cluster or network? an emulation facility for research

27
1 Cluster or Network? An Emulation Facility for Research Jay Lepreau Chris Alfeld David Andersen (MIT) Mac Newbold Rob Place Kristin Wright Dept. of Computer Science University of Utah http://www.cs.utah.edu/flux/testbed/ February 3, 2000

Upload: thane

Post on 22-Jan-2016

25 views

Category:

Documents


0 download

DESCRIPTION

Cluster or Network? An Emulation Facility for Research. Jay Lepreau Chris Alfeld David Andersen (MIT) Mac Newbold Rob Place Kristin Wright Dept. of Computer Science University of Utah http://www.cs.utah.edu/flux/testbed/ February 3, 2000. Research We Do. - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: Cluster or Network? An Emulation Facility for Research

1

Cluster or Network?An Emulation Facility for

Research

Jay Lepreau Chris AlfeldDavid Andersen (MIT) Mac Newbold

Rob Place Kristin Wright

Dept. of Computer ScienceUniversity of Utah

http://www.cs.utah.edu/flux/testbed/

February 3, 2000

Page 2: Cluster or Network? An Emulation Facility for Research

2

Research We Do

•Operating systems, local and distributed

•Distributed systems

Web caching schemes, distributed objects, ...

•Active Networks

code in every packet: route me!

Configurable router

•Router operating systems

Page 3: Cluster or Network? An Emulation Facility for Research

3

What?

•A configurable Internet (cluster) in a room

230 nodes, 1000 links, BFS (switch)

virtualizable topology, links, software

•An instrument for experimental CS research

•Universally available to any remote experimenter

•Simple to use!

Page 4: Cluster or Network? An Emulation Facility for Research

4

Why?

• “We evaluated our system on five nodes.” -job talk from university with 300-node cluster

• “We evaluated our Web proxy design with 10 clients on 100Mbit ethernet.”

• “Simulation results indicate ...”

• “Memory and CPU demands on the individual nodes were not measured, but we believe will be modest.”

• “The authors ignore interrupt handling overhead in their evaluation, which likely dominates all other costs.”

• “Resource control remains an open problem.”

Page 5: Cluster or Network? An Emulation Facility for Research

5

Why 2

• “You have to know the right people to get access to the cluster.”

• “The cluster is hard to use.”

• “<Experimental network X> runs FreeBSD 2.2.x.”

• “October’s schedule for <experimental network Y> is…”

• “<Experimental network Z> is tunneled through the Internet”

Page 6: Cluster or Network? An Emulation Facility for Research

6

Complementary to Other Experimental Environments

•Simulation

•Small static testbeds

•Live networks

•Maybe someday, a large scale set of distributed small testbeds (“Access”)

Page 7: Cluster or Network? An Emulation Facility for Research

7

Some Unique Characteristics

• Significant scale: initially 225 nodes, degree four 100Mb links between 42 core routers.

•User-configurable control of “physical” characteristics: shaping of link latency/bandwidth/drops/errors(via invisibly interposed “shaping nodes”),router processing power, buffer space, …

•Node breakdown: 42 core, 160 edge, 26 shaping, 2 management

Page 8: Cluster or Network? An Emulation Facility for Research

8

More Unique Characteristics

• Capture of low-level node behavior such as interrupt load and memory bandwidth

•User-replaceable node OS software

•User-configurable physical link topology(VLAN via BFS; “P-LAN” via BFPP)

• Completely configurable and usable by external researchers, including node power cycling

Page 9: Cluster or Network? An Emulation Facility for Research

9

Fundamental Research Leverage:

Extremely Configurable

Page 10: Cluster or Network? An Emulation Facility for Research

10

Obligatory Pictures

Page 11: Cluster or Network? An Emulation Facility for Research

11

Prototype Pieces: edge nodes

Page 12: Cluster or Network? An Emulation Facility for Research

12

Big Iron

Page 13: Cluster or Network? An Emulation Facility for Research

13

A View from the Dark Side

Page 14: Cluster or Network? An Emulation Facility for Research

14

And the Light Side

Page 15: Cluster or Network? An Emulation Facility for Research

15

Artist’s Conception

Page 16: Cluster or Network? An Emulation Facility for Research

16

Zoom in: “Delay” Node

Page 17: Cluster or Network? An Emulation Facility for Research

17

Feature:Automatic mapping of desired

topologies and characteristics to physical resources

•Algorithm goals:

minimize likelihood of experimental artifacts (bottlenecks)

“optimal” packing of multiple simultaneous experiments

Complete in finite time!

• Constraint-based heuristic algorithm (version 2!)

• Feature: accepts ns-compatible specification

Page 18: Cluster or Network? An Emulation Facility for Research

18

Current Algorithm

• Simulated annealing

Make random change (move node from one switch to another), compute score, accept/reject based on current temp.

•Heuristic algorithm

•~ 4 seconds for 30 nodes; polynomial

• Improve:

Hardwired node connections will slow it down x100

Edge nodes

Speed - incremental score recomputation

Page 19: Cluster or Network? An Emulation Facility for Research

Virtual Topology

Page 20: Cluster or Network? An Emulation Facility for Research

Mapping into Physical Topology

Page 21: Cluster or Network? An Emulation Facility for Research

21

Roatan: Remote Console for a Node

Page 22: Cluster or Network? An Emulation Facility for Research

22

Early Network Configuration GUI

Page 23: Cluster or Network? An Emulation Facility for Research

23

Research Applications

• Simulation validation

•Active networks

•Resource demands of services inside routers

•Denial-of-service resistance

• Interaction of adaptive applications and protocols

•All sorts of distributed system experiments

• ...

Page 24: Cluster or Network? An Emulation Facility for Research

24

Research Applications (continued)

•Detailed performance monitoring and analysis

•Relationships between {node, link, topology} characteristics and

Application performance

Task scheduling and assignment

Communication software

Application algorihms

….

Page 25: Cluster or Network? An Emulation Facility for Research

25

Study: Interconnection Techniques

• Point-to-point vs.always through a switch

Salmon et al (Caltech)

• Cost vs. performance

•Of most interest on large clusters

• Locality of communication patterns

• Interference with local processing

•Ad hoc mobile networking

Page 26: Cluster or Network? An Emulation Facility for Research

26

Research Issues and Other Challenges

• Calibration, validation, and scaling: how to emulate different speed networks? Scaling behavior of emulating faster links by slowing nodes?

• Can we sufficiently capture real router internal behavior in a PC?

•Assuring validity: detecting switch bottlenecks, measuring and controlling physical characteristics without introducing artifacts.

•Algorithms and software to map requirements to resources while minimizing artifacts.

• Integrate with ns?

• Providing a reasonable user interface to all this.

Page 27: Cluster or Network? An Emulation Facility for Research

27

Final Remarks

•Should be limping next month

•Looking for feedback on your potential use

•Looking for early users

•Collaborators/clients: UU Physics, CMU CS, MIT CS, Georgia Tech, IBM research

•Sponsors: University of Utah, Novell, DARPA, Compaq, Nortel, <your_name_here>