Transcript calu99
Building Beowulfs for High Performance Computing Duncan Grove Department of Computer Science University of Adelaide http://dhpc.adelaide.edu.au/projects/beowulf Anatomy of a “Beowulf” • “Cluster” of networked PCs – – – – Intel PentiumII or Compaq Alpha Switched 100Mbit/s Ethernet or Myrinet Linux Parallel and batch software support Switching Infrastructure Outside World Front-end Node n1 n2 Compute Nodes nN Why build Beowulfs? • Science/$ • Some problems take lots of processing • Many supercomputers are used as batch processing engines – Traditional supercomputers wasteful high throughput computing • Beowulfs: – “ [useful] computational cycles at the lowest possible price.” – Suited to high throughput computing – Effective at an increasingly large set of parallel problems Three Computational Paradigms • Data Parallel – Regular grid based problems • Parallelising compilers, eg HPF • Eg physicists running lattice gauge calculations • Message Passing – Unstructured parallel problems. • MPI, PVM • Eg chemists running molecular dynamics simulations. • Task Farming – “High throughput computing” - batch jobs • Queuing systems • Eg chemists running Gaussian. A Brief Cluster History • • • • • • • • • Caltech Prehistory Berkeley NOW NASA Beowulf Stone SouperComputer USQ Topcat UIUC NT Supercluster LANL Avalon SNL Cplant AU Perseus? Beowulf Wishlist • Single System Image (SSI) – Unified process space – Distributed shared memory – Distributed file system • Performance easily extensible – Just “add more bits” • Is fault tolerant • Is “simple” to administer and use Current Sophistication? • Shrinkwrapped “solutions” or do-it-yourself – Not much more than a nicely installed network of PCs – A few kernel hacks to improve performance – No magical software for making the cluster transparent to the user – Queuing software and parallel programming software can create the appearance of a more unified machine Stone SouperComputer Iofor • • • • • • Learning platform Program development Simple benchmarking Simple performance evaluation of real applcaions Teaching machine Money lever iMacwulf • Student lab by day, Beowulf by night? – MacOS with Appleseed – LinuxPPC 4.0, soon LinuxPPC 5.0 – MacOS/X “Gigaflop harlotry” • Machine Cost # Processors ~ Peak Speed • • • • Cray T3E SGI Origin 2000 IBM SP2 Sun HPC 10s million 10s million 10s million 1s million 1084 128 512 64 1300Gflop/s 128Gflop/s 400Gflop/s 50Gflop/s • • TMC CM5 SGI PowerChallenge 5 Million (1992) 1 Million (1995) 128 20 20Gflop/s 20Gflop/s • • Beowulf cluster + myrinet Beowulf cluster 1 Million 300K 256 256 120Gflop/s 120Gflop/s The obvious, but important • In the past: – Commomdity processors way behind supercomputer processors – Commodity networks way, way, way behind supercomputer networks • In the now: – Commomdity processors only just behind supercomputer processors – Commmodity networks still way, way behind supercomputer networks – More exotic networks still way behind supercomputer networks • In the future: – Commodity processors will be supercomputer processors – Will the commodity networks catch up? Hardware possibilities Advantages Disadvantages x86, K7 Mass market commodity Good floating point (Some) SMP capable PowerPC Very good integer More expensive than x86 Poor floating point Alpha Very good floating point Expensive Limited vendors OS possibilities Advantages Disadvantages Linux Large user community Widely available Open source Many platforms Open source Good compiler x86 only NT Good compilers Poor user model Poor stability Poor remote access Poor networking Digital Unix Very good compilers Runs on expensive hardware Solaris Robust Good quality software Runs on x86 Not open source MacOSX Attractive as multipurpose cluster Not out yet! Darwin Open Source May be ported to x86? Small user community Open Source • The good... – Lots of users, active development – Easy access to make your own tweaks – Aspects of Linux are still immature, but recently • SGI has release xfs as open source • Sun has released its HPC software as open source • And the bad... – There’s a lot of bad code out there! Network technologies • So many choices! – Interfaces, cables, switches, hubs; ATM, Ethernet, Fast Ethernet, gigabit Ethernet, firewire, HiPPI, serial HiPPI, Myrinet, SCI… • The important issues – latency – bandwidth – availability – price – price/performance – application type! Disk subsystems • I/O a problem in parallel systems – Data not local on compute nodes is a performance hit – Distributed file systems • CacheFS • CODA – Parallel file systems • PVFS • On-line bulk data is interesting in itself – Beowulf Bulk Data Server • cf with slow, expensive tape silos... Perseus • Machine for chemistry simulations – Mainly high throughput computing – RIEF grant in excess of $300K – 128 nodes. For < $2K per node • Dual processor PII450 • At least 256MB RAM – Some nodes up to 1GB • 6GB local disk each – 5x24 (+2x4) port Intel 100Mbit/s switches Perseus: Phase 1 • Prototype • 16 dual processor PII • 100Mbit/s switched Ethernet Perseus: installing a node Switching Infrastructure Outside World Front-end Node n1 User node, administration, compilers, queues, nfs, dns, NIS, /etc/*, bootp/dhcp, kickstart, ... n2 nN Floppy disk or bootrom Software on perseus • Software to support the three computational paradigms – Data Parallel • Portland Group HPF – Message Passing • MPICH, LAM/MPI, PVM – High throughput computing • Condor, GNU Queue • Gaussian94, Gaussian98 Expected parallel performance • • • Loki, 1996 – 16 Pentium Pro processors, 10Mbit/s Ethernet – 3.2 Gflop/s peak, achieved 1.2 real Gflop/s on Linpack benchmark Perseus, 1999 – 256 PentiumII processors, 100Mbit/s Ethernet – 115 Gflop/s peak • ~40 Gflop/s on Linpack benchmark? Compare with top 500! – Would get us to about 200 currently – Other Australian machines? • NEC SX/4 @ BOM at #102 • Sun HPC at #181, #182, #255 • Fujitsi VPP @ ANU at #400 Reliability in a large system • Build it right! • • Is the operating system and software running ok? Is heat dissipation going to be a problem? – Monitoring daemon • Normal features – CPU, network, memory, disk • More exotic features – Power supply and CPU fan speeds – Motherboard and CPU temperatures • Do we have any heisen-cabling? – Racks and lots of cable ties! The limitations... • • • • • Scalability Load balancing – Effects of machines capabilities – Desktop machines vs. dedicated machines – Resource allocation – Task Migration Distributed I/O System monitoring and control tools Maintenance requirements – Installation, upgrading, versioning • Complicated scripts • Parallel interactive shell? … and the opportuntities • A large proportion of the current limitations compared with traditional HPC solutions are merely systems integration problems • Some contributions to be made in – HOWTOs – Monitoring and maintenance – Performance modelling and real benchmarking