1 Logistical Computing and Internetworking: Middleware for the Use of Storage in Communication Micah...

18
1 Logistical Computing and Internetworking: Middleware for the Use of Storage in Communication Micah Beck Jack Dongarra Terry Moore James Plank University of Tennessee Fran Berman Henri Casanova University of California, San Diego Rich Wolski University of California, Santa Barbara 3 rd International Workshop on Active Middleware Services

Transcript of 1 Logistical Computing and Internetworking: Middleware for the Use of Storage in Communication Micah...

Page 1: 1 Logistical Computing and Internetworking: Middleware for the Use of Storage in Communication Micah Beck Jack Dongarra Terry Moore James Plank University.

1

Logistical Computing and Internetworking: Middleware for the Use

of Storage in Communication

Micah BeckJack Dongarra Terry MooreJames Plank

University of Tennessee

Fran BermanHenri Casanova

University of California, San Diego

Rich Wolski

University of California, Santa Barbara

3rd International Workshop on Active Middleware Services

Page 2: 1 Logistical Computing and Internetworking: Middleware for the Use of Storage in Communication Micah Beck Jack Dongarra Terry Moore James Plank University.

2

LoCI Projects

• Internet Backplane Protocol (Beck, Plank)

• Network Weather Service (Wolski)

• NetSolve (Dongarra)

• Application Level Scheduling (Berman)

LoCI Funded by National Science Foundation Next Generation Software Program

Page 3: 1 Logistical Computing and Internetworking: Middleware for the Use of Storage in Communication Micah Beck Jack Dongarra Terry Moore James Plank University.

3

Internet Backplane Protocol (IBP)

• primitive middleware that supports a layer of network storage

• implemented as a system of buffers exposed for direct scheduling,

• can be used by advanced applications to leverage state management for high-performance.

Page 4: 1 Logistical Computing and Internetworking: Middleware for the Use of Storage in Communication Micah Beck Jack Dongarra Terry Moore James Plank University.

4

Network Weather Service (NWS)

• Monitors and extrapolates network metrics– network bandwidth and latency– storage availability– CPU load

• Prediction is weak reservation– all reservations will sometimes be broken– effective for highly aggregated resources

Page 5: 1 Logistical Computing and Internetworking: Middleware for the Use of Storage in Communication Micah Beck Jack Dongarra Terry Moore James Plank University.

5

NetSolve (NetSolve)

• Provides a programming environment that facilitates the analysis of program dependences to understand an application’s inherent communication requirements.

• A major component of LoCI research is identify and provide opportunities for extracting scheduling information from applications.

Page 6: 1 Logistical Computing and Internetworking: Middleware for the Use of Storage in Communication Micah Beck Jack Dongarra Terry Moore James Plank University.

6

Application Level Scheduling (AppLeS)

• Enables the derivation of an efficient schedule that matches communication requirements.

• Mapping the computation, network and storage resources of the application to the Grid resources subject to current and predicted resource conditions, is a difficult problem.

• AppLeS is the leading instance of a range of approaches we are exploring under LoCI.

Page 7: 1 Logistical Computing and Internetworking: Middleware for the Use of Storage in Communication Micah Beck Jack Dongarra Terry Moore James Plank University.

7

An Analogy with Pipelined Processor Architecture

• The fundamental elements of modern processor architecture are:– Buses and functional units which move and

transform data, and – Memory and cache, registers and pipeline

buffers that store data.

• RISC architecture exposes resources to scheduling by the compiler

Page 8: 1 Logistical Computing and Internetworking: Middleware for the Use of Storage in Communication Micah Beck Jack Dongarra Terry Moore James Plank University.

8

Network Computing has Analogous Components

• In our model of logistical network computing, the fundamental elements are– Predictable networking and computation which

move and transform data, and– Storage that is accessible from the network.

• Logistical Computing exposes resources to external schedulers (including applications)

Page 9: 1 Logistical Computing and Internetworking: Middleware for the Use of Storage in Communication Micah Beck Jack Dongarra Terry Moore James Plank University.

9

Logistical Networking: Exposed Storage Management

• Storage resources available for direct access at network intermediate nodes.

• Allocation and scheduling of storage resources are exposed to the network.

• Some implications– storage resources are shared among operations– applications, intermediate nodes can schedule

Page 10: 1 Logistical Computing and Internetworking: Middleware for the Use of Storage in Communication Micah Beck Jack Dongarra Terry Moore James Plank University.

10

IBP Software Structure

• IBP Depots (servers) are daemons that serve local storage to IBP clients.

• IBP Clients link an IBP client library with a well-defined API.

• Clients talk to depots using TCP/IP.

• Design is for high-performance/scalability.

Page 11: 1 Logistical Computing and Internetworking: Middleware for the Use of Storage in Communication Micah Beck Jack Dongarra Terry Moore James Plank University.

11

Logistical Computation Mechanisms

• The Network Weather Service: Monitoring Resources for Logistical Scheduling

• Logistical Scheduling and the AppLeS Project

• Coscheduling of Storage and Computation in NetSolve

Page 12: 1 Logistical Computing and Internetworking: Middleware for the Use of Storage in Communication Micah Beck Jack Dongarra Terry Moore James Plank University.

12

NetSolve - The Big Picture

Reply Choice

Computational ResourcesClusters

MPP

Workstations

MPI, PVM,Condor...

RequestAgent

Scheduler

Database

Client - RPC like

MatlabMathematicaC, Fortran Java, Perl Java GUI

Page 13: 1 Logistical Computing and Internetworking: Middleware for the Use of Storage in Communication Micah Beck Jack Dongarra Terry Moore James Plank University.

13

State Management in NetSolve

• The Problem: NetSolve calls are functional

• Excessive data transfers

For example:X = F(A, B);Y = G(X, B);

ClientA,B

F

ClientX,B

G

Client

X

Y

Server 1

Server 2

Page 14: 1 Logistical Computing and Internetworking: Middleware for the Use of Storage in Communication Micah Beck Jack Dongarra Terry Moore James Plank University.

14

ClientA

F

G

Client

Y

Server 1

Server 2

Client A,B

F

A,B

G

Client

Y

Server 1

Server 2

X

X,B

Y

Caching

X

B

B

B

Dependence Flow

IBP

Cache

Page 15: 1 Logistical Computing and Internetworking: Middleware for the Use of Storage in Communication Micah Beck Jack Dongarra Terry Moore James Plank University.

15

An Experiment Using NetSolve

• NetSolve Client at UC San Diego

• Computational Servers at UT Knoxville

• MA28 solver library used to solve systems of equations from the Harwell-Boeing collection of the Matrix Market repository

• Uncached to client-directed caching

Page 16: 1 Logistical Computing and Internetworking: Middleware for the Use of Storage in Communication Micah Beck Jack Dongarra Terry Moore James Plank University.

16

Preliminary Results

• Unenhanced NetSolve vs. NetSolve w/IBP caching

16.1 KB 2.68 MB

Page 17: 1 Logistical Computing and Internetworking: Middleware for the Use of Storage in Communication Micah Beck Jack Dongarra Terry Moore James Plank University.

17

LoCI Software Integration

• IBP Depot (server) available for Unix/Linux and Win32

• IBP Client Library also available for Java

• NetSolve 1.4 (just released) supports IBP caching

• Network Weather Service uses IBP internally for monitor state management

Page 18: 1 Logistical Computing and Internetworking: Middleware for the Use of Storage in Communication Micah Beck Jack Dongarra Terry Moore James Plank University.

18

Conclusions

• Logistical Computing defines a comprehensive exposed approach to Grid computing

• Processing, network, and storage resources are explicitly scheduled for performance

• Storage resources sharing enables improvements over stateless computation based solely on end-to-end communication