Modest%20networking

1
Modest networking
Joint work with Maria Papadopouli Hannes
Tschofenig Xiaoming Fu Jochen Eisl Robert Hancock

• Henning Schulzrinne
• Columbia University
• MIND Workshop London, Oct. 7, 2002
• Keynote Address

(Opinions are the speakers and may not be shared
by the co-authors)
2
Overview

• New Realism in networking
• Multimodal networking
• Some thoughts on QoS
• CASP another attempt at QoS signaling

3
New realism

• Old notion build it and they will pay
• Dont want to be just dumb bit carriers
• Value add ? charge exorbitant fees for shipping
  special bits
• Convergence ? all bits are similar
• Cheapest bits win (unless monopolies or
  regulation interfere)
• Almost all of networking is/will be a commodity
  we should be proud of it!

4
Cost of networking
Modality mode speed /MB ( 1 minute of 64 kb/s videoconferencing or 1/3 MP3)
OC-3 P 155 Mb/s 0.0013
Australian DSL (512/128 kb/s) P 512/128 kb/s 0.018
GSM voice C 8 kb/s 0.66-1.70
HSCSD C 20 kb/s 2.06
GPRS P 25 kb/s 4-10
Iridium C 10 kb/s 20
SMS (160 chars/message) P ? 62.50
Motient (BlackBerry) P 8 kb/s 133
5
Spectrum cost for 3G
Location what cost
UK 3G 590/person
Germany 3G 558/person
Italy 3G 200/person
New York Verizon (20MHz) 220/customer
Generally, license limited to 10-15 years
6
Multimodal networking

• use multiple types of networks, with
  transparent movement of information
• technical integration (IP) ? access/business
  integration (roaming)
• variables ubiquity, access speed, cost/bit,
• 2G/3G rely on value of ubiquity immediacy
• but demise of Iridium and other satellite
  efforts
• similar to early wired Internet or some
  international locations
• e.g., Australia

7
Multimodal networking

• expand reach by leveraging mobility
• locality of data references
• mobile Internet not for general research
• Zipf distribution for multimedia content
• short movies, MP3s, news,
• newspapers
• local information (maps, schedules, traffic
  radio, weather, tourist information)

8
Multimedia data access modalities
delay
high low
high 7DS 802.11 hotspots
low satellite SMS? voice (2G, 2.5G)
bandwidth (peak)
9
A family of access points
10
7DS options

• Many degrees of cooperation
• server to client
• only server shares data
• no cooperation among clients
• fixed and mobile information servers
• peer-to-peer
• data sharing and query forwarding among peers

11
7DS options
Query Forwarding
FW
query
query
Host C
Host A
Host B
time
Querying active (periodic) passive
12
Dataholders () after 25 min
high transmission power
P2P
Mobile Info Server
Fixed Info Server
2
13
Message relaying with 7DS
WLAN
Message relaying
WAN
Host B
Host A
messages
WLAN
Gateway
14
Quality of Service
15
Why QoS hasnt happened

• need to admit failure bandwidth too cheap to
  meter
• undemocratic some traffic is more equal than
  other
• dishonest we only talk about the beneficiaries
• reminds you of your mom no, you cant have that
  10 Mb/s now
• socialist administer scarcity - we like SUVs (or
  to drive 100 mph)!
• risky scheme security exposure reserve your
  whole network
• niche only displacement applications (such as
  telephony) need QoS
• touchy-feely requires cooperation ? edge-ISP,
  transit ISPs, end systems
• snake oil add QoS, lose half your router
  interface bandwidth

16
What makes QoS hard

• No, its not RSVP scaling
• network has become harder to evolve
• network address translation
• firewalls
• high packetization overhead (VPNs, IPv6)
• nobody can be trusted
• to be useful, has to be nearly universally
  supported (no, you cant make calls to AS 123)
• network QoS vs. business class model coach is
  empty, please refund fare
• almost all the time, reserved traffic gets same
  delay as best effort
• applications will switch QoS classes

17
What makes QoS hard

• currently, the ISP interface is IP and BGP
  adding a third one is a big deal
• trust model ? ISP or cash model
• payment model completely unclear for peering
• new Internet service model TCP client (inside)
  server (outside)
• exception peer-to-peer on college campuses
• network to host you first, no, you first

18
What is QoS, really?

• Network transparency
• no loss (lt 1)
• very few delay spikes (lt 1)
• close to propagation delay
• anything else is too hard to explain to users!
• QoS is just a facet of network reliability
• consistent 5 packet loss is much better than 5
  probability that network is unavailable for
  seconds
• users are willing to pay for availability
• traditional QoS may help availability during
  outage periods
• e.g., MCI/UUnet breakdown 10/3/02
• DOS attacks
• failure of load distribution links

19
CASP Cross-Application Signaling Protocol

• RSVP is being used for lots of things beyond flow
  setup RSVP TE, midcom,
• Complex and monolithic
• multicast support ?
• multiple reservation styles
• killer reservations and error handling
• receiver-orientation only
• non-RSVP region handling
• interface complexity (LIH)
• fairly closely ties QoS to RSVP
• hard to extract generic signaling protocols
• ? CASP as modular signaling protocol
• currently a proposal for IETF NSIS group

20
What is CASP?

• Generic signaling service
• establishes state along path of data
• one sender, typically one receiver
• can be multiple receivers ? multicast
• can be used for QoS per-flow or per-class
  reservation
• also firewall setup, TE, programmable networks,
  configuration, topology exploration,
• avoid restricting users of protocol (and
  religious arguments)
• sender vs. receiver orientation
• more or less closely tied to data path
• router-by-router
• network (AS)

21
CASP network model on-path
selective
CASP chain
QoS
QoS
QoS midcom
omnivorous

• CASP nodes form CASP chain
• not every node processes all client protocols
• non-CASP node regular router
• omnivorous processes all CASP messages
• selective bypassed by CASP messages with unknown
  client protocols

22
CASP network model out-of-path
Bandwidth broker NAC
CASP
AS15465
AS17
AS 1249
data

• Also route network-by-network
• can combine router-by-router with out-of-path
  messaging

23
CASP protocol structure
client layer (C)
scout protocol
CASP
messaging layer (M)
messaging layer (M)
transport layer (T)
UDP IP router alert

• transport layer
• reliable transport

• client layer does the real work
• reserve resources
• open firewall ports
• messaging layer
• establishes and tears down state
• negotiates features and capabilities

24
Next-hop discovery

• Next-in-path service
• enhanced routing protocols ? distribute
  information about node capabilities in OSPF
• routing protocol with probing
• service discovery, e.g., SLP
• first hop, e.g., router advertisements
• DHCP
• scout protocol
• Next AS service
• touch down once per autonomous system (AS)
• new DNS name space ASN.as.arpa, e.g., 17.as.arpa
• use new DNS NAPTR and SRV for lookup
• similar to SIP approach

25
Mobility and route changes
DEL (B2)
discovers new route on refresh
B1
ADD B2

• avoids session identification by end point
  addresses
• avoid use of traffic selector as session
  identifier
• remove dead branch

26
Conclusion

• Until wireless bits are too cheap to meter, try
  hiding lack of universal high bit density from
  user
• QoS is a reliability mechanism
• CASP as a new signaling platform