In many ways I'm a hardware guy. I enjoy building infrastructure in datacenters from bare metal. Yet I can't think of a single use I would have for these IBM mainframes, nor even what they run (DB2?).
IBM's product line just seems completely irrelevant to modern tech companies.
Think of them like old, proven architectures of yore that run virtualization stacks with APIs with the same kind of capabilities of Docker and you'll understand how awesome they could be if we as an industry put more effort into adopting them as platforms (sans enterprise BS vendors though). You can run Windows and Linux on modern mainframes as well, so they're handy there as well. Add in features that are very, very mature (like, since the 80s) like hotswap CPUs and memory that VMware has added a few years ago themselves. If you're in a typical F500 with terrible, fragmented IT management, mainframes are a breath of fresh air practically because there aren't roving bands of sales goons trying to sell you more management software driving wedges between different silos of dysfunction.
If you'd like to view them more from a hardware deployment perspective, you can think of them more like the Dell Poweredge VRTX series than your usual decoupled stacks of network, pizza box servers, and SAN chassis. Cisco UCS is more connection-oriented with the emphasis upon making your network topologies far more flexible than with mainframes, so mainframes are compute-oriented versions in that respect with historically weaker support for scaling out with interoperability across the rest of your network infrastructure (not sure if anyone at IBM or CA has seriously taken standards like BGP and OSPF into account for mainframes, that is). People still remote into mainframes with TN3270 commands, I know we had customers still asking for that as of 7 years ago with no expectation of sunsetting.
The mainframe market is still $10B, and the fact that you can't think of a good use for one does not mean that IBM's product lines are irrelevant. The market should be addressed by major hardware manufacturers, there is still profit to be made here.
The fact that you are comfortable as a "hardware person" saying things like this publicly is a pretty clear indication that your world is much, much smaller than you think it is, relative to the size of the real world.
No doubt. "Big iron" for me is something like a $30k Dell R910 (pretty beefy for commodity x86). I'm guessing these mainframes go for at least an order of magnitude more per unit. A sibling post added some interesting facts (and without the condescending tone of your post), but the question remains: if the hardware is so superior, why aren't Google et al using it? Surely they can afford it.
You have no idea just how hilariously wrong you are. Just read this passage from an Economist article about IBM mainframes:
> At any rate, the mainframe is a hugely profitable business for IBM. Only around 4% of the firm’s revenues come from mainframe sales. But once additional hardware, storage, software and all kinds of related services have been factored in, the mainframe accounts for a quarter of IBM’s revenue and nearly half of profits, estimates Toni Sacconaghi of Berstein Research.
Read that again. HALF of profits. A QUARTER of revenue.
johansch, you were wrong in such a fundamental way about this subject that it is hard for me to believe you know anything about it at all.
If you have any suggestions about how I can phrase this in a way that makes you both comfortable, and that still makes it clear that I do not believe you have any business speaking on this subject, then I am 100% happy to listen to you. :)
I'm sure you're otherwise intelligent, but this is an area where you should probably just listen.
$10B are spent each year on sales of actual mainframe computers. [1]
The article quoted in the last article claims that everything you sell around mainframes, like services, is a quarter of revenue.
Now, it's your turn to do something for me. Don't respond if you're not willing to read before you speak. I should not have had to explain this to you.
I think you are underestimating the scale of what a Z system can run... You might not have a use but every fortune 500 and banking institution in the world does - and they need it to work, 5 9's isn't good enough.
> IBM Hursley laboratory director Rob Lamb says: “There are 6,900 tweets, 30,000 Facebook likes and 60,000 Google searches per second." The mainframe CICS runs 1.1m transactions per second, which equates to 10bn per day [0]
That equivalence is bogus. If a search was as simple as a single CICS transaction, Google would just run that and be done.
Mainframes are overpriced and inefficient, but they are the only option for a F500 without the in-house talent to build any kind of distributed, fault tolerant system.
If as you say mainframes are overpriced and inefficient, that means there is a great opportunity for some organization to move with a much cheaper, more efficient option.
But people have been predicting the death of big iron for several decades now, yet they live on.
I don't doubt mainframes might be overpriced, but I also suspect the reason they persist is they have yet to come up with a cheaper option, offering the same performance figures.
Long one of the main reasons for
IBM mainframes was the bet your business
software that wouldn't run anywhere
else and that would be too expensive
to rewrite to run somewhere else.
Also, there is a remark that in major
parts of the financial industry, running
an IBM mainframe is nearly a necessary
condition for compliance.
> would be too expensive to rewrite to run somewhere else.
I'm don't doubt that is a major factor. Add to that the major risk that what every new system you move to might actually fail to work or end up costing more.
> If as you say mainframes are overpriced and inefficient, that means there is a great opportunity for some organization to move with a much cheaper, more efficient option.
But isn't that what Facebook, Google, and Amazon are doing? Using massively distributed commodity x86 hardware to eat away at incumbent businesses that would outsource their IT services to mainframes? Last I read, Google is about to go into auto insurance, and all three companies I listed do payment processing.
If software is eating the world, SV behemoths are eating business verticals.
The electrical power ($600/day vs $32/day), floor space (10,000 sq ft vs 400 sq ft), and cooling costs for those mainframes were less than those of distributed servers handling a comparable load. In addition, those mainframes required 80 percent less administration/labor (>25 people vs <5 people); “Mean Time Between Failure” measured in decades for mainframe vs months for other servers.
96 of the world’s top 100 banks, 23 of the 25 top US retailers, and 9 out of 10 of the world’s largest insurance companies run System z
Seventy-one percent of global Fortune 500 companies are System z clients
Nine out of the top 10 global life and health insurance providers process their high-volume transactions on a System z mainframe
Mainframes process roughly 30 billion business transactions per day, including most major credit card transactions and stock trades, money transfers, manufacturing processes, and ERP systems.
The new mainframe delivered in 2010 improved single system image performance by 60 percent, while keeping within the same energy envelope when compared to previous generations. And the newest mainframe which shipped in 2012 has up to 50 percent more total system capacity, as well as availability and security enhancements.
It uses 5.5 GHz hexa-core chips – hardly old technology. It is scalable to 120 cores with 3 terabytes of memory.
A single search on Google could lead to 10x-100x actual requests to the backend system. So the comparison here is not really a fair game.
Second, since I assume, most of the programmers here don't have access to mainframes, it is hard to testify those numbers. Also, since it is a benchmark it will be useful to revel what exactly the task they are using here, otherwise I would simply throw this claim into my 'pure PR mess, don't take it seriously' bin :)
CICS itself is essentially just a way to put
up the forms for a user interface, but
a CICS application usually makes
heavy use of database, say, relational database,
e.g., DB/2 although there may still be some
IMS usage still hanging on.
One use of CICS was for heads down medical
claims processing, across all four US
time zones. The site our team from
IBM Research visited wanted high reliability:
If the site was down for, say, an hour,
then the data entry staff would have to
be called back on a Saturday, for at least
half a day, at a higher rate per hour.
One such outage in a year, and the CIO
could lose his bonus. Two and he could
lose his job. The site was very uptight.
Getting into the glass house was
not easy; might have been easier to get
into the White House Oval Office.
At one time to make CICS more secure,
there was some interest in having
processor hardware support for
address sub-spaces. Another
idea was cross memory where a
program could call and execute, say,
a function in another address space.
There were also data spaces, that
is, address spaces with just data and
no code but that could be accessed
by other address spaces with code.
Net, the IBM mainframes are not really
simple things. Cloning one would not
be easy, and at IBM's next version of
hard/software, the clone could be
unable to run the newer software and
suddenly be a boat anchor.
I have practically zero experience with mainframes, but I've always heard about their insane throughput figures. I've never really seen much on their architecture. Any insight in how they work and do so much?
The mainframes have their own CISC type architecture and typically have massive amounts of cache and a high clock speed (5Ghz and above)
Their instructions sets are also different in that its not strictly of the von-Neumann variety. Mainframes can do things like memory copies directly in memory without requiring copying via registers. This kind-of attacks the von-Neumann bottleneck directly and is good for batch and high volume transaction processing.
The software for mainframes is also typically fused into their kernels, things like CICS and DB2 are not "user" programs, they're part of the OS so I/O is handled much better and things don't "block" as much.
if you want reliability and solid software you don't go anywhere else other than mainframes and minis from IBM (z, i, and x)
The companies that run these do so because they are proven, the languages they support are all business oriented (math is a specialty), and the code bases are vast and stable. Oh, they all do Web-centric work just fine too.
db2 is just fine with SQL and highly optimized as well. Modern is what they are, quit thinking small is modern
IBM doesn't and never has as far as I can see targeted "modern tech companies." They target large enterprises, and research/academia (in the later case often with mainframes on the administrative side, and linux clusters on the research side).
Edit: I believe that the linux server lines have recently been moved to Lenovo though
IBM's product line just seems completely irrelevant to modern tech companies.