Transcript Performance Measurements Euro-Amerocan Meeting

Performance Measurement and
Monitoring
Internet2 Fall Member Meeting
Philadelphia, PA
Eric L. Boyd – Internet2
Nicolas Simar – Dante
Agenda
• Internet2/G2 JRA1/ESnet Interaction
Update
• Internet2 Performance Activities
• GÉANT2-JRA1 Performance Activities
• Next Steps / Open Issues
perfSONAR: Overview
• Joint effort of ESnet, GÉANT2 JRA1 and
Internet2 PAT
• Webservices network performance
framework
•
•
•
•
Network measurement tools
Network measurement archives
Distributed scheduling/authorization
Multi-domain policy
perfSONAR: Accomplishments
•
•
•
•
Architecture document (Fall ’04)
Framework Design document (Spring ’05)
Prototype (Summer – Fall ’05)
Workshops in Brussels (09/04), Zurich (04/05),
Ann Arbor (05/05) and Poznan (08/05)
• Development Environment (05/05)
• Communications:
– Paper submissions (e2emon, TNC05 and ICSOC05)
– TNC05 presentation
perfSONAR: Current Work
• Current work is focused on developing a
prototype that will allow interface utilization data
to be shared.
• Relatively simple use case, but demonstrates
the feasibility of sharing data across multiple
administrative domains.
perfSONAR: Services (1)
•
•
•
•
•
•
•
Measurement Point Service (MP)
Measurement Archive Service (MA)
Look-up Service (LS)
Authentication Service (AS)
Transformation Service (TS)
Topology Service (ToS)
Resource Protector Service (RP)
perfSONAR : Services (2)
• Measurement Point Service
– Publishes measurement data to one or several
consumer.
– Capability of starting a new tests.
– Initiates active measurements, queries passive
measurement devices or packet capture .
– Integrated within the tools or wrapper around legacy
tools.
• Measurement Archive Service
– Storage of measurement data (over long period of
time).
– A MP or a TS publish data to the MA.
perfSONAR: Services (3)
• Lookup Service
– Allows the client to discover the existing services and
other LS services.
– Dynamic: Services registration themselves to the LS
and mention their capabilities, they can also leave or
be removed if a service gets down.
• Authentication Service
– Internet2 MAT, GN2-JRA5
– Authentication functionality for the framework
– Users can have several role, the authorisation is done
based on the user role.
– Trust relationship between networks.
perfSONAR Services (3)
• Transformation Service
– Transform the data (aggregation, concatenation,
correlation, translation, etc).
• Topology Service
– Make the network topology information available to
the framework.
– Find the closest MP, provide topology information for
visualisation tools
• Resource protector
– Arbitrate the consumption of limited resources.
Useful
Useful graph
graph
Client
Token MA
Here
is who I am, Token
I’d likeMB
to access MA B
Here is who
I’d likeA,toMA
access
a,b,cI am,
: Network
A, ASMA
A A
Where Link utilisation
along
- Path a,
a,b,c?
Get link
utilisation
b, c
you go
Get
Link
utilisation
a,b,c
Get link Here
utilisation
c,d,e,fAS B
AS A
Here
you
go.
Here
you
a,b,c:
go
Network
A
–
LS
A,
Where Link utilisation along - Path a,b,c,d,e,f?
c,d,e,f : Network B, MA B, AS B
LS A
a
MA A
LS B
b
e
c
Network A
MA B
d
Network B
f
Agenda
• Internet2/G2 JRA1/ESnet Interaction
Update
• Internet2 Performance Activities
• GÉANT2-JRA1 Performance Activities
• Next Steps / Open Issues
Current Projects
• Performance Tools
–
–
–
–
BWCTL
NDT
OWAMP
Thrulay
• Performance
Measurement
Framework
– piPEs -> perfSONAR
– GGF NMWG
• Member Outreach
– Network Performance
Measurement
Workshops
– Performance Tool
Cookbooks
• Bulk Transport
– Design Space
– Prototype
OWAMP (1-way ping)
• LOTS of new deployments (Network Performance
Workshop Attendees)
• New “developers” release to support latest version (14)
of owdp spec
• TTL (hop count)
• Early terminated sessions handled more gracefully
• Sender will skip sending “late” records and shares that information with
receiver
BWCTL (Bandwidth Test Controller)
• LOTS of new deployments (Network
Performance Workshop Attendees)
• New alpha release
• Bug fixes
• Ported to Solaris, OS X
• NTP dependency eliminated
NDT and Thrulay
• NDT
– Duplex Mismatch Detection
– Grant from NIH / NLM
• Thrulay
– UDP Mode
– Google Summer of Code enhancements
GGF NMWG
• Version 1 of the schema “all but done”
– Employed by piPEs, Advisor, AMP,
MonALISA, and SLAC
• Version 2 of the schema continues to
evolve
– perfSONAR work benefits from and informs
this project
Network Performance
Measurement Workshops (1)
• Goals
– Installed base of BWCTL/Iperf, OWAMP, and
NDT at GigaPoP and regional campuses.
– Begin integration into IT support processes.
– Create and installed base for perfSONAR
deployment.
– Give each participant tool-specific cookbooks.
Network Performance
Measurement Workshops (2)
• Completed
–
–
–
–
SOX / GaTech (03/05)
CENIC / UCLA (06/05)
JT – Vancouver (07/05)
MAGPI / FMM (09/05)
• Planned
– OARNet / OSU (09/05)
– APAN (01/06)
• Under Consideration
– MERIT, MAX, Winter Joint Techs, …
Other Outreach
• Next Generation Measurement Panel/BoF
(07/05)
• Bridging the Gap Workshop (08/05)
• Application-Community-Specific Network
Performance Workshops (mini-version of
the workshop, focusing on use of tools, not
installation) being developed
Bulk Transport Tool (1)
• Killer App for High Performance Networks
(i.e. why else do we need fat pipes)
• Remedies for TCP’s maladies
• Tuning: buffers, window scaling, timestamps,
SACK
• Use multiple streams
• Something Else
• Replace the kernel and use different congestion
control
• Replace all the routers and kernels
Bulk Transport Tool (2)
• Many alternative TCP/IP congestion
control algorithms
• Modified kernels are incompatible with
regular kernel security patches
• Get the benefits of kernel-level
modifications to TCP/IP congestion control
algorithms in a user level tool, avoiding
security issue with alternate kernels
Bulk Transport Tool (3)
• Design Space Document
• Early Stage Prototype
• Google Summer of Code efforts
Agenda
• Internet2/G2 JRA1/ESnet Interaction
Update
• Internet2 Performance Activities
• GÉANT2-JRA1 Performance Activities
• Next Steps / Open Issues
GÉANT2 JRA1
• 15 European NRENs putting resources together
to work on multi-domain monitoring and on
performance measurements.
– Arnes (SI), Belnet (BE), Carnet (HR), Cesnet (CZ),
DFN (DE), FCCN (PT), GARR (IT), GRnet (GR), ISTF
(BG), Uninett (NO), PSNC (PL), redIRIS (ES),
Renater (FR), Surfnet (NL), SWITCH (CH), DANTE.
• Works with
– The Performance Enhancement Response Team.
– The multi-domain L2 circuits activity
to provide them multi-domain measurement data.
Requirements
• Questionnaires sent to NRENs, Projects and
End-users (system administrators).
– 45 answers received (15 each).
• Requirements
– Strong interests to access monitoring information form
multiple networks.
– Readiness to open access to measurement data
varies greatly.
– On-demand capability (to and from other domains).
– Be able to monitor the services deployed.
• IP QoS, IPv4/v6, multicast
– Great variety of tools deployed.
Requirements [2]
• Requirements
– Monitoring Information:
• RTT and OWD.
• Bandwidth Utilisation and achievable TCP
throughput.
• RTT and OWD packet loss.
• Delay variation.
• Interfaces error and drops.
• Routing/path information.
Tools
• Work on the integration of few selected
measurement tools into the framework.
– Evaluate the different tools before selecting one.
– DFN IPPM (OWD), BWCTL/iperf, RRD –
December 05.
– Enhancement of those measurement tools.
– Investigate netflow and packet capture uses.
• Make use of existing visualisation tools
– NEMO (Uninett), CNM (DFN).
• Will build (new) visualisation tools based on
users feedback.
Other tasks
• Work on data aggregation and
concatenation.
• Deployment of a test infrastructure.
• Multi-domain L2 circuit monitoring (SDH
and Ethernet based circuits).
Agenda
• Internet2/G2 JRA1/ESnet Interaction
Update
• Internet2 Performance Activities
• GÉANT2-JRA1 Performance Activities
• Next Steps / Open Issues
perfSONAR: Prototype
• Phase 0
– Simplistic client which requests data to a MA (RRD filesystem)
using web-services (Done)
• Phase 1
– Include simplistic LS web-services (on-going)
– Visualisation – map based (on-going)
• Phase 2
– Request additional data (OWD, packet drops)
– Dynamic registration to LS
– Ping MP
• Phase 3 (Dec 05)
–
–
–
–
Handel attributes for other services
Distributed LS data across several domains
MP get’s on-demand capability (BWCTL)
Make use of the attributes to offer different functionalities to the
users
What’s Next?
• Current Status:
– Regular discussions
– Development is underway
– About to use perfSONAR to provide data to an international
project (link capacity and link utilisation).
• We are at a key moment of the collaboration:
–
–
–
–
Distributed development process emerging
Making compromises between the vision and the technology
Where should we cut corners on the prototype?
Does the prototype form the basis of the deployed system?
Questions?
• Eric Boyd, Internet2
([email protected])
• Nicolas Simar, DANTE / GÉANT2 – JRA1
([email protected])