cluster packages/distributions roundup
Many of your questions may have already been answered in earlier discussions or in the FAQ. The search results page will indicate current discussions as well as past list serves, articles, and papers.
Andrew Shewmaker shewa at inel.govFri Mar 15 14:32:54 PST 2002
- Previous message: Network interface failure detection
- Next message: cluster packages/distributions roundup
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
Hello, I have decided to review some of the Linux cluster/ssi software that has been produced, and I would like feedback on my initial list of candidates as well as the judging criteria. In the case of commercial distributions, I plan on evaluating the basic or trial versions. Also, I welcome anybody who wants to help me evaluate any of these. Background info: I am a computer scientist (BA) at the INEEL. I have built and administered a couple of medium size clusters between school and work, using both Scyld and Mandrake Linux. Suggested candidate list is (in no particular order): Scyld http://www.scyld.com MSC.Linux http://www.msclinux.com/software/msclinux/ ROCK Linux http://www.rocklinux.org/projects/mpp/mpp.html Although the current version of ROCK includes the MPP projects's software, I will probably wait until version 1.7 is released in a couple months. OSCAR http://oscar.sourceforge.net A significant collaboration including SGI, Intel, Dell, MSC.Linux, NCSA, IBM, and others. Makes use of the System Installation Suite (http://www.sisuite.org), which grew out of VA's SystemImager and IBM's LUI projects. Alinka Raisin http://www.alinka.com/araisin.php3 Clubmask http://clubmask.sourceforge.net IBM's CSM/ETC http://www-1.ibm.com/servers/eserver/clusters/software/ Clusterit http://www.garbled.net/clusterit.html ClumpOS - a mini Linux/Mosix distribution http://clumpos.psoftware.org It isn't a full distribution since it is dependent on a head node having Mosix (soon OpenMosix) already installed, but it looks like a great solution for slave nodes. Clustermatic http://www.clustermatic.org A Bproc based distribution produced by Los Alamos National Laboratory. That group is doing some very interesting work in many areas including LinuxBIOS, a parallel language with checkpointing built into the compiler, and fault tolerant MPI. Warewulf http://www.runlevelzero.net/greg/warewulf/ Warewulf is brand new, and it is mostly a slave node builder right now. NPACI Rocks Cluster Software http://rocks.npaci.edu Scalable Cluster Environment http://www.opensce.org Developed by Kasetsart University in Thailand. A very complete looking distribution. SCore http://www.pccluster.org The PC Cluster Consortium develops SCore and the Omni OpenMP compiler. They say that their OpenMP compiler can actually compile programs to run on a cluster (over ethernet) with a software distributed shared memory system called SCASH. Single System Image Cluster for Linux http://ssic-linux.sourceforge.net This project was started by Compaq and it inherited some of their Unixware code, but it also borrows from Mosix. It isn't ready yet, but it looks like they have virtual clusters up and running with User Mode Linux. Debian http://www.debian.org Turbolinux with Enfuzion http://www.turbolinux.com/products/enf/ Suggested evaluation criteria: *Installation +hardware support -interconnects (I can only test fast ethernet currently) -sensors +flexibility -heterogenous nodes -diskfull/less +difficulty +duration *Administration +configuration -tuning -load balancing +security +upgradability +monitoring -performance -hardware +system accounting *Development +languages/compilers +libraries -mpi -pvm -scalapack, blas, etc. (atlas) -fftw -hdf[45] -netcdf -peformance counters -checkpointing -interval arithmetic +debugging *End User +LSB compliance +applications -basic tools -batch system/grid access -benchmarks -visualization +stability +performance *General +commercial support +community support +license/cost of code +fault tolerance +type of SSI -processes -memory -filesystem I will also be taking into account the guidelines created by the NACSE** . http://www.nacse.org/distributions/HPCreqts/report/ Thank you for any feedback/help. Andrew Shewmaker
- Previous message: Network interface failure detection
- Next message: cluster packages/distributions roundup
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the Beowulf mailing list
