<html><head><meta http-equiv="Content-Type" content="text/html charset=utf-8"></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;"><span style="font-family: Optima-Regular;">[Apologies if you have received multiple copies of this email]</span><br><div><div style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;"><div><span style="font-family: Optima-Regular;"><br></span></div><div><div><font face="Optima-Regular">1st Programmable File Systems Workshop (PFSW’14)</font></div><div><font face="Optima-Regular">
in conjunction with</font></div><div><font face="Optima-Regular">The 23rd International ACM Symposium on High Performance Parallel and Distributed Computing (HPDC 2014)</font></div><div><font face="Optima-Regular">Vancouver, BC, Canada on June 23-27, 2014 (workshop is one day TBD)</font></div><div><font face="Optima-Regular"><br></font></div><div><font face="Optima-Regular"><a href="http://www.cs.ucsc.edu/~carlosm/PFSW/">http://www.cs.ucsc.edu/~carlosm/PFSW/</a></font></div><div><font face="Optima-Regular"><br></font></div><div><font face="Optima-Regular">WORKSHOP ABSTRACT</font></div><div><font face="Optima-Regular">A major milestone in the evolution of digital computers was the development of</font></div><div><font face="Optima-Regular">the stored-program concept and the design of Turing-complete machines as</font></div><div><font face="Optima-Regular">opposed to fixed-program computers. Yet, we still treat an increasingly</font></div><div><font face="Optima-Regular">important subsystem of computers largely as a fixed-program computer: file and</font></div><div><font face="Optima-Regular">storage systems. Among the key reasons for this history is the justified fear</font></div><div><font face="Optima-Regular">that (1) any interface changes in file and storage systems will make legacy</font></div><div><font face="Optima-Regular">data inaccessible and locks the data to a particular system and (2)</font></div><div><font face="Optima-Regular">programmability will increase the probability of data loss.</font></div><div><font face="Optima-Regular"><br></font></div><div><font face="Optima-Regular">Yet with the advent of open source file systems a new usage pattern emerges:</font></div><div><font face="Optima-Regular">users isolate subsystems of these file systems and put them in contexts not</font></div><div><font face="Optima-Regular">foreseen by original designers. Examples are: (1) an object-based storage back</font></div><div><font face="Optima-Regular">end gets a new RESTful front end to become a Amazon Web Service's S3 compliant</font></div><div><font face="Optima-Regular">key value store, (2) a data placement function is used as a placement function</font></div><div><font face="Optima-Regular">for customer accounts, and (3) the HDF5 scientific data access library is</font></div><div><font face="Optima-Regular">embedded into parallel storage systems. This trend shows a desire for the</font></div><div><font face="Optima-Regular">ability to use existing file system services and compose them to implement new</font></div><div><font face="Optima-Regular">services — a desire, however, that is frequently stumped by the difficulty of</font></div><div><font face="Optima-Regular">bringing new services of advanced functionality up to production quality and</font></div><div><font face="Optima-Regular">sufficiently low probability of data loss. At the same time government and</font></div><div><font face="Optima-Regular">industry are heavily investing into the development of new, extremely</font></div><div><font face="Optima-Regular">scalable, and highly efficient, distributed I/O stacks that largely abandon</font></div><div><font face="Optima-Regular">traditional file and storage system interfaces.</font></div><div><font face="Optima-Regular"><br></font></div><div><font face="Optima-Regular">Designing programmability into file and storage systems has the following</font></div><div><font face="Optima-Regular">benefits: (1) we are achieving greater separation of storage performance</font></div><div><font face="Optima-Regular">engineering from storage reliability engineering, making it possible to</font></div><div><font face="Optima-Regular">optimize storage systems in a wide variety of ways without risking years of</font></div><div><font face="Optima-Regular">investments into code hardening; (2) we are creating an environment that</font></div><div><font face="Optima-Regular">encourages people to create a new stack of storage systems abstractions, both</font></div><div><font face="Optima-Regular">domain-specific and across domains, including sophisticated optimizers that</font></div><div><font face="Optima-Regular">rely on machine learning techniques; (3) we are informing commercial parallel</font></div><div><font face="Optima-Regular">file system vendors on the design of low-level APIs for their products so that</font></div><div><font face="Optima-Regular">they match the versatility of open source storage systems without having to</font></div><div><font face="Optima-Regular">release their entire code into open source; and (4) we are using this</font></div><div><font face="Optima-Regular">historical opportunity to leverage the tension between the versatility of open</font></div><div><font face="Optima-Regular">source storage systems and the reliability of proprietary systems to lead the</font></div><div><font face="Optima-Regular">community of storage system designers.</font></div><div><font face="Optima-Regular"><br></font></div><div><font face="Optima-Regular">GOAL</font></div><div><font face="Optima-Regular">This one-day workshop focusses on frameworks that allow the programmability of</font></div><div><font face="Optima-Regular">file and storage systems while addressing the risks of data interface change.</font></div><div><font face="Optima-Regular">The workshop aims to serve as a venue for leaders in the file system and</font></div><div><font face="Optima-Regular">storage community to exchange ideas outside the tradition of half a century of</font></div><div><font face="Optima-Regular">classic file and storage systems research which focussed on a small set of</font></div><div><font face="Optima-Regular">unchanging interfaces. </font></div><div><font face="Optima-Regular"><br></font></div><div><font face="Optima-Regular">PAPER SUBMISSIONS</font></div><div><font face="Optima-Regular">Authors are invited to submit papers with unpublished, original work of not</font></div><div><font face="Optima-Regular">more than 8 pages of double column text using single-spaced 10 point size on</font></div><div><font face="Optima-Regular">8.5 x 11 inch pages (including all text, figures, references, and appendices),</font></div><div><font face="Optima-Regular">as per ACM 8.5 x 11 manuscript guidelines (document templates can be found at</font></div><div><font face="Optima-Regular"><a href="http://www.acm.org/sigs/publications/proceedings-templates">http://www.acm.org/sigs/publications/proceedings-templates</a>). Electronic</font></div><div><font face="Optima-Regular">submissions in pdf format are received at</font></div><div><font face="Optima-Regular"><a href="https://www.easychair.org/conferences/?conf=pfsw2014">https://www.easychair.org/conferences/?conf=pfsw2014</a> at the submission</font></div><div><font face="Optima-Regular">deadline. </font></div><div><font face="Optima-Regular"><br></font></div><div><font face="Optima-Regular">TOPICS</font></div><div><font face="Optima-Regular">Addressing programmability of the non-volatile part of the memory hierarchy,</font></div><div><font face="Optima-Regular">the workshop seeks contributions on relevant topics, included but not limited</font></div><div><font face="Optima-Regular">to:</font></div><div><font face="Optima-Regular"><br></font></div><div><font face="Optima-Regular">- Programming models </font></div><div><font face="Optima-Regular">- Data interface change management and isolation </font></div><div><font face="Optima-Regular">- Interface metadata management and propagation </font></div><div><font face="Optima-Regular">- Compile-time and runtime storage optimization </font></div><div><font face="Optima-Regular">- Data and task placement in large-scale storage stack </font></div><div><font face="Optima-Regular">- Local and distributed performance management and isolation</font></div><div><font face="Optima-Regular">- Nonstop storage system evolution</font></div><div><font face="Optima-Regular"><br></font></div><div><font face="Optima-Regular">IMPORTANT DATES</font></div><div><font face="Optima-Regular">Submission of papers: February 21, 2014, 11:59 PM PST</font></div><div><font face="Optima-Regular">Author notification: March 18, 2014</font></div><div><font face="Optima-Regular">Camera-ready papers: April 15, 2014</font></div><div><font face="Optima-Regular">Workshop: One day during June 23-27, 2014</font></div><div><font face="Optima-Regular"><br></font></div><div><font face="Optima-Regular">WORKSHOP ORGANIZERS</font></div><div><font face="Optima-Regular">Carlos Maltzahn - University of California, Santa Cruz</font></div><div><font face="Optima-Regular">Patrick McCormick - Los Alamos National Laboratory</font></div><div><font face="Optima-Regular"><br></font></div><div><font face="Optima-Regular">PROGRAM COMMITTEE</font></div><div><div>John Bent, EMC</div><div>André Brinkmann, Johannes Gutenberg-Universität Mainz</div><div>Randal Burns, Johns Hopkins University</div><div>Phil Carns, Argonne National Laboratory</div><div>Yong Chen, Texas Tech University</div><div>Toni Cortes, Universitat Politècnica de Catalunya </div><div>Evan Felix, Pacific Northwest National Laboratory</div><div>Maya Gokhale, Lawrence Livermore National Laboratory</div><div>Gary Grider, Los Alamos National Laboratory</div><div>Dean Hildebrand, IBM Almaden</div><div>Dries Kimpe, Argonne National Laboratory</div><div>Scott Klasky, Oak Ridge National Laboratory</div><div>Quincey Koziol, HDF Group</div><div>Jay Lofstead, Sandia National Laboratory</div><div>Barney Maccabe, Oak Ridge National Laboratory</div><div>Carlos Maltzahn, University of California at Santa Cruz</div><div>Adam Manzanares, HGST</div><div>Pat McCormick, Los Alamos National Laboratory</div><div>Michael Mesnier, Intel</div><div>Kiran-Kumar Muniswamy-Reddy, <a href="http://Amazon.com">Amazon.com</a></div><div>Neoklis Polyzotis, University of California at Santa Cruz</div><div>Rob Ross, Argonne National Laboratory</div><div>Sage Weil, Inktank Storage</div><div>Brent Welch, Google</div><div>Jon Woodring, Los Alamos National Laboratory</div></div><div style="font-family: Optima-Regular;"><br></div></div><br><br><br><div><span class="Apple-style-span" style="border-collapse: separate; border-spacing: 0px;"><div style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;"><span class="Apple-style-span" style="border-collapse: separate; orphans: 2; text-align: -webkit-auto; widows: 2; border-spacing: 0px;"><div style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;"><span class="Apple-style-span" style="border-collapse: separate; border-spacing: 0px;"><div style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;"><span class="Apple-style-span" style="border-collapse: separate; border-spacing: 0px;"><div style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;"><span class="Apple-style-span" style="border-collapse: separate; border-spacing: 0px;"><div style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;"><span class="Apple-style-span" style="border-collapse: separate; border-spacing: 0px;"><div style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;">-- <br>Carlos Maltzahn<br>Associate Adjunct Professor<span class="Apple-tab-span" style="white-space: pre;"> </span><br>Computer Science Department<br>University of California, Santa Cruz<span class="Apple-tab-span" style="white-space: pre;"> </span><br><a href="http://www.cs.ucsc.edu/~carlosm/">http://www.cs.ucsc.edu/~carlosm/</a></div><div><br></div></span></div></span></div></span></div></span></div></span></div></span></div></div></div><br></body></html>