Warning: Always look at the date when you read a hardware article. Some of the content in this article is most likely out of date, as it was written on 2/2/05. Check out our more recent articles. | |||
| Introduction | |||
When configuring a server or high end custom computer, we are often asked about the performance benefits of SCSI over SATA. 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. | |||
| Background | |||
As with any analysis, we must first look at the benchmarks. As you may know, the biggest difference between SCSI and SATA is that while SCSI has a processor integrated into the controller, SATA makes greater use of the system processor to serve that function. Therefore, the first step we will take in our analysis is to take a close look at how big the controller and rest of the computer plays in the performance of the drives. Will a higher end SCSI controller greatly increase the performance of a SCSI drive, and will a faster system processor help an SATA drive? | |||
| SATA Benchmarks | |||
For nearly a year now, we have been benchmarking every system that leaves our door. This gives us access to an incredible wealth of data that we can put to great use here. We will begin by looking at all benchmarks with a 74GB 10k RPM SATA hard drive, to see how the disk performance differs from system to system. | |||
| Native Command Queuing | |||
What is native command queuing? It is a technology that has been used in the SCSI world for quite a while, but only recently has been introduced to SATA drives. This explanation is an excerpt from Neoseeker's Nforce 4 Tech Preview.
So, we see that while the speed of the computer plays very little role in the performance of the disk, NCQ does make a difference. | |||
| SCSI Benchmarks | |||
| |||
| Benchmark Comparison | |||
| |||
| Disclaimers | |||
Now keep in mind that we're strictly talking about hard drive performance. Take a look at the "XP Booting" benchmarks in the last graphic -- you'll notice that is the area in which SCSI holds one of the only advantages to SATA. This is due to CPU utilization -- SCSI drives simply don't use as much CPU power to run, leaving more CPU time for the rest of the system. Based on those numbers, if you are looking to build the fastest possible computer, it does appear that SCSI holds onto a very marginal performance lead. If you are only concerned with getting the highest disk throughput possible, then SATA with NCQ is the way to go! I should also add that given the right SCSI drive (ie, a 146GB 15k RPM), you can still beat the performance of the 74GB Raptor with NCQ, but your costs will be three to four times higher. | |||
| |||
Puget SATA RAID Servers
![]() | ![]() | ![]() | ![]() | ![]() | |
| Summit S1-2U | Summit S1-3U | Summit S2-4U | Summit S1-T | Summit S2-T | Custom Servers |
We encourage you to browse our configuration pages above. We feel we have some of the best configuration tools in the industry, so have fun and put them to good use!
Share this article!











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
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
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
I wonder if that's hyperbole?
That's a GREAT idea for an article. ;-)