A note on the testing
Like we do with all new reviews, we've used Windows XP Professional as our test operating system. Unfortunately, using XP Pro exposes all sorts of SCSI performance baggage related to the WRITE_THROUGH flag. To get a better idea of how WRITE_THROUGH can affect SCSI performance in Windows XP, check out this page of my 10K-RPM drive comparison. Because WRITE_THROUGH can be important for high-end workstations and servers, all SCSI drives were tested as basic disks in Windows XP. No attempts were made to get around the WRITE_THROUGH flag.
Purists will no doubt be aghast at the collection of competitors we've rounded up for Seagate's Cheetah 15K.3, but we like to see how products perform against a wide range of direct and indirect competitors. Today, we'll be looking at the Cheetah 15K.3's performance against an older 15K-RPM SCSI drive from IBM, 10K-RPM SCSI drives from Maxtor and Seagate, a 10K-RPM Serial ATA drive from Western Digital, and a two-drive ATA/133 RAID 0 array. We've also thrown in a couple of Atlas 15K drives from Maxtor, one with firmware dating back to July, and a new drive with the latest shipping firmware. It should be interesting to see how much a simple firmware upgrade can change the Atlas 15K's performance, and we'll be focusing our analysis on how well Maxtor's old and new firmware revs match up with the Cheetah 15K.3.
Though the Atlas 15K and Cheetah 15K.3 drives we're comparing today have identical capacities, our 10K RPM SCSI drives, Raptor Serial ATA drive, UltraStar 15K, and IDE RAID array are all different sizes. Smaller drives generally use fewer platters and can offer quicker seek times and marginally better performance than large-capacity drives that use more platters.
Our testing methods
All tests were run three times, and their results were averaged, using the following test system.
|Processor||Intel Pentium 4 2.26GHz|
|Front-side bus||533MHz (4x133MHz)|
|Motherboard||Tyan Trinity GC-SL|
|Chipset||ServerWorks Grand Champion SL|
|North bridge||ServerWorks CMIC-SL|
|South bridge||ServerWorks CSB5|
|Memory size||512MB (1 DIMM)|
|Memory type||CAS 2.5 PC2100 ECC DDR SDRAM|
|Graphics||ATI Rage XL|
SIIG Serial ATA PCI
|3ware Escalade 7500|
Silicon Image 18.104.22.168
IBM UltraStar 15K 18GB
Western Digital Raptor WD360GD 37GB
|Maxtor 740X-6L 40GB|
2-drive RAID 0
|Operating System||Windows XP Professional SP1|
The Adaptec 29320-R was used in the motherboard's 64-bit, 133MHz PCI-X slot, while the 3ware Escalade 7500 was used in the motherboard's 64-bit, 100MHz PCI-X slot. Since the Escalade 7500 only supports 64-bit PCI speeds up to 33MHz, it shouldn't be at any disadvantage in a PCI-X slot that offers a top speed of 100MHz.
A special thanks goes out to the Computer Repair Shop for kicking in the Western Digital Raptor WD360GD and the UltraStar 15K.
We used the following versions of our test applications:
The test systems' Windows desktop was set at 1024x768 in 32-bit color at a 75Hz screen refresh rate. Vertical refresh sync (vsync) was disabled for all tests.
All the tests and methods we employed are publicly available and reproducible. If you have questions about our methods, hit our forums to talk with us about them.
|The SSD Endurance Experiment: Only two remain after 1.5PB||61|
|Friday night topic: Conspiracy theories||193|
|GeForce 344.11 WHQL drivers support new cards, new games, G-Sync||7|
|Deal of the week: A 23'' IPS monitor for $150, a 200-mm fan for free, and more||23|
|GeForce GTX 970, 980 cards already widely available||31|
|Curved VA panel powers 27'' Samsung monitor||24|
|Android L to encrypt devices by default||7|
|Nvidia's GeForce GTX 980 and 970 graphics cards reviewed||366|