idnits 2.17.1 draft-dreibholz-rserpool-applic-distcomp-16.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 5, 2014) is 3761 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** Obsolete normative reference: RFC 4960 (Obsoleted by RFC 9260) == Outdated reference: A later version (-34) exists of draft-dreibholz-rserpool-asap-hropt-13 == Outdated reference: A later version (-33) exists of draft-dreibholz-rserpool-delay-12 == Outdated reference: A later version (-31) exists of draft-dreibholz-rserpool-enrp-takeover-10 Summary: 1 error (**), 0 flaws (~~), 4 warnings (==), 2 comments (--).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 Simula Research Laboratory 4 Intended status: Informational January 5, 2014 5 Expires: July 9, 2014 7 Applicability of Reliable Server Pooling for Real-Time Distributed 8 Computing 9 draft-dreibholz-rserpool-applic-distcomp-16.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 July 9, 2014. 34 Copyright Notice 36 Copyright (c) 2014 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 Table of Contents 51 1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . 2 52 1.1. Scope . . . . . . . . . . . . . . . . . . . . . . . . . . 2 53 1.2. Terminology . . . . . . . . . . . . . . . . . . . . . . . 2 54 2. Distributed Computing using RSerPool . . . . . . . . . . . . 2 55 2.1. Requirements . . . . . . . . . . . . . . . . . . . . . . 3 56 2.2. Architecture . . . . . . . . . . . . . . . . . . . . . . 3 57 2.3. Limitations . . . . . . . . . . . . . . . . . . . . . . . 4 58 3. Reference Implementation . . . . . . . . . . . . . . . . . . 4 59 4. Testbed Platform . . . . . . . . . . . . . . . . . . . . . . 5 60 5. Security Considerations . . . . . . . . . . . . . . . . . . . 5 61 6. IANA Considerations . . . . . . . . . . . . . . . . . . . . . 5 62 7. References . . . . . . . . . . . . . . . . . . . . . . . . . 5 63 7.1. Normative References . . . . . . . . . . . . . . . . . . 5 64 7.2. Informative References . . . . . . . . . . . . . . . . . 6 65 Author's Address . . . . . . . . . . . . . . . . . . . . . . . . 8 67 1. Introduction 69 Reliable Server Pooling defines protocols for providing highly 70 available services. The services are located in a pool of redundant 71 servers and if a server fails, another server will take over. The 72 only requirement put on these servers belonging to the pool is that 73 if state is maintained by the server, this state must be transferred 74 to the other server taking over. 76 The goal is to provide server-based redundancy. Transport and 77 network level redundancy are handled by the transport and network 78 layer protocols. 80 The application may choose to distribute its traffic over the servers 81 of the pool conforming to a certain policy. 83 1.1. Scope 85 The scope of this document is to explain the way of using Reliable 86 Server Pooling mechanisms to manage and access pools of Distributed 87 Computing resources. 89 1.2. Terminology 91 The terms are commonly identified in related work and can be found in 92 the Aggregate Server Access Protocol and Endpoint Handlespace 93 Redundancy Protocol Common Parameters document [RFC5354]. 95 2. Distributed Computing using RSerPool 96 2.1. Requirements 98 The application scenario for Distributed Computing is defined as 99 follows: 101 o Clients generate large computation jobs. Jobs have to be 102 processed by servers as soon as possible (real-time), i.e. unlike 103 concepts like SETI@home [SETIatHome-Website], it is not possible 104 to let clients fetch a job, process it later and may be some day 105 upload the result. 107 o Jobs may be partitionable, i.e. they can be split up to smaller 108 pieces which can be processed independently and the processing 109 results can be concatenated to the processing result of the 110 complete job. Jobs have to be processed by servers. 112 o Servers may be unreliable; i.e. user computers may be temporarily 113 added to the pool of computing resources and may be revoked when 114 they are used again by their owners. Furthermore, they may simply 115 disappear because of broken network connections (modems, etc.) or 116 power turned off. 118 o The processing power of servers in a pool of computing resources 119 may be very heterogeneous, i.e. a few supercomputers and many low- 120 end user PCs. 122 Maintaining a Distributed Computing pool for the scenario described 123 above arises the following requirements to the pool management: 125 o It must be possible to manage large server pools, e.g. up to some 126 hundreds or even thousands of servers. 128 o Due to heterogeneous processing resources within a pool, it must 129 be possible to use appropriate server selection procedures to 130 meaningfully utilize the available resources. 132 o It must be possible to dynamically add and remove servers. 134 o Servers may be unreliable, especially when the servers are 135 represented by user PCs. Failover mechanisms are required to 136 continue an interrupted computation session. 138 2.2. Architecture 140 All requirements for pool and session management of the Distributed 141 Computing scenario defined in the previous section can be fulfilled 142 by the Reliable Server Pooling architecture: 144 o An efficient implementation of the handlespace management 145 structures allows pools to contain thousands of elements. 146 Handlespace management structures have been proposed, implemented 147 and analyzed in [IJHIT2008], [Dre2006]. 149 o RSerPool allows to specify server selection rules by pool member 150 selection policies [RFC5356]. A set of adaptive and non-adaptive 151 policies is already defined. To fulfill the requirements of new 152 applications, it is also possible to define new policies. 153 Research has already been made on the subject of load distribution 154 efficiency of pool policies in Distributed Computing scenarios: 155 see [Dre2006], [IJAIT2009], [LCN2005], [Tencon2005], 156 [Euromicro2007] for details. 158 o Dynamic addition and removal of PEs is a feature of RSerPool 159 [RFC5352]. 161 o The control/data channel concept [RFC5351] of RSerPool realizes a 162 session layer. That is, RSerPool already handles the main task of 163 maintaining and monitoring connections between PUs and PEs; the 164 only task of the application layer to provide full failover 165 functionality is to realize an application-dependent failover 166 procedure. By the usage of client-based state synchronization 167 [IJAIT2009], [LCN2002] in the form of ASAP Cookies, a failover may 168 be fully transparent to the PU while only a state restoration is 169 necessary on the PE side. A demo application [RSerPool-Website] 170 using the RSerPool session layer in a Distributed Computing 171 application is described in [Infocom2005]. 173 2.3. Limitations 175 Applying RSerPool for distributed computing applications, the duties 176 of the RSerPool architecture are still limited to the management of 177 pools and independent sessions only. It is in particular a non-goal 178 to provide functionalities like data synchronization among sessions, 179 user authentication, accounting or the support for more than one 180 administrative domain. Such functionalities are considered to be 181 application-specific and are therefore out of the scope of RSerPool. 183 3. Reference Implementation 184 The RSerPool reference implementation RSPLIB, including example 185 Distributed Computing applications, can be found at 186 [RSerPool-Website]. It supports the functionalities defined by 187 [RFC5351], [RFC5352], [RFC5353], [RFC5354] and [RFC5355] as well as 188 the options [I-D.dreibholz-rserpool-asap-hropt], 189 [I-D.dreibholz-rserpool-enrp-takeover] and 190 [I-D.dreibholz-rserpool-delay]. An introduction to this 191 implementation is provided in [Dre2006]. 193 4. Testbed Platform 195 A large-scale and realistic Internet testbed platform with support 196 for the multi-homing feature of the underlying SCTP protocol is 197 NorNet. A description of NorNet is provided in [PAMS2013-NorNet], 198 some further information can be found on the project website 199 [NorNet-Website]. 201 5. Security Considerations 203 The protocols used in the Reliable Server Pooling architecture only 204 try to increase the availability of the servers in the network. 205 RSerPool protocols do not contain any protocol mechanisms which are 206 directly related to user message authentication, integrity and 207 confidentiality functions. For such features, it depends on the 208 IPSEC protocols or on Transport Layer Security (TLS) protocols for 209 its own security and on the architecture and/or security features of 210 its user protocols. 212 The RSerPool architecture allows the use of different transport 213 protocols for its application and control data exchange. These 214 transport protocols may have mechanisms for reducing the risk of 215 blind denial-of-service attacks and/or masquerade attacks. If such 216 measures are required by the applications, then it is advised to 217 check the SCTP (see [RFC4960]) applicability statement [RFC3257] for 218 guidance on this issue. 220 6. IANA Considerations 222 This document introduces no additional considerations for IANA. 224 7. References 226 7.1. Normative References 228 [RFC3257] Coene, L., "Stream Control Transmission Protocol 229 Applicability Statement", RFC 3257, April 2002. 231 [RFC4960] Stewart, R., "Stream Control Transmission Protocol", RFC 232 4960, September 2007. 234 [RFC5351] Lei, P., Ong, L., Tuexen, M., and T. Dreibholz, "An 235 Overview of Reliable Server Pooling Protocols", RFC 5351, 236 September 2008. 238 [RFC5352] Stewart, R., Xie, Q., Stillman, M., and M. Tuexen, 239 "Aggregate Server Access Protocol (ASAP)", RFC 5352, 240 September 2008. 242 [RFC5353] Xie, Q., Stewart, R., Stillman, M., Tuexen, M., and A. 243 Silverton, "Endpoint Handlespace Redundancy Protocol 244 (ENRP)", RFC 5353, September 2008. 246 [RFC5354] Stewart, R., Xie, Q., Stillman, M., and M. Tuexen, 247 "Aggregate Server Access Protocol (ASAP) and Endpoint 248 Handlespace Redundancy Protocol (ENRP) Parameters", RFC 249 5354, September 2008. 251 [RFC5355] Stillman, M., Gopal, R., Guttman, E., Sengodan, S., and M. 252 Holdrege, "Threats Introduced by Reliable Server Pooling 253 (RSerPool) and Requirements for Security in Response to 254 Threats", RFC 5355, September 2008. 256 [RFC5356] Dreibholz, T. and M. Tuexen, "Reliable Server Pooling 257 Policies", RFC 5356, September 2008. 259 [I-D.dreibholz-rserpool-asap-hropt] 260 Dreibholz, T., "Handle Resolution Option for ASAP", draft- 261 dreibholz-rserpool-asap-hropt-13 (work in progress), July 262 2013. 264 [I-D.dreibholz-rserpool-delay] 265 Dreibholz, T. and X. Zhou, "Definition of a Delay 266 Measurement Infrastructure and Delay-Sensitive Least-Used 267 Policy for Reliable Server Pooling", draft-dreibholz- 268 rserpool-delay-12 (work in progress), July 2013. 270 [I-D.dreibholz-rserpool-enrp-takeover] 271 Dreibholz, T. and X. Zhou, "Takeover Suggestion Flag for 272 the ENRP Handle Update Message", draft-dreibholz-rserpool- 273 enrp-takeover-10 (work in progress), July 2013. 275 7.2. Informative References 277 [Dre2006] Dreibholz, T., "Reliable Server Pooling - Evaluation, 278 Optimization and Extension of a Novel IETF Architecture", 279 March 2007, . 283 [Euromicro2007] 284 Dreibholz, T., Zhou, X., and E. Rathgeb, "A Performance 285 Evaluation of RSerPool Server Selection Policies in 286 Varying Heterogeneous Capacity Scenarios", Proceedings of 287 the 33rd IEEE EuroMirco Conference on Software Engineering 288 and Advanced Applications, Pages 157-164, 289 ISBN 0-7695-2977-1, DOI 10.1109/EUROMICRO.2007.9, August 290 2007, . 293 [IJAIT2009] 294 Dreibholz, T. and E. Rathgeb, "Overview and Evaluation of 295 the Server Redundancy and Session Failover Mechanisms in 296 the Reliable Server Pooling Framework", International 297 Journal on Advances in Internet Technology (IJAIT), Volume 298 2, Number 1, Pages 1-14, ISSN 1942-2652, June 2009, 299 . 302 [IJHIT2008] 303 Dreibholz, T. and E. Rathgeb, "An Evaluation of the Pool 304 Maintenance Overhead in Reliable Server Pooling Systems", 305 SERSC International Journal on Hybrid Information 306 Technology (IJHIT), Volume 1, Number 2, Pages 17-32, 307 ISSN 1738-9968, April 2008, 308 . 311 [Infocom2005] 312 Dreibholz, T. and E. Rathgeb, "An Application 313 Demonstration of the Reliable Server Pooling Framework", 314 Proceedings of the 24th IEEE INFOCOM, March 2005, 315 . 318 [LCN2002] Dreibholz, T., "An Efficient Approach for State Sharing in 319 Server Pools", Proceedings of the 27th IEEE Local Computer 320 Networks Conference (LCN), Pages 348-349, 321 ISBN 0-7695-1591-6, DOI 10.1109/LCN.2002.1181806, November 322 2002, . 326 [LCN2005] Dreibholz, T. and E. Rathgeb, "On the Performance of 327 Reliable Server Pooling Systems", Proceedings of the IEEE 328 Conference on Local Computer Networks (LCN) 30th 329 Anniversary, Pages 200-208, ISBN 0-7695-2421-4, 330 DOI 10.1109/LCN.2005.98, November 2005, 331 . 334 [Tencon2005] 335 Dreibholz, T. and E. Rathgeb, "The Performance of Reliable 336 Server Pooling Systems in Different Server Capacity 337 Scenarios", Proceedings of the IEEE TENCON, 338 ISBN 0-7803-9312-0, DOI 10.1109/TENCON.2005.300939, 339 November 2005, . 343 [PAMS2013-NorNet] 344 Dreibholz, T. and E. Gran, "Design and Implementation of 345 the NorNet Core Research Testbed for Multi-Homed Systems", 346 Proceedings of the 3nd International Workshop on Protocols 347 and Applications with Multi-Homing Support (PAMS), Pages 348 1094-1100, ISBN 978-0-7695-4952-1, DOI 10.1109/ 349 WAINA.2013.71, March 2013, . 353 [SETIatHome-Website] 354 SETI Project, , "SETI@home: Search for Extraterrestrial 355 Intelligence at home", 2010, 356 . 358 [RSerPool-Website] 359 Dreibholz, T., "Thomas Dreibholz's RSerPool Page", Online: 360 http://www.iem.uni-due.de/~dreibh/rserpool/, 2013, 361 . 363 [NorNet-Website] 364 Xiang, J., "NorNet -- A Real-World, Large-Scale Multi- 365 Homing Testbed", Online: http://www.nntb.no/, 2013, 366 . 368 Author's Address 369 Thomas Dreibholz 370 Simula Research Laboratory, Network Systems Group 371 Martin Linges vei 17 372 1364 Fornebu, Akershus 373 Norway 375 Phone: +47-6782-8200 376 Fax: +47-6782-8201 377 Email: dreibh@simula.no 378 URI: http://www.iem.uni-due.de/~dreibh/