Tell me more ×
Super User is a question and answer site for computer enthusiasts and power users. It's 100% free, no registration required.
up vote -2 down vote favorite

If I start a software process that uses 100% CPU, and keep it running many days, is it going to crash the computer in a short time (one month)? I don't think so but I see some guys talking about these and I don't believe it, because, of course, the fan keep the processor cold.

share|improve this question
I would say: Yes but no... Will not fry any hardware piece but maybe the CPU. The only thing is that your PC will be a pain in the neck to use while the CPU is taken at 100% – r0ca Jun 27 '11 at 12:30
Please make a question out of a problem, not purely based on interest. You are asking a yes / no question that doesn't have a yes / no answer, because it really depends on in which context it runs. I can say "No, the process itself won't cause the computer to crash" and "Yes, if you have bad hardware the computer will crash." and "No, if you run this on a super computer it is very unlikely that it will crash." and "No, I have a server that has been running X for months..." and "Yes, my computer crashes within 1 hour if I do so."... :) – Tom Wijsman Jun 27 '11 at 12:51
Consider "How can I decide what the system requirements are for running a heavy process stable for months?" or "How can I verify that my computer is stable enough to run a heavy process for months?" which can really help you solve your problem... – Tom Wijsman Jun 27 '11 at 13:00

closed as not a real question by Linker3000, Tom Wijsman, Sathya♦ Jun 28 '11 at 11:35

It's difficult to tell what is being asked here. This question is ambiguous, vague, incomplete, overly broad, or rhetorical and cannot be reasonably answered in its current form. For help clarifying this question so that it can be reopened, see the FAQ.

4 Answers

up vote 4 down vote

Yes, or no!

There's too many variables to give a definitive answer - yes, processor overheating is a possibility, but it also depends on the robustness of the code, its data management routines (garbage collection), robustness of the system board, memory timing, power stability. system cooling effectiveness.....it's a 'try it and find out' situation.

share|improve this answer
up vote 4 down vote

All computer components are built to tolerances and have certain inbuilt "error rates". Running a computer on a heavy duty cycle for a long period of time will increase the chance that you hit one of these errors during the course of your program running.

As an example it is not unknown (though it is relatively uncommon) for bits to instantaneously "flip" in DRAM modules and as a result ECC memory is recommended for high-uptime servers as it can correct the data "in-flight" before your program has anything to do with it.

In a study by Google they found that in DRAM memory sticks there were up to:

4,000 errors per year

That may not sound like a high fraction, but bear these factors in mind, too: each memory module experienced an average of nearly 4,000 correctible errors per year, and unlike your PC, Google servers use error correction code (ECC) that can nip most of those problems in the bud. That means an correctable error on a Google machine likely is an uncorrectable error on your computer, said Peter Glaskowsky, an analyst at the Envisioneering Group (and member of CNET's blog network).

Read more: http://news.cnet.com/8301-30685_3-10370026-264.html#ixzz1QTxjigI8

That equates to somewhere around 330 memory faults per month.

If you care about running a process for a long period of time then you'll need to keep it cool (as temperature can also affect bit-flip action), make it as rock solid a system as you can (premium components) and make sure that wherever possible error correction is in use.

share|improve this answer
Most of those memory faults would be in data, not executable code, at least on my box with my usage. They would cause problems but not crashes. – CarlF Jun 27 '11 at 15:08
up vote 3 down vote

When you say crash, if you mean physically damage, then that is highly unlikely - It would really require there to be a significant hardware fault, and in that cause your computer would likely be heading for a failure anyway.

If you mean cause the software, or operating system to stop functioning correctly, or stop all together then that is more possible.

If you genuinely have the CPU nailed at 100% then there will be very little opportunity for your operating system to perform the little house-keeping tasks it would normally run periodically and so over time your computer could start to malfunction.

Also, if your program is using 100% of the CPU, this could also indicate that your computer may not be up to the task, which could cause the program itself to fail.

Ultimately, though, it's going to be hit an miss. Computers do crash, even when not overloaded, overloading them makes it more likely but not certain.

share|improve this answer
up vote 2 down vote

Yes, it could happen. However, no, it's not supposed to. If the equipment has a weak point, you may well find it. If it's all up to spec though, it shouldn't be a problem.

share|improve this answer

Not the answer you're looking for? Browse other questions tagged or ask your own question.