Tools Overview

1
Tools Overview

• Richard Carlson
• January 30, 2007

2
Basic Premise

• Applications performance should meet your
  expectations!
• If they dont you should complain!

3
Underlying Assumption

• When problems exist, its the networks fault!

4
Simple Network Picture
Bobs Host
Network Infrastructure
Carols Host
5
Network Infrastructure
6
Tools, Tools, Tools

• Ping
• Traceroute
• Iperf
• Tcpdump
• Tcptrace
• BWCTL
• NDT
• OWAMP

• AMP
• Advisor
• Thrulay
• Web100
• MonaLisa
• pathchar
• NPAD
• Pathdiag

• Surveyor
• Ethereal
• CoralReef
• MRTG
• Skitter
• Cflowd
• Cricket
• Net100

7
Basic Connectivity Tests

• Ping
• Confirms that remote host is up
• Some network operators block these packets
• Traceroute
• Identifies the routers along the path
• Same blocking problem as above
• Routers treat TR packets with lower priority

8
Sample ping output
9
ping results

• Intro message
• Identifies remote host name and IP address
• States size of packets being sent
• Setting larger sizes may reveal hidden problems
• Output lines
• Who responded, and the RTT, maybe other details
• Summary lines
• Number of packets sent/received/lost
• RTT statistics min/average/max
• Note 1 msec RTT 50 miles of between hosts

10
Sample tracert output
11
traceroute results

• Intro messages
• Name and address of remote host
• Maximum number of link before giving up
• Status messages
• One line per router in path
• indicates router didnt respond
• Routers usually rate limit replies
• No name indicates DNS entry is missing
• Hops required to reach remote host or max number
  from above

12
Test It Yourself

• OK, now you try!

13
Advanced user tools

• Existing NDT tool
• Allows users to test network path for a limited
  number of common problems
• Existing NPAD tool
• Allows users to test local network infrastructure
  while simulating a long path

14
Network Diagnostic Tool (NDT)

• Measure performance to users desktop
• Identify real problems for real users
• Network infrastructure is the problem
• Host tuning issues are the problem
• Make tool simple to use and understand
• Make tool useful for users and network
  administrators

15
NDT user interface

• Web-based JAVA applet allows testing from any
  browser
• Command-line client allows testing from remote
  login shell

16
NDT sample Results
17
Finding Results of Interest

• Duplex Mismatch
• This is a serious error and nothing will work
  right. Reported on main page, on Statistics
  page, and mismatch on More Details page
• Packet Arrival Order
• Inferred value based on TCP operation. Reported
  on Statistics page, (with loss statistics) and
  order value on More Details page

18
Finding Results of Interest

• Packet Loss Rates
• Calculated value based on TCP operation.
  Reported on Statistics page, (with out-of-order
  statistics) and loss value on More Details page
• Path Bottleneck Capacity
• Measured value based on TCP operation. Reported
  on main page

19
Finding a Server

• What? You dont have one running at your site?
• Install the Internet2 Network Performance
  Toolkit Knoppix Disk

20
Finding NDT Servers
21
Test It Yourself

• OK, now you try!

22
NPAD/pathdiag

• A new tool from researchers at Pittsburgh
  Supercomputer Center
• Finds problems that affect long network paths
• Uses Web100-enhanced Linux based server
• Web based Java client

23
Long Path Problem

• E2E application performance is dependant on
  distance between hosts
• Full size frame time at 100 Mbps
• Frame 1500 Bytes
• Time 0.12 msec
• In flight for 1 msec RTT 8 packets
• In flight for 70 msec RTT 583 packets

24
Long Path Problem
H2
70 msec H1 H3
1 msec H1 H2
X
H3
H1
25
TCP Congestion Avoidance

• Cut number of packets by ½
• Increase by 1 per RTT
• LAN (RTT1msec)
• In flight changes to 4 packets
• Time to increase back to 8 is 4msec
• WAN (RTT 70 msec)
• In flight changes to 292 packets
• Time to increase back to 583 is 20.4 seconds

26
NPAD Server main page
27
NPAD Sample results
28
npad results - 1

• Data rate test Pass!
• Pass data rate check maximum data rate was
  8.969226 Mb/s
• Maximum data rate this link did achieve

29
Npad results - 2

• Loss rate test Pass!
• Pass measured loss rate 0.035214 (2839 packets
  between loss events).
• Loss caused by TCP overdriving the path
• FYI To get 7 Mb/s with a 1460 byte MSS on a 22
  ms path the total end-to-end loss budget is
  0.282486 (354 packets between losses).
• Worst case scenario for packet loss

30
Npad results - 3

• Suggestions for alternate tests
• FYI This path may even pass with a more
  strenuous application
•     Try rate7 Mb/s, rtt62 ms
•     Try rate8 Mb/s, rtt48 ms
• Or if you can raise the MTU
•     Try rate7 Mb/s, rtt383 ms, mtu9000 bytes
•     Try rate8 Mb/s, rtt299 ms, mtu9000 bytes
• Helpful hints, you might do better or go farther
  at this rate

31
Npad results - 4

• Network buffering test Pass!
• Pass The network bottleneck has sufficient
  buffering (queue space) in routers and switches.
• Measured queue size, Pkts 36 Bytes 52560
• This corresponds to a 48.333600 ms drain time.
• To get 7 Mb/s with on a 22 ms path, you need
  19250 bytes of buffer space.
• Report on Network devices in path. A cheap
  switch would show up as something with small
  buffers
• ? character indicates clickable icon for more
  details

32
Finding a Server

• What? You dont have one running at your site?
• Install the Internet2 Network Performance
  Toolkit Knoppix Disk

33
Finding NPAD servers
34
Test It Yourself

• OK, now you try!

35
Network Admin Tools

• BWCTL Bandwidth Control
• Allows single person operation over wide area
  testing environment
• Runs NLANR iperf program
• OWAMP One way Delay Measurement
• Advanced ping command
• Allows single person operation over wide area
  testing environment

36
Sample BWCTL results
37
BWCTL Highlights

• You must pre-install BWCTL software package
• New Internet2 default permits basic TCP test from
  any member
• Sites can restrict access to known remote users

38
Using BWCTL commands

• bwctl -L90 -i2 -t20 -c nms1-ipls.abilene.ucaid.ed
  u
• bwctl -L90 -i2 -t20 -s nms1-sttl.abilene.ucaid.edu
  
• Bwctl name of program
• L90 wait up to 90 seconds for a test
• i2 report intermediate results every 2 seconds
• t20 run test for 20 seconds
• s name remote end will send data to you
• c name you will send data to the remote host

39
3rd party testing command

• bwctl -L90 -i2 -t20
• -c nms1-sttl.abilene.ucaid.edu
• -s nms1-ipls.abilene.ucaid.edu
• User can run a test between 2 remote hosts

40
Finding a Server

• What? You dont have one running at your site?
• Install the Internet2 Network Performance
  Toolkit Knoppix Disk

41
Finding BWCTL Servers
42
Test It Yourself

• OK, now you try!

43
OWping Results
44
OWAMP Highlights

• You must pre-install OWAMP software package
• User program is called owping
• New Internet2 default permits basic test from any
  member
• Sites can restrict access to known remote users

45
Using OWPING

• owping nms4-sttl.abilene.ucaid.edu
• owping program name
• nms4 name of server
• Output results
• Separate statistics for both directions
• Number of packets sent and lost
• One-way delay statistics min/median/max
• Number of IP hops in path
• Number of packets that arrives out-of-order

46
Finding a Server

• What? You dont have one running at your site?
• Install the Internet2 Network Performance
  Toolkit Knoppix Disk

47
Finding OWAMP Servers
48
Test It Yourself

• OK, now you try!

49
Under Development

• Emerging PerfSonar tool
• Allows users to retrieve network path data from
  major national and international REN network

50
PerfSonar Next Steps in Performance Monitoring

• New Initiative involving multiple partners
• ESnet (DOE labs)
• GEANT (European Research and Education network)
• Internet2 (Abilene and connectors)

51
PerfSONAR Services

• Measurement Archive (MA)
• Measurement Point (MP)
• Lookup Service (LS)
• Topology Service (TS)
• Authentication Service (AS)

52
PerfSonar Router stats on a path

• Demo ESnet tool
• https//performance.es.net/cgi-bin/perfsonar-trace
  .cgi
• Paste output from Traceroute into the window and
  view the MRTG graphs for the routers in the path
• Author Joe Metzger ESnet

53
Traceroute Visualizer
54
Google it!

• Enter tuning tcp into the google search engine.
• Top 2 hits are
• http//www.psc.edu/networking/perf_tune.html
• http//www-didc.lbl.gov/TCP-tuning/TCP-tuning.html

55
PSC Tuning Page
56
LBNL Tuning Page
57
Conclusions

• Primary tools still useful
• Advanced tools are being developed
• Developing tools will make things even easier