idnits 2.17.1 draft-dreibholz-rserpool-applic-distcomp-09.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 contain a disclaimer for pre-RFC5378 work, and may have content which was first submitted before 10 November 2008. The disclaimer is necessary when there are original authors that you have been unable to contact, or if some do not wish to grant the BCP78 rights to the IETF Trust. If you are able to get all authors (current and original) to grant those rights, you can and should remove the disclaimer; otherwise, the disclaimer is needed and you can ignore this comment. (See the Legal Provisions document at https://trustee.ietf.org/license-info for more information.) -- The document date (July 2, 2010) is 5018 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** Obsolete normative reference: RFC 4960 (Obsoleted by RFC 9260) == Outdated reference: A later version (-33) exists of draft-dreibholz-rserpool-asap-hropt-06 == Outdated reference: A later version (-32) exists of draft-dreibholz-rserpool-delay-05 == Outdated reference: A later version (-30) exists of draft-dreibholz-rserpool-enrp-takeover-03 Summary: 1 error (**), 0 flaws (~~), 4 warnings (==), 2 comments (--).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 July 2, 2010 5 Expires: January 3, 2011 7 Applicability of Reliable Server Pooling for Real-Time Distributed 8 Computing 9 draft-dreibholz-rserpool-applic-distcomp-09.txt 11 Abstract 13 This document describes the applicability of the Reliable Server 14 Pooling architecture to manage real-time distributed computing pools 15 and access the resources of such pools. 17 Status of this Memo 19 This Internet-Draft is submitted in full conformance with the 20 provisions of BCP 78 and BCP 79. 22 Internet-Drafts are working documents of the Internet Engineering 23 Task Force (IETF). Note that other groups may also distribute 24 working documents as Internet-Drafts. The list of current Internet- 25 Drafts is at http://datatracker.ietf.org/drafts/current/. 27 Internet-Drafts are draft documents valid for a maximum of six months 28 and may be updated, replaced, or obsoleted by other documents at any 29 time. It is inappropriate to use Internet-Drafts as reference 30 material or to cite them other than as "work in progress." 32 This Internet-Draft will expire on January 3, 2011. 34 Copyright Notice 36 Copyright (c) 2010 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. Code Components extracted from this document must 45 include Simplified BSD License text as described in Section 4.e of 46 the Trust Legal Provisions and are provided without warranty as 47 described in the Simplified BSD License. 49 This document may contain material from IETF Documents or IETF 50 Contributions published or made publicly available before November 51 10, 2008. The person(s) controlling the copyright in some of this 52 material may not have granted the IETF Trust the right to allow 53 modifications of such material outside the IETF Standards Process. 54 Without obtaining an adequate license from the person(s) controlling 55 the copyright in such materials, this document may not be modified 56 outside the IETF Standards Process, and derivative works of it may 57 not be created outside the IETF Standards Process, except to format 58 it for publication as an RFC or to translate it into languages other 59 than English. 61 Table of Contents 63 1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . . 3 64 1.1. Scope . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 65 1.2. Terminology . . . . . . . . . . . . . . . . . . . . . . . . 3 66 2. Distributed Computing using RSerPool . . . . . . . . . . . . . 3 67 2.1. Requirements . . . . . . . . . . . . . . . . . . . . . . . 3 68 2.2. Architecture . . . . . . . . . . . . . . . . . . . . . . . 4 69 2.3. Limitations . . . . . . . . . . . . . . . . . . . . . . . . 5 70 3. Reference Implementation . . . . . . . . . . . . . . . . . . . 5 71 4. Security Considerations . . . . . . . . . . . . . . . . . . . . 5 72 5. IANA Considerations . . . . . . . . . . . . . . . . . . . . . . 6 73 6. References . . . . . . . . . . . . . . . . . . . . . . . . . . 6 74 6.1. Normative References . . . . . . . . . . . . . . . . . . . 6 75 6.2. Informative References . . . . . . . . . . . . . . . . . . 7 76 Author's Address . . . . . . . . . . . . . . . . . . . . . . . . . 8 78 1. Introduction 80 Reliable Server Pooling defines protocols for providing highly 81 available services. The services are located in a pool of redundant 82 servers and if a server fails, another server will take over. The 83 only requirement put on these servers belonging to the pool is that 84 if state is maintained by the server, this state must be transferred 85 to the other server taking over. 87 The goal is to provide server-based redundancy. Transport and 88 network level redundancy are handled by the transport and network 89 layer protocols. 91 The application may choose to distribute its traffic over the servers 92 of the pool conforming to a certain policy. 94 1.1. Scope 96 The scope of this document is to explain the way of using Reliable 97 Server Pooling mechanisms to manage and access pools of Distributed 98 Computing resources. 100 1.2. Terminology 102 The terms are commonly identified in related work and can be found in 103 the Aggregate Server Access Protocol and Endpoint Handlespace 104 Redundancy Protocol Common Parameters document [RFC5354]. 106 2. Distributed Computing using RSerPool 108 2.1. Requirements 110 The application scenario for Distributed Computing is defined as 111 follows: 113 o Clients generate large computation jobs. Jobs have to be 114 processed by servers as soon as possible (real-time), i.e. unlike 115 concepts like SETI@home [SETIatHome], it is not possible to let 116 clients fetch a job, process it later and may be some day upload 117 the result. 119 o Jobs may be partitionable, i.e. they can be split up to smaller 120 pieces which can be processed independently and the processing 121 results can be concatenated to the processing result of the 122 complete job. Jobs have to be processed by servers. 124 o Servers may be unreliable; i.e. user computers may be temporarily 125 added to the pool of computing resources and may be revoked when 126 they are used again by their owners. Furthermore, they may simply 127 disappear because of broken network connections (modems, etc.) or 128 power turned off. 130 o The processing power of servers in a pool of computing resources 131 may be very heterogeneous, i.e. a few supercomputers and many low- 132 end user PCs. 134 Maintaining a Distributed Computing pool for the scenario described 135 above arises the following requirements to the pool management: 137 o It must be possible to manage large server pools, e.g. up to some 138 hundreds or even thousands of servers. 140 o Due to heterogeneous processing resources within a pool, it must 141 be possible to use appropriate server selection procedures to 142 meaningfully utilize the available resources. 144 o It must be possible to dynamically add and remove servers. 146 o Servers may be unreliable, especially when the servers are 147 represented by user PCs. Failover mechanisms are required to 148 continue an interrupted computation session. 150 2.2. Architecture 152 All requirements for pool and session management of the Distributed 153 Computing scenario defined in the previous section can be fulfilled 154 by the Reliable Server Pooling architecture: 156 o An efficient implementation of the handlespace management 157 structures allows pools to contain thousands of elements. 158 Handlespace management structures have been proposed, implemented 159 and analyzed in [IJHIT2008], [Dre2006]. 161 o RSerPool allows to specify server selection rules by pool member 162 selection policies [RFC5356]. A set of adaptive and non-adaptive 163 policies is already defined. To fulfill the requirements of new 164 applications, it is also possible to define new policies. 165 Research has already been made on the subject of load distribution 166 efficiency of pool policies in Distributed Computing scenarios: 167 see [Dre2006], [IJAIT2009], [LCN2005], [Tencon2005], 168 [Euromicro2007] for details. 170 o Dynamic addition and removal of PEs is a feature of RSerPool 171 [RFC5352]. 173 o The control/data channel concept [RFC5351] of RSerPool realizes a 174 session layer. That is, RSerPool already handles the main task of 175 maintaining and monitoring connections between PUs and PEs; the 176 only task of the application layer to provide full failover 177 functionality is to realize an application-dependent failover 178 procedure. By the usage of client-based state synchronization 179 [IJAIT2009], [LCN2002] in the form of ASAP Cookies, a failover may 180 be fully transparent to the PU while only a state restoration is 181 necessary on the PE side. A demo application [RSerPoolPage] using 182 the RSerPool session layer in a Distributed Computing application 183 is described in [Infocom2005]. 185 2.3. Limitations 187 Applying RSerPool for distributed computing applications, the duties 188 of the RSerPool architecture are still limited to the management of 189 pools and independent sessions only. It is in particular a non-goal 190 to provide functionalities like data synchronization among sessions, 191 user authentication, accounting or the support for more than one 192 administrative domain. Such functionalities are considered to be 193 application-specific and are therefore out of the scope of RSerPool. 195 3. Reference Implementation 197 The RSerPool reference implementation RSPLIB, including example 198 Distributed Computing applications, can be found at [RSerPoolPage]. 199 It supports the functionalities defined by [RFC5351], [RFC5352], 200 [RFC5353], [RFC5354] and [RFC5355] as well as the options 201 [I-D.dreibholz-rserpool-asap-hropt], 202 [I-D.dreibholz-rserpool-enrp-takeover] and 203 [I-D.dreibholz-rserpool-delay]. An introduction to this 204 implementation is provided in [Dre2006]. 206 4. Security Considerations 208 The protocols used in the Reliable Server Pooling architecture only 209 try to increase the availability of the servers in the network. 210 RSerPool protocols do not contain any protocol mechanisms which are 211 directly related to user message authentication, integrity and 212 confidentiality functions. For such features, it depends on the 213 IPSEC protocols or on Transport Layer Security (TLS) protocols for 214 its own security and on the architecture and/or security features of 215 its user protocols. 217 The RSerPool architecture allows the use of different transport 218 protocols for its application and control data exchange. These 219 transport protocols may have mechanisms for reducing the risk of 220 blind denial-of-service attacks and/or masquerade attacks. If such 221 measures are required by the applications, then it is advised to 222 check the SCTP (see [RFC4960]) applicability statement [RFC3257] for 223 guidance on this issue. 225 5. IANA Considerations 227 This document introduces no additional considerations for IANA. 229 6. References 231 6.1. Normative References 233 [RFC3257] Coene, L., "Stream Control Transmission Protocol 234 Applicability Statement", RFC 3257, April 2002. 236 [RFC4960] Stewart, R., "Stream Control Transmission Protocol", 237 RFC 4960, September 2007. 239 [RFC5351] Lei, P., Ong, L., Tuexen, M., and T. Dreibholz, "An 240 Overview of Reliable Server Pooling Protocols", RFC 5351, 241 September 2008. 243 [RFC5352] Stewart, R., Xie, Q., Stillman, M., and M. Tuexen, 244 "Aggregate Server Access Protocol (ASAP)", RFC 5352, 245 September 2008. 247 [RFC5353] Xie, Q., Stewart, R., Stillman, M., Tuexen, M., and A. 248 Silverton, "Endpoint Handlespace Redundancy Protocol 249 (ENRP)", RFC 5353, September 2008. 251 [RFC5354] Stewart, R., Xie, Q., Stillman, M., and M. Tuexen, 252 "Aggregate Server Access Protocol (ASAP) and Endpoint 253 Handlespace Redundancy Protocol (ENRP) Parameters", 254 RFC 5354, September 2008. 256 [RFC5355] Stillman, M., Gopal, R., Guttman, E., Sengodan, S., and M. 257 Holdrege, "Threats Introduced by Reliable Server Pooling 258 (RSerPool) and Requirements for Security in Response to 259 Threats", RFC 5355, September 2008. 261 [RFC5356] Dreibholz, T. and M. Tuexen, "Reliable Server Pooling 262 Policies", RFC 5356, September 2008. 264 [I-D.dreibholz-rserpool-asap-hropt] 265 Dreibholz, T., "Handle Resolution Option for ASAP", 266 draft-dreibholz-rserpool-asap-hropt-06 (work in progress), 267 January 2010. 269 [I-D.dreibholz-rserpool-delay] 270 Dreibholz, T. and X. Zhou, "Definition of a Delay 271 Measurement Infrastructure and Delay-Sensitive Least-Used 272 Policy for Reliable Server Pooling", 273 draft-dreibholz-rserpool-delay-05 (work in progress), 274 January 2010. 276 [I-D.dreibholz-rserpool-enrp-takeover] 277 Dreibholz, T. and X. Zhou, "Takeover Suggestion Flag for 278 the ENRP Handle Update Message", 279 draft-dreibholz-rserpool-enrp-takeover-03 (work in 280 progress), January 2010. 282 6.2. Informative References 284 [Dre2006] Dreibholz, T., "Reliable Server Pooling -- Evaluation, 285 Optimization and Extension of a Novel IETF Architecture", 286 Ph.D. Thesis University of Duisburg-Essen, Faculty of 287 Economics, Institute for Computer Science and Business 288 Information Systems, URL: http:// 289 duepublico.uni-duisburg-essen.de/servlets/DerivateServlet/ 290 Derivate-16326/Dre2006-final.pdf, March 2007. 292 [Euromicro2007] 293 Dreibholz, T., Zhou, X., and E. Rathgeb, "A Performance 294 Evaluation of RSerPool Server Selection Policies in 295 Varying Heterogeneous Capacity Scenarios", Proceedings of 296 the 33rd IEEE EuroMirco Conference on Software Engineering 297 and Advanced Applications, August 2007. 299 [IJAIT2009] 300 Dreibholz, T. and E. Rathgeb, "Overview and Evaluation of 301 the Server Redundancy and Session Failover Mechanisms in 302 the Reliable Server Pooling Framework", International 303 Journal on Advances in Internet Technology (IJAIT) Volume 304 2, Number 1, June 2009. 306 [IJHIT2008] 307 Dreibholz, T. and E. Rathgeb, "An Evalulation of the Pool 308 Maintenance Overhead in Reliable Server Pooling Systems", 309 International Journal of Hybrid Information Technology 310 (IJHIT) Volume 1, Number 2, April 2008. 312 [Infocom2005] 313 Dreibholz, T. and E. Rathgeb, "An Application 314 Demonstration of the Reliable Server Pooling Framework", 315 Proceedings of the 24th IEEE Infocom, March 2005. 317 [LCN2002] Dreibholz, T., "An efficient approach for state sharing in 318 server pools", Proceedings of the 27th IEEE Local Computer 319 Networks Conference, October 2002. 321 [LCN2005] Dreibholz, T. and E. Rathgeb, "On the Performance of 322 Reliable Server Pooling Systems", Proceedings of the 30th 323 IEEE Local Computer Networks Conference, November 2005. 325 [RSerPoolPage] 326 Dreibholz, T., "Thomas Dreibholz's RSerPool Page", 327 URL: http://tdrwww.iem.uni-due.de.de/dreibholz/rserpool/. 329 [SETIatHome] 330 "SETI@home: Search for Extraterrestrial Intelligence at 331 home", URL: http://setiathome.ssl.berkeley.edu. 333 [Tencon2005] 334 Dreibholz, T. and E. Rathgeb, "The Performance of Reliable 335 Server Pooling Systems in Different Server Capacity 336 Scenarios", Proceedings of the IEEE TENCON, November 2005. 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/