SCSI vs SATA, Which is Faster?

[PCC-Jon]

Summary:
When configuring a server or high end custom computer, we are often asked about the performance benefits of SCSI over ATA. Since SCSI is much more expensive, the common perception is that it must be significantly faster. The short answer we give to that issue is that with the release of 10,000 RPM SATA drives, SCSI simply does not hold the edge it used to, and we do not feel it is worth the sizable increase in cost. Of course, that statement is very general. Surely there are still applications that greatly benefit from SCSI, and it is the goal of this article to take a deeper look at the performance differences in SCSI vs SATA, and to tell you how those differences translate to performance in real world applications.

View the entire article: http://www.pugetsystems.com/articles.php?id=19

Post your discussion here!

[MaxMercury]

Jon,
I really enjoyed reading this article. It looks like you were using the HD test suite from PCMark04 for benchmarking? (Just curious.) The part I was most interested in had to do with NCQ, which I've been looking forward to on principle, even if I didn't see any significant performance increase -- I just like the idea of my HDs operating in a more efficient, "intelligent" manner. ;-) I've also read that HDs supporting NCQ can have a greater longevity since they're operating more efficiently, and that such drives are also useful for people like myself who do a lot of multitasking. Nice! :-)

I'm a little confused in that I was under the impression that WD's 74GB Raptor doesn't support NCQ but rather TCQ (tagged command queueing), since it's not a native SATA drive but has a PATA <-> SATA bridge. Is there any significant difference between NCQ and TCQ, or are they just different acronyms for pretty much the same thing?

Anyway, what I found most helpful and exciting about your article is that you demonstrated the following: a) TCQ/NCQ enhances the performance of a single HD when paired with a quality motherboard that supports it. So, you don't have to have some type of RAID array to see benefits; and b) A person can get the benefits of command queueing at a reasonable cost by using any nForce4 Ultra-based motherboard along with a 74GB Raptor. That's terrific, since other NCQ-ready HDs, like those from Seagate and Maxtor, seem to be pretty pricey at the moment.

I'd like to add a note for anyone looking for motherboards that can support HDs with NCQ: Chances are, you won't find the term "NCQ" anywhere in the motherboard specs. So, you need to look for terms like "SATA II" or "SATA 3.0Gb/s." I think the latter term is what Asus uses.

Again, thanks for an interesting article! :thumbsup
-- Max

[PCC-Jon]

Thanks for the correction, Max! You're right, it should have read "TCQ." I'm not too up on the differences...and it appears that most places treat the two as pretty near the same. TomsHardware.com tried to do a comparion at http://www6.tomshardware.com/storage/20041116/command_queuing-02.html , but didn't end up with very conclusive results...the Raptor blew 'em all away :-D

[PaulDriver]

In my experience, there is little diference between individual drives when comparing ATA, SATA, and SCSI.

Where the diferences start to add up, is when you are comparing multiple drive configurations, where a volume is striped across several (3 or better) drives.

This is where SCSI starts to destroy ATA and SATA.

[allen_96er]

i'm just curious, what if SCSI raid 0 vs SATA raid 0, assume both of the set up is based on individual raid controller card? :thumbsup

allen

[lithos]

For relative sizes i suppose the test was accurate but what about the smaller scsi drives which provide more performance (typically) then the larger drives or what was the difference in cache sizes. I dont wanna bash the article im just wondering the difference in speeds of different sizes and/or similar cache sizes.

[DanialThom]

This is perhaps the dumbest artical I've ever encountered. Not only are the tests faulty and ill-conceived, but the conclusions are all wrong.

SCSI benefits most when multiple drives are in use. SCSI drives and SATA drives are fundamentally the same mechanically. The test fails to establish a control, which would be to use a similar front end on the same motherboard. What the first few tests "establish" is that all systems will yield different results, so you can't compare one drive on one MB with another drive on a different MB.

The test that show 4 SCSI drives being slower than 1 illustrated the stupidity of the tests. Clearly the test isn't exercising the drives in a way that would be considered a proper benchmark.

Supermicro makes several MBs that have both SATA and SCSI, but even in that scenario the controllers are different so who's to say you are not testing the controller more than the drive? SCSI often appears faster because of the front end controller used for the scsi while SATA usually uses a raw controller. Using a SCSI-like controller for SATA (such as Areca products) can change that and make SATA function more like a SCSI with front-end buffering. Of course for the price of the controller you could buy a faster processor which may change results in the other direction.

The bottom line is that there is no way to really compare SCSI to SATA directly. You can try a lot of system combinations and say that the fastest SCSI system is faster than the fastest SATA system. But there are too many other variables to isolate one drive against another. Just like you can't really compare AMD vs Intel, because they don't run on the same chipsets. You can only compare one collection of components against another collection of componants.

DT

[PCC-Richard]

This is perhaps the dumbest artical I've ever encountered.

I wonder if that's hyperbole?

[SEO-Dan]

Just like you can't really compare AMD vs Intel

http://www.google.com/search?sourceid=navclient&ie=UTF-8&rls=GGLJ,GGLJ:2006-34,GGLJ:en&q=amd+vs+intel

That's a GREAT idea for an article. ;-)