I just installed my new IBM Ultra66 22GB drive and a Promise Ultra66
controller. The machine is an older Pentium 120, 64MB ram with i430FX
chipset.
I applied your patch and rebooted...
Uniform Multi-Platform E-IDE driver Revision: 6.19
PIIX: IDE controller on PCI bus 00 dev 38
PIIX: not 100% native mode: will probe irqs later
PIIX: neither IDE port enabled (BIOS)
PIIX: IDE controller on PCI bus 00 dev 39
PIIX: not 100% native mode: will probe irqs later
ide0: BM-DMA at 0x3000-0x3007, BIOS settings: hda:pio, hdb:pio
ide1: BM-DMA at 0x3008-0x300f, BIOS settings: hdc:pio, hdd:pio
PDC20262: IDE controller on PCI bus 00 dev 98
PDC20262: not 100% native mode: will probe irqs later
PDC20262: (U)DMA Burst Bit ENABLED Primary PCI Mode Secondary PCI Mode.
ide2: BM-DMA at 0x6400-0x6407, BIOS settings: hde:DMA, hdf:DMA
ide3: BM-DMA at 0x6408-0x640f, BIOS settings: hdg:pio, hdh:DMA
hda: SAMSUNG PLS-31274A, ATA DISK drive
hdc: FX001DE, ATAPI CDROM drive
hde: IBM-DJNA-372200, ATA DISK drive
ide0 at 0x1f0-0x1f7,0x3f6 on irq 14
ide1 at 0x170-0x177,0x376 on irq 15
ide2 at 0x6000-0x6007,0x6102 on irq 11
hda: SAMSUNG PLS-31274A, 1213MB w/256kB Cache, CHS=616/64/63
hde: lost interrupt <---- A pause of 3-4 seconds here....
hde: set_geometry_intr: status=0x00 { }
hde: IBM-DJNA-372200, 21557MB w/1966kB Cache, CHS=43800/16/63, UDMA(66)
hdc: ATAPI 4X CD-ROM drive, 128kB Cache
My hdparm -Tt numbers improved quite a bit...
Before my new IBM drive was slave to my samsung drive on the motherboard
ide controller.
The numbers were this:
Timing buffer-cache reads: 128 MB in 4.35 seconds = 29.40 MB/sec
Timing buffered disk reads: 64 MB in 18.44 seconds = 3.47 MB/sec
And after moving the IBM drive to the Promise Ultra66 controller and using
an Ultra66 cable the numbers look like this:
Timing buffer-cache reads: 128 MB in 4.21 seconds =30.40 MB/sec
Timing buffered disk reads: 64 MB in 5.24 seconds =12.21 MB/sec
In what other ways can I test / stress test this new code? I'm going to
setup nfs and samba going to that drive and pound on it.
Dax Kelson
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/