Current Meeting Report
Slides


2.7.12 Performance Implications of Link Characteristics (pilc)

NOTE: This charter is a snapshot of the 52nd IETF Meeting in Salt Lake City, Utah USA. It may now be out-of-date. Last Modified: 03-Dec-01
Chair(s):
Spencer Dawkins <spencer.dawkins@fnc.fujitsu.com>
Aaron Falk <falk@isi.edu>
Transport Area Director(s):
Scott Bradner <sob@harvard.edu>
Allison Mankin <mankin@isi.edu>
Transport Area Advisor:
Allison Mankin <mankin@isi.edu>
Mailing Lists:
General Discussion:pilc@grc.nasa.gov
To Subscribe: majordomo@grc.nasa.gov
In Body: subscribe pilc
Archive: http://pilc.grc.nasa.gov/pilc/list/archive/
Description of Working Group:
Erik Nordmark (nordmark@eng.sun.com) is the Technical Advisor.

The Internet network-layer and transport-layer protocols are designed to accommodate a very wide range of networking technologies and characteristics. Nevertheless, experience has shown that the particular properties of different network links can have a significant impact on the performance of Internet protocols operating over those links, and on the performance of connections along paths that include such links. This is especially of concern to the wireless networking community.

The PILC working group will produce several BCP/Informational documents. The first document will discuss considerations for link-layer designers from the perspective of best supporting existing IETF protocols will be produced. The next document will discuss the capabilities, limitations and pitfalls of 'performance enhancing proxies' (PEPs), that is, active network elements that modify or splice end-to-end flows in an attempt to enhance the performance they attain in the face of particular link characteristics. The remaining documents will either discuss the impact and mitigations for a problematic link-layer characteristic (or group of closely related characteristics), or provide overviews of which other PILC documents apply to particular problem domains.

As one of its first work items, the WG will review an existing I-D on considerations for "long, thin" networks (one of the salient characteristics of terrestrial wireless links). This will be published as a preliminary assessment of the problem domain, to be refined by later PILC documents.

All documents will identify which of their considerations remain research topics versus which are established as advanced development. Research topics will be explicitly flagged as not part of any recommendations. All documents will also identify any security implications associated with their considerations.

The working group will also serve as a forum for discussing possible modifications to IETF protocols to improve performance in environments with problematic link characteristics - however, not to the detriment of performance and stability in the general Internet, nor to undermine existing security models.

It is incumbent upon the chairs to ensure that the WG maintains good communications with other groups interested in related technology issues, such as wireless forums.

Goals and Milestones:
Done   Submit Internet-Draft on significantly low bandwidth links.
Done   Submit Internet-Draft on significantly lossy links.
Done   Submit Internet-Draft on long-thin networks (based on draft-montenegro-pilc-ltn-01.txt) submitted to the IESG for publication.
Done   Draft of link-layer design considerations document.
Done   Draft of PEP capabilities and limitations document.
Done   Draft on asymmetric network paths.
Done   Document on lossy links to IESG for publication as BCP.
Done   Document on PEP capabilities and limitations submitted for publication as Informational.
Done   Document on low bandwidth links to IESG for publication as BCP.
Aug 01   Draft of TCP Over Wireless document to the IESG as BCP
Aug 01   Document on link-layer design considerations submitted for publication as BCP.
Aug 01   Document on asymmetric network paths submitted to the IESG for publication as BCP.
Aug 01   Possible rechartering of WG to address modifications to IETF protocols.
Internet-Drafts:
Request For Comments:
RFCStatusTitle
RFC3135 Performance Enhancing Proxies Intended to Mitigate Link-Related Degradations
RFC3150 End-to-end Performance Implications of Slow Links
RFC3155 End-to-end Performance Implications of Links with Errors

Current Meeting Report

Performance Implications of Link Characteristics WG (pilc)

The PILC working group meeting was held on Tuesday, December 11 at 1300-1400. The meeting was chaired by Aaron Falk and the following agenda was followed completely.

AGENDA:
Agenda Bashing chairs 2min
Working Group Status chairs 3min
CDMA2000 issues F. Khafizov 10min
draft-khafizov-pilc-cdma2000-00.txt
Q: integrate into 2.5g3g or new doc?
2.5g/3g Update H. Inamura 10min
draft-ietf-pilc-2.5g3g-05.txt
Q: ready for wg last call?
LINK last call comments P. Karn 10min
draft-ietf-pilc-link-design-08.txt M. Allman
PILC-related issues in ROHC C. Borman 10min
IP-DVB announcement G. Fairhurst 2min
Adjourn

The meeting started promptly at 13:00 and Blue Sheets were circulated.

Aaron Falk went over the Working Group Status ARQ is in IESG review. ASYM is going to IESG any day. LINK design is in last call. Mark Allman will be taking over editing for Phil Karn's 2.5/3G document is near last call but needs to incorporate CDMA2000 information.

=========================

CDMA2000

F. Khafizov presented slides on TCP performance over CDMA 2000 networks. Issues to be addressed include bandwidth oscillation, high BER, and bandwidth asymmetry. Bandwidth oscillation degrades throughput through spurious timeouts. True of any system with widely varying bandwidth.

* Bandwidth Oscillations (BO)
- Significant throughput degradation
- Not cdma2000 specific
- Related to resource contention
- Fixes include 1) fix TCP, 2) Fix network or 3) leave as is.
- Possible fixes
o Adjust RTO value
o enable Time Stamp option
o increase window size
o minimize ACK delay
- Other recommendations
o Aggressive link level error recovery
o disable VJ header compression
o use SACK
- Options
o Incorporate BO in 2.5g/3g and/or LINK ID
o make a separate ID for BO
o have a section in 2.5G/#g ID addressing specifics of CMDA2000

Suggestions from chair and floor moved toward including in existing documents rather than stand-alone document.

F. Khafizov volunteer to generate text for the documents.

============

Hiroshi Inamura presented slides on 2.5G/3G
* Reviewed open issues
- header compressions
- active queue mgt.
- Others
* RTO typically 2s is to small?
- Yes
* New Sections
- VJ header compression not recommended

Comments from the floor:

ECN section needs expansion as ECN may be quite beneficial. Question as to whether or not the effects of cell changes being incorporated into draft.

=============

Phil Karn commented that the LINK document appears to be very near completion. Bandwidth on Demand and bandwidth oscillations may need some additional attention.

Floor Comments:
Asymmetry may need a bit of revision as it was written early on.

============

Carsten Bormann presented slides on issues in Robust Header Compression related to PILC

The following is a summary of Carsten's slides:

Robust Header Compression (ROHC)
- Header Compression is prerequisite for all IP wireless
- Wireless = lossy, long latency

Work items

Robust Header Compression of IP/UDP/RTP
- need for e2e VoIP/video
- RFC3095 july 2001 used by 3GPP and 3GPP2
- ROHC over PPP; 0-byte LLA submitted to IESG

ROHC for TCP is starting to gel

New: signaling compression (reduce latency)
- universal decompressor

ROHC is working on MIBs
Next work will probably be related to SCTP

RFC 2507 is not good enough as it does not handle options like SACK, timestamps
- need to compress ECN bits well
- cope with TCP's extensibility
- (state of the ar ha advanced)

Requirements drafts presented: 2 drafts
- please read and comment on 01/03 versions once available!

Solutions : two drafts in the process of merging
Need wider input wrt next generation TCP

ROHC TCP Requirements
- Links with few residual erros but may have packet loss
- Robustness
o Should not disable TCOP mechanisms
o Must NOT generate damaged headers
o Must deal with current and future TCPs
o TCP sequence numbers and IP ID less predictable

TCP Sample Issues
- TCP checksum and.or additional CRC for checking
- Unidirectional vs bi-directional compression
- Can ROHC ignore IP options?
- Compress in tunnel encapsulations, too?
o Reordering (prohibited, detected, allowed)?
- Integrate with ASYM mechanisms
- What are the assumptions about ECN behavior?
- What loss amplifications behaviours are actually acceptable?
- IPR

Comments from floor

- even if residual error is low, what is error distribution (burst errors vs uniform distribution errors). However, residual bit errors as defined by ROHC are packet with errors passed from layer 2 too layer 3.

===================

IP-DVB announcement G. Fairhurst 2min

G. Fairhurst extended an invitation to an informal meeting on 12/12 at 15:30 - 17:30. The meeting will be on IP over DVB. It is not an BoF, but a maillist will be created for those interested in this subject.
More information can be found at http://www.erg.abdn.ac.uk/users/gorry/ip-dvb/.

Slides

Agenda
TCP over CDMA2000 networks