Big HDD performance drop going from nForce2 to nForce3

[DarrenM]

Just upgraded from a 2800+ on an Abit NF7-S to a 3500+ on an MSI K8N Neo2 board and my HDD performance has dropped significantly.

On the nForce2 board
/dev/hda:
Timing cached reads: 1752 MB in 2.00 seconds = 876.13 MB/sec
Timing buffered disk reads: 168 MB in 3.02 seconds = 55.66 MB/sec

On the nForce3 board
/dev/hda:
Timing cached reads: 3752 MB in 2.00 seconds = 1875.35 MB/sec
Timing buffered disk reads: 118 MB in 3.04 seconds = 38.83 MB/sec

I also have raid0 on 2 SATA drives. On the nForce2 board the performance was around 100MB/sec, now it's around 60.

Uniform Multi-Platform E-IDE driver Revision: 7.00alpha2
ide: Assuming 33MHz system bus speed for PIO modes; override with
idebus=xx
NFORCE3-250: IDE controller at PCI slot 0000:00:08.0
NFORCE3-250: chipset revision 162
NFORCE3-250: not 100% native mode: will probe irqs later
NFORCE3-250: BIOS didn't set cable bits correctly. Enabling workaround.
NFORCE3-250: 0000:00:08.0 (rev a2) UDMA133 controller
ide0: BM-DMA at 0xf000-0xf007, BIOS settings: hda:DMA, hdb:DMA
ide1: BM-DMA at 0xf008-0xf00f, BIOS settings: hdc:DMA, hdd:DMA
Probing IDE interface ide0...
hda: ST320414A, ATA DISK drive
ide0 at 0x1f0-0x1f7,0x3f6 on irq 14
Probing IDE interface ide1...
hdd: LITE-ON DVDRW SOHW-812S, ATAPI CD/DVD-ROM drive
ide1 at 0x170-0x177,0x376 on irq 15
NFORCE3-250-SATA2: IDE controller at PCI slot 0000:00:09.0
NFORCE3-250-SATA2: chipset revision 162
NFORCE3-250-SATA2: BIOS didn't set cable bits correctly. Enabling
workaround.
NFORCE3-250-SATA2: BIOS didn't set cable bits correctly. Enabling
workaround.
NFORCE3-250-SATA2: 0000:00:09.0 (rev a2) UDMA133 controller
NFORCE3-250-SATA2: 100% native mode on irq 11
ide2: BM-DMA at 0xdc00-0xdc07, BIOS settings: hde:DMA, hdf:pio
ide3: BM-DMA at 0xdc08-0xdc0f, BIOS settings: hdg:DMA,
hdh:pio

/dev/hda:
multcount = 16 (on)
IO_support = 1 (32-bit)
unmaskirq = 1 (on)
using_dma = 1 (on)
keepsettings = 0 (off)
readonly = 0 (off)
readahead = 256 (on)
geometry = 38792/16/63, sectors = 20020396032,
start = 0
Model=ST320414A, FwRev=3.05, SerialNo=7EC04122
Config={ HardSect NotMFM HdSw>15uSec Fixed DTR>10Mbs RotSpdTol>.5% }
RawCHS=16383/16/63, TrkSize=0, SectSize=0, ECCbytes=0
BuffType=unknown, BuffSize=2048kB, MaxMultSect=16, MultSect=16
CurCHS=16383/16/63, CurSects=16514064, LBA=yes, LBAsects=39102336
IORDY=on/off, tPIO={min:240,w/IORDY:120}, tDMA={min:120,rec:120}
PIO modes: pio0 pio1 pio2 pio3 pio4
DMA modes: mdma0 mdma1 mdma2
UDMA modes: udma0 udma1 udma2 udma3 udma4 *udma5
AdvancedPM=no WriteCache=enabled
Drive conforms to: device does not report version: 1 2 3 4

Anyone know why it would be so much less or what I could be missing? amd74xx ide and nvidia sata drivers are loaded. Silicon Image driver for the nForce2. Not sure what the nForce3 uses for SATA. 2.6.10 kernel.

[agent_jdh]

Where to start on this one - different motherboard, processor, i/o controllers, drivers (for the sata controllers - the NF3 uses an nvidia sata controller, your old abit was sil).

Also, hdparm is a pretty unsophisticated drive speed test, and I am not aware of a performance test for Linux that matches what is available on Windows.

If there is any major performance hit, I suppose the only reasonable explanations are blacklisting (e.g. a known drive/controller compatability issue has caused the kernel driver to compromise somewhere to achieve reliable transfers, usually at the expense of performance), or that the driver for the newer controller is not as mature as that for the older one, a situation which would hopefully improve over time.
_________________
Jingle Jangle Jewellery