RAID 1.5 With IDE: Added Value Or Eyewash?

Test Setup

Swipe to scroll horizontally
Test System
ProcessorAMD Athlon XP 2200+
MotherboardDFI LANParty KT400AVIA KT400A ChipsetBIOS : May 6, 2003
RAM256 MB DDR333/PC2700, CL2 Corsair Micro
Controller & Hard DrivesVIA VT8235 UltraATA/133HighPoint HPT372N On-BoardBIOS 2.3422x Western Digital WD2000BB
Display AdapternVIDIA GeForce3 Ti4200, 64 MB
Network Card3COM 905TX PCI 100 MBit
Operating SystemWindows 2000 Professional5.00.2195, Service Pack 3
Benchmarks and Tests
Performance MeasurementsHD Tach 2.61, c’t h2benchw
I/O performanceIntel IOMeter
Drivers and Settings
Graphics DriverNVIDIA Reference Driver 41.09
DriversIntel Application Accelerator 2.3
DirectX Version9.0
Resolution1024 x 768, 16 Bit, 85 Hz refresh

Owing to time restraints, we limited the capacity of the RAID array to 25 GB. Tests on total capacities of up to 400 GB would have taken much longer and would not have produced a different result. All the low-level measurements (IOMeter, HDTach) are only run without partitions anyway and refer to the total capacity of the RAID array.

  • lifeisstudy
    So RAID 1.5 won't work because the heads of the disk still need to move to the next data block to read... If you skip blocks, you still have to move past them.

    What about RAID 1.5 with Solid State disks. You have nothing to move, yet you can double your read speed with mirroring. Sounds perfect for server caches.