New Posts  All Forums:Forum Nav:

Raid 101 - Page 2

post #21 of 80
1/20/05 at 11:27pm
Quote:
Originally Posted by los_blankeys
i'm not sure why anyone would question a performance gain with raid0. it's obviously going to read/write faster than a single drive (assuming you're talking about the same drives). whether you need the drive speed is a different story. and i have no clue what's controlling the raid in the 7700, mine's still being built...

i wouldn't trust a single drive any more than a raid0. i don't believe in "more likely to fail", just back it up if it matters, raid0 or not.
well said there is no doubt that raid 0 is faster then non raid when comparing identicle drives. and ill add in that with raid 0 each drive gets worked about half as hard to write the same amount of data as a single.
Reply
Reply
post #22 of 80
1/20/05 at 11:36pm
Quote:
Originally Posted by JUSTlN SANE
well said there is no doubt that raid 0 is faster then non raid when comparing identicle drives. and ill add in that with raid 0 each drive gets worked about half as hard to write the same amount of data as a single.

Thats wrong, it writes stripe AND parity information. It's used as much if not more. Iwas writing microcode for Mylex controllers before most people here were born. And for the last time, it's not the fact that it's RAID0, the damn controller is faster, they average 32MB of cache for heavans sake.
Reply
Reply
post #23 of 80
1/20/05 at 11:46pm
Quote:
Originally Posted by Time-Pilot
Thats wrong, it writes stripe AND parity information. It's used as much if not more. Iwas writing microcode for Mylex controllers before most people here were born. And for the last time, it's not the fact that it's RAID0, the damn controller is faster, they average 32MB of cache for heavans sake.
the numbers dont lie read back i posted some. And even recently places like the screensavers on tech tv did a raid vs non raid review where raid won. you can say its not faster but i can say the sky is pink too. fact is every review and benchmark that compared raido vs non raid with the same drives came out with raid 0 being the faster combo. do some research for your self becuase you only look silly in here saying other wise, like the kid in school who claimed his 4 cylinder pinto blew away a corvette on the way to school.
here is a review u can read http://www.overclockercafe.com/Articles/RAID/
like they say in gaming you get no increase in fps or such but you do get faster loading times.
Reply
Reply
post #24 of 80
1/21/05 at 12:06am
Quote:
Originally Posted by JUSTlN SANE
the numbers dont lie read back i posted some. And even recently places like the screensavers on tech tv did a raid vs non raid review where raid won. you can say its not faster but i can say the sky is pink too. fact is every review and benchmark that compared raido vs non raid with the same drives came out with raid 0 being the faster combo. do some research for your self becuase you only look silly in here saying other wise, like the kid in school who claimed his 4 cylinder pinto blew away a corvette on the way to school.
AMD Athlon 64 3000

AOpen AK86-L mainboard

Thermaltake K8 Silent Boost Cooler

Maxtor Diamond Max 9 SATA 80gb HDD

Corsair XMS3500 DDR (x2)

VisionTek Radeon 9800 XT

Generic CD-ROM

Windows XP Professional with all patches and service packs installed.

Results

With the workloads balanced between the two disks, Sandra 2004 Pro's File System Bench was no surprise to us at all.

I'm not saying it not faster, however your comparing a SATA150 controller to a Ultra 133. Duh? Ya think it's faster? Plug that single driver into a 2GB Fiber GBIC and we will se who wins, it's not gonna be the SATA controller.

you could have have a damn mirror and still get better performance than ULTRA 133, it's the controller not the RAID set.
Reply
Reply
post #25 of 80
1/21/05 at 12:47am
Quote:
Originally Posted by Time-Pilot
I'm not saying it not faster, however your comparing a SATA150 controller to a Ultra 133. Duh? Ya think it's faster? Plug that single driver into a 2GB Fiber GBIC and we will se who wins, it's not gonna be the SATA controller.

you could have have a damn mirror and still get better performance than ULTRA 133, it's the controller not the RAID set.
???? The whole point of this was to compair the same drives in a raid or non raid . no one here has said even once that certain drive setups may be better then others what we are compairing in this thread is raid0 vs non raid using the same drives. please read more closely in the future as to avoid confussing your self.
Reply
Reply
post #26 of 80
1/21/05 at 12:56am
Quote:
Originally Posted by JUSTlN SANE
???? The whole point of this was to compair the same drives in a raid or non raid . no one here has said even once that certain drive setups may be better then others what we are compairing in this thread is raid0 vs non raid using the same drives. please read more closely in the future as to avoid confussing your self.

And a non-raid drive on a SATA controller is as fast, and in fact faster than a RAID 0 config.

Here is what you not getting, and hat your article cleary states in the third pararaph. Given to you *have to* or choose to use array Raid 0 (striping) is the fastest of the array choices avialable.

Given that you have a better controller and the same drive then direct attached is better, and safer. That article is so misleading in its wording, typical of people who have only been using the technology for a few years.
Reply
Reply
post #27 of 80
1/21/05 at 12:56am
Quote:
Originally Posted by Time-Pilot
Thats wrong, it writes stripe AND parity information.
RAID 0 doesn't write any parity information.

Quote:
Originally Posted by Time-Pilot
I'm not saying it not faster, however your comparing a SATA150 controller to a Ultra 133. Duh? Ya think it's faster? Plug that single driver into a 2GB Fiber GBIC and we will se who wins, it's not gonna be the SATA controller.

you could have have a damn mirror and still get better performance than ULTRA 133, it's the controller not the RAID set.
No, the review tests SATA in RAID 0 vs. single drive SATA. None of the drives were Ultra ATA133. Try reading.
Reply
Reply
post #28 of 80
1/21/05 at 1:02am
The P4EE is powerful...not sure how worth it though...big price.
Reply
Reply
post #29 of 80
1/21/05 at 1:02am
Quote:
Originally Posted by venom8599
RAID 0 doesn't write any parity information.



No, the review tests SATA in RAID 0 vs. single drive SATA. None of the drives were Ultra ATA133. Try reading.

I did read it, and they use the same damn controller, thats a terrible test, and yes it does write parity, it writes a RIS sector (Raid Information Sector) it's the tracking portion that tells the controller where you data resides. Sheesh, you think the controller saves that somehow? Damn you you have not been at this very long have ya? Ummmm, thats an extra write operation ya know.
Reply
Reply
post #30 of 80
1/21/05 at 1:03am
Quote:
Originally Posted by thecommish16
The P4EE is powerful...not sure how worth it though...big price.
The P4EE is crap, but how does that relate to RAID 0?

Stop threadjacking.
Reply
Reply
post #31 of 80
1/21/05 at 1:12am
Quote:
Originally Posted by Time-Pilot
I did read it, and they use the same damn controller, thats a terrible test, and yes it does write parity, it writes a RIS sector (Raid Information Sector) it's the tracking portion that tells the controller where you data resides. Sheesh, you think the controller saves that somehow? Damn you you have not been at this very long have ya? Ummmm, thats an extra write operation ya know.
I've been around long enough to know that RAID 0 performs better than non-RAID.

So you think a proper test would be to use a different SATA controller for RAID and plain-old SATA? That makes a comparison of real-world performance faulty, since most people mobos that support RAID (most people use onboard RAID now) use the same controller to support SATA. Your way would leave the benchmarks flawed due to the individual quirks of the different controllers, and would not be making a scientific comparison.
Reply
Reply
post #32 of 80
1/21/05 at 1:37am
Quote:
Originally Posted by venom8599
I've been around long enough to know that RAID 0 performs better than non-RAID.

So you think a proper test would be to use a different SATA controller for RAID and plain-old SATA? That makes a comparison of real-world performance faulty, since most people mobos that support RAID (most people use onboard RAID now) use the same controller to support SATA. Your way would leave the benchmarks flawed due to the individual quirks of the different controllers, and would not be making a scientific comparison.
I'll be nice and post a test that at least brings them even, butgbenerallty it's slower. It's all about the overhead, and it always will be, RAID has been a redundancey standard sine I was working on mainframes, not performace, thats fiber. One system requires immense procession, the other does not. There are MANY MANY other examples if you want them.

Reply
Reply
post #33 of 80
1/21/05 at 3:21am
Quote:
Originally Posted by Time-Pilot
I'll be nice and post a test that at least brings them even, butgbenerallty it's slower. It's all about the overhead, and it always will be, RAID has been a redundancey standard sine I was working on mainframes, not performace, thats fiber. One system requires immense procession, the other does not. There are MANY MANY other examples if you want them.
LMAO this noob is to much hes comparing totaly different hardrives . this post is about taking exact same hardrives and controlers and comparing if raid 0 is faster then non LMAO i gota show this to the other guys at work LMAO And besides that we already posted numbers showing in some cases the difference is small or non but over all and most the time its faster. damn dude you make me pee my pants luaghing at you so hard. every one has already told you we know its faster so stop wasting your time trying too fool others into thinking its not.
Reply
Reply
post #34 of 80
1/21/05 at 3:27am
and the argument continues....
Reply
Reply
post #35 of 80
1/21/05 at 5:31am
Thread Starter 

Raid hmmmmmmmm

wow, I had a feeling RAID could turn into a heated debate when I first started this thread,
which I figured would only delay my decision so I ordered my 7700 last week,
here's what I decided...

http://notebookforums.com/showthread.php?t=59962
Reply
Reply
post #36 of 80
1/21/05 at 7:41am
Quote:
Originally Posted by T4sys
wow, I had a feeling RAID could turn into a heated debate when I first started this thread,
which I figured would only delay my decision so I ordered my 7700 last week,
here's what I decided...

http://notebookforums.com/showthread.php?t=59962
there really is no debate at all facts are raid 0 smokes non raid . only one guy here seems to want to confuse you. so he starts talking about controlers and mix and match stats. fact and bottom line take 2 identicle drives and controlers run 1 in a raid 0 and 1 normal . raid 0 will be the faster setup hands down proven science. no debate about that. will you miss not having it with a single drive? probably not . its mostly for people who want that extra boost in speed .
Reply
Reply
post #37 of 80
1/21/05 at 1:08pm
Thread Starter 

RAID upgrade

Is RAID available as an upgrade? Or, is it not a good idea to try an upgrade your hard drive?
Reply
Reply
post #38 of 80
1/21/05 at 1:24pm
Quote:
Originally Posted by JUSTlN SANE
there really is no debate at all facts are raid 0 smokes non raid . only one guy here seems to want to confuse you. so he starts talking about controlers and mix and match stats. fact and bottom line take 2 identicle drives and controlers run 1 in a raid 0 and 1 normal . raid 0 will be the faster setup hands down proven science. no debate about that. will you miss not having it with a single drive? probably not . its mostly for people who want that extra boost in speed .

Read the chart above, numbers don't lie those are the same Raptor hard drives.
Reply
Reply
post #39 of 80
1/21/05 at 1:36pm
Quote:
Originally Posted by Time-Pilot
Read the chart above, numbers don't lie those are the same Raptor hard drives.
Hey Time-Pilot why don't you post the link to the full article and all of the benchmarks instead of just the one chart? I mean game performance is barely affected by RAID0, it is more intensive and large file applications that see the benefits of RAID.

I know the reason why you only posted the one chart, but I wonder if the other people do
Reply
Reply
post #40 of 80
1/21/05 at 1:46pm
"The RAID-configurations not only do well in most stopwatch trials; they also 'feel' faster, reflecting an increase in the overall responsiveness of the system. When coming from a single Raptor WD740GD to two striped Raptor WD740GDs a sense of relief is noticeable. You get used to it quickly, but stepping back to the single Raptor again confirmed that there is a notable difference; the single Raptor felt 'slower'. Sure, it's still a mighty fast drive on its own, but it doesn't come close to a striped setup. For power users with a well-developed instinct for responsiveness, RAID will deliver. For beginners or less-demanding users who spend more time worrying about getting their printer or dial-up connection to work, the difference might not be noticeable. But then again, that's not the target audience, is it?"

- Maybe you are just a beginner or less demanding user Time-Pilot? Is your printer working ok?

http://www.tweakers.net/reviews/515/1
Reply
Reply
New Posts  All Forums:Forum Nav:
  Return Home