Linux On Big Iron

panker writes "eWeek is running an article about a company who converted their IBM mainframe into a Linux email server. "The technical support manager at Winnebago Industries Inc. recently oversaw the deployment of Version 7 of SuSE Linux AG's Linux operating system on an IBM zSeries mainframe to run his company's e-mail server supporting 700 users." "

Comments

So how well does it run?

[farsighed]

As someone who oversees an email system with close to a million addresses (in various states of utilization from heavy to "what account?"), I'm kinda interested in how this works out. Has anybody done high-load stresstesting of these yet?

-- F.S.

Re:So how well does it run?

[Anonymous Coward]

What - are you a sysadmin at hotmail?

Re:So how well does it run?

[40ohms]

This is pretty silly. I administered one box with 1000 email clients 80 web sites and a few other things running on a Pentium 90 with 48 MB of RAM. Rarely did the system load go over .3 It was exceptionally reliable. On a mainframe this is major overkill.

Re:So how well does it run?

[Anonymous Coward]

I've spoken with folks at Sendmail - they're working on a zVM/Linex implementation of over 12 million users.

Re:So how well does it run?

[ReidMaynard]

I was thinking the exact same thing.

I re-read it, thinking "he must mean 700k users"

On a side note: $150,000 for a MS mail solution to handle 700 users? That's over $200/user.

It makes Steve Martin's "gasoline-powered turtleneck sweater" sound like a rational product.

Re:So how well does it run?

[farsighed]

A Large Governmental Organization (we're here to help, ma'am), actually. Trying to keep a system for the entire LGO running off of one Sun machine (which is working much better than expected, which is to say at all; we were in pilot status when 9/11 happened and suddenly we were a lot more "live" than we'd planned). We're upgrading soon, and while the current plan is to stay with what we got (iPlanet Mail Server/Solaris/Sun Ultra-class boxen), it's always interesting to see what everybody else is doing.

Although I doubt investing in a new IBM mainframe to run linux on will be seen as a cost-cutting measure. :)

And, well, heck, it got me a First Relevant post. :)

--F.S.

Re:So how well does it run?

[farsighed]

No, I think they're serious about the 700 users. Winnebago is not *that* large a company.. and while I can see them buying out, say, Airstream, I don't think it's gonna add that many users.

I think this can be a viable solution- and a great way to upgrade, for those who already have Massive Big Iron providing their winter heating requirements. And god knows, the Winnebago execs are going to be recieving their emails before the sender lets go of the mouse button. But I think it's overkill for a 700-user base.

-- F.S. (I can see it now... Instant messaging? Whatever for?)

Re:So how well does it run?

[WasterDave]

Not very well apparently:

"It's using between 7 percent and 10 percent of those to run Linux and the e-mail system."

For seven hundred email addresses, this strikes me as piss poor. Hell, a second hand P200 with good SCSI drives could run 700 accounts of qmail without breaking into a sweat.

Dave

Re:So how well does it run?

[Anonymous Coward]

Yeah but they aren't running qmail, they're running Bynari Insight, which is the whole IMAP/Calendar/Groupware deal. (Well maybe they are using a little box with qmail somewhere to push mail out to the Internet).

Overkill???

[MadCow42]

You can support 700 users on a decent dual desktop system with Linux, what's this guy thinking?

Maybe he's just got an extra mainframe laying around...? You've got to think the support/maintenance on a mainframe would be horrendous compared to buying a new desktop server for this?

MadCow.

Re:Overkill???

[Anonymous Coward]

No doubt, I wish I had an old mainframe in my basement I setup to play CIV II on :)

Re:Overkill???

[Karl Cocknozzle]

You can support 700 users on a decent dual desktop system with Linux, what's this guy thinking?

I would tend to agree, but it's also possible they're planning a large acquisition and need the horsepower to support a few thousand new employees instantly.

In these crazy days of "Merge merge merge" you never know...

Re:Overkill???

[rhost89]

I support over 5000 dialup users on a dual mp system, this guy has either a very large budget, smoking crack, or neds to spend the rest of alloted budget quicly before the new fiscal year.

Re:Overkill???

[Havokmon]

I would tend to agree, but it's also possible they're planning a large acquisition and need the horsepower to support a few thousand new employees instantly.

That's possible too, but head on over to Matt Simerson's FreeBSD Toaster. I'm SURE that could easily support a few thousand users in a clustered environment (NFS & Mysql)
Need more users? Add another box.

Re:Overkill???

[Garg]

It would be overkill if they were using the mainframe only for this. But they already had a mainframe. With these machines, you can create a logical partition and run Linux in it. That's what they're doing... just taking a few resouces away from their regular system.

Garg

Re:Overkill???

[theEd]

The writer may have mistyped, since they mentioned $150k for a similar size Exchange environment, which seems large to me. Second, considering that the mainframe environment only cost them $24k I would think that it was for an existing mainframe environment, which is probably running other business application. They probably used some free MIPS for the mail server and setup a VM guest for mail. They may not be mentioning the other applications because they may be running in OS/390 or some other type of VM guest. Also if the mainframe was existing, they would already have a support structure in place.

Re:Overkill???

[MrBoring]

What are the 700 users doing? I doubt you could get 700 active developers doing builds on a desktop machine. This could be done on a mainframe, however, because they tend to be optimized for I/O throughput.

Re:Overkill???

[zio pera]

Well, it has to be a very very big acquisition... A couple of year ago I set up a qmail server for handling the mail of a local ISP with about 30000 users (that's right, 30 thousands), and we used a dual cpu DELL poweredge, with only one cpu installed. The idea was to see if the box could handle the load, and eventually install the second CPU. Well, the load never got above 0.30, so we saved the money for the second CPU. And we are speaking of a PIII-500, no more.

Re:Overkill???

[linzeal]

Appearently in italy they don't have people spamming 5 megabyte movies to each other.

Re:Overkill???

[Anonymous Coward]

get 700 active developers doing builds on a desktop machine.

how do you do builds through e-mail? which make flag is that?

Re:Overkill???

[ahde]

You can support 700 users on a decent pentium 133. With DNS and dialup and basic web hosting. I know.

Re:Overkill???

[ahde]

Set your mailbox limit to 4 megabytes. And put a link in your "message too big" folder that directs them to a tutorial on FTP.

Unless, of course, your service agreement states that you provide unlimited storage for every user.

Re:Overkill???

[ahde]

I haven't read it, but if this is the same Winnebego that switched like a year ago, I believe its 150K over 5 years.

Re:Overkill???

[Waffle Iron]

But they already had a mainframe.

I wonder what they did with the applications that used to run on that mainframe. I predict we'll find out next week's story on Slashdot: "Company Moves Business Applications from Monolithic Mainframe to Dozens of x86 PCs"

Re:Overkill???

[0x0d0a]

sendmail exploits?

"Bob, the mail server seems overly bogged down. Check it out!"

"Yes, sir!"

--two hours later--

"Well, sir, it appears that all the developers have been using it for all their builds on the sly."

Re:Overkill???

[Garg]

They didn't do anything with the old apps. That's what I meant by "logical partition". You essentially create an address space that thinks it's its own machine, and can run a different OS.

The old stuff still runs without modification, albeit with slightly less resources.

Garg

Re:Overkill???

[madfgurtbn]

Set your mailbox limit to 4 megabytes. And put a link in your "message too big" folder that directs them to a tutorial on FTP.

Why would you do that? Now you've got all your users learning about FTP on company time and probably calling the help desk to use up their time too. User-friendliness saves $$ in a big company.

Most users have reached a point where they can send an attachment (or maybe I should say that most email clients have reached a point where users can figure out how to attach files), but most users don't know or want to know how to ftp. Why force a learning experience on them when you have the hardware and bandwidth to provide large email attachments?

Re:Overkill???

[tryavds]

Actually, the mainframe can be sliced into logical partitions, LPAR. My guess is that they already had a mainframe which they use with one of the mainframe OS's to run their accounting, inventory, or manufacturing. They allocated a small LPAR for this, put Linux and the mail server software on it and voila, no more exchange. The software they use (Insight Server from Bynari) allows running exchange type capabilities from outlook, so they replaced MS Exchange (which for 700 accounts is something like $50,000-$75,000 including OS, mail server, hardware for at least 2 intel boxex, CAL for both OS and Exchange), maybe more and not including Sysadmin, with this.

Re:Overkill???

[Anonymous Coward]

Overkill? That's what I though.

In fact, we run our entire email operation from an Apple Performa 6400 with EIMS and System 8.5 or something. It does only that for about 1200 users, ranging from heavy use to light use.

I guess I should ditch it to buy a mainframe and run Linux, so I can look cool and stuff.

Re:Overkill???

[chez69]

They didn't buy a mainframe just for mail, they already had one, and decided to run their mail off a LPAR.

Re:Overkill???

[hellsop]

They already have the mainframe, for other reasons. So, they got a mail server for 700 users for the price of setting it up. No additional hardware, no additional license, no new box to buy electricity and maintenance plans for, and it's already included in their current backup plans. All it cost Winnebago is some time and education, that they would have had to spend otherwise, and probably saved them $5000 over the course of the next two years.

They can do the same thing with other services too, that they may otherwise have to buy equipment for or farm out to consulting and hosting services.

ObDisclaim: I work for IBM, but didn't have anything to do with this deal.

Re:Overkill???

[Anonymous Coward]

Yeah, I was just thinking that.
Or hell, even more users on a lower end system using one of the *BSD's...

700 users on a main frame, what a waste.

Re:Overkill???

[davidrwilson]

He's most likely running Linux on a single small partition on the mainframe.

The bulk of the MF could be devoted to other partitions running other operating systems.

Re:Overkill???

[ahde]

So they spend thirty seconds learning which button to click. Your employees time is better spent learning proper resource management than watching movies on company time anyway.

And the discussion was about ISP users, not companies, which, by the way, already have size limits. If you're using POP3, it makes a whole lot of sense to cut out as many extra copies as you can. That's why MX was invented.

If one user is sending a 5 MB file to another, the likelihood is that the first user downloaded it from somewhere else (like a movie trailer), and can just send a link; or that it may be sent to multiple users, in which case it should be put on a shared drive, NFS, or some other networked partition, in which case, again, you can send a link.

Integrating FTP or some P2P file transfer mechanism into an email client might be a nice touch and would definitely cut down on the wasted bandwidth of multiple copying, but introduces more potential security risks than benefits.

Re:Overkill???

[Anonymous Coward]

Linux on the mainframe 101;

they are running the email server as a virtual machine(VM) within the the mainframe, not the entire mainframe. Linux on big iron generally takes this approach. A VM for email, a VM for web serving, a VM for cooking chicken pot pie etc.
You don't just through every program under one system and pray that one doesn't crash and bring the whole thing down, you compartmentalize.

Re:Overkill???

[deKernel]

Obviously you didn't _UNDERSTAND_ what the article says. I bet your mail supports only POP3 and not IMAP for which his mail software does. Bit oh difference!

Understand before you post please.

Re:Overkill???

[Dave_bsr]

you must be running my parent's ISP at home. They have a pile of lost connections, DNS failures, and misc. other problems. if you are serious about being able to do this...what possibly can my parent's ISP be using?

Re:Overkill???

[buck_wild]

Very true. The mainframe is very robust. When the resources are defined on the hardware management console, they are (or can be) defined as a slice the entire machine. Thus, they share their resources. Unlike a regular server, if they're not using 100 percent of their respective resources (CPU or memory), said resources are available for other partitions to utilize.

While there are likely test partitions on the mainfame as well, the various partitions operate on an 'importance' level too. In other words, if a test partition process spins up to 100 percent CPU and the production partition needs those resources, it will essentially 'starve' the test partition while it takes what it needs...up to a point.

Re:Overkill???

[Inoshiro]

Mail over NFS?

Don't do that.

Re:Overkill???

[Havokmon]

Don't do that

Not only do I think you're WAY off, but I don't think you read the toaster provided. Your link refers to Cyrus' IMAP server.

From the text:
Reliable: qmail's straight-paper-path philosophy guarantees that a message, once accepted into the system, will never be lost. qmail also optionally supports maildir, a new, super-reliable user mailbox format. Maildirs, unlike mbox files and mh folders, won't be corrupted if the system crashes during delivery. Even better, not only can a user safely read his mail over NFS, but any number of NFS clients can deliver mail to him at the same time.

From that page, the jist is: NFS isn't an issue for Maildir mailboxes.

Re:Overkill???

[webgiant]

You can support 700 users on a decent dual desktop system with Linux, what's this guy thinking?

Maybe he's just got an extra mainframe laying around...? You've got to think the support/maintenance on a mainframe would be horrendous compared to buying a new desktop server for this?

Well, the standard line on getting people to try out Linux is "Linux can run on anything! Get that old computer out of your closet and turn it into a computing powerhouse with Linux!"

So he's just fulfilling the Linux promise that it will run on nearly anything and on the Linux promise that chances are that old machine you have will run Linux just fine. The fact that it is big iron is irrelevant.

And now it can encourage people to collect big iron! Now instead of having it sit around doing 50-year old software, you can run the latest and greatest software! Maybe Linux's power-saving features will mean your latest acquisition will only cause a brownout once or twice a month!

Linux for the PDP-11: it could happen! :)

Recycling

[SuperCal]

I love the idea of recycling old high-end machines. I think this could be a big thing in the future... Buying a cheap old mainframe could be cheaper and more reliable then using a PC workstation with server software. Besides it sounds like fun hehe.

Re:Recycling

[October_30th]

Besides it sounds like fun hehe.

Until it's time to pay for the all the electricity your mainframe and air conditioning consume.

Re:Recycling

[ostiguy]

It could be. But probably not.

We have a HPUX box in a 30ishU rack that is a big waste of space in our lab area. It would draw tons of power (you need a 30amp 110v twist lock socket for it, IIRC), it has raid - a raid of 2 gig disks, and its hpux isn't y2k compatible - it accepts 70-99 as valid years, IIRC, and onlyhas 128 megs of ram.

Honestly, for general unix stuff, mirrored 7200rpm drives and intel hardware would probably draw a fifth of the power, and be at least as quick (I would think it would be orders of magnitude quicker). I haven't bother pricing out HPUX upgrades for this nightmare. It just isn't worth the time or effort.

ostiguy

Re:Recycling

[madfgurtbn]

Honestly, for general unix stuff, mirrored 7200rpm drives and intel hardware would probably draw a fifth of the power
The main plant at Forest City employs over 3500, and they build motorhomes from scratch, including extruding their own aluminum windowframes and arcwelding their chassis together. If this mainframe took 50x the power, it wouldn't be noticed. PLus, it's _already running_ for other purposes, so it's actually saving power by taking yet another small box off the grid.

Re:Recycling

[jedidiah]

How is this different from the electric bill and cooling costs of a room full of glorified desktop XT's.

Re:Recycling

[Anonymous Coward]

There's more to recycling that old stuff than just getting it home from the salvage yard. They can suck up huge amounts of electricity compared to a contemporary machine. Nevermind the cost of adequate staffing. People who know how to run the old stuff tend to have a lot of years in the industry and expect a salary that reflects their senority. Then you've got to find parts when it breaks.

ummmmm

[j0nkatz]

Why the fuck would I wanna put Lunix on big iron when I have Solaris and a room full of E5000's?

Dip shits!

I was just wondering

[DaffyDuck101]

Considering I've got a SparcstationII handling mail for over 1000 users just fine, maybe he'd be interested in switching systems?

Harris County (Houston, TX)

[totallygeek]

I recently went to the Red Hat Certification class and there were two people from the core data services for Harris County. They were there to get some training on Linux because the county is deploying Linux on their IBM mainframes. And, yes, that means more than one!

By the way, if you are thinking of taking the RHCE course 300 (fast track for UNIX proficient people), I really enjoyed it.

Linux on a Mainframe

[saveth]

It's frequently said that Linux is not stable enough for mainframe systems. It's also frequently said that mainframes have been obsoleted by smaller, more powerful computers.

I am quite relieved to see that Winnebago has challenged the "norms" and put Linux to use on a mainframe. Linux is commonly used for mission-critical software, like the Linux server sitting next to me that handles our company's mail, but to see it doing something mission-critical on a mainframe is quite impressive.

Good work, Winnebago.

Re:Linux on a Mainframe

[Anonymous Coward]

Hmmm...Article about Microsoft funding anti-Unix ads followed by an article about Linux running on IBM big iron. As an IBMer, gotta love it ...

Re:Linux on a Mainframe

[buck_wild]

It should pointed out that there is merely a Unix kernel on the mainframe. It's not as robust as, say, a Sun/Solaris 6.4 setup or anything. Not that there's more or less risk of failure, it's just that the command set isn't there.

Runs fine as a web server, though.

Re:Linux on a Mainframe

[Anonymous Coward]

Actually, in a way, it is MORE robust than the sun box.

Linux VM on the IBM chokes up. Cool. Start another one. Kill the locked one. How long would this take, compared to rebooting a Sun box and spinning up all those SCSI drives again?

Re:Linux on a Mainframe

[buck_wild]

I agree, in a certain sense. The environment may essentially be more stable, and booting time would certainly be cut.

There are a still a few drawbacks, though:

Mainframes are generally (from my experience) rebooted (IPLd) weekly, bi-weekly or monthly. Sun boxes can remain up for months.

Like I said in my previous post, the Unix command-set just isn't all there, as it doesn't really apply to the mainframe box and it's configuration. The essentialls are there, of course, but a unix guru isn't going to be able to affect the box the way he might affect his Linux boxes.

Rather overkill, isn't it?

[Anonymous Coward]

A zSeries running Linux, sounds like a really nice box. But, all this for a mere 700 users???? Come on, a dual processor Intel box could easily handle that kind of load for a LOT less money. Hell even Microsoft Exchange on such an Intel box could easily handle the load.

Re:Rather overkill, isn't it?

[chez69]

They didn't buy a mainframe for just mail. They use it for other stuff too.

Linux under VM

[rlp]

IBM has a Virtual Machine OS, that allows you to run multiple OS's on a mainframe. You can run Linux (or even multiple instances of Linux) and still run your legacy apps under OS/390.

excellent

[jeffy124]

ah. the perfect follower

What the hell?

[Anonymous Coward]

You can support hundreds of thousands of mails a day with a 400 MHz box. Just give it enough disk if you have a 50 Mb quota per user.

Re:What the hell?

[Fred2]

You can support hundreds of thousands of mails a day with a 400 MHz box. Just give it enough disk if you have a 50 Mb quota per user. I think it was said earlier that they were intending to run other programs on it as well...

MIPS??

[Corby911]

"What's more, IBM officials said 11 percent of the mainframe mips (million instructions per second) shipped by the company in the fourth quarter of last year were configured to run Linux."

Perhaps it's just me, but that makes no sense whatsoever. How do you ship a measure of speed? "Shipping" millions of instructions per second seems to me to be the same as "shipping" miles per hour. It just doesn't make sense. My guess is that the author of the article got some terminology wrong.

Re:MIPS??

[MrBoring]

Maybe the logic works like this:
They could say how many machines shipped with Linux vs z/OS or z/VM. But that doesn't count the processing power of those machines, so they sum it by the MIPS count. It would tend to mean more if a Linux customer was using a more powerful machine.

Re:MIPS??

[Havokmon]

IBM officials said 11 percent of the mainframe mips

Since IBM machines can run paritioned (one machine, multiple os's at the same time), think of it as each machine IBM ships runs 11% Linux, the other 89% could be anything from OS/400 to AIX..

Correct me if I'm wrong..

Re:MIPS??

[owlmeat]

I don't have a problem with it. If you need an automotive analogy, compare MIPS to horsepower and it makes more sense.

Re:MIPS??

[CornfedPig]

more like shipping horsepower; it's a way of coming up with a single metric that normalizes the range of machines/configurations the company sells -- kind of like a capitalization-weighted stock index; the big boxes count for more, which they wouldn't if you just went by units shipped.

Re:MIPS??

[shakah]

Imagine that IBM sold three models, with the following MIPS capacity:
Model A: 10 MIPS
Model B (Linux): 100 MIPS
Model C: 1000 MIPS

And they sold the following amounts:
Model A: 5000 units (total of 5000*10=50000 MIPS)
Model B: 500 units (total of 500*100=50000 MIPS)
Model C: 50 units (total of 50*1000=50000 MIPS)

Don't you think a statement like "33% of our sales (by MIPS capacity) was configured for Linux" is a little more informative (and accurate) than "9% of our sales were Linux servers"?

Re:MIPS??

[WinPimp2K]

Big Iron is generally measured in MIPS, (been that way for over twenty years). So what the Big Blue Spokesperson is saying is:
"In the fourth quarter of last year, eleven per cent of the total computer power we shipped was tunning Linux."

Now that might mean that they shipped a total of 100 Mainframes (Really Big Boxes) of various models. They added up the MIPS of all of them and came up with some number of total MIPS -lets say 100,000. Of that 100 mainframes, thrity of them (relatively low end) totalling 11,000 MIPS were configured with Linux.

I'll agree, it seems kinda dumb, it would be like Ford reporting sales based on the total horsepower of all the engines in all the cars and trucks they sold, and then giving the percentage of them "configured" for diesel.
Maybe an UBMer would care to explain why it makes sense?

Re:MIPS??

[finkployd]

When you buy a mainframe from IBM you pay for the processing you want. They ship you a complete system (anywhere between 4 and 16 processors I believe?) and turn on (and charge you for) only the number you want. Some of the processors can be configured to only run Linux, and that is what they mean by "mips" being configured to run Linux.

The reason for configuring the processors to only run linux is that many mainframe software vendors charge based on the number of MIPS your machine runs at. If I am buying an MVS application I do not want my Linux processors in the mainframe to affect the price I am paying.

Finkployd

Re:MIPS??

[foobar104]

Perhaps it's just me, but that makes no sense whatsoever. How do you ship a measure of speed? "Shipping" millions of instructions per second seems to me to be the same as "shipping" miles per hour.

It's just you. ;-)

In the mainframe world, where virtualized hardware is the norm, systems are sold by the MIPS. In other realms of computing we talk about a 32-processor or a 128-processor system (or, if you buy Sun, a 106-processor system, for some reason). In mainframe land, you talk about a 12 MIPS system or a 45 MIPS system or whatever.

It makes a lot of sense, too, when you think about the fact that a four processor system, mainframe or otherwise, from five years ago is probably less powerful than a one-processor system now. It sort of normalizes it if you talk about system capacity in MIPS rather than in terms of "x processors of type y at z megahertz."

Don't compare the practice to shipping "miles per hour," but rather to horsepower. General Motors could, if they wanted to, say that they shipped umpteen million horsepower worth of engines last year, and it wouldn't be that hard to understand. It's just a different way of counting.

Re:MIPS??

[finkployd]

I'll agree, it seems kinda dumb, it would be like Ford reporting sales based on the total horsepower of all the engines in all the cars and trucks they sold, and then giving the percentage of them "configured" for diesel.

IBM charges you for your mainframe (and support contract) based on MIPS. The software you run in MVS (in most cases) is priced based on the number of MIPS you run in your mainframe shop. Ford doesn't charge for their cars based on horsepower :)

It makes sense because it lets you know that 11% of all mainframe computing power sold in the 4th quarter of last year is running Linux. IBM doesn't sell "boxes" per se, they sell MIPS.

Finkployd

Re:MIPS??

[ichimunki]

Because simply reporting unit sales doesn't accurately represent how much of the world's data is being processed by what OS, probably. As to the Ford example, I'm not sure they would do this by fuel type, but if they did it wouldn't be HP they reported, rather hauling capacity. Now if Ford had a stake in diesel fuel (like IBM seems to be taking in Linux), then you probably would see ads like this to make it look like Ford & diesel fuel were truly good options. Internally, this allows the business analysts to understand whether to devote resources. If I'm IBM I don't want to devote R&D time to Linux or any other OS simply based on machines running it, or licenses sold, I want to know how many customers are using it, and how much.

Re:MIPS??

[Corby911]

Ah, it was just a question of phrasing. The sentence I quoted was worded in such a fashion that I was confused. I fully understand the concept of MIPS and why it is often a better indicator of server capacity, I just read the text, and took the phrase "11 percent of the mainframe mips (million instructions per second) shipped" as "11 percent of the millions of instructions per second shipped", which makes a great deal less sense if you don't work with mainframes routinely(read: never). I probably would have put a footnote or something in the article explaining that, or tried to find a clearer wording (I've been trying for 5 mins or so, without luck).

(Thanks to all for the clarification)

Re:MIPS??

[damien_kane]

I think this makes total sense.
x86 processors vary on the speed at which they run.
Since with mainframes they are bought for their speed and reliability, with the reliability being stable, the speed is the only part that varys.
Because of this it makes sense to price the mainframe based on speed. If you're benchmarking the price against speed, then that's what you count when shipping...
If you sell a mainframe that does 1.26*10^4 mips, then you shipped 1.26*10^4 mips, right?

Re:MIPS??

[brer_rabbit]

Maybe an UBMer would care to explain why it makes sense?

IBM, UBM, we all BM.

Re:MIPS??

[WinPimp2K]

Damn my human fingers!

Re:MIPS??

[morcheeba]

One reason: Ford doesn't have to deal with the orders-of-magnitude in product variations that occur in computers, so counting vehicles means more than counting computers.

The limits of vehicles seem to be about 10:1 at most (2 passenger car : 50 passenger bus), 50:500 hp, maybe 1 ton car: 5 ton bus.

In computers you've got a much wider dynamic range... 1 user:1000 user, 32kHz (Sega VMU):2.2 GHz (P4), 1K:16GB memory, 56kbps modem : 2 Gbps fibre channel, etc.

Re:MIPS??

[Anonymous Coward]

"(or, if you buy Sun, a 106-processor system, for some reason)."

The reason is (wait for it...) Marketing.

The E15K series supports up to 18 boards with 4 CPUs and a bunch of RAM. Its a NUMA box, so each 4 CPU module can access other module's RAM via the crossbar backplane (though its much slower than the local node RAM).

What's that you say? 18 * 4 is only 72? Where do the extra 34 CPUs come from?

Well, this machine has a lot of PCI slots too. So Sun sells PCI cards with two CPUs on them, which you can plug in. Of course, this is completely useless, since memory bandwidth to and from the PCI cards is simply terrible, so you only get reasonable performance if you stay entirely within the 8meg cache, which is pretty unlikely for the kind of tasks you'd buy an E15K for.

Its just a half-hearted attempt at entering the supercomputer market. Its not going anywhere though, Sun just doesn't know that market.

Just ignore Sun's marketing drivel and think of the E15K as a 72 CPU NUMA and things will make a lot more sense.

Re:MIPS??

[Anonymous Coward]

Big Iron is generally measured in MIPS, (been that way for over twenty years). So what the Big Blue Spokesperson is saying is:
"In the fourth quarter of last year, eleven per cent of the total computer power we shipped was tunning Linux."

Now that might mean that they shipped a total of 100 Mainframes (Really Big Boxes) of various models. They added up the MIPS of all of them and came up with some number of total MIPS -lets say 100,000. Of that 100 mainframes, thrity of them (relatively low end) totalling 11,000 MIPS were configured with Linux.

I'll agree, it seems kinda dumb, it would be like Ford reporting sales based on the total horsepower of all the engines in all the cars and trucks they sold, and then giving the percentage of them "configured" for diesel.
Maybe an UBMer would care to explain why it makes sense?

It makes sense in the same way that "X percent of the dollars of computer hardware we shipped was running Linux." or "Fred Smith currently has a batting average of .500 on night games in the eastern states on days after it rains."

IBM can say "90 percent of our computers shipped had MS Operating systems," if they want to make MS happy, or they can say, "50% of our CPU's shipped were X" (which adds weight to multi-CPU boxes), etc. Overall, Fred Smith probably bats .100, but if you play with the numbers, you can make anything look good.

Re:MIPS??

[Anonymous Coward]

Read other's posts about running Linux in a partition using the VM OS -- When they say "11% of computing power", that's probably exactly what they mean --they aren't counting machines or CPUs.

Re:MIPS??

[Anonymous Coward]

Yeah but I don't think that's what they are doing.

Say you bought 1 Model C @ 1000 MIPS. You then configured it so that your Linux partition took no more than 10% CPU. In practice it averages 8%.

Then the little phone-home PC box connected to mainframe reports back to IBM that 8% of your MIPS is being used for Linux, along with whatever other diagnostic info. There's the number.

The thing to consider is that mainframes are sold by MIPS, not CPUs. You can buy say a 500 MIPS machine, and then pay IBM to flip on the CPUs later to make it a 800 MIPS machine.

A mainframe for 700 users?

[alen]

My company is planning to purchase a quad Xeon CPU 4GB RAM server as part of our Exchange 2000 migration for over 1000 users at a fraction of the price. And even with the licensing it's still going to be cheaper than this Linux mainframe.

Re:A mainframe for 700 users?

[Gopher]

They already had the mainframe, they just are just adding a processor and moving their email onto it.

Yes, a mainframe would be overkill for serving email for 700 people.

Re:A mainframe for 700 users?

[Anonymous Coward]

Let us know how it goes. My prayers are with you.

Re:A mainframe for 700 users?

[einer]

Wow... So does that mean that Microsoft products are better than Linux and IBM and that this guy is a moron? Oh wait... You didn't read the article did you... Otherwise you'd know that they're not buying a new mainframe... Bully for your company, but they could put Linux on it, instead of Exchange for a fraction of a fraction of the price... Even WITH licensing... ;)

Re:A mainframe for 700 users?

[alen]

Our Exchange 5.5 system on NT 4 runs fine. In fact it's so good that I'm forgetting Exchange since there is nothing to do on it.

Re:A mainframe for 700 users?

[swillden]

My company is planning to purchase a quad Xeon CPU 4GB RAM server as part of our Exchange 2000 migration for over 1000 users at a fraction of the price.

How is buying a new machine, plus a bunch of commercial software, plus sending techs to classes to learn how to manage the software, going to be cheaper than free software that your people already understand on a machine you already have? They did turn on an additional CPU, so there's some cost there, but more than likely they were getting close to maxing out their current system anyway and will benefit from the additional horsepower.

Plus, your solution is going to be far, far less reliable. There are IBM mainframes that have been running continuously for decades, with no downtime at all even through hardware and OS upgrades. Not that e-mail really needs to have six 9s uptime, but if you can get it for no additional cost, why not?

Re:A mainframe for 700 users?

[finkployd]

But if you already had the mainframe, it would be cheaper to just utilize it.

Finkployd

Re:A mainframe for 700 users?

[alen]

Forgot to mention. The Exchange databases will be stored on one of our EMC SAN's. In fact were looking at booting the whole thing from our Symettrix. And we just purchased a company with a Lotus Notes cluster on NT Enterprise. My guess is soon it's going to be a Win2000 Advanced Server cluster running Exchange 2000 Enterprise.

We have a Win2000 cluster running a Java app. All the problems come from the Java app.

Re:A mainframe for 700 users?

[Profane Motherfucker]

When you have a motherfucking hammer (linux) every teensy piece shit looks like a fucking nail (email).

Re:A mainframe for 700 users?

[redhatbox]

Ah... but where would they get the nifty calendar stuff Exchange gives you? Oh, wait... we were talking about *email* servers ;). I never did get that stuff...

Re:A mainframe for 700 users?

[Slashamatic]

You are doing what MS normally recommend I guess and you have a couple of systems (at least) just for E2K server, you did remember that second system to replicate on did you?

In the end you have a couple of boxes that runs E2K.

Yes, that was a full stop.What these guys are doing is running Linux under a single VM instance. It will cost them serious money because Linux for these boxes isn't cheap. However, they pay only for the first instance at their shop.

I have gone through the price options on W2K Enterprise Server, Advanced Server and Professional with Exchange Server and so on. There is *no* way that we are not talking serious cash here and that is for s/w alone. MS recommends that you dedicate particular systems for certain functionality like E2K - which is great but this costs.

The end result here is that you say that your company is planning to purchase. Come back when everything is working and tell us how much it really cost.

Re:A mainframe for 700 users?

[WildBeast]

Don't waste your time, no matter what you say they won't believe you

Re:A mainframe for 700 users?

[thelexx]

Then your Java coders suck. In the MS-dominated shop I work in, my Java app is the only thing which doesn't require at least a bi-monthly head scratching session that culminates in a reboot, since none of the MCSE's can actually FIX anything beyond applying yet another patch or checking settings. Meanwhile, the Java proggie takes in another few thousand apps from our clients... The only time it goes down is when Windows craps its own memory and throws an exception outside the VM. And yes I'd rather run it on a Linux box, but no! That wouldn't be a Microsoft solution that our 'expert' MCSE's can maintain! Jesus wept.

LEXX

Re:A mainframe for 700 users?

[Rascalson]

And how much a year do you spend maintaining your virus and filtering software? And how about when your virus and filtering software company no longer supports your version? Ohh, your not connected to the internet!! Never mind then, hehehhehehe

Re:A mainframe for 700 users?

[Anonymous Coward]

You are on confused. Period.

Re:A mainframe for 700 users?

[AnyLoveIsGoodLove]

EMC Best Practices tell us not to boot a server from the Symm. You have finger pointing from the OS/ HW vendors and possible fan in / fan out issues...

boot locally ... store your data on the Symm

Re:A mainframe for 700 users?

[Anonymous Coward]

You are correct. Exchange is pretty easy to maintain.

Re:A mainframe for 700 users?

[Anonymous Coward]

Wow, our POP3 server serves 3000 users everyday and is only a 300MHz Sun Ultra 2. Exchange must be a hog. :-)

Re:A mainframe for 700 users?

[Anonymous Coward]

RTFA! You still seem to be missing the point: IT COSTS LESS. WIntel can't match the uptime of the mainframe or the speed of the processor. Unfortunately, the specific article at the top of this thread doesn't contain the critical bit of info contained in the "old news" IBM post mentioned elsewhere in this list, so I'll copy it here for you:

On average, Winnebago Industries processes 160,000 data transactions on its mainframe each day. In addition, the virtual server capabilities of the mainframe allow the company to run Web and domain-name servers utilizing IBM's Virtual Machine (VM/ESA) operating system. The company also plans to consolidate the work of 40 additional servers, currently handling file serving and other applications, on the same mainframe to gain additional efficiencies.

Sorry, there's just no way to add all of that to a WIntel system for $26K, not to mention what happens when they consolidate the OTHER 40 SERVERS onto ONE mainframe.

Re:A mainframe for 700 users?

[Anonymous Coward]

The article said they are using the Bynari solution. Bynari provides scheduling using Outlook.

Why I think IBM sucks

[rosewood]

... This is Offtopic and Flamebait but hopefully it is interesting and informative as well. The 4 should balance to where it is just "okay"

I have been doing work on IBM AS400s of recent, mainly installing ethernet cards into 9402-400s, 9401-150s. Well, I had two machines completely die on me.

I followed the instructions from the repair / maintanance manual on installing and removing hardware to a T. Didnt swap hardware while the machine was hot, I was grounded, etc etc etc.

The two machines have warrentys on all the hardware but no where on the machine does it say working with it, removing the case, etc. voids your warrenty. There are no break me, void warrenty stickers. I was using IBM instructions on 100% IBM hardware doing a standard install -- nothing crazy.

There is no direct evidence linking the two sepereate ethernet cards and cages to the death of two seperate machines. Granted, its a coincidence that should be considered but there is no 100% proof. The fact that two seperate cards were used and the unlikelyness that a bad card would completely kill a system (namely the CPU card) is far fetched. More often do you see AS400s that die when powered down and moved. Its not insane to think that these very old machines were just waiting to have something fuck up on them.

However, the two incompotent IBM techs that came out to the second machine are crying fowl saying the machine itself is not under warrenty. This flys in the face of what Ive been told from the company I do this for and what I have read! Granted, these techs "rarely work on AS400s" and didnt know a single fucking thing other then to look in the manual. Had the office not had the repair manual, they woulda been fucked. They also had to have a tech on the phone the whole god damn time. They did not bring a 7mm socket to get into the system so they had to use my power driver and sockets. They removed and handled the CPU card w/o grounding themselves (one guy pulled it and just handed it to the other guy who was on the phone to read a SN). They left the machine on, w/ error code, overnight with everything just scattered this way and that.

So - now we are just waiting to see what kind of outrageous bill they send to my offices. Re-damn-diculous.

But, thats why I no likey the IBM. Im sure there are going to be replies that say of course I voided the warrenty, tell me that I am a moron and broke it, but I will be 100% honest -- I really don't thing it had anything to do with what I did.

Re:Why I think IBM sucks

[owlmeat]

Sounds like you're a moron and you broke it.

Re:Why I think IBM sucks

[delcielo]

IBM has consistently given me the best support I've found anywhere. They're patient, competent, and skilled.

The CE's I've dealt with have all been very professional; and have displayed none of the behavior you saw.

In one case, I even had a tech from supportline call me back weeks after he'd already solved a problem for me, to tell me about an alternate method he'd picked up from one of the more senior people. He'd used it on another customer's problem, and called me back to let me know it was an option that I might prefer if it came up again. Now that's service.

Re:Why I think IBM sucks

[October_30th]

Sounds like you're a moron and you broke it.

Hey, I know you!

You do Dell's telephone support service in Canada!

Re:Why I think IBM sucks

[owlmeat]

Yeah, and you're another moron that broke it.

Re:Why I think IBM sucks

[October_30th]

You really seem to have perfected the helpline support technique: you actually manage to "solve" the problem so that the company cannot be held liable and you also keep the calls short thus saving your company lots of money.

Your boss must be so proud of you.

Re:Why I think IBM sucks

[rosewood]

I will say that the phone people and the first CE I delt with was a okay

they two frik and fraks kill me

Re:Why I think IBM sucks

[0x0d0a]

You know, there's a reason most people troll AC -- trolls lose a lot of force when anyone can see that every single comment you've posted historically is a troll.

Re:Why I think IBM sucks

[Zurk]

umm...ok..im not too familiar with your systems but ive taken apart and put together an IBM AS/400 720e (running V4R4M0).
Firstly, YOU ARE NOT SUPPOSED TO OPEN THE DAMN THINGS. IBM will send out techs for FREE to install hardware you want to install on em. They do NOT supply service manuals in general. i dont know where you got yours from. Most AS/400s (high end models) are LOCKED and cant be opened without breaking the lock with a screwdriver or using a special key from IBM. I had to break the lock with a screwdriver to open the damn thing. its the cheap plastic lock that prevents you from exposing the front panel.
Secondly there arent any screws. its snap out assembly kinda like dells. The screws are on the modular boards, holding delicate connections together, which you arent supposed to take apart anyway.
Thirdly, there arent any CPU cards. the CPU modules are placed in a a cage with the memory assembly which you arent supposed to take apart. The assembly snaps into the backplane slots as one module. Taking apart the CPU module assembly will destroy it completely if you arent really really careful. that thing is fragile and protected by metal casing for a good reason.
Fourthly, its easy to check if your machine is under warranty. the thing has a modem built in which you can connect to a phone line and allows the machine to phone home, check the software and hardware licenses and warranty info right on your console. just login as QSECOFR and you should get in.

Re:Why I think IBM sucks

[rosewood]

No - I opened the machines and I am sure.

These are OLD OLD OLD OLD Mofos. 9402-400 running V3R7M0. First snap off the front and back panels. Next, take off the top cover which has 2 7mm head screws. Then, take off the side cover which has two more screws. Now, take off the metal side cover which has 8-14 screws (cant remember but its a lot, all 7mm heads). Now, to add an ethernet card and expansion gate take off the back access pannel which is another 12 screws. The ethernet card is NOT some little PCI thing. It is a big mofo that slides into an expansion gate that you also have to plug in. This gate plugs into the mainboard via a ribbon cable and the ethernet plugs into the gate by snapping into place with the clips on the back.

IBM CEs will NOT come install this hardware for free - I specifically asked. They said it would have to be under billable time. There are no locks are stickers on the machines I worked with. There are not machines sitting at a place like Boeing, etc. Each independent agent I go to has his own AS400. The agents lease these machines. Manuals for checking and repairing are provided, I know because I used them.

The CPU card we pulled was not in any casing but it did hold the memmory and the CPU. It was handled VERY poorly by IBM techs and since it is not protected (the ethernet card was not exposed PCB. It had ESD protection all around it. The CPU card however was.

It is under warrenty but how the hell could we do that if we couldnt even get the thing to IPL? Also, just logging in as QSECOFR doesnt boom present you a menu that tells you what to do to get warrenty info.

But the main point of you arent suposed to open these things. Maybe the ones you have worked on but there are no such signs on these big bad boys.

I thought so too...

[WinPimp2K]

so I Read The Fine Article:

• he saved over 120K bucks vs an MSFT Exchange Server solution (for 700 users - what is Bill G smoking?)
• It is using less than ten per cent of the mainframe's capacity, they do plan to migrate other server jobs currently on discrete machines to the mainframe
• Yes they are already a mainframe shop. One mainframe is far more capable than a desktop server. Given a choice between supporting a single mainframe or a couple of hundred desktop servers, the mainframe costs less
• The article covers a lot more than just this one instance, but it has a nice number to start with - that big dollar savings

Re:I thought so too...

[Perl-Pusher]

Thank you! You have expressed my thoughts quite eloquently.

Re:I thought so too...

[TonyZahn]

what is Bill G smoking?

Rolls of hundred dollar bills, that's what.

Re:I thought so too...

[Anonymous Coward]

what is Bill G smoking?

Rolls of hundred dollar bills, that's what.

At first you'd think that's crazy, but when you think about the fact that most bills are used to snort coke you get a nice flavored high by smoking those hundred dollar bills.

Re:I thought so too...

[Trekologer]

It is using less than ten per cent of the mainframe's capacity, they do plan to migrate other server jobs currently on discrete machines to the mainframe

Exactly.

This sroty is turning into a whole bunch of "But I can do email suing this old 486 in my basement". But you are all missing the point. Since the mainframe's capacity isn't full, there are a lot of things that can be put on to it.

I guess no one saw the the IBM commercial where the company manager calls the cops because he thinks that all the servers were stolen. The tech walks out and says that they weren't and the room of servers was moved onto one machine. "It will save us a bundle."

Bingo.

Re:I thought so too...

[Anonymous Coward]

what is Bill G smoking?

Rolls of hundred dollar bills, that's what.

At first you'd think that's crazy, but when you think about the fact that most bills are used to snort coke you get a nice flavored high by smoking those hundred dollar bills.

No one uses hundrreds to snort coke...

Re:I thought so too...

[Anonymous Coward]

The IBM commercial I like is the one where they are all playing basketball. The guy with 'linux' on his jersey is over there dribbling away, and the coach tells his buddy 'He's so stupid, he works for free.'

Re:I thought so too...

[swb]

Is 120k for the licenses?

We have E2k for 500 users w/antivirus on a dual PIII 933 box w/2GB of RAM and the CPU meter seldom bleeps about 10% util.

Re:I thought so too...

[Anonymous Coward]

If you happened to notice, Detlef Schrempf(sic?)(former NBA star), plays Linux.
I think I also saw Mugsey Bogues in a more recent commercial.

Re:I thought so too...

[Anonymous Coward]

Yeah, but I bet you're still not putting anything else on that machine. Or at least I wouldn't :)

Re:I thought so too...

[Anonymous Coward]

yeah, you can just use mount $dir;

They already had the frame

[drew_kime]

The need to ensure uptime was one reason Winnebago chose to run Linux on its mainframe. Last year, faced with an expensive upgrade to Exchange 2000, IT managers at the motor home and recreation vehicle manufacturer decided against the move and instead proposed running their e-mail system on Linux on the company's mainframe.

The company had success using Linux for domain name servers, Web serving and file sharing on its IBM S/390 mainframe running the Virtual Machine/Enterprise System Architecture operating system. After Winnebago officials decided they wanted their e-mail system on a reliable system, they chose to upgrade the company's mainframe, adding a second processor using IBM's virtualization technology, zVM, to run several Linux servers on a single mainframe.

They had the frame already, and just moved a new app onto it.

not necessarily overkill

[stray]

well, depending on what kind of services you provide on your e-mail server, you could actually do with some additional horsepower. Things like virus checking, spam filtering, large IMAP homes with automated archiving mechanisms spring to mind. running everything over ssl will add to the load, too i guess.

but generally, i agree with you that you can tend to quite a lot of regular mail users with a decent beige box, although i always prefer not to run services on desktop hardware, tempting as it may be (well, i might change my mind if there's a hot spare standing by... :))

In Other News...

[Anonymous Coward]

My friend pete just installed Linux on his home computer. Does this mean I get to have a featured headline on slashdot???!

Overkill? Not at all.

[Samarkind]

There are several posts that are wondering if this is overkill, so I'll respond to all. It's not since they already had the hardware and only added a single CPU to their existing mainframe. They got the whole nine yards for $26K, but they don't have to add a new server, license Exchange, hire a Windows admin if they don't already have one and, as the exec said, they don't want to use Intel hardware.

freaking waste

[king_ramen]

I hade over 40,000 users on a Pentium 667 w/ 256MB of RAM, and this includes LDAP, POP, SMTP, IMAP, webmail, qmail, apache, etc.

If that machine ever hits 1% utilization he did something stupid.

Re:freaking waste

[Anonymous Coward]

Sure, I coudl have 3 billion account if no one used them. What mail server software are you running, somethign you brought back for the 73rd century?

Re:freaking waste

[Anonymous Coward]

1. They already had the machine

2. IBM hardware means superior quality to anything you could find for a PC-style box

3. Linux for zSeries means rock stability

4. Their mainframe isnt a dedicated mail server. Thet run other mainframe-specific applications which would probably have some "problems" running on your box.

Do I need to say more?

Re:freaking waste

[0x0d0a]

I think there's a reasonable argument that the usage patterns of the users are an issue.

If you're running a small dialup ISP, then there are going to be few users doing work at once, probably more POP3 than IMAP work, the transfer sizes are likely to be smaller and you aren't going to have large numbers of people cc:ing lists of other users on your server. This would probably not hold true for at least some office mail servers.

Of course, I've never admined a mail server other than the one on my desktop, so I don't have much room to make strong claims.

You missed something

[NitsujTPU]

This is the mail server. They still have to support mail CLIENTS at the desk. Just like they would if the mail server was running off a smaller/cheaper workstation. Soo... Either the mainframe does something else (doesn't sound like it) or it's overkill.

Re:You missed something

[Perl-Pusher]

It is using less than ten per cent of the mainframe's capacity, they do plan to migrate other server jobs currently on discrete machines to the mainframe Yes they are already a mainframe shop. One mainframe is far more capable than a desktop server. It sounds like that covers your last sentence.

Re:You missed something

[Ooblek]

Nah, they are secretly planning to overtake all the extra bandwidth on the internet by processing high-volumes of spam. I think they code-named the mainframe MCP or something......it might talk too, but I'm not sure.

Re:You missed something

[Dave_bsr]

This...is a troll. yeah. right. For the fool who mod'ed this guy down, it might help to point out that the MCP is from a movie called Tron and this post was _humor_.

Re:You missed something

[buck_wild]

Agreed.

The point that the rest of you seem to be missing is that the mainframe will process all of the email...but you still must have an end-user license to actually read it. So you may save (doubt it) money on the server side, but you're still going to lose your shirt on the client side. Depending on the server-side Corporate clients usually get a quantity of clients thrown in to seal the deal.

Re:You missed something

[Anonymous Coward]

?

they should be able to set up POP or IMAP and use the existing e-mail client most of their computers will come with (Outlook or Outlook SE) just fine. No additional license cost for email clients, because they've already paid for it.

Setting up and licensing a cluster of Win2K AS machines to host 700 email addresses, with Exchang Server, probably did not look good to them, if they already were a mainframe group. They already have their mainframe knowledge in-house, probably. They hire a couple of Linux sysadmins to mesh with the mainframe people who keep the hardware going. Makes perfect sense to me, instead of hiring a whole gaggle of MSCE's to keep the Win2K boxes going and coordinating their daily reboot schedules.

Re:You missed something

[buck_wild]

Good point. They certainly COULD use the product that came with the operating system. That may not be as robust as a typical server-based environment, though.

We don't seem to be the target audience here...

[glwtta]

"In other words, Linux has come a long way from being Linus Torvalds' student computer project. "

Oh shit, it has? I better get on that there Linux thing then! Is it just me, or did that whole article have the "this isn't going to teach me anything new" feel to it?

Re:We don't seem to be the target audience here...

[zio pera]

"...in 1983 Microsoft made an equally risky decision to name its product after a term commonly used in the trade..." wich term ? DoS ? Sorry... could't resist ;)

big achievement...

[mbennis]

Now i have to save some money, buy a big iron in order to play "Return to Castle Wolfenstein" with a clear conscience.. Do I ?

For those who call it overkill....

[SuperCal]

The article says ". Altogether, the company has 128 mainframe mips. It's using between 7 percent and 10 percent of those to run Linux and the e-mail system." They use the other 90 someodd % for other applications...

Fitting

[monkey butler]

A fitting story to come directly after this one

Re:Overkill? Not at all.

[debaere]

I disagree with your disagreement :)

This is serious overkill in the money department (but kudos for the cool factor :)

My company uses a dual PIII 500 PC (built from scratch) with 1GB RAM running FreeBSD and it supports 6000 email addresses without a hitch.

Total cost: $2,000 Canadian.

Happened 9 months ago...

[hangdog]

...according to this arcitle on IBM's Website.

Re:Happened 9 months ago...

[ahde]

Thank you. I was looking for that.
More links:

The Bynari site:
http://www.bynari.net/

From Consulting Times:

http://consultingtimes.com/connector.html

While we need case studies to show the actual savings that can be achieved through the deployment of InsightConnector, it's hard not to start counting additional money in the bank. For starters, the Connector fee schedule goes from $39 for a single user, down to $25 per seat for 100 users, with negotiable volume discounts for larger organizations. By contrast, Microsoft charges $92 per client licensed Exchange seat, so that a firm with 100 seats will experience a gross savings of $6,700, or 72 percent, right off the bat.

Linux using ESCON?

[Steve72]

How does Linux for mainframe connect to mainframe DASD? Do you have device files for 3390-3 and 9's? Do they mask it as SCSI volumes? What about FICON?

-Steve

Re:Linux using ESCON?

[Jay]

It talks over ESCON or FICON, whatever you have. SCSI is not there yet, but they demo'ed a z800 at linux world with SCSI attached CD-ROMs and other fun stuff. It's all in here:

mplinux1:/usr/src/linux/drivers/s390/block # uname -a
Linux mplinux1 2.2.16 #1 SMP Fri Mar 23 06:25:46 EST 2001 s390 unknown

mplinux1:/usr/src/linux/drivers/s390/block # ls *.c
dasd.c dasd_9336_erp.c dasd_eckd.c mdisk.c
dasd_3370_erp.c dasd_9343_erp.c dasd_eckd_erp.c xpram.c
dasd_3990_erp.c dasd_diag.c dasd_fba.c
mplinux1:/usr/src/linux/drivers/s390/b lock #

Re:Linux using ESCON?

[spudnic]

So how much does an entry level z800 cost? I know the number would be wildly innaccurate, but say something to replace about 40 servers performing mail, web, dns, dhcp, etc.

Any ideas?

.

Re:Linux using ESCON?

[Jay]

The number I've heard is ~400k for a z800 for running linux only under VM - No z/OS or z/OS.e

That system will certainly be able to host those 40 services. Hmmm. Now that I think about it, I think that 400k is for a fully configured z800 with 4 processors and lots o RAM. From what I've seen, it's got quite a bit of zoot. Probably enough for at least 100 such infrastructure machines.

See my second bullet point

[WinPimp2K]

They do plan on migrating more server type tasks onto that machine and off of standalone servers that have kind of "just grown". They probably don't have any other single tasks that will realize six figure savings from the migration, (and they aren't moving jobs to Linux due some secretive penguin fetish) but they willbe movinng other tasks where they find a good justification. The licensing costs for the mailserver made it their "killer app/service".

Re:See my second bullet point

[NitsujTPU]

Ahh, it kind of makes a bit more sense now. I just don't think I quite absorbed it the first time. The savings allows them to aquire a machine, which they will have future savings/lower LOE on. Gotcha.

Re:Overkill? Not at all.

[debaere]

of course, if I finished reading your reply (or bothered to read the article in the first place :) I'd have noticed the "Doesn't want to use Intel" bit, which makes my argument a tad pointless. oh well

It seems more appropriate now.

Good

[Sims Youth]

This oughta show those Unisys jerks that Linux can kick ass on big iron!

Sounds like a tremendous waste...

[jlockard]

What a complete waste. REALLY. I've got an old Dell server running an oldish version of RedHat and Cyrus, serving email for about 1200 users. The machine is far from taxed right now. I would say that the whole setup cost about $4000 when first purchased.

We're replacing that setup with a newish Dell 1U server running a newer version of RedHat and a newer version of Cyrus and making tweaks along the way. With being a school that has promised email accounts for life to alumni, we're planning for growth, but the server still cost around $4000 plus the cost of the RAID for email data store.

Re:Sounds like a tremendous waste...

[AVee]

Read the article, it's not like the thing is 'only' serving mail. They run other apps on it and used zVMS to run linux in a separate virtual machine.

Re:Sounds like a tremendous waste...

[LinuxHam]

I've got an old Dell server running an oldish version of RedHat and Cyrus, serving email for about 1200 users. The machine is far from taxed right now

I think a lot of Intel-oriented people would be floored if they learned about the hardware reliability and flexibility that mainframes offer. Do you have dual power supplies in your Dell box? Can you hot swap them? Do you have hardware RAID? What about redundant hardware RAID attached to a dual-channel RAID storage box (also with dual hot-swap power supplies)? Can you hot plug your processors? RAM? RAID controllers?

A key feature of Linux is that it lets you select reliability and availability just by turning a dial. From handhelds to Intel to RISC to midrange and mainframe, you get to decide how mission critical your apps are. If you accidentally unplug your Dell box, your users are SOL until it reboots.

Re:Sounds like a tremendous waste...

[afidel]

actually our compaq's have all the features except hotswap motherboard components, and I believe some of the newer ones allow hot add of ram (though not hot replace?). The pci slots are all hot swap, the drives are all hot swap, the power supplies are hotswap etc. And they still cost a very small fraction of a mainframe.

Re:Sounds like a tremendous waste...

[LinuxHam]

The pci slots are all hot swap, the drives are all hot swap, the power supplies are hotswap etc. And they still cost a very small fraction of a mainframe

You're right.. I too have worked with Compaqs that have all those features. The original poster said he was running "an oldish Dell". Of course, the full-featured Compaq boxes did come close to the $18k mark, which approaches the $26k Winnebago spent on upgrading the mainframe to support their new Linux operations. Add another virtual server, and their choice was much more cost effective. Add ten more virtual servers and its no question which choice was better.

I'll run my setup script to bring another virtual server online in about 5 minutes, and you'll start over asking for another $15k for YAB.

Re:Sounds like a tremendous waste...

[deviator]

I would have to agree that using a mainframe to serve e-mail to 700 users is seriously massive overkill, and that the "Dell server" (although Dell is not my favorite Intel-based server) option actually makes more financial sense.

Yes, many Dell servers are available with dual (if not more) HOT-SWAP power supplies. Yes, many Dell servers support *expandable* hot-plug hardware RAID. Yes, Dell has the dual-channel RAID storage box. Yes, hot-plug PCI is an option. No, PC architecture does not yet support hot-plug RAM or processors, but it's only a matter of time. (Not that you would need these if the server was properly spec'ed out to begin with).

I would be interested in seeing what the incendiary costs are for running a mainframe vs. a server--how much electricity does that thing eat up, anyhow? What are the contractual costs with IBM? Yes, their service & support is great, but I can't see why a company would spend all of that extra money for 100% uptime when they can have "99.9999%" uptime for a fraction of the cost. I understand mainframes are legendary for their reliability, but many companies simply don't NEED that and the cost differential required to simply maintain and run them may be a big waste of money.

Given a competent administrator/integrator and the right combo of server software, a PC server should be able to give very reliable service at far less cost than maintaining mainframes. E-mail, while important, is simply not as "mission-critical" in most cases as a gigantic ERP solution, and even those run well on PC servers these days.

I understand mainframes are still "cool," but if you have a competent staff in place they're simply not a good use of a company's resources these days for things that are better served by commodity hardware. It sounds like the guy who did this really wanted to play with it and see if it would work; using Microsoft's licensing costs to justify it was an easy out, despite the fact that there are other products comparable to Exchange in features that are far less expensive. Also, the article didn't say anything about the features that were LOST by using Linux to serve e-mail instead of a real groupware package.

Smoke & mirrors... "look at me! I put Linux on a mainframe! Isn't that cool of me?"

(okay, call me jaded :)

LPAR / Logical Partitions...

[Shivetya]

On their minis (AS/400) they are known as Logical Partitions, which allow the machines to run Linux, Notes servers, and various versions of OS400, and rumored to eventually include other OSes...

Many times easier to support one machine that multiples... and its easier to execute a backup machine for it as well.

Re:LPAR / Logical Partitions...

[finkployd]

They are called LPARs in z/390 lingo as well. However, you are limited to the number of LPARs you can run (12 or 14 if I remember correctly). Most shops who run Linux in production (as opposed to just playing with it) run it under zVM which has no limit as to the number of virtual machines you can run. Well, the processing power would eventually becoming a limiting factor, but there is no hard coded limit.

LPAR is literally a stripped down VM that runs in the microcode.

Finkployd

thats not good

[Anonymous Coward]

man, that makes it sound like it can ONLY handle 700 users. I know for a fact that something like that can handle well over 15000 (IMAP)

Hmm...

[GearheadX]

Wouldn't this whole idea be the perfect counterpoint to what's going on in this thread ?

Overkill

[ruvreve]

As a hack this would have been nice, but email accounts for only 700 users doesn't need the capabilities of a mainframe. A high-end workstation or a low-end server would have fit this role nicely.

Options exist for about $25,000, that mirror each other so when one server crashes the other machine immediately takes over.

Now for the MS Exchange licenses I don't know the exact cost but $100,000 seems extreme. If you have the support staff to run the linux email server on a mainframe then its probably a viable option. Otherwise, your going to pay more in support in the next few years.

Picking up steam..

[LinuxHam]

if you are thinking of taking the [fast track] RHCE course I really enjoyed it.

Same here, last June. And when I took my Linux on S/390 training in December, I was in class with people from a major online bill payment company, a major auto insurer, Canada's DOD, and many others. Most had already deployed it and wanted to see what they hadn't figured out for themselves yet.

In August, 2000, I sat next to an IBM'er by coincidence on a flight. He saw I was reading the "Linux for S/390" RedBook. He said I'd become a "demigod" if I get into that. I've already gone thru one consolidation project, starting a second one on Monday in NYC, and have a third one queued up, waiting for me to finish up in NY. It seems we recently gave a customer a server upgrade plan, and they replied, "what, no Linux?" So we're redoing it as a consolidation plan for Linux on S/390.

I'd say Linux on S/390 is picking up steam big time. When I spoke to a friend about this setup, he replied, "Wow, you finally sound like one of those mainframe IBM'ers we used to make fun of!" Of course, he still has no reply to the argument that I can reduce just about any single data center to a couple of 48U racks, and give all the servers five nines.

Re:Picking up steam..

[Telastyn]

My father now works for IBM (bought and outsourced to them) so he gets all the newsletters and the such. Last year IBM had something akin to 20x mainframe sales after the linux initiative. It pretty much saved the department.

The only problem I've seen is most current admins are used to/learned linux on little dinky spare desktop machines. 'Mainframe' carries a big scary connotation. The name itself intimidates, like a *nix prompt scares most MCSE's.

Plus most bosses 'know' that mainframes are *so* 1970's...

Re:Picking up steam..

[totallygeek]

It is great to see Linux (a free product) drive major sales in the computer industry for hardware and software solutions. I don't think that anyone thought it possible this soon if ever. I remember everyone I trained with, but there were five people from Compaq (well, there are in Houston), and they were all five vintage DEC people. There was a guy from Texas A&M.

I would have liked it when I was at A&M if we ran Linux.

Re:Picking up steam..

[Anonymous Coward]

Ahh 5 nines up time on a mainframe.... I believe that if
1. You NEVER need to patch that version 1.x of Linux on the Mainframe
2. You NEVER need to patch the software emmulator that runs Linux on the mainframe.
3. You luck out and get all the Mainframe crap configured correctly the first time.

The only place I see this being a good solution is for shops that already have a well trained staff on supporting mainframes. People seem to miss the point that it is a royal pain to support one of these boxes. Why do you think companies like Sun, HP, DEC ect... came in to being?

You can get near 5-9's on standard Intel box now. Heck if you cluster it, you will have 5 nines. Although my guess is that you (the admin) will have to take the box down for some upgrade (thus killing the uptime...).

What I have found is that most companies with mainframes still find it much cheaper to purchase separate Intel boxes for mail, file/print, DNS, DHCP, ect..

I do applaud IBM for doing this, but PLEASE don't be fooled in to thinking that this is just a "STANDARD" Linux install. This is nothing more than running VMWare on a box. You have to know both operating systems to support it.

Steve Michael
steve.michael@performancestrategies.com

Re:Picking up steam..

[Banjonardo]

Heh, your post just hit me with the full irony:

In the early 80s, IBM used MS-DOS because it thought hardware was where the money is. Now Microsoft is, well....Microsoft.

Now in the early 00s, IBM is using a free operating system and raking the big bucks in... you guessed it! Hardware!

Aahhhh, computer irony.

Winnebago is always on the cutting edge..

[asv108]

Ever see SpaceBalls?

Read Article?

[ackthpt]

700, yeah, ok, sure, there's about 200 posts all approximating: "What? I can support 700 mail users on a cruddy old 486" (which we once did, btw, it worked peachy)

But if you read the article you see that they don't want to support more servers, they want to support less, i.e. not buying anymore Intel servers, which are like so many cats. The only downside I see is a single point of failure, the zSeries goes 'poot!' and the staff takes the afternoon off.

But adding that function to an existing piece of hardware does keep support costs down, and as they've noted, pay once to get their mail running on there, as opposed to paying Microsoft for Exchange, year in, year out, well, it looks smarter, doesn't it?

Last, but not least, if they decide to move it off the mainframe later, hey, they should be able to migrate it with little pain, since the OS runs on just about anything.

'Bago 2005: "Tell eWeek we just moved the entire mail server to a hacked TiVo, will you, don't forget to mention it does voice and video email, too."

Re:Read Article?

[chez69]

Remember, a z-series machine is not your average cruddy x86 machine. It is much more reliable.

you're right, and also

[Anonymous Coward]

they didn't have to "add" any hardware, they just enabled an existing CPU to run Linux on a virtual partition.

the mainframe is not running JUST the email.

Re:Overkill? Not at all.

[shaldannon]

Moreover, if you'd read some of the other posts, you'd notice that only a fraction of the system is being used for the email server, and that as a vm. The rest is running other odd apps. Of course, what I'm curious about is if you can fileshare between the mainframe and the vm on the mainframe...

Then again...

[shaldannon]

Maybe he really wants to waste power *and* has plenty of time trying to make it y2k compliant :}

Email != groupware

[einhverfr]

Exchange and Bynari are groupware packages which incorporate email functionalities within their capabilities. Same with PHPGroupWare.

If you just wanted email, you would probably stick with SendMail, Qmail, or the like. However, the shared calendars, todo lists, etc. are important in the groupware environment!

Re:Overkill? Not at all.

[jidar]

Well.. ok, but I run a mail server for an ISP with about 1900 email accounts on a dual p3 machine that costs me about $1500.

I feel compelled to quote Scott McNealy

[AnalogBoy]

Just where you can get sun microsystems's view on this (not neccesarily mine.. but perhaps.. but maybe not..)

To quote This Article in computerworld magazine:

Q: Sun has done quite a bit in the way of Linux support, but you really haven't gone the IBM route of marketing Linux-based systems. Why is that?

A: We're the No. 1 Linux appliance server supplier in the world with the Cobalt line [from the acquisition of Cobalt Networks Inc. last year] (see story). We have Linux extensions to Solaris. We just don't think a Linux partition on a mainframe makes a lot of sense. It's kind of like having a trailer park in the back of your estate.

Re:Overkill? Not at all.

[ahde]

There are a couple of things you're missing.

1) They're running IMAP, not just POP3 (though your system could probably handle 700 IMAP users easily)

2) They're using Insight from Bynari so that all their outlook clients can have their popups.

They may have antivirus software too, and that will really eat CPU and I/O.

The other contestants:

[qurob]

http://ipswitch.com/Products/IMail_Server/multid om ain.html

We've ran 400 users on this, on a K62 300MHZ

On a related note, wouldn't it be a smarter idea to have a cluster of cheap intel boxes? Cheaper at the least. Mainframes are just not my idea of a mail server.

Never mind a mainframe, you can do it on a PII.

[Anonymous Coward]

Up until very recently I was running about 3000 POP accounts off of a single-processor PII with redhat 7.1, qmail and vpopmail, an ide drive (that's right, not SCSI) and as much ram as the board could support. It ran just fine and generally had very little load. About half the accounts were dormant or saw little use and a quarter of them used web-based mail instead of POP. E-mail is I/O-bound and bandwidth-bound, not processor-bound. Putting 700 accounts on a mainframe is a complete waste. Rather than wasting money on a high-end "server-class" machine or a dual, the money is better spent on a bunch of regular desktop machines with SCSI drives. Your server load will be next to nothing even if you have a few thousand accounts on the box. If you have less than a thousand accounts you'll do just fine with a recent desktop system and an IDE drive.

I'm always left with this question when reading

[ScrewTivo]

about Linux on big iron. If I took over the entire mainframe with one instance of Linux and running a database app like DB2...what kind of benchmark numbers would it produce?

Considering a DB2 standard license is only 3-4K would it replace the need for an Enterprise license at 20K/cpu? Hummmmm

I never seem to find benchmarks on big iron installs.
TIA

I worked at an ISP in the mid 1990's and...

[Anonymous Coward]

...supported 30,000 users' email accounts on a Pentium Pro 150 MHz machine with 64MB memory running FreeBSD back in the early days. Handled it perfectly fine except when spammers hijacked it as a spam relay before we learned about how to properly secure against unauthorized relaying.

interesting

[archen]

as many people have said, it looks like they just added another process to an existing mainframe - it still does the other tasks.

But at first glance I still got this weird picture in my head that along with this machine running as a mail server, they got a gigantic cray sitting in the corner for a firewall...

Re:Overkill? Not at all.

[Steve Hamlin]

It's not since they already had the hardware and only added a single CPU to their existing mainframe. They got the whole nine yards for $26K, but they don't have to add a new server, license Exchange...

And that's what I think the earlier posters were talking about, and what still hasn't been answered.

It makes sense to spend $26,000 on a zSeries/Linux solution over "spending $150,000 on new hardware and software for a Microsoft Corp. Exchange upgrade."

But why spend to the $26,000 at all if you can support 700 users on a $5,000 semi-high-end traditional Linux x86 email server?

Is it worth the $26k to not have to worry about an extra physical box? The administration is the same, it is just running Linux on a zSeries for $26k vs. running Linux on a x86 SMP for $5k.

What am I missing? Does the $26,000 include a bunch of consulting services that they needed? $26k to have the IBM name and support?

loafing along at 10% capacity

[Anonymous Coward]

Now they have to figure out what to to with the other 90% of the cycles ...

Not a waste...

[DarkMan]

Take an AK-47

Take a magazine of 7.62 mm S ammo, and load.

Walk into computer room.

Aim at [Your Dell, The IBM]. Empty magazine at said server.

Which one still works?

More usefully, which one can you fix up back to full condition, without losing a single email?

That's reliability.

Re:Not a waste...

[DysonSphere]

"More usefully, which one can you fix up back to full condition, without losing a single email?"

Uhhh.. How are you going to fix anything in a jacket with the sleeves in the back?

Windows on 8way systems

[Anonymous Coward]

"And robust Linux kernel support for very large servers--those with more than eight processors--will be needed for the open-source operating system to become a true competitor to Unix, Windows and OS/390 on larger servers."
Since when does anyone run windows on >8 way systems? Oh yea datacenter lol. Please windows is not a defacto enterprise option yet. 2k has only just come out and we are seeing that yes it is a decent OS, but its still got a long way to go before it becomes a glass house OS. How annoying that MS continues to buy its way into credibility. While linux is still labeled the stuggling newcomer. Can it really handle enterprise loads?? Yes it can you jackasses. Except for the really high end stuff you can replace ever server in you company with linux and do well. FYI MOST servers in large companies are not >8-way. They are not even 4-way. So fine run Sol or whatever on your "enterprise servers", linux will gladly run well on the remaining 90% of servers in your companies. Arrrgggghhh.

Yawn ...

[Anonymous Coward]

128 MIPS? That is not much. The current z900 tops out at 2,694 MIPS. This must be either a very old mainframe or a Multiprise. And they are only using 11% of those MIPS.

And to put ~2,700 MIPS into perspective, IBM's engineers estimated the "Condor Plus" (a.k.a., p690) RISC system with 24 600 MHz CPUs at over 2,700 MIPS. Yes, that means IBM Mainframes are not the world's most powerful commercial computers. IBM is just afraid of the truth that thier new p690 is probably as powerful as a 5,000 MIP mainframe, if there was such a thing. In short, RISC/UNIX has won the high-end commercial computing performance wars.

So the people who noted they could support the same 700 users on a single CPU 1 GHz system, or a dual CPU 500 MHz system are probably accurate.

Linux as a guest OS on mainframe VM is a good way to quickly provision services (like an ISP), but a corporate email system is not something you throw together in a couple of hours.

As for availability, mainframes provide excellent hardware availablity, but Linux on the mainframe is nowhere near as mature as the native mainframe OSs, so the occurence of software faults would be similar to Linux on Intel.

The really good thing is that anyone who is running apps on Linux on the mainframe has set themselves up to save a boatload of money by moving to Linux on Intel.

Winnebago may have made good use of overbought mainframe compute and storage capacity, but I would bet a HA cluster of a couple of dual CPU, 1 GHz Dell boxes running Redhat and using NAS or cheap VLD SCSI RAID storage would have done the job with four times the performanc and at less cost than 11% of the mainframe's maintenance costs alone.

Really overkill

[Anonymous Coward]

At work, I use 4 SGI 1450 servers (Dual Xeon each) which fiber channel storage to store 2000 accounts (NFS, SMB, IMAP, SMTP). 1.8TB total disk storage, 4 DLT stackers for backup.
Each user stores all of his data on the servers. The acounts are 50 % MS Windows/Office users and 50 % CAD/CAM users (CATIA on SGI Iris Workstations).

A mainframe to store only 700 accounts is really overkill ! Annual maintenance costs of such a beast probably exceed the cost of my 4 x86 servers !

How a Mainframe works

[pcs305]

I note that there is quite a few peoples that do not know how things are done on a mainframe. I will TRY and clarify. If you have an average box, say 400 mips, there will be a couple of things happening on this box. Starting of with the OS, OS/390 (or z/OS, VSE, VM). Then a network server VTAM and TCP/IP, a Security server, the some DB's DB2, IMS/DB(or some vendor DB). Then transaction servers CICS or/and IMS serving 4000+ concurrent online users logged on to CICS or IMS. Then you may have oh lets say 500+ programmers, system programmers, DBA, Administrators etc, logged on to the OS "shell" TSO doing programming, compiling, admin, editing and in general doing what these kinda people do, maintaining the monster. The there may be a MQSeries or two running handling client connections and messaging applications and client (pc's, server's *nix's) connections to DB2.. (i'm touching the surface here!) So in general there is a little more happening on a mainframe than on you average wintel box. So in order to separate the production and development, and test environments you can go and partition this one little box up into three logical partitions, called LPAR's in dinosaur speak. Each LPAR can be IPL'd (BOOT in dino speak) without affecting any one of the other LPAR's. So now you have one IBM 2064 400MIP box, 3 LPAR'S and still have room to breathe. Add another LPAR, install VM, Load LINUX/390 and reboot the LINUX LPAR. But still only one Linux server on the box? But we have 250 NT boxes to replace? Not to Worry!! under VM on your brand new LPAR on your mainframe box you can begin to start Linux images at will. So in the end we have 1 Box, 3 OS/390 Mainframe partitions, 1 VM partition with 250 Linux servers running. But now the 400 mips is kinda running out of steam. Call up IBM and they will come and add another cpu. And if you were planning ahead the IBM 2064 should have an idle couple of CPU's under the hood not being used. So you call IBM, they give you the code and you go to the master console and issue a "very cpu online" command and off you go. No IPL required, no downtime. Do that on your duel XEON Intel with Windows... any kind of Windows. I'm not going to go into Parallel Sysplex'ing, syscon's and CICSPlexing etc.

Re:How a Mainframe works

[buck_wild]

I'm sure this is a small nitpick, but you 'vary' things online in the mainframe world. Also, you don't do this from the Master console, you do it from the HMC (Hardware Management Console) and it takes a Power On Reset (essentially like pressing the reset button on your PC) to do it.

Re:How a Mainframe works

[Anonymous Coward]

Nah. You can vary stuff on- and offline from SDSF these days, or from any EMCS console program running in batch.

Re:How a Mainframe works

[pcs305]

My intention was not to rewrite the IBM manuals. But ok...lets be more accurate then. The exact command to "vary" a CPU online is : "cf cpu(1),online,vfon" (there is some more parms.. but you can consult the manual for them). You were right, this is actually a "cf" command, (cf is short for configure) and not a "vary" command, although the vary commands are the more commonly used ones. About the console. This is from the MVS System Commands manual: "You can enter the CONFIG command only from a console with master authority. "

Re:How a Mainframe works

[pcs305]

Oh yeah...no "power reset".

Re:How a Mainframe works

[buck_wild]

So sorry. You're correct, of course. I must have been on crack at the time of posting.

When my company switched from OS/390 to a zSeries box, we underestimated our processing needs (having gone from 10 cpus to two high-powered cpus). That said, we needed to turn on another zSeries cpu and I believe that (at least in my shop) required a POR, and needed to be done from the HMC.

linux a true competitor of windows?

[Anonymous Coward]

"And robust Linux kernel support for very large servers--those with more than eight processors--will be needed for the open-source operating system to become a true competitor to Unix, Windows and OS/390 on larger servers."

Dear Tard-

[Anonymous Coward]

Read the article and the previous posts... The e-mail server is running in an logical partition on the mainframe, along with other applications that are running one the same mainframe in other logical partitions.
Dumb ass.

Oh puh-lease I assume this is a joke???

[coupland]

Two points of contention here folks:

1. Linux on big iron
You're telling me that running a 700-user e-mail system on Linux is an example of Linux on big iron? Sure the server is big but I could do the same job on a medium-range Intel workstation. Are we supposed to be impressed by this feat of server load balancing? Whooo.... 700 POP accounts on a single server, it's magic...

Second point:

>the move allowed him to avoid spending $150,000 on new hardware and software for a Microsoft Corp. Exchange upgrade

$150,000 for a 700-user Exchange infrastructure?!?!? Where does he work cause I thought my company liked to throw money into the wood chipper! You could easily support 700 users with full redundancy for $60k. Ever seen FUD working in the opposite direction? You have now.

Not very well

[Anonymous Coward]

They would do better to port and run BSD or AIX.

VM gives access to these things

[Anonymous Coward]

I've been told (though I'm not a mainframer myself) that this is one of the benefits of running Linux as a "guest OS" under VM. Supposedly, VM makes a lot of things totally transparent to the "guest OS".

Re:VM gives access to these things

[Anonymous Coward]

Actually... Linux for S/390 (or z/Series) knows how to talk over the channel interfaces to I/O devices.

VM just virtualizes the hardware and allows you to share the processor, memory and in certain ways the disk (DASD) storage.

What running Linux under VM buys you is you can run hundreds (or thousands) of Linux systems on one box. VM handles the system management of the entire processor complex, while each Linux guest goes off and does it's thing

(old timer VM sysprog)

Consider benefits of "Logical" network

[Anonymous Coward]

Everyone is completely unimpressed about an email server running 700 users. Guess what? So am I.

Stop for a minute, and consider the things that can be done on a mainframe that CANNOT be done on other systems. First, consider the potential of VM (now termed z/VM, I think). VM alone is spectacular -- and it's old technology. One can partition a mainframe and load VM on 1 or more partitions. For each VM instance, one can load many "guest" operating systems (MVS, Linux, another instance of VM, etc.). Each guest operating system runs independently. With this in mind, one can set up a "virtual network" of many servers talking to one another using TCP/IP, but with the help of "hypersockets", this "network traffic" is really running at internal hardware speeds.

For those of you that are biased towards PCs, do yourself a favor and find out what other systems can do (that your PCs cannot!).

Cheers!

Re:I feel compelled to quote Scott McNealy

[jedidiah]

Actually, Unix is supposed to be architected specifically to allow the trailer trash and the bluebloods to next to each other in perfect harmony. Is this Sun's way of admitting that they don't design their Estates well enough to accomodate a wide variety of occupants?

Although, the key thing that is not being said here is: Next to zOS, Solaris is just a "double-wide".

Ha!

[Chazbot 2002]

Likely scenario is they didn't have any other software running on the mainframe, so instead of turning it into a giant space heater, they thought they'd keep the sucker plugged in to run e-mail.

700 User e-mail systems...

[andrewski]

Damn, it kind of sounds like overkill to use a z-series mainframe to handle a measly 700 e-mail accounts. A 486 should be quite sufficient for that.

Re:700 User e-mail systems...

[Anonymous Coward]

At an ISP, once, a while ago, we handled a user community of 12,000 accounts with a 128MB PPro200 and FreeBSD, sendmail, qpopper. Worked fine.

Whats the big deal

[Anonymous Coward]

You always hear all this hype about Linux is such a "great" OS and how so many people use it, why is it noteworthy that a company installed Linux on their mainframe? Big fucking deal.

Another IBM buzzphrase

[Anonymous Coward]

Is it me or is IBM the only place where they use terms like "big iron" or "bare metal" in reference to their machines?
Please, let IBM use their lingo, but don't let it pass into the mainstream by propogating their terminology on headlines...

Re:Another IBM buzzphrase

[pcs305]

Not IBM's term but the users and media's term for Mainframes.

Oh, wow. 700 users.

[Anonymous Coward]

Be still my heart. Heck, I'll bet my Playstation 2 would be able to support 700 users with a Linux kit. Surely, there are a few zeros missing from that number.

Re:Overkill? Not at all.

[Anonymous Coward]

How much $26K of that was for Bynari Insight?

The article also says that they are only using 10% of their CPU for mail, which versus an additional box (or two because they consider the service "critical") is not so bad.

mainframe?

[Anonymous Coward]

back in 1997 i ran 7000 email accounts off a pentium/166 with 128 megs of ram. big deal. i was running freebsd 2.x.

Re:Overkill? Not at all.

[Anonymous Coward]

Great. Does this box also run SAP, or any other application at all besides Exchange?

Does it run whatever custom IBM-based (CICS?) applications the company might still need to run because there is no equivalent on other systems? Is this mainframe going to require either paying for 700 client licenses or a 700-user server license, or do you pay for the unlimited user access license? etc.

What is the cost for all the OTHER boxes and licenses you need to allow your Exchange Server box to function in a Windows network?

Re:Overkill? Not at all.

[Anonymous Coward]

Is it worth the $26k to not have to worry about an extra physical box? The administration is the same, it is just running Linux on a zSeries for $26k vs. running Linux on a x86 SMP for $5k.

What am I missing? Does the $26,000 include a bunch of consulting services that they needed? $26k to have the IBM name and support?

The $26K gave them enough CPU power to run TEN of those boxes, bringing the per partition cost down to $2600, vaguely half of the $5K box you pictured... plus it buys them the staggering I/O bandwidth in the zSeries hardware which you just can't get on x86, and it provides them with a number of helpfull features, including the ability to do (nearly instant) failover within the box, and backup/restore in linux is a non-issue, the linux system is backed up as part of the normal 390 backup process, so if disaster strikes they only have *one* machine to restore, not several... when the 390 tapes finish applying you just throw the switch and presto, everything is back up and running. Plus doing it on a mainframe can give them live upgrades and replacements of much of the hardware, with only minimal distruption (possibly none at all - I've seen a failed processor be taken offline and replace with a new one with only a couple jobs getting toasted (the poor suckers that were exectuing when it went dead) - newer predictive failure hardware will actually allow it to happen without killing jobs, they are simply moved to another processor when the hardware detects that theirs is about to fail.)

never underestimate the bandwidth

[Anonymous Coward]

of a winnebago loaded with dat tapes hauling down the highway at 45 mph.