How to achieve 160 Mbytes/S transfer speed with a 29160 card

Dr. Andras Solyom solyom at eik.bme.hu
Wed Nov 15 04:59:29 PST 2000


Hi,

when replacing our internet server we have bought a 2960 card and a
Quantum Atlas_V__9_WLS 160 disk,
hoping to get the 160 Mbytes/s speed from the AIC driver.

Unfortunately it operates only at 80Mbytes/s. Is there anything  I can
do to enable the 160 M/s speed for the driver?

Our setup is the folowing:

600 MHz. Pentium III (Katmai) processor,  256Mbyte RAM,
Debian Linux with 2.2.17 pre6 kernel
SCSI card is used with auto termination. In the SCSI BIOS settings all
device is configured with  160 M/s throughput,
and of course we use the special dedicated 160 M/s SCSI cable.
Still when booting we got the following messages:

(scsi0) <Adaptec AIC-7892 Ultra 160/m SCSI host adapter> found at PCI
0/11/0
(scsi0) Wide Channel, SCSI ID=7, 32/255 SCBs
(scsi0) Downloading sequencer code... 392 instructions downloaded
scsi0: Adaptec AHA274x/284x/294x (EISA/VLB/PCI-Fast SCSI) 5.1.31/3.2.4
           <Adaptec AIC-7892 Ultra 160/m SCSI host adapter>
scsi1: SCSI Host Adapter emulation for IDE ATAPI devices
scsi: 2 hosts.
scsi(0:0:2:0) Synchronous at 80 Mbyte/sec, offset 63
    Vendor: QUANTUM    Model: Atlas_V__9_WLS  Rev:0230
     Type: Direct-Access
ANSI  SCSI Revision: 03

Apart from the displayed slower speed the card operates correctly.

I have read  Mike Sharp's letter (Work on the 29160?) who says that  his
system when it boots at all operates at only 40
Mbyte/sec, but his system log says 160 Mbyte/s! Ihave also tried bonie++
which gives a block write speed of about
44 Mbyte/s.  (My Quantum Fireball LM ATAPI drive at home gives 27
Mbyte/s with the same test run on a 350 MHz
processor, using Ultra DMA 33...)

So it is also possible that the data transfer speed displayed at boot
time is incorrect. If so how can I determine the real speed?

            I'd appreciate any hint or pointer!

Andras



To Unsubscribe: send mail to majordomo at FreeBSD.org
with "unsubscribe aic7xxx" in the body of the message




More information about the aic7xxx mailing list