Slashdot Mirror

Even a single anecdote would disprove your theory of 'thousands of years'.

It is not a "theory", I offer a mathematical proof. You, on the other hand, would not offer even an anecdote.

There is no such thing as 'thousands of years' of runtime on a drive,

Not on a drive, but for an array — a RAID5 with disks failing randomly will survive for millennia before two unrelated failures happen within the period of replace/rebuild-time of each other.

I'm sure you won't understand the content of this article

Ah, how insulting... I don't think, you understood it :) They take their fancy charts from a NetApp's "study":

The NetApp comparison is not specific about the bit error rates of the devices tested, the reliability of the drives themselves, or the length of the period over which the probability of data loss is calculated; therefore, we did not attempt to reproduce these specific results. The important point to observe in figure 1 is the stark measured difference in the probability of data loss between RAID-5 and RAID-6.

That's a rather uncritical acceptance of data supplied by the vendor of storage solutions obviously interested in selling bigger boxes and more of them.

And, no doubt, they too populated their boxes with identical drives leading to correlated failures. Do not do that.

For a single drive, go with the most reliable model. For a RAID, however, be sure to mix different manufacturers, models, and batches to avoid correlated failures...

Because, if the failures are random, your mirror or even a large-count RAID5 will do fine for millennia, assuming you replace the failing ones in a reasonable time.

But if the drives are all the same, they may all — after spending the same time in the same enclosure under the same load — fail for the same reason at the same time. Having hot-spares or multiple redundancy will not help you...

While it is, indeed, prudent to keep a cold spare on the shelf, wasting a slot in your enclosure for a "hot spare" is just that -a waste. Here is my proof of it, but you can find other people telling you the same thing.

Aha! Found the theoretician!

Illustrating that while, in theory there is no difference between theory and practice, in practice there is.

My Personal file server is software RAID-5 with a hot spare and a replacement drive on the shelf

While it is, indeed, prudent to keep a cold spare on the shelf, wasting a slot in your enclosure for a "hot spare" is just that — a waste. Here is my proof of it, but you can find other people telling you the same thing.

It is extremely unlikely, that a second disk will randomly die on you during those few hours it will take you to replace the first one with your cold spare and for the array to rebuild. What you want to avoid is correlated failures — when multiple drives fail for the same reason (such as a firmware bug, manufacturing defect, or an environmental factor — like heat).

But having a hot spare online is not helping against that either — buy drives from different manufacturers, different models, and from different batches.

Oh, and if by "software RAID-5" you mean anything other than ZFS (RAID-Z), then you really ought to upgrade.

I currently disallow usage of my software by people owning Che Guevara T-shirts and other items bearing the scumbag's liking. Perhaps, it is time to make the license more encompassing by prohibiting all Communist-sympathizers...

I have used your software to generate images of Che Guevara and it does so very well. Thanks!

I currently disallow usage of my software by people owning Che Guevara T-shirts and other items bearing the scumbag's liking. Perhaps, it is time to make the license more encompassing by prohibiting all Communist-sympathizers...

Friends don't let friends join MySpace....

Both EVITE and Wikipedia have deleted the little picture, that I wanted to use as my own logo on my own user-page. Evite simply suspected I used someone else's artwork, but Wikipedia acted in full knowledge, that it was mine — they just wanted me to change the license to allow everyone in the world to use it...

There is a feature on Evite.com, which lets you associate your own icon with your "account". Obviously, using copyrighted images is prohibited.

Well, the geniuses at Evite have deleted my logo, which I created in Paintbrush back in 1993 (before switching to Unix for good), because — they thought — it can't possibly be my own creation...

Well, ass-covering, ignorant dimwits working for a corporation... Spit-spit-spit...

Years later, the same image is forcibly deleted by Wikipedia — where it was only used on my own user-page.

The idiocy spreads...

Maybe, there is some artistic merit to that poorly-drawn cat on a castle wall? Should I try selling it or something?

4 core CPU has no use at homes unless you are content creator. I'm software engineer, I don't think that any of my colleagues I work with knows how to write app that will take advantage of 2 cores; let alone 4.

Well, fortunately, some of this software has already been written just for you and your colleagues. Check out make(1) manual page — look for the -j option...

And no, it is not only for software engineering either. Every time I come back from vacation, I use make to convert my digital pictures from the lossless "raw" format of the camera to the lower resolution JPEG for the web-pages. Having four CPUs makes that process four times faster. Great idea, uhm?..

Your colleagues may be doofusen, but people, who will finally bring us reliable speech-generation and parsing (as an example) will certainly be smart enough to take full advantage of the multiple processors.

Meanwhile, you can schedule a meeting to discuss using OpenMP in your company's software... Compilers (including Visual Studio's and gcc) have been supporting this standard for some years now.

it can handle multiple catastrophic disk and machine failures.

I tried to crudely calculate a RAID5's MTTF recently, and even if I assume, the drive-manufacturers are exaggerating their drives' MTTFs ten times, I'm still getting MTTF of an array counted in centuries — assuming a failed-drive is replaced within a couple of days.

Here are my attempts (the text is the Gnuplot script, which produces the graphics), what do your company's experts say?

Even if my calculations are wrong, I suspect, the a failure of another disk, while the RAID is recovering from an earlier disk-failure is so improbable (even if the RAID spans dozens of drives), no efforts to reduce that already minuscule risk can possibly be justified. The companies peddling such reductions (RAID6 is how some solutions are called) are praying on their customers' being bad in Statistics...

Now, for RAIDs spanning many hundreds of drives — maybe...

But if it did, would one be able to use epoll to make tail -f more efficient? Or is that, whan [id]notify are for?

As for mmap() -- please download my simple program and try to get it to work on Linux.

You just need to call mremap after the ftruncate call.

Anyway, try to get my little program to work on Linux (without local buffers) and send me the diff...

Here, try this little program. Compile and link with -lbz2...