[Beowulf-announce] SCE 1.5 Release Announcement

Somsak Sriprayoonsakul ssy at prg.cpe.ku.ac.th
Tue Jun 18 08:41:03 PDT 2002


Parallel Research Group, Kasetsart University prouds to announce the public
release of a new version of SCE, SCE 1.5, a truly integrated scalable
computing
environment. SCE is distributed free of charge and includes source code. SCE
development is supported in part by AMD Far East, Inc. , Kasetsart
University, and COMPAQ.

SCE 1.5 is available in two forms:
 - Full distribution that can be used to build a new diskless cluster.
 - Software package that can run on NAPCI Rocks clusters and RedHat 7.2/7.3
based cluster.

New features in SCE 1.5:
 - Fast and automatic installation for diskless cluster
 - Support cluster built by NPACI Rocks 2.2.1 (diskfull cluster)
 - New AMATA technology, provides basic HA support out of the box
 - Increased stability
 - Built-in automatic dependencies check
 - The new config generation tool for building basic configuration files
 - Improved performance and many bugs fix
 - Builtin computing portal that link to batch scheduler (SQMS)

SCE Features
 - Powerful system management and monitoring tools
 - Parallel unix command
 - System health monitoring
 - Web and X window interface
 - Powerful user-level cluster middleware
 - Global process space
 - Fast process creation
 - Global signal and event service
 - Rich set of APIs for developers
 - Simple batch scheduling
 - System statistics logging

SCE is available from http://www.opensce.org/

Bugs report is can be sent to http://prg.cpe.ku.ac.th/bug/. Questions or
comments can be directed to sce at prg.cpe.ku.ac.th.

Thank you for using SCE software!

What is SCE?

One of the problem with the wide adoption of clusters for mainstream high
performance computing is the difficulty in building and managing the system.
There are many efforts in solving this problem by building fully automated,
integrated stack of software distribution from several well known open
source software.
The problem is that these set of software comes never been designed to work
together as a truly integrated system. With the experiences and tools
developed to
build many clusters in our site, we decided to build an integrate software
tool that is easy to use for cluster user community. These software tools,
called SCE
(Scalable Computing Environment), consists of cluster builder tool, complex
system management tool (SCMS), scalable real-time monitoring, web base
monitoring
software(KCAP), parallel unix command, and batch scheduler. These software
run on top of our cluster middleware that provides cluster wide process
control and
many services. MPICH are also included. All tools in SCE are designed to be
truly integrated since all of them except MPI and PVM are built by our
group. SCE also
provides more than 30 APIs to access system resources information, control
remote process execution, ensemble management and more. These APIs and the
interaction among software components allows user to extends and enhance SCE
in many way. SCE is also designed to be very easy to use. Most of the
installation
and configuration are automated by complete GUI and Web.

Why use SCE?

It is easier to manage cluster than normal remote shell command by hacked
shell script. Also, SCE collects and shows resource usage statistics for
later analyzing. MPI users always get the fresh update host list. All jobs
are queued and scheduled to automated discovery computing nodes.

How do I find out more about SCE?

There are many papers describing overview of SCE and its individual
components in detail. All of them are available at http://www.opensce.org/.
Questions may be
sent to sce at prg.cpe.ku.ac.th for more information. You can keep track of the
development by subscribe to the mailing list at
http://prg.cpe.ku.ac.th/mailman/sce.







More information about the Beowulf-announce mailing list