Raid 0: Blessing or hype? 380
Yoeri Lauwers writes "Tweakers.net investigates matters a bit more clearly and decides that AnandTech and Storagereview should think twice before they shout that "RAID 0 is useless on the desktop". Tweakers.net's tests illustrate the contrary"
Re:I use RAID 0... (Score:2, Insightful)
Re:I use RAID 0... (Score:5, Insightful)
If you haven't tried it, don't knock it. (Score:5, Insightful)
I personally jumped from a single drive to a 4-drive SATA raid-0 system, composed of 120GB drives from two different manufacturers.
The system screams.
I can't tell you how nice it is to have my computer boot in half the time... how your system feels like you always wished it would feel. You can add all the memory you want, all the processing power you want, but if you can't feed the computer, it's all pointless.
The only thing I wish now was that my system had a faster and/or wider bus that would allow me to take advantage of all the currently unused bandwidth available from the four drives.
Methodology (Score:5, Insightful)
Of course they do. After all, they've spent extra money and time pimping out their rigs.
Re:Sure, RAID 0 is great for data loss! (Score:2, Insightful)
*shudder* (Score:5, Insightful)
That's not to say there isn't a purpose for RAID-0 - it teaches people how useful backups are. The hard way.
Re:Methodology (Score:5, Insightful)
If you've spent the extra money on RAID 0, you're going to believe there's a difference going in. Hell, I've done it myself - I have 2 machines with RAID 0 setups, but that's because they're commonly used for working with multi-gig sized files in photoshop - IE: I actually need the strong sequential speed.
For normal desktop setups, I'd absolutely agree with AT and SR on this one. Unless you're doing massive amounts of large sequential reads/writes, you're just not going to see a difference in speed worth the cost of another drive and the major increase in potential failure and data loss. Remember, by adding that second drive, your chance of failure goes up *exponentially* which is something a lot of hardcore "tweakers" forget.
Re:performance vs. reliability (Score:3, Insightful)
It's not the interface that makes IDE drives less reliable, it's just that manufacturers want to keep server/workstation drives out of desktop machines for good reason - the 10/15kRPM drives need to be cooled, and as soon as people start to put them in desktop machines, they're gonna get a lot of warranty returns. Thereby lowering their profits further, and removing any advantage that they had.
There are two possible choices:
#1 has been done by WD with their Raptor drives, but they are still expensive, and have a low capacity to reduce heat.
#2 is unlikely to work unless all the manufacturers do it at once, which isn't going to happen. And, they can't separate the pro and consumer drives as easily as when the consumer drives were IDE and pro were on SCSI.
There just isn't anything in it for the drive makers.
Re:I support desktop RAID 0 boxes... (Score:5, Insightful)
Let's suppose that both the 80Gb and the 160Gb drives have a possibility of failing in a month of 10%.
Now, with the 1x160Gb you have 10% of having a failure this month, obviously. What's the probability for both drives?
Well, since each one won't fail 90% of the time, the probabilities of both not failing is 81% (0.9*0.9). The rest, 19% is the possibility that one or both fail, therefore, instead of a 10% failure rate, you get 19%... nearly twice!
RAID 0 is a start. (Score:4, Insightful)
Ideally, you should bring hot spots on the disk closer together, which is what filesystem optimization tools do, and have one disk for each "hot spot" on your system. %systemroot%, the swap partition, your system temporary files directory, your applications, and your profile could each be given a separate disk so that the disk head that's sitting there writing your cached files doesn't get hauled off to the other end of the disk to read a plugin from %systemroot% or a write an old dirty block to the swapfile. Old timers will remember dedicated swap disks and swap partitions on every drive, fast dedicated
With enough drives and an OS that's aware of the physical layout, you should be able to get the same kind of performance improvement from RAID 0 on Windows. Hardware RAID, of course, won't help much with the seeking problem because the OS doesn't know it's got two heads to do seek optimization on. Software RAID, if Windows is smart about seek optimization, should give you a superlinear speedup for many workloads.
Re:Sure, RAID 0 is great for data loss! (Score:1, Insightful)
No, because that's not a common form for failure, so it doesn't mean the mirroring is twice as likely to lose data as a single drive. You imply that's mirroring is just as dangerous as striping. It's not.
A service tech loose his balance while replacing a down drive in a HOT Raid-5. He fell backward while squating pushing in the new drive. He grabed another drive in the same array to stop his fall, and pulled it out... Every bad shutdown for a production system, and a very long recovery.
I guess you don't use hot spares? That would be smarter than chairs. With hot spares you can wait until you're fully redundant again before you mess with the hardware.
Re:Not For Everyone (Score:3, Insightful)
A disk-bound application is one where the application's performance is directly proportional to disk speed. EG, a disk-bound app's performance will improve by 10% if you improve your disk I/O by 10%.
Remember with RAID-0 you are not halving your MTBF (mean time between failures), you're reducing it by the inverse of number of drives squared. If the MTBF for a single drive is T, then for an N-drive RAID-0 array it's (1/N^2)T, not T/N as you might assume. Put another way for the math-impared, a 2-drive RAID-0 array is four times as likely to die as a single drive; a 4-drive RAID-0 array is SIXTEEN times as likely to fail.
poor article (Score:4, Insightful)
The fact is that the article readily admits that desktop workloads show poor average IOps (under 1.5) and modest average IO size (23K). Those numbers prove that there is little opportunity to accelerate performance either with parallel access or random access designs. The first tests show clearly that the IO sizes in question leave little opportunity for large transfer gains while the lack of decent command queue depths rules out good load balance with larger stripe sizes. Interestingly, the author didn't provide the stripe size for that test. It's easy to deduce from the chart but it demonstrates his limited grasp of the subject matter.
Regarding the tests dispelling the myth of poor RAID 5 performance, hardly! Poor RAID 5 performance is no myth. First off, the RAID 5 configuration was trounced by lesser RAID 0 IDE drives. Second, the benchmarks consistently avoided writes, notably small writes, where RAID 5 massively fails, and uses a large writeback cache to further hide write performance and to cause the configuration to shine is small read tests. If you are going to sing the praises of RAID 5 for data protection you should probably mention the data integrity disaster that writeback caches introduce. If I were offering the RAID 5 config myself I would feel like I just got my ass kicked.
Ultimately this article is nothing other that a rant by someone who disagrees with others' contention that RAID 0 is of limited benefit. He justifies his position by saying that performance matters when "performance matters", that is specifically when you create disk-intensive loads you can see a benefit. Well, no shit. When you create large command queue depths through multiple disk-intensive processes then you will benefit. Again, no shit. Boot times can get shaved a little. Big deal. Beyond that he doesn't know what he talking about. There's a big difference between RAID 0 being theoretically capable of superior performance and it being a performance value to a desktop user. This is a subjective matter and he fails to make his case. Just how often does he or any other "power user" actually benefit from these unusual workloads and is that often enough to justify the costs?
The quality of any forum depends in the reader (Score:2, Insightful)
Tweakers.net is kinda like /. except it focusses on tech and to where you got some real rocket scientists posting on /. tweakers.net seems to have more kids. Maybe a lack of moderation?
So just as some people hate /. some hate tweakers.net or some other tech site. It all depends on wether the site agrees or disagrees with their point of view.
Nothing upsets some people more then reading that their latest purchase is a piece of shit.
I agree about the language. While speaking dutch is all nice and local it stops it being usefull to roughly 99% of the world population. It is not like dutch people can't read english well enough for even the techiest of articles.
So I partly agree with the parent and disagree with the grandparent. Tweakers.net is just another tech site with its share of bullshit and crap. No better or worse then any other site.
As to my opionon on raid 0 (Use several raids myself including raid 0 for a while) it is definitly faster. Doesn't matter that much for me since only games require the regular loading of stuff from disk in a speedy fashion and the improvement can be lived without. So a level loads a few seconds faster. Yippie. Then again, raid 0 is pretty cheap and if you want those couple of seconds then it makes perfect sense.
The people who are against raid 0 are the same who are against dual processor or large amounts of ram etc etc. They can't afford it and therefore it must suck. Ignore or pity such people but never take their advice. They are truly the ones who said 640k should be enough for anyone (unlike bill gates who apparently never said it).
Re:RAID-0 is stupid. (Score:3, Insightful)
The important thing to remember, Raid (1, 3, 5, whatever) is not a substitute for backups. rm -rf will work on a raid volume prefectly well, as will a lightening strike or thieves.
Article Summary (Score:5, Insightful)
2. So we changed the benchmarks to really need the things that RAID 0 is good at.
3. And now, RAID 0 improves things!
4. Therefore, the benchmarks in #1 were wrong.
Summary of the summary:
I'm looking for my keys under this lamppost because the light is better here.
Oh jeepers, we are talking overclockers here (Score:4, Insightful)
Well I got a very simple solution to that, one that the overclockers I care about all use. It is called a small server with real Raid to store all the "real work" they got.
The game machine is the game machine and it doesn't need to have a long live as it won't be around longer then a year anyway.
Raid 0 fits in the "getting 1% extra fps" scene. It does not fit in the office scene.
Anatech and a whole lot of /.ers just don't seem to get that to some people every bit of extra speed is worth it. You would review a ferrari as a lesser car then a ford focus since a ferrari costs more and who needs the speed.
Does speed matter? Oh yeah, does reliability? Hell no, this ain't a server. Only thing I could loose is a few hours reinstalling windows and my games. I do that often enough anyway whenever a new piece of hardware arrives.
I much rather have Raid 1 then raid 0 (Score:3, Insightful)
On a different note, I really wish that laptops and desktops came with duel hard-drives standard w. Hardware raid 1 installed. Especially laptops.
Re:I use RAID 0... (Score:3, Insightful)
Backups are essential for desktop machines. With current storage technology, they don't appear to be going away anytime soon. Might as well get used to it.
Re:BUSINESS Winstone, not games (Score:3, Insightful)
Most of the time games spend loading is not disc bound, but cpu bound. Decompressing pack files, initiating bsp-trees, ect.
Every modern disk can load 50mb/s. THe largest quake3 level has 27 MB.
Re:Sure, RAID 0 is great for data loss! (Score:3, Insightful)
Exactly. RAID should never be used in place of backups. How often could you have potentially lost data to human error in software usage/config? And how often to hardware failure?
If you suffer from human error with the software while relying on RAID, you lost your data and get a rude lesson in RAID and backups addressing mutually exclusive problems.
Real RAID, buys production systems time to keep going while a (hopefully) hotspare rebuilds or a replacement disk gets delivered for rebuilding.
RAID saves productivity during what should be only a brief period of vulnerability. Backups prevent complete loss. People who use RAID as a backup, don't understand the limits of RAID or the value of real backups.
So many times, I have had to order tapes from a data bank because some user deleted an "important" file from RAID protected storage.
Hell, I am a sole trader, who legally must keep business records for tax purposes, etc. I rsync my records, email, web site, server configs, site documentation, etc across 5 different machines, spanning 3 different architectures and 5 different OSes. On top of that I keep rotating weekly (CDRW) and permanent monthly (CDR) backups.
This might seem like paranoia, but I do it because I easily can and CDR's are cheap. I can also move to any of those machines and resume my emailing, invoicing, doco, etc. Take one of them on the road (Thinkpad or iBook) if business or disaster dictates and not worry that a worm is going to prevent me from earning my living or answering to the tax man.
Use RAID-0, but be smart about it. (Score:4, Insightful)
There are a number of desktop applications that can benifit from RAID-0, but you have to be smart about it.
RAID-0 is perfect for booting an OS and loading large applications. It's also excellent for swap space, and initializing your JVM.
It's less well suited, however, for small documents and anything important (like documents).
Thus, my strategy would be to use a RAID-0 array for my OS, JVM, applications, and swap space, and a non-RAID drive for application data. A good way to achieve this on Linux would be to format the single non-RAID drive and mount it as /home, and install everyting else onto the raid array.
Seems to be a good strategy for a desktop system to me. Add in some backup for the single disk mounted as /home, and if anything goes wrong with the RAID, you're important data is completely protected.
Yaz.
My issue with Anand's article (Score:3, Insightful)
What I was looking for was a 0+1 array, striped and mirrored, using inexepensive drives. I'm one of those old fashioned people that didn't switch to using "independent".
So Anand shows that if you take the fastest drive available, you don't get much by striping it. But what about the average 7200rpm drive, is there a performance increase? Does it get close to a single raptor?
How would you think about using a Raptor as your main drive where application would reside, and a mirrored array of inexpensive 200GB drive to store your various collections of files, would that be a better choice?
Re:RAID-0 is stupid. (Score:3, Insightful)
Sure, you should always keep backups. But restoring from them is inevitably a pain. I keep nightly backups of the important files on my machine. If my hard drive were to fail, I'd still:
That's a pain. Why make that more likely with RAID-0, when you could make it unnecessary with real RAID?
Re:Methodology (Score:3, Insightful)
Asymptotic behavior (linear vs. quadratic vs. ... vs. exponential) is only important when talking about large values of n. Here n would be 1-4. No one's ever going to RAID-0 more than four drives.
When you're talking about a specific change in n, as in 1->2:
...asymptotic behavior is completely meaningless. Every time you say "exponentially" you should have a "with n" that follows it. There's no n left; you plugged in 1 and 2. You've got to make more concrete statements like "you square the probability of not-failure." (Which increases the probability of failure, since probabilities lie between 0 and 1.)
There are no exponentially increasing probabilities. They can be exponentially decreasing (approaching zero). But exponentially increasing functions approach infinity; probabilities are bounded at 1. Graph the function yourself. If it goes over 1, it's wrong. The function is not exponential. More precisely 1-(1-p)^n != omega(e^n). Check the definition of omega [brpreiss.com], specifically the bit that says you need a positive constant.
I agree with your broader point that RAID-0 is unreliable. But your supporting math is bad.