LWN.net Weekly Edition for July 18, 2002

The road to World Domination

Linux, it seems, is on a roll. In the past week we've had news of the LLNL cluster sale (see below), of Norway's decision to drop its exclusive contract with Microsoft (despite losing the substantial discounts that contract provided), of Steve Ballmer's admission that Linux is giving Microsoft some trouble, of MandrakeSoft's improving bottom line, and more. The world increasingly understands that free software is better, cheaper, and, of course, free.

Those of us who wish to promote the free software cause can't rest yet, however. Free software still has a great many hurdles to overcome, including:

• Security. The free software community likes to claim greater security, and this claim may even be true. The security of free software is not yet good enough, however. Recent bugs in packages like Apache, Squid, and OpenSSH have put large numbers of systems at risk; they are the stuff that large-scale destructive worms are made of. There are still too many silly mistakes turning up in free software; we need to do better.

• Interoperability. The free office suites currently available are more than good enough for most users at this point. At least, until those users need to exchange documents with people using proprietary packages. Until this problem is solved, people will stay with proprietary systems. Linux systems also need to do better at running software written for other operating systems. Progress is being made, but we are not yet there.

• Proprietary software support. It will be a long time before free packages rival the variety of proprietary software out there. Where are the free business plan writers, training systems, contact managers, math tutors, foreign language instructors, genealogy assistants, home designers, tax preparers, high-end games, etc.? Until we have filled in those gaps, we should be friendlier to software vendors who make Linux systems more attractive to more people. That means standards compliance, stable interfaces, and an end to outright hostility toward software vendors. As long as those vendors comply with the licenses of the free software they are using, they are only helping the Linux cause by porting their products.

• Business models. Some companies seem to be doing OK, if not great, as free software businesses. Consider Red Hat, Zope Corp., Sleepycat, Collabnet, IBM, etc. Many others are hurting, or have gone out of business. Free software needs successful businesses to keep up its current rate of growth, and it would be better if we didn't end up with just a small number of huge companies employing most free software hackers. There is still work to be done on the business side of free software.

• Legal issues. Intellectual property law, including repressive copyright terms, "anti-circumvention" provisions, software patents, and more, threatens to hamper (or ban outright) Linux in many parts of the world. Somehow we have got to get a handle on our legislative systems and not allow free software to be pushed aside by laws favoring a small number of large corporations. This battle will not be easy; the opposing interests are powerful and this is not an issue that is interesting or understandable to most people. We must fight it anyway, though, or much of the rest of our work may turn out to be in vain.

There is, in other words, a lot of work to do still. Free software has always been surprising in what it has been able to accomplish, though. The free software community has a great chance of being able to handle these challenges as well.

Comments (4 posted)

The largest Linux cluster

Linux NetworX has sent out a press release proclaiming the sale of "the largest and most powerful Linux cluster" ever. This system has been sold to Lawrence Livermore National Laboratory, and should be operational this fall. This cluster, which will employ 1920 2.4-GHz Intel Xeon processors, is expected to be one of the five fastest supercomputers in the world.

LWN has long maintained that Linux-based clusters were going to take over the supercomputing field. The economics of clusters built with commodity hardware and free software are simply too good to ignore. The biggest impediment to cluster World Domination, perhaps, has been the "some assembly required" nature of Linux clusters. Supercomputers are, in general, not low-maintenance devices, but Linux clusters have tended to require even more than the usual amount of work. To be truly successful, Linux clusters must become polished, easy to manage products.

Linux NetworX, like other cluster vendors, has long understood the need for more refined cluster products. Some of the features of their current cluster offerings are worth a look as an indication of how far Linux clustering has come. Linux NetworX is certainly not the only vendor offering these sorts of features; in the context of this sale, however, they make a good example.

Early Linux clusters consisted of large numbers of beige boxes with even larger numbers of cables between them. Modern cluster vendors have long since moved past that mode, which is wasteful of energy, space, and system administrator time. In this case, Linux NetworX is employing its "Evolocity II" product, which crams two processors into a "sub 1U" rack space. Throw in easy interconnects and the basic job of plugging the cluster together becomes much easier.

Then, throw in the "ICE Box," a small, Linux-powered box which performs console management, power management, and temperature monitoring for a set of cluster nodes. Among other things, this box allows a (remote) administrator to power down sets of nodes when they are not in use; when your cluster has thousands of nodes, turning off unneeded nodes can yield significant power savings.

What about when you want to bring those idle nodes back up to get some work done? One of the interesting things that Linux NetworX has done is to work with the LinuxBIOS project. LinuxBIOS replaces the regular BIOS on the motherboard, allowing a system to boot into a Linux kernel in as little as three seconds.

Finally, there is the issue of how one manages a cluster with almost 2000 nodes. The Simple Linux Utility for Resource Management (SLURM) is a cooperative project between Linux NetworX and LLNL; it gives administrators the ability to control access to groups of processors in an easy manner. SLURM appears to be in an early state of development at this time; the plan is to release it under the GPL at some point.

All of this, of course, leaves out one crucial part of the problem: making the customer's applications work on a clustered system. Parallelizing a program so that it makes the best use of a cluster is a hard task. There is still no easy way around this one. A cluster-optimizing version of gcc remains the stuff of dreams at this point.

Even with the programming challenges, Linux clusters are earning an increasing amount of respect in the high performance computing world. They are getting steadily more powerful, easier to buy, and easier to run. Brad Rutledge of Linux NetworX tells us: "We anticipate this is the first of many Linux clusters that will measure as top supercomputers within in the next year." Things look likely to turn out just that way.

Comments (1 posted)

Some advertising changes on LWN.net

We're trying out a new way of selling advertising space on LWN. The old "cost per thousand" scheme is out; instead, advertisers get a percentage of the total site impressions proportional to the amount of money they wish to spend on the campaign. So, if advertising demand is low (as it generally is), a small investment will buy a great many exposures on the site. In other words, advertising on LWN has just gotten cheaper; please see the announcement for the details.

Comments (none posted)