If this is your first visit, be sure to check out the FAQ by clicking the link above. You may have to register before you can post: click the register link above to proceed. To start viewing messages, select the forum that you want to visit from the selection below. |
|
|
Thread Tools | Display Modes |
#1
|
|||
|
|||
Interesting someone posted a link in the ABIT group - no benefits from RAID 0
Well no practical benefits on DESKTOP PCs not servers obviously . The
article points out artificial benchmarks come out much better but not real world use. http://www.anandtech.com/storage/sho...tml?i=2101&p=1 Im flabbergasted because thats exactly what I posted before. Id read it didnt make much difference and that benchmarks came out OK but not a big difference in real world performance. This was long long ago. But then as I posted in the other group I could swear that Id read an Anandtech article later on recommending raid 0 for a desktop. And several skeptics who used to make fun of the ATA 100-133 transition as a marketing scam vociferously started defending RAID. And of course zillions have touted it all over the newsgroups and at various websites. I thought I was out of date and that maybe the newer hard disks and raid technoloigy had made it worthwhile. Hmmmmmmm, subjectively as I posted - it "feels" snappier. This must be a really powerful mass delusion or maybe Im reacting to very tiny differences. Even now as I said - before I did it , a website tested it for gaming and there was no gain in framerates etc but the one thing even skeptics claimed was that things seemed to load faster. In this test they even looked at game loading in FAR CRY and found virtually no advantage and think increased chance of hardware problems doesnt make it worth it at all. Now heres my question - Anyone else feel a subjective improvement in performance? And what kind of apps would have any kind of real world benefit on a desktop? Heres the conclusion from Anandtechs article: Final Words If you haven't gotten the hint by now, we'll spell it out for you: there is no place, and no need for a RAID-0 array on a desktop computer. The real world performance increases are negligible at best and the reduction in reliability, thanks to a halving of the mean time between failure, makes RAID-0 far from worth it on the desktop. There are some exceptions, especially if you are running a particular application that itself benefits considerably from a striped array, and obviously, our comments do not apply to server-class IO of any sort. But for the vast majority of desktop users and gamers alike, save your money and stay away from RAID-0. If you do insist on getting two drives, you are much better off putting them into a RAID-1 array to have a live backup of your data. The performance hit of RAID-1 is just as negligible as the performance gains of RAID-0, but the improvement in reliability is worthwhile...unless you're extremely unlucky and both of your drives die at the exact same time. When Intel introduced ICH5, and now with ICH6, they effectively brought RAID to the mainstream, pushing many users finally to bite the bullet and buy two hard drives for "added performance". While we applaud Intel for bringing the technology to the mainstream, we'd caution users out there to think twice before buying two expensive Raptors or any other drive for performance reasons. Your system will most likely run just as fast with only one drive, but if you have the spare cash, a bit more reliability and peace of mind may be worth setting up a RAID-1 array. Bottom line: RAID-0 arrays will win you just about any benchmark, but they'll deliver virtually nothing more than that for real world desktop performance. That's just the cold hard truth. |
#2
|
|||
|
|||
On Sun, 04 Jul 2004 11:25:58 GMT, "
wrote: Well no practical benefits on DESKTOP PCs not servers obviously . The article points out artificial benchmarks come out much better but not real world use. Heres some posts at websites from RAID users : --------------------------------------------------------- The 10k drives in RAID0 give you amazing performance. If you dislike loading screens in your games, a RAID0 with two of these drives IS a good solution. Personally, I run a RAID0 with two 36GB Raptors at home, and I love it. Game load times are fairly nonexistant. I've tried going back to a single drive and had to switch back - I just didn't have the patience for it any longer -------------------------------------- Overclockers Cafe Conclusion The practical value of RAID 1 stands on its own merit. RAID 0 obviously gives us faster access times that did seem to make a difference in load times for programs which is beneficial for the multitasking business environment. As far as gaming is concerned, there is no real statistically significant improvement. Actually, the results are a dead heat. You don't lose anything by running RAID 0. Two 80 gb hard drives equal 160 gigs here where in RAID 1 they equal 80 gb of storage. So there you have it; if you want faster speed where every little bit helps, run RAID 0. While it won't really help you get more frames per second it will speed along other apps making life more pleasant between games. ----------------------------------------------------- SATA and Raid 0 My two penn'orth, then: 1. Correct. My IDE Raid 0 array is significantly and noticably faster than my old single drive setup, especially when installing programs and loading games levels (to use two data-transfer intensive operations as examples). I would imagine that the difference with a SATA Raid 0 array would be comparably significant. -------------------------------------------------- |
#3
|
|||
|
|||
" wrote in message ...
Well no practical benefits on DESKTOP PCs not servers obviously . The article points out artificial benchmarks come out much better but not real world use. I've often wondered if 2 smaller drives raided would be similar in performance to a single larger drive. Say you've got a raid of 2 x 120 gig drives and compared that to a single 240gig drive. The actual bits of data on the 240gig drive will be smaller so the performance should be much greater. OR the 240gig drive might be 2 platter compared to a single platter for the 120gig. If everything else is equal then it's like having a raid inside the single drive because it is reading from 2 platters at once instead of one. The raid is also reading from 2 platters at once, they are just seperated. Personally, I thought raid was much faster but I had it a while ago on 40gig drives with an athlon 1.4. -- Michael Culley |
Thread Tools | |
Display Modes | |
|
|
Similar Threads | ||||
Thread | Thread Starter | Forum | Replies | Last Post |
Last/Fastest cB0 stepped 'gray zone' Celerons work natively on Abit ZM6/BM6? | pgtr | General | 15 | July 9th 04 07:29 PM |
Abit IC7 MAX3 and SATA | Rollin 4 Eva | General | 2 | April 4th 04 05:33 PM |
Im pissed at ABIT ! Continuing ABIT kx7-333R woes | [email protected] | General | 2 | January 3rd 04 08:54 AM |
Interesting Article about cpu cooling | Robotnik | General | 5 | September 15th 03 02:26 PM |
Motherboard problems - abit and Asus | [email protected] | General | 1 | August 31st 03 08:13 PM |