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 biggest argument to why you would ever need a faster CPU is often that everything is disk limited anyways, so getting a faster CPU isn't the solution to your performance woes. While, to an extent, this is true, we have seen over the years that quite a few things are just as CPU bound as they are disk bound.
We've shown in the past that even very disk intensive operations, such as extracting a zip archive, can vary significantly with CPU. We've also shown that disk bound benchmarks, such as Winstone, can significantly reduce the performance benefit seen when upgrading to a faster CPU.
More than anything, what we've learned in the past is that there is no one component that significantly bottlenecks the system; rather, it's a combination of all of your components - your CPU, chipset, video card, memory and hard drive - that determine the performance of your system. While one component (e.g. your video card) may be the major determinant of performance in a particular application (e.g. a game), it's rare that the only applications you run are bound by a single component. To put this into perspective, would you ever not upgrade your CPU for a next generation game just because "everything is GPU bound to begin with"? Of course not. Take a 500MHz Athlon and pair it up with a X800 Pro and you'll realize quickly that this sort of logic won't work. So why, then, apply it to hard drives?
Luckily, the average AnandTech reader is smarter than that, and understands the importance of maintaining a balance of performance within his/her system. But here's where the problem resides: how do we measure hard drive performance?
Hard drives continue to be the only component where performance is measured using purely synthetic benchmarks. Our latest CPU review has no less than 12 real world application benchmarks to showcase the performance of the CPU. Our last GPU review took 13 games, and we benchmarked them to help you decide what video card would run games the fastest. But look around for hard drive reviews and you see a bunch of numbers that are, at best, great hypothetical indicators of performance or over-exaggerations of the impact of a particular hard drive. If we converted all of our CPU and GPU reviews to a similar set of synthetic benchmarks, you would quickly find a replacement site for your information, so why settle for the same treatment with hard drives?
We've tried numerous times in the past to bring hard disk reviews to AnandTech, but the limitations have seemingly been unsurmountable. At first, we couldn't get drives, then we had no good benchmarks; then, we got drives and benchmarks, but had no time to tackle the testing. Finally, we are able to offer a good test suite, review the drives that you want reviewed, and do so on a regular basis.
In order to kick off our new suite of drive benchmarks and our return to hard drive reviews, we figured that we'd focus on one of the hot-topic drives as of late: the 2nd generation Western Digital Raptor.
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