Comparison of cluster software

From Wikipedia, the free encyclopedia
Jump to: navigation, search

The following tables compare general and technical information for notable computer cluster software. This software can be grossly separated in 4 categories: Job scheduler, nodes management, nodes installation and integrated stack (all the above).

General information[edit]

Software Maintainer Category Development status ArchitectureOCS High-Performance/ High-Throughput Computing License Platforms supported Cost
Alchemi
Amoeba MIT
Base One Foundation Component Library Proprietary
Beowulf clusters
HTCondor [1] University Of Wisconsin CS dep Job/Data Scheduler actively developed Distributed master/executions/submits node HTC Apache license v2.0 Unix-like, Windows, Mac OS X Free (paid support available)
DIET INRIA, SysFera, Open Source All in one actively developed GridRPC, SPMD, Hierarchical and distributed architecture, CORBA HTC/HPC CeCILL Unix-like, Windows, Mac OS X, AIX Free (paid support available)
Distributed objects
DragonFly BSD
Ganglia [2] Monitoring actively developed BSD Unix, Linux, Windows NT/XP/2000/2003/2008, FreeBSD, NetBSD, OpenBSD, DragonflyBSD, Mac OS X, Solaris, AIX, IRIX, Tru64, HPUX. free
GreenTea Software
Gridbus Toolkit
Globus Toolkit Globus Alliance, Argonne National Laboratory Job/Data Scheduler actively developed SOA Grid Linux Free
Grid MP [3] Univa (formerly United Devices) Job Scheduler actively developed Distributed master/worker HTC/HPC Proprietary Windows, Linux, Mac OS X, Solaris Cost
grun Erik Aronesty (Expression Analysis) actively developed master/worker HPC/HTC GPL Linux, Mac OS X, BSD Free
JPPF Laurent Cohen (founder) actively developed distributed master/worker and P2P HPC/HTC Apache license v2.0 Windows, Linux, Mac OS X, Solaris Free
LanderCluster Lander Software Technology Co. Ltd Job Scheduler/Monitoring actively developed Proprietary Windows, Linux, & UNIX platforms Cost
JSTM
Moab Cluster Suite Cluster Resources, Inc. Job Scheduler/Monitoring actively developed HPC Proprietary Linux, Mac OS X, Windows, AIX, OSF/Tru-64, Solaris, HP-UX, IRIX, FreeBSD & other UNIX platforms Cost
Moab Cluster Suite [4] Cluster Resources, Inc. Job Scheduler actively developed HPC Proprietary Linux, Mac OS X, Windows, AIX, OSF/Tru-64, Solaris, HP-UX, IRIX, FreeBSD & other UNIX platforms Cost
‌Maui Cluster Scheduler followup? Job Scheduler HTC/HPC Proprietary Unix-like, free
NetworkComputer ‌RTDA Runtime Design Automation actively developed HTC/HPC Proprietary Unix-like, Windows time-based license
OAR INRIA and LIG Job Scheduler actively developed HPC/HTC GPL Linux/*nix Free
PBS Professional PBS Works (A division of Altair) Job Scheduler/Monitoring actively developed HPC Proprietary Unix, Linux, Windows Cost
Platform LSF [5] Platform Computing Job Scheduler actively developed HPC/HTC Proprietary Unix, Linux, Windows Cost
Platform Cluster Manager Platform Computing All in one actively developed HTC/HPC OpenSource Linux free
Rocks Cluster Distribution Open Source/NSF grant All in one actively developed HTC/HPC OpenSource CentOS free
Popular Power
ProActive INRIA, ActiveEon, Open Source All in one actively developed Master/Worker, SPMD, Distributed Component Model, Skeletons HTC/HPC GPL Unix-like, Windows, Mac OS X Free
PRUN Andrey Budnik Job Scheduler actively developed Master node/exec clients, multiple admin/submit nodes HTC Apache license v2.0 Linux/*nix Free
RPyC Tomer Filiba actively developed MIT License *nix/Windows Free
SLURM SchedMD Job Scheduler actively developed HPC/HTC GPL Linux/*nix Free (paid support available)
formerly Sun Grid Engine now Oracle Grid Engine formerly Sun Microsystems now Oracle Job Scheduler actively developed Master node/exec clients, multiple admin/submit nodes HPC/HTC SISSL (only for forks of former FOSS Grid Engine project) *nix/Windows Cost
SynfiniWay Fujitsu actively developed HPC/HTC  ? Unix, Linux, Windows Cost
TORQUE Resource Manager Torque Cluster Resources, Inc. Job Scheduler actively developed custom Linux, *nix Free
UniCloud Univa All in One (dynamic cluster creation/re-sizing, cloud bursting, etc.) Actively Developed Proprietary Oracle Unbreakable Linux, RHEL, and Cent Os Cost
UniCluster [6] Univa All in One Functionality and development moved to UniCloud (see above) free (paid support available)
UNICORE
Univa Grid Engine [7] Univa Job Scheduler actively developed Master node/exec clients, multiple admin/submit nodes HPC/HTC Proprietary *nix/Windows Cost
Vaakya [8] Vaakya Technologies Pvt Ltd R&D Technology provider actively developed Cross-Platform, Distributed Computing Architecture Proprietary Windows/Linux Cost
XGE
Xgrid Apple Computer
Software Maintainer Category Development status Architecture High-Performance/ High-Throughput Computing License Platforms supported Cost

Table Explanation

  • Software: The name of the application that is described

Technical information[edit]

Software programation language Authentification Encryption Integrity Global File System Global File System + Kerberos Heterogeneous/ Homogeneous exec node Jobs priority Group priority Queue type SMP aware Max exec node Max job submitted CPU scavenging Parallel job Job checkpointing
Torque C SSH, munge None, any Heterogeneous Yes Yes Programmable Yes tested tested Yes Yes Yes (blcr)
OAR Perl, Ocaml, Ruby SSH None, NFS Heterogeneous Yes Yes Programmable Yes tested 80k tested >20k Yes Yes Yes (blcr)
Platform LSF [9] yes Yes to start jobs. Did it suspend job when the person come back? Yes
Condor [10] C++ GSI, SSL, Kerberos, Password, File System, Remote File System, Windows, Claim To Be, Anonymous None, Triple DES, BLOWFISH None, MD5 None, NFS, AFS Not official, hack with ACL and NFS4 Heterogeneous Yes Yes Fair-share with some programmability basic (hard separation into different node) tested ~10000? tested ~100000? Yes MPI, OpenMP, PVM Yes
Slurm [11] C Munge, None, Kerberos Heterogeneous Yes Yes Multifactor Fair-share yes tested 120k tested 100k No Yes Yes (blcr)
Univa Grid Engine [12] C Authentification Encryption Integrity Arbitrary, e.g. NFS, Lustre, HDFS, AFS AFS Fully heterogeneous Yes; automatically policy controlled (e.g. fair-share, deadline, resource dependent) or manual Yes; can be dependent on user groups as well as projects and is governed by policies Batch, interactive, checkpointing, parallel and combinations Yes, with core binding, GPU and Intel Xeon Phi support commercial deployments with many tens of thousands hosts >300K tested in commercial deployments Yes; can suspend job on interactive usage Yes, with support of arbitrary parallel environments such as OpenMPI, MPICH 1/2, MVAPICH 1/2, LAM, etc. Yes, with support for user, kernel or library level checkpointing environments
Software programation language Authentification Encryption Integrity Global File System Global File System + Kerberos Heterogeneous/ Homogeneous exec node Jobs priority Group priority Queue type SMP aware Max exec node Max job submitted CPU scavenging Parallel job Job checkpointing

Table Explanation

  • Software: The name of the application that is described
  • SMP aware:
    • basic: hard split into multiple virtual host
    • basic+: hard split into multiple virtual host with some minimal/incomplete communication between virtual host on the same computer
    • dynamic: split the resource of the computer(CPU/Ram) on demand

History and adoption[edit]

Notes[edit]

See also[edit]

External links[edit]