Connecting HPIO Capabilities with Domain Specific Needs Rob Ross MCS Division Argonne National Laboratory

Slides:



Advertisements
Similar presentations
MicroKernel Pattern Presented by Sahibzada Sami ud din Kashif Khurshid.
Advertisements

University of Chicago Department of Energy The Parallel and Grid I/O Perspective MPI, MPI-IO, NetCDF, and HDF5 are in common use Multi TB datasets also.
Priority Research Direction (I/O Models, Abstractions and Software) Key challenges What will you do to address the challenges? – Develop newer I/O models.
Transaction.
® IBM Software Group © 2006 IBM Corporation Rational Software France Object-Oriented Analysis and Design with UML2 and Rational Software Modeler 04. Other.
1 Presentation at SciDAC face-to-face January 2005 Ron A. Oldfield Sandia National Laboratories The Lightweight File System.
Objektorienteret Middleware Presentation 2: Distributed Systems – A brush up, and relations to Middleware, Heterogeneity & Transparency.
Week 8 Implementation Design Alex Baker. Implementation Design System Design – Describes what the system should do Implementation Design – Describes what.
1 I/O Management in Representative Operating Systems.
Chiba City: A Testbed for Scalablity and Development FAST-OS Workshop July 10, 2002 Rémy Evard Mathematics.
SciDAC 2005 Achievements and Challenges for I/O in Computational Science Rob Ross Mathematics and Computer Science Division Argonne National Laboratory.
Operating Systems Concepts 1. A Computer Model An operating system has to deal with the fact that a computer is made up of a CPU, random access memory.
Web Application Architecture: multi-tier (2-tier, 3-tier) & mvc
Chapter 3.1:Operating Systems Concepts 1. A Computer Model An operating system has to deal with the fact that a computer is made up of a CPU, random access.
ICOM 5995: Performance Instrumentation and Visualization for High Performance Computer Systems Lecture 7 October 16, 2002 Nayda G. Santiago.
Chapter 6 Operating System Support. This chapter describes how middleware is supported by the operating system facilities at the nodes of a distributed.
COMP 410 & Sky.NET May 2 nd, What is COMP 410? Forming an independent company The customer The planning Learning teamwork.
1 High level view of HDF5 Data structures and library HDF Summit Boeing Seattle September 19, 2006.
HDF5 A new file format & software for high performance scientific data management.
A Metadata Based Approach For Supporting Subsetting Queries Over Parallel HDF5 Datasets Vignesh Santhanagopalan Graduate Student Department Of CSE.
1 Operating System Overview. 2 Today’s Objectives Explain the main purpose of operating systems and describe milestones of OS evolution Explain fundamental.
Programming Models & Runtime Systems Breakout Report MICS PI Meeting, June 27, 2002.
Victoria, May 2006 DAL for theorists: Implementation of the SNAP service for the TVO Claudio Gheller, Giuseppe Fiameni InterUniversitary Computing Center.
CCGrid 2014 Improving I/O Throughput of Scientific Applications using Transparent Parallel Compression Tekin Bicer, Jian Yin and Gagan Agrawal Ohio State.
Building a Parallel File System Simulator E Molina-Estolano, C Maltzahn, etc. UCSC Lab, UC Santa Cruz. Published in Journal of Physics, 2009.
SciDAC All Hands Meeting, March 2-3, 2005 Northwestern University PIs:Alok Choudhary, Wei-keng Liao Graduate Students:Avery Ching, Kenin Coloma, Jianwei.
Frontiers in Massive Data Analysis Chapter 3.  Difficult to include data from multiple sources  Each organization develops a unique way of representing.
Magellan: Experiences from a Science Cloud Lavanya Ramakrishnan.
Opportunities in Parallel I/O for Scientific Data Management Rajeev Thakur and Rob Ross Mathematics and Computer Science Division Argonne National Laboratory.
Advanced Computer Networks Topic 2: Characterization of Distributed Systems.
Parallel and Grid I/O Infrastructure W. Gropp, R. Ross, R. Thakur Argonne National Lab A. Choudhary, W. Liao Northwestern University G. Abdulla, T. Eliassi-Rad.
Project 4 : SciDAC All Hands Meeting, September 11-13, 2002 A. Choudhary, W. LiaoW. Gropp, R. Ross, R. Thakur Northwestern UniversityArgonne National Lab.
CE Operating Systems Lecture 3 Overview of OS functions and structure.
MapReduce Kristof Bamps Wouter Deroey. Outline Problem overview MapReduce o overview o implementation o refinements o conclusion.
DOE PI Meeting at BNL 1 Lightweight High-performance I/O for Data-intensive Computing Jun Wang Computer Architecture and Storage System Laboratory (CASS)
Towards Exascale File I/O Yutaka Ishikawa University of Tokyo, Japan 2009/05/21.
1 Public DAFS Storage for High Performance Computing using MPI-I/O: Design and Experience Arkady Kanevsky & Peter Corbett Network Appliance Vijay Velusamy.
Processes Introduction to Operating Systems: Module 3.
I/O on Clusters Rajeev Thakur Argonne National Laboratory.
CCGrid 2014 Improving I/O Throughput of Scientific Applications using Transparent Parallel Compression Tekin Bicer, Jian Yin and Gagan Agrawal Ohio State.
May 2003National Coastal Data Development Center Brief Introduction Two components Data Exchange Infrastructure (DEI) Spatial Data Model (SDM) Together,
Welcome to the PVFS BOF! Rob Ross, Rob Latham, Neill Miller Argonne National Laboratory Walt Ligon, Phil Carns Clemson University.
1 MotoHawk Components Scalable, Secure, Model-Based Design of Embedded Systems MotoHawk Training.
Using IOR to Analyze the I/O Performance
The HDF Group Introduction to netCDF-4 Elena Pourmal The HDF Group 110/17/2015.
Connections to Other Packages The Cactus Team Albert Einstein Institute
CS525: Big Data Analytics MapReduce Computing Paradigm & Apache Hadoop Open Source Fall 2013 Elke A. Rundensteiner 1.
The Mach System Silberschatz et al Presented By Anjana Venkat.
Parallel I/O Performance Study and Optimizations with HDF5, A Scientific Data Package MuQun Yang, Christian Chilan, Albert Cheng, Quincey Koziol, Mike.
Introduction Why are virtual machines interesting?
Parallel NetCDF Rob Latham Mathematics and Computer Science Division Argonne National Laboratory
Accelerating High Performance Cluster Computing Through the Reduction of File System Latency David Fellinger Chief Scientist, DDN Storage ©2015 Dartadirect.
Copyright ©: Nahrstedt, Angrave, Abdelzaher1 Operating System Overview Tarek Abdelzaher Lawrence Angrave Vikram Adve.
SDM Center High-Performance Parallel I/O Libraries (PI) Alok Choudhary, (Co-I) Wei-Keng Liao Northwestern University In Collaboration with the SEA Group.
SDM Center Parallel I/O Storage Efficient Access Team.
PIDX PIDX - a parallel API to capture the data models used by HPC application and write it out in an IDX format. PIDX enables simulations to write out.
Parallel I/O Performance Study and Optimizations with HDF5, A Scientific Data Package Christian Chilan, Kent Yang, Albert Cheng, Quincey Koziol, Leon Arber.
Climate-SDM (1) Climate analysis use case –Described by: Marcia Branstetter Use case description –Data obtained from ESG –Using a sequence steps in analysis,
LIOProf: Exposing Lustre File System Behavior for I/O Middleware
An Introduction to GPFS
Parallel Virtual File System (PVFS) a.k.a. OrangeFS
Hadoop Aakash Kag What Why How 1.
Chapter 3: Windows7 Part 4.
Lecture 1: Multi-tier Architecture Overview
Inventory of Distributed Computing Concepts
Hadoop Technopoints.
Lecture Topics: 11/1 General Operating System Concepts Processes
Chapter 2: Operating-System Structures
Introduction to Operating Systems
L. Glimcher, R. Jin, G. Agrawal Presented by: Leo Glimcher
Presentation transcript:

Connecting HPIO Capabilities with Domain Specific Needs Rob Ross MCS Division Argonne National Laboratory

2 I/O in a HPC system Many cooperating tasks sharing I/O resources Relying on parallelism of hardware and software for performance Application I/O System Software … Storage Hardware … Clients running applications (100s-1000s) I/O devices or servers (10s-100s) Storage or System Network

3 Motivation HPC applications increasingly rely on I/O subsystems –Large input datasets, checkpointing, visualization Applications continue to be scaled, putting more pressure on I/O subsystems Application programmers desire interfaces that match the domain –Multidimensional arrays, typed data, portable formats Two issues to be resolved by I/O system –Very high performance requirements –Gap between app. abstractions and HW abstractions

4 I/O history in a nutshell I/O hardware has lagged behind and continues to lag behind all other system components I/O software has matured more slowly than other components (e.g. message passing libraries) –Parallel file systems (PFSs) are not enough This combination has led to poor I/O performance on most HPC platforms Only in a few instances have I/O libraries presented abstractions matching application needs

5 Evolution of I/O software Goal is convenience and performance for HPC Slowly capabilities have emerged Parallel high-level libraries bring together good abstractions and performance, maybe Local disk, POSIX Remote access (NFS, FC) Serial high-level libraries Parallel file systems MPI-IO Parallel high-level libraries (Not to scale or necessarily in the right order … )

6 I/O software stacks Myriad I/O components are converging into layered solutions Insulate applications from eccentric MPI-IO and PFS details Maintain (most of) I/O performance –Some HLL features do cost performance High-level I/O Library MPI-IO Library Parallel File System I/O Hardware Application

7 Role of parallel file systems Manage storage hardware –Lots of independent components –Must present a single view –Provide fault tolerance Focus on concurrent, independent access –Difficult to pass knowledge of collectives to PFS Scale to many clients –Probably means removing all shared state –Lock-free approaches Publish an interface that MPI-IO can use effectively –Not POSIX

8 Role of MPI-IO implementations Facilitate concurrent access by groups of processes –Understanding of the programming model Provide hooks for tuning PFS –MPI_Info as interface to PFS tuning parameters Expose a fairly generic interface –Good for building other libraries Leverage MPI-IO semantics –Aggregation of I/O operations Hide unimportant details of parallel file system

9 Role of high-level libraries Provide an appropriate abstraction for the domain –Multidimensional, typed datasets –Attributes –Consistency semantics that match usage –Portable format Maintain the scalability of MPI-IO –Map data abstractions to datatypes –Encourage collective I/O Implement optimizations that MPI-IO cannot (e.g. header caching)

10 Example: ASCI/Alliance FLASH FLASH is an astrophysics simulation code from the ASCI/Alliance Center for Astrophysical Thermonuclear Flashes Parallel netCDF IBM MPI-IO GPFS Storage ASCI FLASH Fluid dynamics code using adaptive mesh refinement (AMR) Runs on systems with thousands of nodes Three layers of I/O software between the application and the I/O hardware Example system: ASCI White Frost

11 FLASH data and I/O 3D AMR blocks –16 3 elements per block –24 variables per element –Perimeter of ghost cells Checkpoint writes all variables –no ghost cells –one variable at a time (noncontiguous) Visualization output is a subset of variables Portability of data desirable –Postprocessing on separate platform Ghost cell Element (24 vars)

12 Tying it all together FLASH tells PnetCDF that all its processes want to write out regions of variables and store them in a portable format PnetCDF performs data conversion and calls appropriate MPI-IO collectives MPI-IO optimizes writing of data to GPFS using data shipping, I/O agents GPFS handles moving data from agents to storage resources, storing the data, and maintaining file metadata In this case, PnetCDF is a better match to the application

13 Future of I/O system software More layers in the I/O stack –Better match application view of data –Mapping this view to PnetCDF or similar –Maintaining collectives, rich descriptions More high-level libraries using MPI-IO –PnetCDF, HDF5 are great starts –These should be considered mandatory I/O system software on our machines Focusing component implementations on their roles –Less general-purpose file systems -Scalability and APIs of existing PFSs aren ’ t up to workloads and scales –More aggressive MPI-IO implementations -Lots can be done if we ’ re not busy working around broken PFSs –More aggressive high-level library optimization -They know the most about what is going on Application Domain Specific I/O Library High-level I/O Library MPI-IO Library Parallel File System I/O Hardware

14 Future Creation and adoption of parallel high-level I/O libraries should make things easier for everyone –New domains may need new libraries or new middleware –HLLs that target database backends seem obvious, probably someone else is already doing this? Further evolution of components necessary to get best performance –Tuning/extending file systems for HPC (e.g. user metadata storage, better APIs) Aggregation, collective I/O, and leveraging semantics are even more important at larger scale –Reliability too, especially for kernel FS components Potential HW changes (MEMS, active disk) are complementary