Western Digital WD740ADFD: Bottled Lightning
by Gary Key on February 7, 2007 3:30 AM EST- Posted in
- Storage
iPeak Video/Audio Tests
The iPeak based Video/Audio benchmarks are designed around simulating media encoding and HTPC activities. These are basic benchmarks at this time as this section will be expanded once we start testing under Vista. Our change to a dual core processor will assist us in maintaining a balance between the CPU and Storage systems during the trace file creation and benchmarking processes. These benchmarks are CPU intensive in nature but also require a balanced storage system with the ability to handle read and write requests simultaneously in a very efficient manner.
The AnyDVD benchmark is heavily weighted to write requests with the results showing a common pattern with the two 16MB cache Raptors finishing first and second and the WD740ADFD once again showing its strength in the write intensive benchmarks. However, we found the WD740GD was constantly pausing during writes due to the smaller cache size, and we witnessed buffer overruns on the large file sizes included in this test. Even with the pauses, its superior transfer rates still kept the drive ahead of the other 8MB cache drives in this benchmark.
The Nero Recode 2 benchmark is weighted to streaming read requests but is balanced by continuous write operations near the end of the test. This benchmark is one of the most demanding ones in our test suite with the disk being active the entire trace file with several 100% utilization peaks. The two 16MB cache Raptors finish near the top with the WD740GD 8MB cache drive placing near the bottom. Upon reviewing the trace file results it was obvious that the WD740GD was hampered by its smaller cache and lower sustained transfer rates as it had a significant number of buffer overruns during testing.
iPeak Game Installation Tests
Our iPeak based Game Installation benchmarks simply show the ability of the hard drive to write data as quickly as possible to the disc based upon the installation software instructions. As detailed in our iPeak setup description we installed the games from our source drive in order to eliminate the optical drive bottleneck. In separate application timing we witnessed basically the same percentage spread when installing the games via our DVD drive so these results are representative of actual installation performance.
The Raptors once again finish at or near the top in our gaming tests although we expected the WD740ADFD to finish closer to the WD1500ADFD due to the amount of write operations involved in the game installations. A review of the trace files did not indicate any real standout issues with the 74GB drive, although we noticed several minor dips when the drive was reading information off the source drive. This did not occur with the 150GB Raptor.
We need to remember these tests reflect pure hard drive performance and will be mitigated by the overall system platform as we will see in our application tests. These tests are basically designed around continual read/write requests that favor large cache sizes, properly tuned firmware, and high sustained transfer rates.
iPeak Game Play Tests
The iPeak based Game Play tests are centered on the benefits of having a hard disk that can load non-linear or sequential data files quickly without interrupting the flow of the game.
When it comes to gaming the Raptors rule. All three Raptors place in the top three spots with the two 16MB cache versions finishing one and two once again. Although we are looking at pure performance results, in subjective testing the Raptor family of drives could always be identified when loading or playing a game. Although the capacities of the drives are small, if you want the best overall gaming performance in a drive with a SATA interface then your only choice are the Raptors.
The iPeak based Video/Audio benchmarks are designed around simulating media encoding and HTPC activities. These are basic benchmarks at this time as this section will be expanded once we start testing under Vista. Our change to a dual core processor will assist us in maintaining a balance between the CPU and Storage systems during the trace file creation and benchmarking processes. These benchmarks are CPU intensive in nature but also require a balanced storage system with the ability to handle read and write requests simultaneously in a very efficient manner.
The AnyDVD benchmark is heavily weighted to write requests with the results showing a common pattern with the two 16MB cache Raptors finishing first and second and the WD740ADFD once again showing its strength in the write intensive benchmarks. However, we found the WD740GD was constantly pausing during writes due to the smaller cache size, and we witnessed buffer overruns on the large file sizes included in this test. Even with the pauses, its superior transfer rates still kept the drive ahead of the other 8MB cache drives in this benchmark.
The Nero Recode 2 benchmark is weighted to streaming read requests but is balanced by continuous write operations near the end of the test. This benchmark is one of the most demanding ones in our test suite with the disk being active the entire trace file with several 100% utilization peaks. The two 16MB cache Raptors finish near the top with the WD740GD 8MB cache drive placing near the bottom. Upon reviewing the trace file results it was obvious that the WD740GD was hampered by its smaller cache and lower sustained transfer rates as it had a significant number of buffer overruns during testing.
iPeak Game Installation Tests
Our iPeak based Game Installation benchmarks simply show the ability of the hard drive to write data as quickly as possible to the disc based upon the installation software instructions. As detailed in our iPeak setup description we installed the games from our source drive in order to eliminate the optical drive bottleneck. In separate application timing we witnessed basically the same percentage spread when installing the games via our DVD drive so these results are representative of actual installation performance.
The Raptors once again finish at or near the top in our gaming tests although we expected the WD740ADFD to finish closer to the WD1500ADFD due to the amount of write operations involved in the game installations. A review of the trace files did not indicate any real standout issues with the 74GB drive, although we noticed several minor dips when the drive was reading information off the source drive. This did not occur with the 150GB Raptor.
We need to remember these tests reflect pure hard drive performance and will be mitigated by the overall system platform as we will see in our application tests. These tests are basically designed around continual read/write requests that favor large cache sizes, properly tuned firmware, and high sustained transfer rates.
iPeak Game Play Tests
The iPeak based Game Play tests are centered on the benefits of having a hard disk that can load non-linear or sequential data files quickly without interrupting the flow of the game.
When it comes to gaming the Raptors rule. All three Raptors place in the top three spots with the two 16MB cache versions finishing one and two once again. Although we are looking at pure performance results, in subjective testing the Raptor family of drives could always be identified when loading or playing a game. Although the capacities of the drives are small, if you want the best overall gaming performance in a drive with a SATA interface then your only choice are the Raptors.
Facebook
Twitter
RSS
26 Comments
View All Comments
Genx87 - Wednesday, February 7, 2007 - link
Once you have one you cant go back :DThey are wonderful drives. The capacity issue isnt a big deal unless you are opting for the 36GB version. I havent had a need for excessive amounts of capacity since I built my sever a couple of years ago.
I built a server with a pair of the 36GBs with a 500GB array behind it for storage. It is a very nice step up from the pair of 80GB 7200 rpm drives in there before.
aka1nas - Wednesday, February 7, 2007 - link
They definately make great OS/Applications drives if you back them up with a bigger drive for bulk storage.Genx87 - Wednesday, February 7, 2007 - link
oops forgot to mention my machine at home has the newest 74GB raptor in it. Which is an upgrade from the 1st run 74GB raptor in my old machine.Blazing fast, as usual.
Muzzy - Wednesday, February 7, 2007 - link
"Of course, if you are into benchmarking or run a lot of disk intensive applications, then a pair of Raptors in RAID 0 will be even better."Um, aren't you guys contradicting yourself here? In July 1st, 2004 article about Raptor drives in RAID-0, you stated "If you haven't gotten the hint by now, we'll spell it out for you: there is no place, and no need for a RAID-0 array on a desktop computer." I love my 150GB Raptor despite the noise, don't get me wrong. Really do wish though that other company would give WD some competition in this category. $190 for 150GB??
JarredWalton - Wednesday, February 7, 2007 - link
Most people don't really care about running benchmarks for bragging rights, and most desktop users do not "run a lot of disk intensive applications". We don't think RAID 0 is even remotely necessary for 99% of people, but there are still benchmarks where it is obviously faster. If you have BitTorrent running in the background with other networked computers streaming data off of the same drive and you start to run games that load off of the same drive, yes, RAID 0 will clearly outperform a single drive. That's more of a server/workstation workload, which is why we say that RAID 0 on a desktop computer isn't needed.Axbattler - Thursday, February 8, 2007 - link
*Ponders*Where RAID-0 excels is in STR performance. Loading of applications that benefit from STR (e.g. XP), copying a large massive file, working with a large massive file (video editing) etc. are applications where you will see a significant gain with RAID-0.
RAID-0 may well be faster than a single drive identical drive in most applications (you do pay slightly in access time, but the gain from STR can probably offset it more often than not).. But how about a well two individual drives in a reasonably configured system? I am not convinced that in the scenario that you've described (which, I do not believe reflects the nature of the workload in a server in the first place), that you are necessarily better off with RAID-0 than two individual drives. I would rather have one drive running the game, and the other doing the streaming/torrenting. Game loading time is not exactly where I've seen RAID-0 shine the most (and once the game is running, you'll pretty much get no gain from RAID-0).
JarredWalton - Thursday, February 8, 2007 - link
Then carry it a bit further. Basically, I'm saying that if you generate enough concurrent HDD accesses, RAID 0 will outperform single drives. You might get better performance from two drives without RAID 0, but then you need to worry about having separate volumes and what happens if most of the accesses start to target a single drive. Basically, RAID 0 can be faster than an individual drive, but this mostly occurs in unrealistic situations, as you point out. RAID 0 mostly seems to be for bragging rights, and I certainly don't recommend it.lemonadesoda - Wednesday, February 7, 2007 - link
Most Raptorers (the people who love and install them) typically choose a dual drive RAID setup for ultimate HDD performance.However, seeing the (very close) performance of Seagate 7200.10, I would be very interested to see Raptors in RAID vs 7200.10 in RAID.
Would the performance gap INCREASE or DECREASE in such a configuration?
Le Québécois - Wednesday, February 7, 2007 - link
It's nice to see my WD1500ADFD is still the top gaming drive on the market. Still something has been bothering me for some time now.I've always found intriguing that my Raptor temperature is about 40% lower (idle and under load) than the one you post on every HDD articles. I have a 80mm Antec front fan but still the temperature is 40% lower, not 25%.
What's the room temperature? You always post the base dB of the room but I don't remember ever seeing the temperature.
jabber - Wednesday, February 7, 2007 - link
Indeed, I bought one of these 74Gb Raptors a few weeks ago and it never gets more than slightly warm. Certainly doesnt warrant an 80mm fan blasting on it.I do recommend the WD Secure SATA cable though. Great bit of kit. How the standard SATA cable connection setup got approved I'll never know.
The niggle I have is that 74Gb is too small? I have a full XP install, several apps and games (BF2/Total War etc. etc. and its still got plenty of space. Why would you bother cluttering up your main system HD with non-essential stuff like media files? Just get a cheap 400Gb+ for that sort of thing where performance isnt an issue.