Transcript Measurement Projects Overview
Measurement Projects Overview
Matt Zekauskas
I2 Measurements WG Meeting San Diego, CA 20 November 1998
Outline
Classification
Broad project organizations
Specific projects
Caveats
My personal expertise: active measurements, IETF IPPM
Not exhaustive
Research/education focus
If you see something left out, speak up!
Classification
Active measurements
Passive measurements
Utilization [usually SNMP]
Routing [usually BGP/traceroute]
Broad Organizations
IETF
• IP Performance Metrics (IPPM) • Realtime Traffic Flow Measurement (RTFM)
NLANR
• Measurement & Operations Analysis Team • National Center for Network Engineering
CAIDA
IPPM: Scope
Develop metrics that measure
• Quality • • Performance Reliability
of Internet data delivery services
Quantitative measures
• not a value judgement
IPPM: Metrics
Framework: RFC2330
Connectivity
One-way delay and loss
Round-trip delay and loss
Flow capacity/Bulk transfer capacity
Delay variation (jitter) http://www.advanced.org/IPPM/
RTFM
Measure network flows through passive measurments
Standards for
• architecture; metrics for traffic flows • language to describe flows • MIB to control meter & gather measurements
Origin in accounting
RTFM
Philosophy: aggregate on meter, accurately count everything
Bytes/link, bytes/port, bytes/flow
Rule-based production system
Look at header only
http://www.auckland.ac.nz/net/Internet/rtfm
Projects
IPMA
Surveyor
RIPE Test Traffic
pingER
NIMI
NLANR/MOAT NAI corresponding CAIDA deployment?
IPMA
Routing history
tool development (like NLANR/CAIDA)
“Decentralized infrastructure”
MRT, RouteTrackerd, Salamander
ASExplorer, FlapGraph, RouteTracker, ...
http://www.merit.edu/ipma
Surveyor & RIPE TT
Implementations of IPPM one-way metrics: active measurements
also routing via traceroute
Surveyor O(40) machines, mostly US and Canada, now getting some European & Pacific; Target O(100)
RIPE O(15) machines, European focus
PingER
ESNET / physics community (also XIWT)
Long-term ping measurements
Set of cooperating measurement sites -- not just random hosts
http://www.slac.stanford.edu/xorg/icfa/ntf/home.html
http://www.slac.stanford.edu/xorg/icfa/ntf/tool.html
NIMI
Emphasis on the I - Infrastructure
Platform for network experiments
Outgrowth of Vern’s npd project
Emphasis on active measurements
Currently traceroute, Treno, PoIP
Should be able to roll your own
General (beta) release imminent
NIMI Structure
“Uniform” platform (hw, os, nimid) Owners control: CPOC access lists; crypto for security Researchers schedule experiments: MPOC nimid handles resource scheduling Plans for synchronized time source (not yet) http://www.ncne.org/
Network Analysis Infrastructure
HPNSP focus
Passive measurement infrastructure
Keep headers for research
Adding performance data (active)
Also SNMP data (vBNS today)
Also BGP data (from Oregon RA)
Tools: Platform
NIMI
Windmill
• UofM/MERIT • • Passive experimentation focus Listen to selective protocol messages, and replay locally to understand endpoint state • • Example: snooping BGP peering session Not released; SIGCOMM98
Tools: Routing
Traceroute servers
IPMA tools (based on BGP peering)
Skitter: tomography (CAIDA)
Tools: Active performance
Treno
mping (windowed ping): invasive
pathchar: estimate router Qs bottleneck bandwidth
traditional: ping, ftp, ttcp, netperf
Tools: Passive
NeTraMet: Nevil Brownlee’s RTFM
IBM Research’s RTFM
tcpdump
OCxMON: passive optical
Coral
~Cisco’s NetFlow, and
cflowd (CAIDA/ANS)
Tools: Utilization
Mainly commercial? Network management tools (e.g., OpenView)
MRTG
NetScarf?
Parting Thoughts
Integration with network management? (They want measurement results for operations!)
Don’t neglect commercial tools