Q2 2004 Desktop Hard Drive Comparison: WD Raptor vs the World
by Anand Lal Shimpi on June 7, 2004 12:05 AM EST- Posted in
- Storage
The Test
Our hard drive test bed is designed to shift the bottlenecks, as much as possible, onto the hard drive, but while still within reason. To accomplish that purpose, our test bed is configured as follows:
Intel Pentium 4 Extreme Edition 3.4GHz
Intel D875PBZ Motherboard
1GB DDR400 SDRAM
ATI Radeon 9800 Pro (128MB)
Creative Labs Audigy
Ultra ATA/100 or Serial ATA 150 cables were used where appropriate
The important drivers used are as follows:
Intel Chipset INF 5.1.1002
ATI Catalyst 4.5
Windows XP Service Pack 1 (no further updates were installed)
What's important to point out is that although we could have outfitted our test bed with 256MB of memory, we wanted to avoid over-exaggerating the performance impact of the hard drive. After all, if your system is swapping to disk a lot, you should be considering a memory upgrade before or in tandem with a hard drive upgrade.
The tests we run are as follows:
Business Winstone IPEAK - a playback test of all of the IO operations that occur within Business Winstone 2004.
Content Creation IPEAK - a playback test of all of the IO operations that occur within Multimedia Content Creation Winstone 2004.
Business Winstone 2004 - the official Business Winstone 2004 test suite.
Multimedia Content Creation Winstone 2004 - the official Multimedia Content Creation Winstone 2004 test suite.
SYSMark 2004 - the official SYSMark 2004 test suite.
Far Cry Level Load Test - a timed test of loading a level in Far Cry.
Unreal Tournament 2004 Level Load Test - a timed test of loading a level in Unreal Tournament 2004.
More details about each individual test will appear in the section of the review dedicated to that particular test.
Facebook
Twitter
RSS
50 Comments
View All Comments
MikhailT - Wednesday, June 9, 2004 - link
For a gamer, it would be a better idea to get a single 74gb raptor instead of raid0 with 2x36 raptors. I don't think there will be any difference between both situation. Raid0 might have data failure issue over long term no?ElFenix - Wednesday, June 9, 2004 - link
I'd like to see the SATA version of the 7200.7 myself, SR generally feels that the SATA version is somewhat faster than the PATA version.Also, about the Hitachis... they tend to 'meow' at you every once in a while... supposedly that increases their reliability, but when i'm going for silence it isn't wanted. When silence is key i'll go with the ultra-quiet, reliable, non-meowing, still fast, and dirt cheap ($0.35/gig) 7200.7
T8000 - Tuesday, June 8, 2004 - link
#36, it is nice to know you did get a performance boost, but I would like to ask what drive you had before and if you bought the 74 GB Raptor.This is important, because there is a large performance difference between the latest 7200 RPM drives and the early sub 20 GB ones.
Also, SCSI drives are famous for their loud whining noise, so a lot of people I heard would not even use a SCSI drive if it would be free, unless they become more silent, so this may be a good reason why SCSI drives are not used much in workstations.
Tostada - Tuesday, June 8, 2004 - link
The SATA Hitachi Deskstar 7K250 (which has 8MB cache and a 3-year warranty) is generally cheaper, faster, and quieter than every comparable drive. Well, the Samsung is a little quieter. The Hitachi 7K250 is about as fast as a Raptor 36G, though. In my experience, the only practical drives to buy these days are:Samsung for ATA
Hitachi 7K250 for SATA
Raptor 740GD for SATA if you want the absolute best performance.
Look at NewEgg's current price of the Hitachi 7K250 SATA line with 8MB cache and 3-year warranty:
80GB = $74.00 delivered
160GB = $103.50 delivered
250GB = $194.00 delivered
Raptor 740GD = $200.00 delivered
The Raptor 740GD is 25% faster in some situations. Still, in most systems I would prefer to spend $200 for a RAID of two 160GB Hitachi's instead of a single 74GB Raptor.
I see many people still recommending WD's non-Raptor drives, which just don't keep up. Here's some stats from StorageReview.
High-End DriveMark 2002:
Raptor 740GD: 585 IO/sec
Raptor 360GD: 467 IO/sec
Hitachi 7K250: 442 IO/sec
WD800JB: 375 IO/sec
StorageReview Gaming DriveMark 2002:
Raptor 740GD: 749 IO/sec
Raptor 360GD: 588 IO/sec
Hitachi 7K250: 588 IO/sec
WD800JB: 477 IO/sec
WB99 Max Read Transfer Rate:
Raptor 740GD: 71.8 MB/sec
Raptor 360GD: 57.4 MB/sec
Hitachi 7K250: 60.4 MB/sec
WD800JB: 49.3 MB/sec
Idle Noise:
Raptor 740GD: 42.3 dB/A
Raptor 360GD: 43.1 dB/A
Hitachi 7K250: 41.5 dB/A
WD800JB: 45.0 dB/A
tmhartsr - Tuesday, June 8, 2004 - link
Recently upgraded my primary desktop to Raptor 10K. Actual improvement in everyday system performance and quickness is very noticable! An excellent practical measure of disk performance is writing/restoring a Ghost Image between two of these various drives. The difference is strikingly clear in this real world measure. I think disk performance has been much overlooked recently and deserves much more attention. Also that SCSI 320 should always be included in these comparisions. SCSI 320 is under-utilized in high end systems? Also what effect will new PCI Express boards have on HD performance and development?Kravahn - Tuesday, June 8, 2004 - link
A little clarification... I'm used to seeing frank recommendations on AnandTech, and this was more than ambiguous. It should have said... 'if you want the best performance possible, the latest Raptor is for you; with that in mind, nearly equivalent performance, and certainly more bang for the buck can be had with the current 8MB PATA iterations tested here.'Kravahn - Tuesday, June 8, 2004 - link
Another point regarding final analyses... a 10% increase in performance is definitely notable, but when that 10%increase relates to a 39 second vs. a 42 second load time, it becomes negligible. It seems silly to me to pay more money for less storage to save three seconds. The geek in me loves the numbers, but as a reseller it's hard for me to sell a product just because it's a little faster, especially when my customer would be sacrificing 50G of storage. I think the summary should include a bit of reality and not just factual conclusions.Mackintire - Monday, June 7, 2004 - link
demonbug - Monday, June 7, 2004 - link
First of all, great HD performance comparison - I just have a nitpick. My only comment is in regards to the game loading test. You must have one quick thumb on the stopwatch to measure down to the ten-thousandth of a second as you show on the graphs. I know, probably comes from averaging, but come on - round it to the nearest tenth, or hundredth at least (if you think you were really that quick with the stopwatch). Didn't they ever teach you about significant digits in school?GOSHARKS - Monday, June 7, 2004 - link
discussion regarding the article in the forums:http://forums.anandtech.com/messageview.cfm?catid=...
i have to say that the article really suprised me and the results are quite INTERESTING