From liefting at nl.ibm.com Mon Feb 19 18:59:05 2001 From: liefting at nl.ibm.com (liefting@nl.ibm.com) Date: Tue Nov 9 01:14:19 2010 Subject: [Beowulf-announce] Presentc and Presentd v1.0 released Message-ID: <802569F8.00525A69.00@d06mta01.portsmouth.uk.ibm.com> I am doing beowulfs on-the-fly, using systems which are available to me only during specific times, and are booted using truly dynamic DHCP. One of the challenges is figuring out which system is available. So I created two simple daemons which tell me which system is available. It works like this: every client node in the network runs the presentc daemon, which takes the servername and portnumber of the master server as an argument. This daemon then sets up a TCP connection to the server and portname provided. It then just sits there. If the connection breaks or if it is impossible to setup the connection, it will retry after 10 seconds, indefinitely. No data is send or received(*). No network bandwidth or CPU cycles are wasted. The server products takes two arguments as well: the portnumber to listen on and a filename. It opens this port and listens for any connections. Every connection is logged and a reverse DNS lookup is being done. Then, the name of the host is added to the file. If a connection drops, the hostname is removed from the file. With these two simple daemons I always have an up-to-date file which contains all the current systems in my cluster. This file can then be used as input for LAM-MPI or something. All programs are written in C against the standard libc library and standard socket calls so they should work under any *nix. I only tested it on Red Hat Linux 6.2 though. I do not have a place available where I can upload things, but if you're interested drop me a line and I'll mail it to you right away. If someone has a website to put it on, go ahead. - Wouter. (*) As a test feature, if presentd is running in the foreground, you can feed it some data from stdin. This is then sent to all clients, who immediately return all data received. This way you can test whether a client is really up. This feature is likely to be deleted in a future release. From brutledge at linuxnetworx.com Thu Feb 22 17:57:50 2001 From: brutledge at linuxnetworx.com (Brad Rutledge) Date: Tue Nov 9 01:14:19 2010 Subject: [Beowulf-announce] Linux NetworX Announces LinuxBIOS on the Alpha Platform Message-ID: <3A9303FF.8300FBB6@linuxnetworx.com> Linux NetworX Announces LinuxBIOS on the Alpha Platform Development Adds Significant Power to Cluster Management and Improves System Reliability SALT LAKE CITY, UTAH, Feb. 20, 2001 - Linux NetworX, a leading provider of large-scale Linux clustering solutions, announced today it has developed LinuxBIOS for the Alpha platform. Linux NetworX will present the development and all of its implications at the Extreme Linux Developer's Forum, Feb. 21-23 in Santa Fe, NM. In conjunction with the LinuxBIOS Open Source project, Linux NetworX has replaced SRM firmware on the Alpha platform with a Linux-based BIOS. Users will now have the ability to boot to Linux directly out of the ROM on the motherboard. "Among the various other benefits, this gives users pre-boot network access and offers the potential for remote firmware updates and remote hardware diagnosis," said Joshua Harr, CTO of Linux NetworX. "Incorporated into ClusterWorX?, this exciting project pushes cluster management technology to the next level." LinuxBIOS offers the potential to dramatically increase the manageability of Alpha-based clusters for the end-user. Significant management and reliability features include remote on-board hardware failure recoveries, firmware updates, kernel updates and booting. Linux NetworX designs and delivers clustering solutions using many standard off-the-shelf components, coupled with its proprietary cluster management hardware and software optimization tools. The company is focused on developing technologies to make clusters more efficient and easier to manage. LinuxBIOS offers an additional feature to the Linux NetworX suite of cluster management tools, falling under the umbrella of ClusterWorX. The Fourth Extreme Linux Developer's Forum is an exclusive, by invitation-only workshop with the focus on sharing information and experience about advanced, bleeding-edge Linux cluster technology. Linux NetworX will send two of its senior software engineers to participate. About Linux NetworX Linux NetworX (www.linuxnetworx.com) brings its powerful cluster technology to those demanding high availability and high performance systems. With the use of cluster computer technology, a method of linking multiple computers through high-speed networks to form a single and more powerful system, Linux NetworX provides solutions for companies with high-computing needs, including Web serving, ISPs, ASPs, research, industry, government and other technological fields. Through innovative hardware, complete cluster management software and solid service and support, Linux NetworX provides end-to-end clustering solutions. To date, the company has built some of the largest cluster systems in the world and has developed unique hardware and versatile software to facilitate overall system management. Linux NetworX has offices in Utah, New York, Calif. and Texas with various international distribution outlets. # # # Linux is a registered trademark owned by Linus Torvalds. All other products, services and companies are trademarks or registered trademarks of their respective owners. From jim at ks.uiuc.edu Sat Feb 24 00:19:39 2001 From: jim at ks.uiuc.edu (Jim Phillips) Date: Tue Nov 9 01:14:19 2010 Subject: [Beowulf-announce] NAMD 2.3b1 Release Message-ID: Hi, NAMD runs well on clusters and we have a new Scyld Beowulf port. -Jim +--------------------------------------------------------------------+ | | | NAMD 2.3b1 Release Announcement | | | +--------------------------------------------------------------------+ February 23, 2001 The Theoretical Biophysics Group at the University of Illinois is proud to announce the public release of a new version of NAMD, a parallel, object-oriented molecular dynamics code designed for high-performance simulation of large biomolecular systems. NAMD is distributed free of charge and includes source code. NAMD development is supported by the NIH National Center for Research Resources. NAMD 2.3b1 has several advantages over NAMD 2.2: - The new psfgen tool for building PSF structure files. - Simpler to run on a single workstation. (No more rsh!) - New ports to the Compaq AlphaServer SC and Scyld Beowulf. NAMD is available from http://www.ks.uiuc.edu/Research/namd/. The Theoretical Biophysics group encourages NAMD users to be closely involved in the development process through reporting bugs, contributing fixes, periodical surveys and via other means. Questions or comments may be directed to namd@ks.uiuc.edu. We are eager to hear from you, and thank you for using our software! From stevenj at alum.mit.edu Sat Feb 24 00:19:40 2001 From: stevenj at alum.mit.edu (Steven G. Johnson) Date: Tue Nov 9 01:14:19 2010 Subject: [Beowulf-announce] MPB 1.0: parallel computation of electromagnetic eigenmodes Message-ID: I am pleased to announce release 1.0 of the MIT Photonic-Bands (MPB) package, a free program to compute electromagnetic eigenmodes and dispersion relations of arbitrary periodic dielectric structures. This is the first version to support parallel machines with MPI, and is available from: http://ab-initio.mit.edu/mpb/ MPB was especially designed for the study of photonic crystals (photonic band-gap materials), but is also well suited for other optical problems, including waveguides and resonant cavities. Its features include: fully-vectorial computations, a flexible scripting interface using GNU Guile, fast iterative eigensolver methods, support for anisotropic and magneto-optic materials in arbitrary geometries, and field output in HDF5 format. The parallel code was primarily tested on an SGI Origin2000, where excellent scaling has been observed even for relatively small problems, but it has also been tested under Linux with MPICH. It should run on any Beowulf cluster, although a fast communications architecture (i.e. not fast ethernet) is probably required for good performance. Cordially, Steven G. Johnson