Higher Speed Ethernet Update Greg Hankins ghankinsforce 10

Higher Speed Ethernet Update Greg Hankins <ghankins@force 10 networks. com> Global Peering Forum 2. 0 GPF 2. 0 2007/03/29

Per IEEE-SA Standards Board Operations Manual, January 2005 At lectures, symposia, seminars, or educational courses, an individual presenting information on IEEE standards shall make it clear that his or her views should be considered the personal views of that individual rather than the formal position, explanation, or interpretation of the IEEE. 2

Higher Speed Ethernet Technology Pull, Not Push n Many different networks are asking for 100 Gb. E today – IXs – ISPs – Content providers – Financial – R&E and HPCC n Already getting media attention and mention by C-level execs n Participation by end users has never been this high in the IEEE before – Presentations at meetings given by individuals from: AMS-IX, Comcast, DT, EDS, Equinix, Google, LBNL, NTT America, NYSE, Sprint, Time Warner, T-Systems, Yahoo! – Over 30 individuals contributing and supporting presentations – Thanks for your support 3

Higher Speeds Drive Density (or, Why Should I Care? ) n 100 Gb. E will benefit everyone – Even if you don’t need it – Drives a fundamental advance in technology n Drives 10 Gb. E port density up and cost down n Possible line-rate combinations – – n 4 1 x 100 Gb. E port 10 x 10 Gb. E ports 100 x 1 Gb. E ports And even more oversubscribed port density… Your bandwidth requirements and port densities are growing, not shrinking

Birth of an IEEE Standard: It Takes About 5 Years Ideas From Industry Feasibility and Research Industry Pioneering 1 Year Ad Hoc Efforts Call for Interest CFI July 18, 2006 Study Group HSSG is Here Task Force Q 4 2007? Working Group Ballot Sponsor Ballot Standards Board Approval Publication 5 IEEE ~4 Years 2009 – 2010?

HSSG Focus MAC data rate objective and architectural issues PHY objectives n Types n Reaches MDI - Medium Dependant Interface PCS - Physical Coding Sublayer PHY - Physical Layer Device PMA - Physical Medium Attachment PMD - Physical Medium Dependent WIS - WAN Interface Sublayer XGMII - 10 Gigabit Media Independent Interface 6 IEEE Std 802. 3 -2005

Next Step: Becoming a Task Force (The Good) n Write a Project Authorization Request (PAR) – PAR A working draft created at January meeting – Vote for chair to present PAR A to IEEE 802. 3 WG at the July Plenary n Answer the 5 Criteria for PAR A – – – n 7 Broad Market Potential: √ (59 / 5 / 12) Compatibility: √ Distinct Identity: √ Technical Feasibility: √ Economic Feasibility: √ HSSG request to extend SG lifetime again – SGs only exist for 6 months – 2 nd extension granted after March Plenary

PAR A Working Draft Objectives Votes Objective (Yes / No / Abstain) Support full-duplex operation only All 73 / 0 / 4 Preserve the 802. 3 / Ethernet frame format at the MAC Client service interface All 76 / 0 / 6 Preserve minimum and maximum Frame. Size of current 802. 3 Std All 74 / 0 / 4 Support a speed of 100 Gb/s at the MAC/PLS interface All 67 / 9 / 14 802. 3 26 / 11 Support at least 10 km on SMF All 86 / 0 / 4 802. 3 40 / 4 Support at least 100 meters on OM 3 MMF All 61 / 3 / 27 802. 3 33 / 2 / 13 Support a BER better than or equal to 10 -12 at the MAC/PLS service interface All 68 / 0 / 4 Under Consideration Support at least 40 km on SMF 8 All 38 / 10 / 32 802. 3 12 / 6 / 16 All: All people in the room, 802. 3: Registered 802. 3 voters

More Objectives: Copper? (The Bad? ) n Several presentations have been given supporting a copper objective – Technical and economic feasibility – 5 m – 10 m reach n Some interest in adding copper as an objective – Straw poll: 34 / 15 / 36 – Currently does not meet >= 75% criteria n 9 May be under consideration for PAR A or a separate PAR

More Objectives: 40 Gb/s? (The Ugly) 10 n Growing support for a 40 Gb/s rate for server applications – January Interim: 22 / 33 / 21 – March Interim: 35 / 33 / 20 n Positioned as a server interconnect technology – Servers do not need 100 Gb. E today – Aligns with 16 x PCIe 2 bus speed – 100 m MMF, copper and backplane reaches n Supported by individuals from component vendors, Intel, Sun, IBM – Others at Dell, HP and IBM only want 100 Gb. E – Little end user support n May be under consideration for PAR A or a separate PAR

Impact of 40 Gb. E on HSSG and 100 Gb. E n Some delay is anticipated – Time needed to accommodate 40 Gb. E objective – This also includes figuring out co-existence of the two speeds – Increased scope and change for slippage – Expected that 40 Gb. E and 100 Gb. E standards would be available at about the same times n Options – Let HSSG voters decide – Compromise and allow market to decide – 40 Gb/s MSA outside of IEEE n 11 Politics are in play, this is not a logical argument

Impact of 40 Gb. E on System Vendors Board design is a lengthy and expensive process – FPGA: 6 – 12 months – $2. 5 M –$5 M development costs – ASIC: 9 – 18 months (it takes 3 months just to make a chip) – $7. 5 M – $10 M development costs n We have to stop work on 100 Gb. E or work on it in parallel – Everyone has limited resources – Delays 100 Gb. E – We’d rather put effort into 100 Gb. E and deliver something faster in n about the same time Dual-rate line cards – Costs everyone more – You pay for a 100 Gb. E line card and run it at a lower speed – Assumes there is some auto-negotiation of speeds n Component vendors face similar constraints – Impacts components available to us to build stuff for you n 12

Impact of 40 Gb. E on the Gear n 40 Gb. E switches need an uplink technology – This would likely be 100 Gb. E n Multiple port combinations will be required – – – 13 10 Gb. E and 40 Gb. E, 10 Gb. E and 40 Gb. E and 100 Gb. E 10 Gb. E, 40 Gb. E and 100 Gb. E Several possible fiber and copper combinations for each speed

Impact of 40 Gb. E on the Market n Will make both technologies more expensive because of volume and market split n Confusion in the marketplace about mass adoption – Delay buying to see who wins and what turns out cheaper n 40 Gb. E would need to be – Cheaper than 4 x 10 Gb. E LAG – Available much sooner than 100 Gb. E – But data from Intel indicates two years between server needs for 40 Gb. E and something faster n Are people going to deploy 10 Gb. E, then 40 Gb. E, then 100 Gb. E to servers? – 10 GBase. T standard in 2006 – Just now starting to see lots of 10 Gb. E NICs on the market – Probably would go straight to 100 Gb. E instead of spending 14 money on a slower technology

What’s Next? April Meeting Agenda 15 n 40 km 100 Gb. E reach objective – Technical feasibility? – Economic feasibility? n 40 Gb/s MAC rate – Add as an objective? – Economic feasibility? – Broad Market Potential? – What reaches? n Copper – Add as an objective? n Motions have to be made in April n Finalize PARs

IEEE 802. 3 HSSG Reflector and Web Page n To subscribe to the HSSG reflector, send mail to <List. Serv@ieee. org> with the following in the body of the message: subscribe stds-802 -3 -hssg <your first name> <your last name> end (over 460 people have subscribed to the list) n HSSG web page has links to all presentations: http: //grouper. ieee. org/groups/802/3/hssg/index. html 16

Future HSSG Meetings n IEEE 802. 3 Interims – http: //grouper. ieee. org/groups/802/3/interims/index. html – April 17 – 19, 2007 – Ottawa, Canada – May 28 – 31, 2007 – Geneva, Switzerland n IEEE 802 Plenary – July 16 – 19, 2007 – San Francisco, CA, USA 17

Thank You 18

Overview of IEEE 802. 3 Standards Process (1/5)- Study Group Phase Idea 802 EC Form SG Check Point Yes Call for Interest Study Group Meetings 802. 3 Form SG No No Check Point Yes Approved PAR Yes Objectives Yes Nes. Com Approve Yes PAR No 802 EC Approve 5 Criteria SASB Approve RIP Check Point No 802. 3 Approve Note: Yes No Check Point At "Check Point", either the activity is ended, or there may be various options that would allow reconsideration of the approval.

Overview of IEEE 802. 3 Standards Process (2/5) - Task Force Comment Phase Approved PAR D 1. 0 No Task Force Meetings To 802. 3 WG Ballot Task Force Review Yes Objectives D 1. (n+1) Proposals Selected Yes No No D 2. 0 TF Review Done Yes A

Overview of IEEE 802. 3 Standards Process (3/5) - Working Group Ballot Phase A 802. 3 WG BALLOT D 2. (n+1) 802. 3 Forward to Sponsor Ballot TF Resolves Comments No A Yes Substantive Changes 802 EC Forward to Sponsor Ballot No Yes In Scope New Negatives No A Yes D 3. 0 No > 75% Check Point Yes B Notes: At "Check Point", either the activity is ended, or there may be various options that would allow reconsideration of the approval. No See 802. 3 Operating Rules 7. 1. 4 and listed references for complete description

Overview of IEEE 802. 3 Standards Process (4/5)- Sponsor Ballot Phase B LMSC Sponsor BALLOT D 3. (n+1) 802. 3 Forward to Rev. Com TF Resolves Comments No B Yes Substantive Changes 802 EC Forward to Rev. Com No Yes In Scope New Negatives No B Yes C No > 75% Check Point No Yes Notes: At "Check Point", either the activity is ended, or there may be various options that would allow reconsideration of the approval. See 802. 3 Operating Rules 7. 1. 5 and listed references for complete description

Overview of IEEE 802. 3 Standards Process (5/5) - Final Approvals / Standard Release C Approved Draft Rev. Com Review Rev. Com Approval No Yes SASB Approval Publication Preparation B Standard Yes No Check Point Notes: At "Check Point", either the activity is ended, or there may be various options that would allow reconsideration of the approval.