1. EMC PresentationApril 20051 Research @ Northeastern University I/O storage modeling and performance –David Kaeli Soft error modeling and mitigation –Mehdi B. Tahoori

2. I/O Storage Research at Northeastern University David Kaeli Yijian Wang Department of Electrical and Computer Engineering Northeastern University Boston, MA kaeli@ece.neu.edu

3. EMC PresentationApril 20053 Outline Motivation to study file-based I/O Profile-driven partitioning for parallel file I/O I/O Qualification Laboratory @ NU Areas for future work

4. EMC PresentationApril 20054 Important File-base I/O Workloads Many subsurface sensing and imaging workloads involve file-based I/O –Cellular biology – in-vitro fertilization with NU biologists –Medical imaging – cancer therapy with MGH –Underwater mapping – multi-sensor fusion with Woods Hole Oceanographic Institution –Ground-penetrating radar – toxic waste tracking with Idaho National Labs

5. EMC PresentationApril 20055 The Impact of Profile-guided Parallelization on SSI Applications Reduced the runtime of a single-body Steepest Descent Fast Multipole Method (SDFMM) application by 74% on a 32-node Beowulf cluster Hot-path parallelization Data restructuring Reduced the runtime of a Monte Carlo scattered light simulation by 98% on a 16-node Silicon Graphics Origin 2000 Matlab-to-C compliation Hot-path parallelization Obtained superlinear speedup of Ellipsoid Algorithm run on a 16-node IBM SP2 Matlab-to-C compliation Hot-path parallelization Soil Air Mine

6. EMC PresentationApril 20056 Limits of Parallelization For compute-bound workloads, Beowulf clusters can be used effectively to overcome computational barriers Middlewares (e.g., MPI and MPI/IO) can significantly reduce the programming effort on parallel systems Multiple clusters can be combined, utilizing Grid Middleware (Globus Toolkit) For file-based I/O-bound workloads, Beowulf clusters and Grid systems are presently ill-suited to exploit the potential parallelism present on these systems

7. EMC PresentationApril 20057 Outline Motivation to study file-based I/O Profile-driven partitioning for parallel file I/O I/O Qualification Laboratory @ NU Areas for future work

8. EMC PresentationApril 20058 Parallel I/O Acceleration The I/O bottleneck –The growing gap between the speed of processors, networks and underlying I/O devices –Many imaging and scientific applications access disks very frequently I/O intensive applications –Out-of-core applications –Work on large datasets that cannot fit in main memory –File-intensive applications –Access file-based datasets frequently –Large number of file operations

9. EMC PresentationApril 20059 Introduction Storage architectures –Direct Attached Storage (DAS) –Storage device is directly attached to the computer –Network Attached Storage (NAS) –Storage subsystem is attached to a network of servers and file requests are passed through a parallel filesystem to the centralized storage device –Storage Area Network (SAN) –A dedicated network to provide an any-to-any connection between processors and disks

10. EMC PresentationApril 200510 I/O Partitioning P An I/O intensive application Disk PPP … PPP … … Data Partitioning Multiple disks (i.e. RAID) Disk P … Data Striping Multiple Processes (i.e. MPI-IO)

11. EMC PresentationApril 200511 I/O Partitioning I/O is parallelized at both the application level (using MPI and MPI-IO) and the disk level (using file partitioning) Ideally, every process will only access files on local disk (though this is typically not possible due to data sharing) How to recognize the access patterns? Profile-guided approach

12. EMC PresentationApril 200512 Profile Generation Run the application Capture I/O execution profiles Apply our partitioning algorithm Rerun the tuned application

13. EMC PresentationApril 200513 I/O traces and partitioning For every process, for every contiguous file access, we capture the following I/O profile information: –Process ID –File ID –Address –Chunk size –I/O operation (read/write) –Timestamp Generate a partition for every process Optimal partitioning is NP-complete, so we develop a greedy algorithm We have found we can use partial profiles to guide partitioning

14. EMC PresentationApril 200514 for each IO process, create a partition; for each contiguous data chunk { total up the # of read/write accesses on a process-ID basis; if the chunk is accessed by only one process assign the chunk to the associated partition; if the chunk is read (but never written) by multiple processes duplicate the chunk in all partitions where read; if the chunk is written by one process, but later read by multiple { assign the chunk to all partitions where read and broadcast the updates on writes; else assign the chunk to a shared partition; } For each partition sort chunks based on the earliest timestamp for each chunk; Greedy File Partitioning Algorithm

15. EMC PresentationApril 200515 Parallel I/O Workloads NASA Parallel Benchmark (NPB2.4)/BT –Computational fluid dynamics –Generates a file (~1.6 GB) dynamically and then reads it back –Writes/reads sequentially in chunk sizes of 2040 Bytes SPEChpc96/seismic –Seismic processing –Generates a file (~1.5 GB) dynamically and then reads it back –Writes sequential chunks of 96 KB and reads sequential chunks of 2 KB Tile-IO –Parallel Benchmarking Consortium –Tile access to a two-dimensional matrix (~1 GB) with overlap –Writes/reads sequential chunks of 32 KB, with 2KB of overlap Perf –Parallel I/O test program within MPICH –Writes a 1 MB chunk at a location determined by rank, no overlap Mandelbrot –An image processing application that includes visualization –Chunk size is dependent on the number of processes

16. EMC PresentationApril 200516 10/100Mb Ethernet Switch RAID Node Local PCI-IDE Disk Local PCI-IDE Disk P2-350Mhz RAID Node P2-350Mhz Beowulf Cluster

17. EMC PresentationApril 200517 Hardware Specifics DAS configuration –Linux box, Western Digital WD800BB (IDE), 80GB, 7200RPM Beowulf cluster (base configuration) –Fast Ethernet 100Mbits/sec –Network Attached RAID - Morstor TF200 with 6-9GB drives Seagate SCSI disks, 7200rpm, RAID-5 –Local attached IDE disks – IBM UltraATA-350840, 5400rpm Fibre channel disks –Seagate Cheetah X15 ST-336752FC, 15000rpm

18. EMC PresentationApril 200518 Write/Read Bandwidth NPB2.4/BT SPECHPC/seis

19. EMC PresentationApril 200519 Write/Read Bandwidth MPI-TilePerf Mandelbrot

20. EMC PresentationApril 200520

21. EMC PresentationApril 200521 Profile training sensitivity analysis We have found that IO access patterns are independent of file-based data values When we increase the problem size or reduce the number of processes, either: –the number of IOs increases, but access patterns and chunk size remain the same (SPEChpc96, Mandelbrot), or –the number of IOs and IO access patterns remain the same, but the chunk size increases (NBT, Tile- IO, Perf) Re-profiling can be avoided

22. EMC PresentationApril 200522 Execution-driven Parallel I/O Modeling Growing need to process large, complex datasets in high performance parallel computing applications Efficient implementation of storage architectures can significantly improve system performance An accurate simulation environment for users to test and evaluate different storage architectures and applications

23. EMC PresentationApril 200523 Execution-driven I/O Modeling Target applications: parallel scientific programs (MPI) Target machine/Host machine: Beowulf clusters Use DiskSim as the underlying disk drive simulator Direct execution to model CPU and network communication We execute the real parallel I/O accesses and meanwhile, calculate the simulated I/O response time

24. EMC PresentationApril 200524 Validation – Synthetic I/O Workload on DAS

25. EMC PresentationApril 200525 Simulation Framework - NAS LAN/WAN Network File System I/O traces Local I/O traces RAID controller Disk Sim I/O requests Filesystem metadata Logical file access addresses

26. EMC PresentationApril 200526

27. EMC PresentationApril 200527 LAN/WAN FileSystem I/O traces Disk Sim Disk Sim Disk Sim Disk Sim Simulation Framework – SAN direct A variety of SAN where disks are distributed across the network and each server is directly connected to a single device File partitioning Utilize I/O profiling and data partitioning heuristics to distribute portions of files to disks close to the processing nodes

28. EMC PresentationApril 200528

29. EMC PresentationApril 200529 Hardware Specifications

30. EMC PresentationApril 200530

31. EMC PresentationApril 200531

32. EMC PresentationApril 200532 Publications 1.“Profile-guided File Partitioning on Beowulf Clusters,” Journal of Cluster Computing, Special Issue on Parallel I/O, to appear 2005. 2.“Execution-Driven Simulation of Network Storage Systems,” Proceedings of the 12th ACM/IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems (MASCOTS), October 2004, pp. 604- 611. 3.“Profile-Guided I/O Partitioning,” Proceedings of the 17th ACM International Symposium on Supercomputing, June 2003, pp. 252-260. 4.“Source Level Transformations to Apply I/O Data Partitioning,” Proceedings of the IEEE Workshop on Storage Network Architecture And Parallel IO, Oct. 2003, pp. 12- 21. 5.“Profile-Based Characterization and Tuning for Subsurface Sensing and Imaging Applications,” International Journal of Systems, Science and Technology, September 2002, pp. 40-55.

33. EMC PresentationApril 200533 Summary of Cluster-based Work Many imaging applications are dominated by file-based I/O Parallel systems can only be effectively utilized if I/O is also parallelized Developed a profile-guided approach to I/O data partitioning Impacting clinical trials at MGH Reduced overall execution time by 27-82% over MPI-IO Execution-driven I/O model is highly accurate and provides significant modeling flexibility

34. EMC PresentationApril 200534 Outline Motivation to study file-based I/O Profile-driven partitioning for parallel file I/O I/O Qualification Laboratory @ NU Areas for future work

35. EMC PresentationApril 200535 I/O Qualification Laboratory Working with Enterprise Strategy Group Develop a state-of-the-art facility to provide independent performance qualification of Enterprise Storage systems Provide a quarterly report to ES customer base on the status of current ES offerings Work with leading ES vendors to provide them with custom early performance evaluation of their beta products

36. EMC PresentationApril 200536 I/O Qualification Laboratory Contacted by IOIntegrity and SANGATE for product qualification Developed potential partners that are leaders in the ES field Initial proposals already reviewed by IBM, Hitachi and other ES vendors Looking for initial endorsement from industry

37. EMC PresentationApril 200537 I/O Qualification Laboratory Why @ NU –Track record with industry (EMC, IBM, Sun) –Experience with benchmarking and IO characterization –Interesting set of applications (medical, environmental, etc.) –Great opportunity to work within the cooperative education model

38. EMC PresentationApril 200538 Outline Motivation to study file-based I/O Profile-driven partitioning for parallel file I/O I/O Qualification Laboratory @ NU Areas for future work

39. EMC PresentationApril 200539 Areas for Future Work Designing a Peer-to-Peer storage system on a Grid system by partitioning datasets across geographically distributed storage devices joulian.hpcl.neu.edu keys.ece.neu.edu Internet 1Gbit/s100Mbit/s RAID 31 sub-nodes8 sub-nodes Head node

40. EMC PresentationApril 200540

41. EMC PresentationApril 200541 Areas for Future Work Reduce simulation time by identifying characteristic “phases” in I/O workloads Apply machine learning algorithms to identify clusters of representative I/O behavior Utilize K-Means and Multinomial clustering to obtain high fidelity in simulation runs utilizing sampled I/O behavior “A Multinomial Clustering Model for Fast Simulation of Architecture Designs”, submitted to the 2005 ACM KDD Conference.