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
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,
- 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
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)
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)
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)
Page editor: Jonathan Corbet
Inside this week's LWN.net Weekly Edition
- Security: Sharp Zaurus Vulnerabilities; Linux attacks on the rise; USENIX Security Symposium papers
- Kernel: Read-copy-update; enforcing locking requirements.
- Distributions: Distribution news from Debian, Mandrake, Red Hat, and more.
- Development: MySQL best practices, Mailman 2.0.12, Cocoon 2, web site tuning, JBoss 3.0, Koha Library Management System, Wine 20020710,
Java web security, Perl 5.8.0 RC 3, Test::MockObject, Generator-based state machines in Python, XML Shell, James Clark interview.
- Commerce: MandrakeSoft Shareholder Newsletter; Evans Data Corp. study on Chinese software development market
- Press: New draft bill on copying and webcasting, internet radio still alive,
RidgeRun closes, Wallmart Linux boxes, Norway cancels MS contract,
aggressive Linux advocacy, virtual prototyping, the Game Theory
of Open Code, Yopy review, Zaurus security holes.
- Announcements: LJ Readers' Choice Awards, Little Linux systems guide,
Conference for Open Source Content Management, Gnumeric Summit, Perl BOF,
Linux-Kongress 2002 tutorials, mod_perl world, Linux clique awards,
GNOME users' forum needed.
- Letters: Scalability; Switching back.