The blogged wandering of Robert W. Anderson
The Linux-guru crowd continues to discount the complexity of installation, maintenance, use, and actual cost of Linux-based OSes.
It would be a full time job to debunk these arguments over and over again. Occasionally, Dan takes the time to do just this: see him dismantle another one of Joe Landman’s CCS attack pieces in Yet another poof piece. And Dan doesn’t even mention the developer-productivity story . . .
Personally, I tend to ignore the “I hate Microsoft, Linux is the answer to everything” arguments. You can build a feasible solution with either platform. As Dan said in his post (specifically about HPC):
Look, I’m not deriding Linux as an OS, or as an HPC OS. It’s been very successful, and it will continue to have success.
The fact is: if you’re using UNIX or Linux, it probably doesn’t make sense to port to Windows.
But if you’re already using Windows, it certainly doesn’t make sense to port to Linux.
They are different toolboxes full of different (albeit similar and overlapping) tools. Depending on all sorts of criteria, different organizations will do better with one platform than the other.
There is huge growth potential in the market for both platforms. Can’t we just get past this?
Or has this truly become a religion?
Tags: .NET, CCS, Digipede, grid, HPC, Linux, Microsoft, Windows
Yeah, I just wrote about the same topic at insideHPC. Unfortunately, I think for many the decision is already made and their minds will never be changed. This might work out ok for them, since the enterprise HPC crowd rarely mingles with the HPTC crowd and this probably won’t change for the 7 years or so it will take enterprise apps to grow to scale.
If Microsoft doesn’t totally screw this up and can grow CCS as the requirements of its user base grow, then they’ll have a bona fide large scale HPC operating system and at that point *nix will probably just go away in HPC; vendors won’t be able to ignore the enterprise HPC market (which I think will be at least an order of magnitude larger than technical/scientific HPC) but also probably won’t be able to afford to maintain two OS streams. At that point, at $10B market for enterprise (CCS) HPC systems will win.
Thanks for the comment, John.
I agree except for the “*nix will probably just go away in HPC” part. As Windows-based HPC gains momentum, my bet is that *nix will get more focus on usability (and other issues) that currently keep it outside of the classic Windows shops.
I don’t think there will be just one winner. Many losers yes, but many winners too. It is a big market.
<a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>