idnits 2.17.1 draft-dreibholz-rserpool-applic-distcomp-06.txt: Checking boilerplate required by RFC 5378 and the IETF Trust (see https://trustee.ietf.org/license-info): ---------------------------------------------------------------------------- No issues found here. Checking nits according to https://www.ietf.org/id-info/1id-guidelines.txt: ---------------------------------------------------------------------------- No issues found here. Checking nits according to https://www.ietf.org/id-info/checklist : ---------------------------------------------------------------------------- No issues found here. Miscellaneous warnings: ---------------------------------------------------------------------------- == The copyright year in the IETF Trust and authors Copyright Line does not match the current year -- The document seems to lack a disclaimer for pre-RFC5378 work, but may have content which was first submitted before 10 November 2008. If you have contacted all the original authors and they are all willing to grant the BCP78 rights to the IETF Trust, then this is fine, and you can ignore this comment. If not, you may need to add the pre-RFC5378 disclaimer. (See the Legal Provisions document at https://trustee.ietf.org/license-info for more information.) -- The document date (January 7, 2009) is 5585 days in the past. Is this intentional? Checking references for intended status: Informational ---------------------------------------------------------------------------- ** Obsolete normative reference: RFC 4960 (Obsoleted by RFC 9260) == Outdated reference: A later version (-34) exists of draft-dreibholz-rserpool-asap-hropt-03 == Outdated reference: A later version (-31) exists of draft-dreibholz-rserpool-enrp-takeover-00 == Outdated reference: A later version (-33) exists of draft-dreibholz-rserpool-delay-02 Summary: 1 error (**), 0 flaws (~~), 4 warnings (==), 2 comments (--). Run idnits with the --verbose option for more detailed information about the items above. -------------------------------------------------------------------------------- 2 Network Working Group T. Dreibholz 3 Internet-Draft University of Duisburg-Essen 4 Intended status: Informational January 7, 2009 5 Expires: July 11, 2009 7 Applicability of Reliable Server Pooling for Real-Time Distributed 8 Computing 9 draft-dreibholz-rserpool-applic-distcomp-06.txt 11 Status of this Memo 13 This Internet-Draft is submitted to IETF in full conformance with the 14 provisions of BCP 78 and BCP 79. 16 Internet-Drafts are working documents of the Internet Engineering 17 Task Force (IETF), its areas, and its working groups. Note that 18 other groups may also distribute working documents as Internet- 19 Drafts. 21 Internet-Drafts are draft documents valid for a maximum of six months 22 and may be updated, replaced, or obsoleted by other documents at any 23 time. It is inappropriate to use Internet-Drafts as reference 24 material or to cite them other than as "work in progress." 26 The list of current Internet-Drafts can be accessed at 27 http://www.ietf.org/ietf/1id-abstracts.txt. 29 The list of Internet-Draft Shadow Directories can be accessed at 30 http://www.ietf.org/shadow.html. 32 This Internet-Draft will expire on July 11, 2009. 34 Copyright Notice 36 Copyright (c) 2009 IETF Trust and the persons identified as the 37 document authors. All rights reserved. 39 This document is subject to BCP 78 and the IETF Trust's Legal 40 Provisions Relating to IETF Documents 41 (http://trustee.ietf.org/license-info) in effect on the date of 42 publication of this document. Please review these documents 43 carefully, as they describe your rights and restrictions with respect 44 to this document. 46 Abstract 48 This document describes the applicability of the Reliable Server 49 Pooling architecture to manage real-time distributed computing pools 50 and access the resources of such pools. 52 Table of Contents 54 1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . . 3 55 1.1. Scope . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 56 1.2. Terminology . . . . . . . . . . . . . . . . . . . . . . . . 3 57 2. Distributed Computing using RSerPool . . . . . . . . . . . . . 3 58 2.1. Requirements . . . . . . . . . . . . . . . . . . . . . . . 3 59 2.2. Architecture . . . . . . . . . . . . . . . . . . . . . . . 4 60 2.3. Limitations . . . . . . . . . . . . . . . . . . . . . . . . 5 61 3. Reference Implementation . . . . . . . . . . . . . . . . . . . 5 62 4. Security Considerations . . . . . . . . . . . . . . . . . . . . 5 63 5. IANA Considerations . . . . . . . . . . . . . . . . . . . . . . 6 64 6. References . . . . . . . . . . . . . . . . . . . . . . . . . . 6 65 6.1. Normative References . . . . . . . . . . . . . . . . . . . 6 66 6.2. Informative References . . . . . . . . . . . . . . . . . . 7 67 Author's Address . . . . . . . . . . . . . . . . . . . . . . . . . 8 69 1. Introduction 71 Reliable Server Pooling defines protocols for providing highly 72 available services. The services are located in a pool of redundant 73 servers and if a server fails, another server will take over. The 74 only requirement put on these servers belonging to the pool is that 75 if state is maintained by the server, this state must be transferred 76 to the other server taking over. 78 The goal is to provide server-based redundancy. Transport and 79 network level redundancy are handled by the transport and network 80 layer protocols. 82 The application may choose to distribute its traffic over the servers 83 of the pool conforming to a certain policy. 85 1.1. Scope 87 The scope of this document is to explain the way of using Reliable 88 Server Pooling mechanisms to manage and access pools of Distributed 89 Computing resources. 91 1.2. Terminology 93 The terms are commonly identified in related work and can be found in 94 the Aggregate Server Access Protocol and Endpoint Handlespace 95 Redundancy Protocol Common Parameters document [RFC5354]. 97 2. Distributed Computing using RSerPool 99 2.1. Requirements 101 The application scenario for Distributed Computing is defined as 102 follows: 104 o Clients generate large computation jobs. Jobs have to be 105 processed by servers as soon as possible (real-time), i.e. unlike 106 concepts like SETI@home [SETIatHome], it is not possible to let 107 clients fetch a job, process it later and may be some day upload 108 the result. 110 o Jobs may be partitionable, i.e. they can be split up to smaller 111 pieces which can be processed independently and the processing 112 results can be concatenated to the processing result of the 113 complete job. Jobs have to be processed by servers. 115 o Servers may be unreliable; i.e. user computers may be temporarily 116 added to the pool of computing resources and may be revoked when 117 they are used again by their owners. Furthermore, they may simply 118 disappear because of broken network connections (modems, etc.) or 119 power turned off. 121 o The processing power of servers in a pool of computing resources 122 may be very heterogeneous, i.e. a few supercomputers and many low- 123 end user PCs. 125 Maintaining a Distributed Computing pool for the scenario described 126 above arises the following requirements to the pool management: 128 o It must be possible to manage large server pools, e.g. up to some 129 hundreds or even thousands of servers. 131 o Due to heterogeneous processing resources within a pool, it must 132 be possible to use appropriate server selection procedures to 133 meaningfully utilize the available resources. 135 o It must be possible to dynamically add and remove servers. 137 o Servers may be unreliable, especially when the servers are 138 represented by user PCs. Failover mechanisms are required to 139 continue an interrupted computation session. 141 2.2. Architecture 143 All requirements for pool and session management of the Distributed 144 Computing scenario defined in the previous section can be fulfilled 145 by the Reliable Server Pooling architecture: 147 o An efficient implementation of the handlespace management 148 structures allows pools to contain thousands of elements. 149 Handlespace management structures have been proposed, implemented 150 and analyzed in [IJHIT2008], [Contel2005], [Dre2006]. 152 o RSerPool allows to specify server selection rules by pool member 153 selection policies [RFC5356]. A set of adaptive and non-adaptive 154 policies is already defined. To fulfill the requirements of new 155 applications, it is also possible to define new policies. 156 Research has already been made on the subject of load distribution 157 efficiency of pool policies in Distributed Computing scenarios: 158 see [LCN2005], [Dre2006], [Tencon2005], [Euromicro2007], [ICN2005] 159 for details. 161 o Dynamic addition and removal of PEs is a feature of RSerPool 162 [RFC5352]. 164 o The control/data channel concept [RFC5351] of RSerPool realizes a 165 session layer. That is, RSerPool already handles the main task of 166 maintaining and monitoring connections between PUs and PEs; the 167 only task of the application layer to provide full failover 168 functionality is to realize an application-dependent failover 169 procedure. By the usage of client-based state synchronization 170 [LCN2002], [Euromicro2005] in the form of ASAP Cookies, a failover 171 may be fully transparent to the PU while only a state restoration 172 is necessary on the PE side. A demo application [RSerPoolPage] 173 using the RSerPool session layer in a Distributed Computing 174 application is described in [Infocom2005]. 176 2.3. Limitations 178 Applying RSerPool for distributed computing applications, the duties 179 of the RSerPool architecture are still limited to the management of 180 pools and independent sessions only. It is in particular a non-goal 181 to provide functionalities like data synchronization among sessions, 182 user authentication, accounting or the support for more than one 183 administrative domain. Such functionalities are considered to be 184 application-specific and are therefore out of the scope of RSerPool. 186 3. Reference Implementation 188 The RSerPool reference implementation RSPLIB, including example 189 Distributed Computing applications, can be found at [RSerPoolPage]. 190 It supports the functionalities defined by [RFC5351], [RFC5352], 191 [RFC5353], [RFC5354] and [RFC5355] as well as the options 192 [I-D.dreibholz-rserpool-asap-hropt], 193 [I-D.dreibholz-rserpool-enrp-takeover] and 194 [I-D.dreibholz-rserpool-delay]. An introduction to this 195 implementation is provided in [Dre2006]. 197 4. Security Considerations 199 The protocols used in the Reliable Server Pooling architecture only 200 try to increase the availability of the servers in the network. 201 RSerPool protocols do not contain any protocol mechanisms which are 202 directly related to user message authentication, integrity and 203 confidentiality functions. For such features, it depends on the 204 IPSEC protocols or on Transport Layer Security (TLS) protocols for 205 its own security and on the architecture and/or security features of 206 its user protocols. 208 The RSerPool architecture allows the use of different transport 209 protocols for its application and control data exchange. These 210 transport protocols may have mechanisms for reducing the risk of 211 blind denial-of-service attacks and/or masquerade attacks. If such 212 measures are required by the applications, then it is advised to 213 check the SCTP (see [RFC4960]) applicability statement [RFC3257] for 214 guidance on this issue. 216 5. IANA Considerations 218 This document introduces no additional considerations for IANA. 220 6. References 222 6.1. Normative References 224 [RFC5351] Lei, P., Ong, L., Tuexen, M., and T. Dreibholz, "An 225 Overview of Reliable Server Pooling Protocols", RFC 5351, 226 September 2008. 228 [RFC5352] Stewart, R., Xie, Q., Stillman, M., and M. Tuexen, 229 "Aggregate Server Access Protocol (ASAP)", RFC 5352, 230 September 2008. 232 [RFC5353] Xie, Q., Stewart, R., Stillman, M., Tuexen, M., and A. 233 Silverton, "Endpoint Handlespace Redundancy Protocol 234 (ENRP)", RFC 5353, September 2008. 236 [RFC5354] Stewart, R., Xie, Q., Stillman, M., and M. Tuexen, 237 "Aggregate Server Access Protocol (ASAP) and Endpoint 238 Handlespace Redundancy Protocol (ENRP) Parameters", 239 RFC 5354, September 2008. 241 [RFC5355] Stillman, M., Gopal, R., Guttman, E., Sengodan, S., and M. 242 Holdrege, "Threats Introduced by Reliable Server Pooling 243 (RSerPool) and Requirements for Security in Response to 244 Threats", RFC 5355, September 2008. 246 [RFC5356] Dreibholz, T. and M. Tuexen, "Reliable Server Pooling 247 Policies", RFC 5356, September 2008. 249 [RFC3257] Coene, L., "Stream Control Transmission Protocol 250 Applicability Statement", RFC 3257, April 2002. 252 [RFC4960] Stewart, R., "Stream Control Transmission Protocol", 253 RFC 4960, September 2007. 255 6.2. Informative References 257 [RSerPoolPage] 258 Dreibholz, T., "Thomas Dreibholz's RSerPool Page", 259 URL: http://tdrwww.iem.uni-due.de.de/dreibholz/rserpool/. 261 [Dre2006] Dreibholz, T., "Reliable Server Pooling -- Evaluation, 262 Optimization and Extension of a Novel IETF Architecture", 263 Ph.D. Thesis University of Duisburg-Essen, Faculty of 264 Economics, Institute for Computer Science and Business 265 Information Systems, URL: http:// 266 duepublico.uni-duisburg-essen.de/servlets/DerivateServlet/ 267 Derivate-16326/Dre2006-final.pdf, March 2007. 269 [LCN2005] Dreibholz, T. and E. Rathgeb, "On the Performance of 270 Reliable Server Pooling Systems", Proceedings of the 30th 271 IEEE Local Computer Networks Conference, November 2005. 273 [Tencon2005] 274 Dreibholz, T. and E. Rathgeb, "The Performance of Reliable 275 Server Pooling Systems in Different Server Capacity 276 Scenarios", Proceedings of the IEEE TENCON, November 2005. 278 [LCN2002] Dreibholz, T., "An efficient approach for state sharing in 279 server pools", Proceedings of the 27th IEEE Local Computer 280 Networks Conference, October 2002. 282 [Euromicro2005] 283 Dreibholz, T. and E. Rathgeb, "RSerPool -- Providing 284 Highly Available Services using Unreliable Servers", 285 Proceedings Proceedings of the 31st IEEE EuroMirco 286 Conference on Software Engineering and Advanced 287 Applications, August 2005. 289 [Euromicro2007] 290 Dreibholz, T., Zhou, X., and E. Rathgeb, "A Performance 291 Evaluation of RSerPool Server Selection Policies in 292 Varying Heterogeneous Capacity Scenarios", Proceedings of 293 the 33rd IEEE EuroMirco Conference on Software Engineering 294 and Advanced Applications, August 2007. 296 [ICN2005] Dreibholz, T., Rathgeb, E., and M. Tuexen, "Load 297 Distribution Performance of the Reliable Server Pooling 298 Framework", Proceedings of the 4th IEEE International 299 Conference on Networking, April 2005. 301 [Infocom2005] 302 Dreibholz, T. and E. Rathgeb, "An Application 303 Demonstration of the Reliable Server Pooling Framework", 304 Proceedings of the 24th IEEE Infocom, March 2005. 306 [Contel2005] 307 Dreibholz, T. and E. Rathgeb, "Implementing the Reliable 308 Server Pooling Framework", Proceedings of the 8th IEEE 309 International Conference on Telecommunications, June 2005. 311 [IJHIT2008] 312 Dreibholz, T. and E. Rathgeb, "An Evalulation of the Pool 313 Maintenance Overhead in Reliable Server Pooling Systems", 314 International Journal of Hybrid Information Technology 315 (IJHIT) Volume 1, Number 2, April 2008. 317 [SETIatHome] 318 "SETI@home: Search for Extraterrestrial Intelligence at 319 home", URL: http://setiathome.ssl.berkeley.edu. 321 [I-D.dreibholz-rserpool-asap-hropt] 322 Dreibholz, T., "Handle Resolution Option for ASAP", 323 draft-dreibholz-rserpool-asap-hropt-03 (work in progress), 324 October 2008. 326 [I-D.dreibholz-rserpool-enrp-takeover] 327 Dreibholz, T. and X. Zhou, "Takeover Suggestion Flag for 328 the ENRP Handle Update Message", 329 draft-dreibholz-rserpool-enrp-takeover-00 (work in 330 progress), December 2008. 332 [I-D.dreibholz-rserpool-delay] 333 Dreibholz, T. and X. Zhou, "Definition of a Delay 334 Measurement Infrastructure and Delay-Sensitive Least-Used 335 Policy for Reliable Server Pooling", 336 draft-dreibholz-rserpool-delay-02 (work in progress), 337 July 2008. 339 Author's Address 341 Thomas Dreibholz 342 University of Duisburg-Essen, Institute for Experimental Mathematics 343 Ellernstrasse 29 344 45326 Essen, Nordrhein-Westfalen 345 Germany 347 Phone: +49-201-1837637 348 Fax: +49-201-1837673 349 Email: dreibh@iem.uni-due.de 350 URI: http://www.iem.uni-due.de/~dreibh/