 0%
ccTLD (62)11%
noDNS12%
arpa 0%
4/8/03 16
Demo
http://miranda.ctd.anl.gov:7123http://miranda.ctd.anl.gov:7123
4/8/03 17
Disclosure/Disclaimer
• This work was supported (in part) by the Office of Science, U.S. Department of Energy under Contract W-31-109-ENG-38
• Packet-Pair work was supported by the Cisco University Research Program Work-for-Others Contract P-03008