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
Pure Hard Disk Performance
Although the point of our test suite is to focus on real world performance, it is useful to look at some theoretical numbers in order to get an idea of drive superiority.
To measure "pure" hard disk performance, we took a real world benchmark - in this case, the entire Winstone 2004 suite - and used Intel's IPEAK utility to capture a trace file of all of the IO operations that take place during a single run of Business Winstone 2004 and MCC Winstone 2004. We then use IPEAK to play back the trace, much like a timedemo, on each of the hard drives, which gives us a mean service time in milliseconds; in other words, the average time that each drive took to fulfill each IO operation.
In order to make the data more understandable, we report the scores as an average number of IO operations per second so that higher scores translate into better performance.
Keep in mind that these performance scores are best only for comparing pure hard disk performance, and in no way do they reflect the actual real world performance impact of these hard drives.
For descriptions of what the Business and Multimedia Content Creation Winstone 2004 tests consist of, reference those benchmark pages.
We see from the Business Winstone IPEAK scores that the two Raptor drives are, by far, the highest performers out of the bunch.
As our focus shifts down to the 7200RPM 8MB cache drives, we see that they all offer similar performance. In this case, the Western Digital WD1200JB and the Maxtor DiamondMax Plus 9 offer basically identical performance. The Seagate Barracuda 7200.7 falls behind somewhat, but what matters most is how these drives perform in the real world.
Looking at the older IBM 75GXP and Maxtor D740X drives, it's interesting to see that the fastest drives of today are around twice as fast as the fastest drives from a few years ago.
As we look at Multimedia Content Creation IPEAK performance, we see that the two Raptors continue to maintain a significant performance advantage over the competition. There is a bit of place switching as the Seagate 7200.7 and WD 1200JB perform much closer, with the Maxtor DiamondMax Plus 9 holding a bit of a lead.
Facebook
Twitter
RSS
50 Comments
View All Comments
SoBizarre - Monday, June 7, 2004 - link
<<I wonder how these drives compare to my Seagate X15?Try the link below and cry... ;)
http://storagereview.com/php/benchmark/compare_rtg...
mjz5 - Monday, June 7, 2004 - link
would have been cool to see how long it takes to zip a folder with a 1000 of files..araczynski - Monday, June 7, 2004 - link
i don't quite see anything about the raptors that warrant the steep price jump, i see the typical milking of the wannabes.BCinSC - Monday, June 7, 2004 - link
I wonder how these drives compare to my Seagate X15?Insomniac - Monday, June 7, 2004 - link
Anand,Could we see some type of test that shows the impact of disk defragmenting? I know it isn't exactly a hard dive test, but it would be nice to see what, if any, performance improvement it adds and how the drives perform when "optimal". Thanks.
MIDIman - Monday, June 7, 2004 - link
IMHO - This is a market that has already been taken in-depth by another very big website that has been alive for almost as long as anandtech. Redundancy is always good though.We'd definitely like to see RAID array comparisons. Its definitely a big buzz word nowadays.
Pollock - Monday, June 7, 2004 - link
I really could have used this article last week in deciding whether or not the 80GB Seagate for $40 last week was fast and reliable...=(00aStrOgUy00 - Monday, June 7, 2004 - link
I think this article was a bit lacking.I would have liked to see how the raptors stacked up to regular 7200RPM drives with denser platters, like the barracuda 200GB one that uses 100Gb platters, especially when the 200GB one that uses 100GB platters is stil far less expensive than either of the raptor drives.
I would also like to see RAID performance compared to the raptor drives.
AnnihilatorX - Monday, June 7, 2004 - link
We missed the most important test! File copy test. Say time taken to duplicate a 1GB file. It's basic but useful for those who are always dealing with large files.People who own high end harddisks tend to be either video editing enthuaists or server-owners. The tests covered general usage but did not well covering those areas. Harddisk and CPU limiting task such as volume batch encoding of videeo to a specific codec, say Xvid or DivX might be a useful benchmark. For servers random access time is important and might as well be tested.
The tests we covered is not wrong, but fail as a target for really those would buy a high end harddisk. Common task such as surfing the net while compressing document; virus checking are basic usage of an average user, and mostly CPU limiting.
While pure file copy test are likely to be harddisk limiting. The CPU ultilisation during file transfer process also indicates how good resources saving of the controllers are and has direct peoformance impact when CPU limit comes to the scene.
Reflex - Monday, June 7, 2004 - link
I want to see a 'service' test of the venders much as is now done for motherboards. Hard drives and CD/DVD drives are by far the highest points of failure in a modern PC, it is important to know what happens when your drive fails. In the past this has been a serious sore point between myself and WD, it has often taken months for them to turn around a failed drive, and due to the extreme failure rates I have had with their drives after about a year, its a serious issue.Heat would also be a good test, it is the main reason that 10k RPM drives have stayed at the high end for so long.
Murst: Most people reading this site would be using NTFS, and a few using FAT32. Under NTFS, fragmentation would not have any serious impact on performance due to properties of the file system and how it works. Unless your suggesting they test NFS and other Unix/Linux filesystems, I am not certain what other file systems you want tested. Most games are not tested under Win9x anymore, I don't see a point in testing other hardware on a 6 year old OS either...