As usual, I have tried to run iozone on my local IDE hard disk and got
very bad results. Running 'iozone 200 8192 /tmp/zz' gives the low
figures à 2 Mo/s writing and 4 Mo/s reading, with kernels ranging
from 2.2.5-22 (RH 6.0 kernel) to 2.2.10-ac8.
These figures are bad, but worse is that during writing, the entire
machine seems frozen (under X, nothing is refreshed during seconds,
even the mouse does not mouve). On the console login, I can not
even log. Once iozone is starting reading, things are a little better.
I do not remember having had that bad performance in the time of
RH 5.2 with 2.0.36 kernel. If I remember correctly, I had around
9+ Mo/s writing and 7+ Mo/s reading.
I have much better results with a Tekram 390F UW card (15 Mb/s writing,
10 Mb/s reading), with no real interactive response loss.
Excerpt of dmesg :
CPU: AMD AMD-K6(tm) 3D processor stepping 00
...
PCI_IDE: unknown IDE controller on PCI bus 00 device 78, VID=10b9, DID=5229
PCI_IDE: not 100% native mode: will probe irqs later
PCI_IDE: simplex device: DMA disabled
ide0: PCI_IDE Bus-Master DMA disabled (BIOS)
PCI_IDE: simplex device: DMA disabled
ide1: PCI_IDE Bus-Master DMA disabled (BIOS)
hda: IBM-DHEA-38451, ATA DISK drive
hdb: CD-ROM CDU701, ATAPI CDROM drive
ide0 at 0x1f0-0x1f7,0x3f6 on irq 14
hda: IBM-DHEA-38451, 8063MB w/472kB Cache, CHS=1027/255/63
$ lspci
00:00.0 Host bridge: Acer Laboratories Inc. M1541 (rev 04)
00:01.0 PCI bridge: Acer Laboratories Inc.: Unknown device 5243 (rev 04)
00:03.0 Bridge: Acer Laboratories Inc. M7101
00:07.0 ISA bridge: Acer Laboratories Inc. M1533 (rev c3)
00:09.0 Ethernet controller: Realtek Semiconductor Co., Ltd. 8029
00:0a.0 Ethernet controller: Digital Equipment Corporation DECchip 21140 [FasterNet] (rev 22)
00:0c.0 SCSI storage controller: Symbios Logic Inc. (formerly NCR) 53c875 (rev 03)
00:0f.0 IDE interface: Acer Laboratories Inc. M5229 (rev c1)
01:00.0 VGA compatible controller: Matrox Graphics, Inc. MGA G200 AGP [Millennium G200 AGP] (rev 01)
A+,
-- Thierry Danis- 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/