idnits 2.17.1 draft-dreibholz-rserpool-applic-distcomp-07.txt: Checking boilerplate required by RFC 5378 and the IETF Trust (see https://trustee.ietf.org/license-info): ---------------------------------------------------------------------------- ** The document seems to lack a License Notice according IETF Trust Provisions of 28 Dec 2009, Section 6.b.ii or Provisions of 12 Sep 2009 Section 6.b -- however, there's a paragraph with a matching beginning. Boilerplate error? (You're using the IETF Trust Provisions' Section 6.b License Notice from 12 Feb 2009 rather than one of the newer Notices. See https://trustee.ietf.org/license-info/.) 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 (July 5, 2009) is 5408 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** Obsolete normative reference: RFC 4960 (Obsoleted by RFC 9260) == Outdated reference: A later version (-34) exists of draft-dreibholz-rserpool-asap-hropt-04 == Outdated reference: A later version (-31) exists of draft-dreibholz-rserpool-enrp-takeover-01 == Outdated reference: A later version (-33) exists of draft-dreibholz-rserpool-delay-03 Summary: 2 errors (**), 0 flaws (~~), 4 warnings (==), 2 comments (--).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 July 5, 2009 5 Expires: January 6, 2010 7 Applicability of Reliable Server Pooling for Real-Time Distributed 8 Computing 9 draft-dreibholz-rserpool-applic-distcomp-07.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 January 6, 2010. 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 in effect on the date of 41 publication of this document (http://trustee.ietf.org/license-info). 42 Please review these documents carefully, as they describe your rights 43 and restrictions with respect to this document. 45 Abstract 47 This document describes the applicability of the Reliable Server 48 Pooling architecture to manage real-time distributed computing pools 49 and access the resources of such pools. 51 Table of Contents 53 1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . . 3 54 1.1. Scope . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 55 1.2. Terminology . . . . . . . . . . . . . . . . . . . . . . . . 3 56 2. Distributed Computing using RSerPool . . . . . . . . . . . . . 3 57 2.1. Requirements . . . . . . . . . . . . . . . . . . . . . . . 3 58 2.2. Architecture . . . . . . . . . . . . . . . . . . . . . . . 4 59 2.3. Limitations . . . . . . . . . . . . . . . . . . . . . . . . 5 60 3. Reference Implementation . . . . . . . . . . . . . . . . . . . 5 61 4. Security Considerations . . . . . . . . . . . . . . . . . . . . 5 62 5. IANA Considerations . . . . . . . . . . . . . . . . . . . . . . 6 63 6. References . . . . . . . . . . . . . . . . . . . . . . . . . . 6 64 6.1. Normative References . . . . . . . . . . . . . . . . . . . 6 65 6.2. Informative References . . . . . . . . . . . . . . . . . . 7 66 Author's Address . . . . . . . . . . . . . . . . . . . . . . . . . 8 68 1. Introduction 70 Reliable Server Pooling defines protocols for providing highly 71 available services. The services are located in a pool of redundant 72 servers and if a server fails, another server will take over. The 73 only requirement put on these servers belonging to the pool is that 74 if state is maintained by the server, this state must be transferred 75 to the other server taking over. 77 The goal is to provide server-based redundancy. Transport and 78 network level redundancy are handled by the transport and network 79 layer protocols. 81 The application may choose to distribute its traffic over the servers 82 of the pool conforming to a certain policy. 84 1.1. Scope 86 The scope of this document is to explain the way of using Reliable 87 Server Pooling mechanisms to manage and access pools of Distributed 88 Computing resources. 90 1.2. Terminology 92 The terms are commonly identified in related work and can be found in 93 the Aggregate Server Access Protocol and Endpoint Handlespace 94 Redundancy Protocol Common Parameters document [RFC5354]. 96 2. Distributed Computing using RSerPool 98 2.1. Requirements 100 The application scenario for Distributed Computing is defined as 101 follows: 103 o Clients generate large computation jobs. Jobs have to be 104 processed by servers as soon as possible (real-time), i.e. unlike 105 concepts like SETI@home [SETIatHome], it is not possible to let 106 clients fetch a job, process it later and may be some day upload 107 the result. 109 o Jobs may be partitionable, i.e. they can be split up to smaller 110 pieces which can be processed independently and the processing 111 results can be concatenated to the processing result of the 112 complete job. Jobs have to be processed by servers. 114 o Servers may be unreliable; i.e. user computers may be temporarily 115 added to the pool of computing resources and may be revoked when 116 they are used again by their owners. Furthermore, they may simply 117 disappear because of broken network connections (modems, etc.) or 118 power turned off. 120 o The processing power of servers in a pool of computing resources 121 may be very heterogeneous, i.e. a few supercomputers and many low- 122 end user PCs. 124 Maintaining a Distributed Computing pool for the scenario described 125 above arises the following requirements to the pool management: 127 o It must be possible to manage large server pools, e.g. up to some 128 hundreds or even thousands of servers. 130 o Due to heterogeneous processing resources within a pool, it must 131 be possible to use appropriate server selection procedures to 132 meaningfully utilize the available resources. 134 o It must be possible to dynamically add and remove servers. 136 o Servers may be unreliable, especially when the servers are 137 represented by user PCs. Failover mechanisms are required to 138 continue an interrupted computation session. 140 2.2. Architecture 142 All requirements for pool and session management of the Distributed 143 Computing scenario defined in the previous section can be fulfilled 144 by the Reliable Server Pooling architecture: 146 o An efficient implementation of the handlespace management 147 structures allows pools to contain thousands of elements. 148 Handlespace management structures have been proposed, implemented 149 and analyzed in [IJHIT2008], [Contel2005], [Dre2006]. 151 o RSerPool allows to specify server selection rules by pool member 152 selection policies [RFC5356]. A set of adaptive and non-adaptive 153 policies is already defined. To fulfill the requirements of new 154 applications, it is also possible to define new policies. 155 Research has already been made on the subject of load distribution 156 efficiency of pool policies in Distributed Computing scenarios: 157 see [LCN2005], [Dre2006], [Tencon2005], [Euromicro2007], [ICN2005] 158 for details. 160 o Dynamic addition and removal of PEs is a feature of RSerPool 161 [RFC5352]. 163 o The control/data channel concept [RFC5351] of RSerPool realizes a 164 session layer. That is, RSerPool already handles the main task of 165 maintaining and monitoring connections between PUs and PEs; the 166 only task of the application layer to provide full failover 167 functionality is to realize an application-dependent failover 168 procedure. By the usage of client-based state synchronization 169 [LCN2002], [Euromicro2005] in the form of ASAP Cookies, a failover 170 may be fully transparent to the PU while only a state restoration 171 is necessary on the PE side. A demo application [RSerPoolPage] 172 using the RSerPool session layer in a Distributed Computing 173 application is described in [Infocom2005]. 175 2.3. Limitations 177 Applying RSerPool for distributed computing applications, the duties 178 of the RSerPool architecture are still limited to the management of 179 pools and independent sessions only. It is in particular a non-goal 180 to provide functionalities like data synchronization among sessions, 181 user authentication, accounting or the support for more than one 182 administrative domain. Such functionalities are considered to be 183 application-specific and are therefore out of the scope of RSerPool. 185 3. Reference Implementation 187 The RSerPool reference implementation RSPLIB, including example 188 Distributed Computing applications, can be found at [RSerPoolPage]. 189 It supports the functionalities defined by [RFC5351], [RFC5352], 190 [RFC5353], [RFC5354] and [RFC5355] as well as the options 191 [I-D.dreibholz-rserpool-asap-hropt], 192 [I-D.dreibholz-rserpool-enrp-takeover] and 193 [I-D.dreibholz-rserpool-delay]. An introduction to this 194 implementation is provided in [Dre2006]. 196 4. Security Considerations 198 The protocols used in the Reliable Server Pooling architecture only 199 try to increase the availability of the servers in the network. 200 RSerPool protocols do not contain any protocol mechanisms which are 201 directly related to user message authentication, integrity and 202 confidentiality functions. For such features, it depends on the 203 IPSEC protocols or on Transport Layer Security (TLS) protocols for 204 its own security and on the architecture and/or security features of 205 its user protocols. 207 The RSerPool architecture allows the use of different transport 208 protocols for its application and control data exchange. These 209 transport protocols may have mechanisms for reducing the risk of 210 blind denial-of-service attacks and/or masquerade attacks. If such 211 measures are required by the applications, then it is advised to 212 check the SCTP (see [RFC4960]) applicability statement [RFC3257] for 213 guidance on this issue. 215 5. IANA Considerations 217 This document introduces no additional considerations for IANA. 219 6. References 221 6.1. Normative References 223 [RFC5351] Lei, P., Ong, L., Tuexen, M., and T. Dreibholz, "An 224 Overview of Reliable Server Pooling Protocols", RFC 5351, 225 September 2008. 227 [RFC5352] Stewart, R., Xie, Q., Stillman, M., and M. Tuexen, 228 "Aggregate Server Access Protocol (ASAP)", RFC 5352, 229 September 2008. 231 [RFC5353] Xie, Q., Stewart, R., Stillman, M., Tuexen, M., and A. 232 Silverton, "Endpoint Handlespace Redundancy Protocol 233 (ENRP)", RFC 5353, September 2008. 235 [RFC5354] Stewart, R., Xie, Q., Stillman, M., and M. Tuexen, 236 "Aggregate Server Access Protocol (ASAP) and Endpoint 237 Handlespace Redundancy Protocol (ENRP) Parameters", 238 RFC 5354, September 2008. 240 [RFC5355] Stillman, M., Gopal, R., Guttman, E., Sengodan, S., and M. 241 Holdrege, "Threats Introduced by Reliable Server Pooling 242 (RSerPool) and Requirements for Security in Response to 243 Threats", RFC 5355, September 2008. 245 [RFC5356] Dreibholz, T. and M. Tuexen, "Reliable Server Pooling 246 Policies", RFC 5356, September 2008. 248 [RFC3257] Coene, L., "Stream Control Transmission Protocol 249 Applicability Statement", RFC 3257, April 2002. 251 [RFC4960] Stewart, R., "Stream Control Transmission Protocol", 252 RFC 4960, September 2007. 254 6.2. Informative References 256 [RSerPoolPage] 257 Dreibholz, T., "Thomas Dreibholz's RSerPool Page", 258 URL: http://tdrwww.iem.uni-due.de.de/dreibholz/rserpool/. 260 [Dre2006] Dreibholz, T., "Reliable Server Pooling -- Evaluation, 261 Optimization and Extension of a Novel IETF Architecture", 262 Ph.D. Thesis University of Duisburg-Essen, Faculty of 263 Economics, Institute for Computer Science and Business 264 Information Systems, URL: http:// 265 duepublico.uni-duisburg-essen.de/servlets/DerivateServlet/ 266 Derivate-16326/Dre2006-final.pdf, March 2007. 268 [LCN2005] Dreibholz, T. and E. Rathgeb, "On the Performance of 269 Reliable Server Pooling Systems", Proceedings of the 30th 270 IEEE Local Computer Networks Conference, November 2005. 272 [Tencon2005] 273 Dreibholz, T. and E. Rathgeb, "The Performance of Reliable 274 Server Pooling Systems in Different Server Capacity 275 Scenarios", Proceedings of the IEEE TENCON, November 2005. 277 [LCN2002] Dreibholz, T., "An efficient approach for state sharing in 278 server pools", Proceedings of the 27th IEEE Local Computer 279 Networks Conference, October 2002. 281 [Euromicro2005] 282 Dreibholz, T. and E. Rathgeb, "RSerPool -- Providing 283 Highly Available Services using Unreliable Servers", 284 Proceedings Proceedings of the 31st IEEE EuroMirco 285 Conference on Software Engineering and Advanced 286 Applications, August 2005. 288 [Euromicro2007] 289 Dreibholz, T., Zhou, X., and E. Rathgeb, "A Performance 290 Evaluation of RSerPool Server Selection Policies in 291 Varying Heterogeneous Capacity Scenarios", Proceedings of 292 the 33rd IEEE EuroMirco Conference on Software Engineering 293 and Advanced Applications, August 2007. 295 [ICN2005] Dreibholz, T., Rathgeb, E., and M. Tuexen, "Load 296 Distribution Performance of the Reliable Server Pooling 297 Framework", Proceedings of the 4th IEEE International 298 Conference on Networking, April 2005. 300 [Infocom2005] 301 Dreibholz, T. and E. Rathgeb, "An Application 302 Demonstration of the Reliable Server Pooling Framework", 303 Proceedings of the 24th IEEE Infocom, March 2005. 305 [Contel2005] 306 Dreibholz, T. and E. Rathgeb, "Implementing the Reliable 307 Server Pooling Framework", Proceedings of the 8th IEEE 308 International Conference on Telecommunications, June 2005. 310 [IJHIT2008] 311 Dreibholz, T. and E. Rathgeb, "An Evalulation of the Pool 312 Maintenance Overhead in Reliable Server Pooling Systems", 313 International Journal of Hybrid Information Technology 314 (IJHIT) Volume 1, Number 2, April 2008. 316 [SETIatHome] 317 "SETI@home: Search for Extraterrestrial Intelligence at 318 home", URL: http://setiathome.ssl.berkeley.edu. 320 [I-D.dreibholz-rserpool-asap-hropt] 321 Dreibholz, T., "Handle Resolution Option for ASAP", 322 draft-dreibholz-rserpool-asap-hropt-04 (work in progress), 323 January 2009. 325 [I-D.dreibholz-rserpool-enrp-takeover] 326 Dreibholz, T. and X. Zhou, "Takeover Suggestion Flag for 327 the ENRP Handle Update Message", 328 draft-dreibholz-rserpool-enrp-takeover-01 (work in 329 progress), January 2009. 331 [I-D.dreibholz-rserpool-delay] 332 Dreibholz, T. and X. Zhou, "Definition of a Delay 333 Measurement Infrastructure and Delay-Sensitive Least-Used 334 Policy for Reliable Server Pooling", 335 draft-dreibholz-rserpool-delay-03 (work in progress), 336 January 2009. 338 Author's Address 340 Thomas Dreibholz 341 University of Duisburg-Essen, Institute for Experimental Mathematics 342 Ellernstrasse 29 343 45326 Essen, Nordrhein-Westfalen 344 Germany 346 Phone: +49-201-1837637 347 Fax: +49-201-1837673 348 Email: dreibh@iem.uni-due.de 349 URI: http://www.iem.uni-due.de/~dreibh/