ISRG and the PostPC Era David Culler U

ISRG and the Post-PC Era David Culler U. C. Berkeley ISRG Retreat Jan, 1999. 1/11/99 ISRG Retreat

Why is Internet-Scale Systems Research Concerned with Small “Post. PC” Devices? 1/11/99 ISRG Retreat 2

The Emerging Platform Pyramid Super. Computers Super. Servers 100 s Departmental Servers 10 Ks Workstations < Million Personal Computers 100 millions Small Devices billions 1/11/99 ISRG Retreat 3

Future Internet-Scale Systems • ~10 Billion of Information Appliances • ~100 Million of Stationary Computers • ~Million Scalable Servers 1/11/99 ISRG Retreat 4

Natural Convergence • “Internet-Scale” => system reaches “everywhere” – small devices will be what is “wherever” • Small devices provide powerful services – because the intelligence is in the infrastructure • The breakthrough ahead is pervasive devices + communication • Services, adaptation, access, customization, simplicity, efficiency, . . . 1/11/99 ISRG Retreat 5

Seeds sewn in many projects • Infopad, Wingman, Mediaboard, Notepals, . . . • Ninja - platform architecture – powerful services on small devices through a powerful infrastructure • Iceberg - integration of computing and telephony • Notepals - new user interfaces • IRAM - high performance multimedia at low power • Aetherstore - the data is out there • Demos around you. . . 1/11/99 ISRG Retreat 6

A Radical Experiment • What we need is not a new research project • It is a new “computing culture” 1/11/99 ISRG Retreat 7

Game Plan (Oct 1998) Build a department-wide, universal wireless PDA infrastructure • Initial Seed: 150+ IBM workpads + lots of cradles + IR + ? ? ? • Running UI classes on them • Bring in all interested 1 st year CS grads • Fill out based on interest, talent and availability • next generation wider and better => “ask a good question and get yours” seminar 1/11/99 ISRG Retreat 8

Fall’ 98 Project Excerpts (see posters) • E-Commerce and Security – Pay-Per-Use Services on the Palm Computing Platform (Mike Chen, Andrew Geweke) – Secure Email Infrastructure for PDAs (Hoon Kang, Rob von Behren) – Sync. Anywhere - Secure Network Hot. Sync (Mike Chen, Helen Wang) • Groupware – – Kiretsu - Ninja Instant Messaging Service (Matt Welsh, Steve Gribble) The MASH Media. Pad - Shared Electronic Whiteboard for the Palm. Pilot (Yatin Chawathe) Note. Pals - Lightweight Meeting Support Using PDAs (Richard Davis) OSKI - Open Shared Kalendaring Infrastructure (Jason Hong, Brad Morrey, Mark Newman) • OS and Communications – Palm. Router - Networking Sporadically Connected Devices (Andras Ferencz, Robert Szewczyk) • Numerous Architecture Studies • CS 160 UI Projects (see James Landay talk) – Ink Chat, Nutrition/Excercise Tracker, Rendezvous - Meeting Scheduler 1/11/99 ISRG Retreat 9

Some Lessons • Communication is enabling • Virtual Environment really is a good thing – Devices connect “into the infrastructure” – Network Hot. Sync, groupware, centralized e-mail => Need lean, clean communication substrate • Much room for improvement in devices • Palm III (Work. Pad) is too slow… – adaptation involves trading cycles for bandwidth and interoperability 1/11/99 ISRG Retreat 10

Lessons… • Development effort is the limiting factor – OSKI: 1 person for infrastructure, 2 for Work. Pad – Debugging is particularly hard => need complete system simulation environment • “User Service” is fundamental – not just profile and customization info – routing point for security • Surprising similarities with the “infrastructure problem” 1/11/99 ISRG Retreat 11

Phase 2 Plan: Real Users • Deploy some real Work. Pad services – Secure e-mail – Network Hot. Sync – Group Calendar • Widespread use of at least one service – more than 50 users? – highly available/reliable 1/11/99 ISRG Retreat 12

Historical Perspective • New eras of computing start when the previous era is so strong it is hard to imagine that things could be different – mainframe -> mini – mini -> workstation -> PC – PC -> ? ? ? • It is always smaller than what came before. • Most think of the new technology as “just a toy” • The new dominant use was almost completely absent before. • So where are we headed in the post-PC era? 1/11/99 ISRG Retreat 13