RSS Feed

HCW Tech Blog

For the latest info on computer hardware, tech, news, video games, software tips, and Linux, check out our new improved front page: HCW Tech Blog

Reviewed by: Carl Nelson [05.11.05]
Manufactured by: Hitachi


PCMark 04 Professional

To test drive-level file copying performance, we chose to use PCMark 04 Professional. PCMark uses RankDisk from Intel, which is able to bypass the file system and Windows cache. This allows measurements to be made independant of system overhead, getting the purest score possible. In addition to that, they are able to replicate various scenarios, to give us an idea of how the drive performs under various levels user interaction and file types.

The first test is the Windows Startup Test:

Windows XP Startup: This is the Windows® XP start trace, which contains disk activities occurring at operating system start-up. This trace contains no user activity.

Application Loading: This is a trace containing disk activities from loading various applications. It includes opening and closing of the following applications:

Microsoft® Word
Adobe® Acrobat® Reader 5
Windows® Media Player
3DMark 2001SE
Leadtek® Winfast® DVD
Mozilla Internet Browser

File Copying: This trace simply contains disk activities from copying approximately 400 Megabytes of files.

General Hard Disk Drive Usage: This trace contains disk activities from using several common applications.

These are:
- Opening a Microsoft® Word document, performing grammar check, saving and closing
- Compression and decompression using Winzip
- Encrypting and decrypting a file using PowerCrypt
- Scanning files for viruses using F-Secure® Antivirus™.
- Playing an MP3 file with Winamp
- Playing a WAV file with Winamp
- Playing a DivX video using DivX codec and Windows® Media Player
- Playing a WMV video file using Windows® Media Player
- Viewing pictures using Windows® Picture Viewer
- Browsing the internet using Microsoft® Internet Explorer
- Loading, playing and exiting a game using Ubisoft™ Tom Clancy’s Ghost Recon

Although the difference isn't pronounced, there is definitely a real-world benefit from using a 3.0 Gb/s transfer rate, especially in a pure file transfer. 1 MB/s here and there might not seem like a lot, but every little bit can count.

Doom 3

To give an idea on how 3 Gb/s can affect game level load times, we tested load times in Doom 3. Our testing method was to load 4 individual levels, which should show a more pronounced difference, and help eliminate human error (loads were timed with a stopwatch).

The group of 4 levels was loaded 4 times rebooting between each group, loading a different level first for each run (the first level is usually around 5-10 seconds slower to load than subsequent loads). The totals were added up, and averaged:

Again, this is where RAID 0 allows the 3 Gb/s transfer rate to shine; we are seeing a consistent decrease in load times by 5 seconds over 4 levels. Think about how many times you load levels in every game you play...

Also note the strange results we're seeing from RAID 1 mode. It is consistently 10 seconds slower than single drive mode. We did not see this occur in any of the other tests performed, and CPU overhead doesn't seem to be high on the NF4 Ultra chipset, so I don't know exactly what is causing this slowdown.

Next Page: (Iometer - File Server Tests)