1 / 24

MOCCA – A Distributed CCA Framework based on H2O

Maciej Malawski, Dawid Kurzyniec, Vaidy Sunderam. Distributed Computing Laboratory in the Dept. of Math and Computer Science, Emory University, Atlanta Institute of Computer Science AGH, Krakow, Poland. MOCCA – A Distributed CCA Framework based on H2O. Outline. CCA and H2O: a good match

neci
Download Presentation

MOCCA – A Distributed CCA Framework based on H2O

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Maciej Malawski, Dawid Kurzyniec, Vaidy Sunderam Distributed Computing Laboratory in the Dept. of Math and Computer Science, Emory University, Atlanta Institute of Computer Science AGH, Krakow, Poland MOCCA – A Distributed CCA Framework based on H2O

  2. Outline CCA and H2O: a good match H2O as underlying platform Goals of MOCCA (Metacomputing Oriented CCA framework) MOCCA technical overview Initial performance results Towards Babel compatibility Future directions and research perspectives

  3. Why CCA and H2O CCA • Component standard for HPC • Uses and provides ports described in SIDL • Support for scientific data types • Existing tightly coupled (CCAFFEINE) and loosely coupled, distributed (XCAT) frameworks H2O • Distributed resource sharing platform • Providers setup H2O kernel (container) • Allowed parties can deploy pluglets (components) • Separation of roles: decoupling • Providers from deployers • Providers from each other • RMIX: efficient multiprotocol RMI extension

  4. H2O Resource sharing platform • Providers own resources • They independentlyshare them over the network • access control policies • Clients discover, locate, and utilize resources • Resources configurable via plugins • Aggregation and reselling: cascading pairwise relationships

  5. Pluglet Kernel Clients Functionalinterfaces (e.g. Hello) Pluglet H2O Component Model • Nomenclature • container = kernel • component = pluglet • Pluglet = remotely accessible object • implementsPluglet interface, used by kernel to signal/trigger pluglet state changes • Remote access: based on the RMI model • Pluglets export functional remote interfaces Interface Pluglet { void init(RuntimeContext cxt); void start(); void stop(); void destroy(); } tutorial/step1/srv/Hello.java public interface Hello extends Remote { String hello() throws RemoteException; }

  6. Example scenarios of H2O Registration and Discovery UDDI JNDI LDAP DNS GIS e-mail,phone, ... ... A nativecode A Publish Find ... Deploy A Provider B A B B Deploy Client Provider Client Provider Client Provider LegacyApp Repository Deploy Repository A B A B C C Reseller Developer 1. Provider = deployer • e.g. resource = legacy application 3. Client = deployer • e.g. client runs custom distributed application on shared resources 2. Reseller:= developer = deployer • e.g. computational service offered within a grid system

  7. RMIX Communication Substrate Service RMIX RMIXJRMPX RMIXXSOAP RMIXRPCX RMIX MYRI Java Web Services ONC-RPC Myrinet SOAP clients • Extensible framework • Remote Method Invocations paradigm • Pluggable protocol providers • Multiple protocols supported • JRMPX, ONC-RPC, SOAP • Request-Response and Asynchronous calls • Combines simplicity, flexibility, and performance

  8. H2O Kernel security H2O Kernel Internet firewall efficiency H2O Kernel H2O Kernel Harness Kernel efficiency H2O Kernel RMIX: multiple protocols • Protocol switching • Protocol negotiation • Various protocol stacks for different situations • SOAP: interoperability • SSL: security • ARPC, custom (Myrinet, Quadrics): efficiency

  9. H2O: Current research areas • (More) Interoperability • Support for Globus proxy credentials • Naming services: JNDI bridge to multiple implementations • Peer-to-peer grids • JXTA transport provider for RMIX; enables RMI over JXTA sockets • JXTA-JNDI naming provider: peer-to-peer resource sharing and discovery • Fault-tolerant MPI across shared resources • FT-MPI & H2O: staging, sharing, heterogeneity, scalability

  10. H2O: Feature Summary • Resource sharing • Deploying components on shared resources • Component isolation and hot-swapping • Pluglets deployed in separate class loaders • Performance • Pluglets run in a single process; efficient local bindings • Distributed communication: efficient binary protocols • Support for asynchronous calls • Security • SSL transport, JAAS authentication, Java sandbox model, security policies • Interoperability • Multiple RMI protocols: SOAP, JRMP, RPC, … • API support for native code: resource staging, linking dynamic libraries

  11. Requirements for a Metacomputing-oriented CCA Framework Facilitated deployment - provide easy mechanisms for creation of components on distributed shared resources; Efficient communication - both for distributed and local components; Flexible - allow flexible configuration of components and various application scenarios; Support native components, i.e. components written in non-Java programming languages and compiled for specific architecture. Interoperable with Grid standards (Web services)

  12. Existing CCA Frameworks CCAFFEINE Tightly coupled Support for Babel MPI support XCAT Loosely coupled Globus-compatible Java-based DCA MPI based MxN problems SCIRun2 Metacomponent model LegionCCA Based on Legion Metacomputing system

  13. MOCCA implementation in H2O • Each component running in separate pluglet • Thanks to H2O kernel security mechanisms, multiple components may run without interfering • Two-level builder hierarchy • ComponentID: pluglet URI • MOCCA_Light: pure Java implementation (no SIDL)

  14. Remote Port Call

  15. How to use MOCCA(step by step) • Implement component code extending CCA interfaces (cca.Port, cca.Component) • Compile component classes into JAR file • Publish application JARs on HTTP server • Use the Java client API or write a Jython script to assemble application from components • Specify components and their connections • Specify locations of H2O kernels where to instantiate components • Running the script automatically deploys necessary pluglets into H2O kernels and spawns application

  16. Example script builder = MoccaMainBuilder() uriKernel1 = URI.create("http://emily.mathcs.emory.edu:7800/") uriKernel2 = URI.create("http://zeus10.cyf-kr.edu.pl:7800/") userBuilderID = builder.addNewBuilder(uriKernel1, "MyBuilderPlugletA") providerBuilderID = builder.addNewBuilder(uriKernel2, "MyBuilderPlugletB") properties = MoccaTypeMap() properties.putString("mocca.plugletclasspath", "http://emily.mathcs.emory.edu/mocca/mocca-samples.jar") properties.putString("mocca.builderID", userBuilderID.getSerialization()) userID = builder.createInstance("My StarterComponent", "mocca.samples.pingpong.impl.MoccaStarterComponent”, properties) properties.putString("mocca.plugletclasspath", "http://emily.mathcs.emory.edu/mocca/mocca-samples.jar") properties.putString("mocca.builderID", providerBuilderID.getSerialization()) providerID = builder.createInstance("MyPingComponent", "mocca.samples.pingpong.impl.PingPongComponent", properties) connectionID = builder.connect(userID, "PingPongUsesPort", providerID, "PingPongProvidesPort") MoccaBuilderClient.invokeGo(userID)

  17. Automatic Flow Composer Example • Compose application graph from initial data (e.g. initial ports) or incomplete graph • First implemented for XCAT framework • Easy migration to MOCCA • Modification of code required (xcat.Port) • Similar performance for XCAT and MOCCA (exchange of text documents)

  18. Communication Intensive Application Benchmark Simplified scenario: 2 components Provides port: receive and send-back array of double (ping-pong) Tested on local Gigabit Ethernet and on transatlantic Internet between Atlanta and Krakow 2.4 Ghz Linux machines Comparison with XCAT

  19. Small Data Packets Factors: SOAP header overhead in XCAT Connection pools in RMIX

  20. Large Data Packets • Encoding (binary vs. base64) • CPU saturation on Gigabit LAN (serialization) • Variance caused by Java garbage collection

  21. Support for Babel Components Currently: MOCCA_Light – pure Java framework Approach: Use Java bindings to Babelized components Automatically generate wrapping code Issues: Babel remote bindings Remote references Package hierarchy: gov.cca.Port extends gov.llnl.sidl.BaseInterface, sidl.BaseInterface

  22. Future directions of MOCCA Support for multilingual components Goal: to enable loading of Babel CCAFFEINE components into MOCCA Automatic generation of wrappers from SIDL Support for dynamic component reconfiguration and adaptiveness CCA standard allows for dynamic creation of ports and connecting/reconnecting at runtime Framework needs to support such behavior Especially interesting for interactive (portal/PSE) usage Investigation of using hierarchical components By using CCA BuilderService components may act as sub-frameworks creating hierarchies of subcomponents inside them

  23. Beyond CCA ? Supporting multiple component standards Goal: to enable loading of components written for different standards (e.g. Corba CCM, other) Examples of similar solutions: CCAFFEINE supports „classic” and „Babel” components; SCIRun2 implementing meta-component model Using MOCCA as promising platform for feasibility studies in various aspects of Grid components For experiments with advanced features Scheduling and load-balancing Fault-tolerance Semantic description and composition As a platform for higher-level grid services and tools

  24. References • Maciej Malawski, Dawid Kurzyniec, and Vaidy Sunderam. MOCCA – towards a distributed CCA framework for metacomputing, Accepted for: 10th International Workshop on High-Level Parallel Programming Models and Supportive Environments (HIPS2005), http://mathcs.emory.edu/dcl/h2o/papers/h2o_hips05.pdf • H2O Project homepage: http://www.mathcs.emory.edu/dcl/h2o/

More Related