The best answer I've recieved for it so far is that it's a hardware
problem... echo's, noise, poor cables, power ripples, etc... The drives
I use are quantum fireball el's and cx's.
I've tried new cables, and older 'known working' cables, no difference...
Let me know if you come up with any better solutions...
Ben.
On Tue, 26 Oct 1999, Dan Yocum wrote:
>
> Andre, Andries, Mark,
>
> Well, we've run into a brand new IDE problem: disk DMA is getting turned off
> mysteriously. Here's one way to reproduce the problem: do a 'hdparm -S 1
> /dev/hdX', wait about a minute then try to write to the disk. The write speed
> is about 3MB/s (ouch!) and this is the error message:
>
> hdc: timeout waiting for DMA
> hdc: irq timeout: status=0xd2 { Busy }
> hdc: DMA disabled
> hdd: DMA disabled
> Oct 24 08:09:30 fnpc229 kernel: hdc: timeout waiting for DMA
> Oct 24 08:09:30 fnpc229 kernel: hdc: irq timeout: status=0xd2 { Busy }
> Oct 24 08:09:30 fnpc229 kernel: hdc: DMA disabled
> Oct 24 08:09:30 fnpc229 kernel: hdd: DMA disabled
> ide1: reset: success
> Oct 24 08:09:31 fnpc229 kernel: ide1: reset: success
>
> Looking at the status of said drive 'hdparm -C /dev/hdX' shows the the DMA to
> be turned off and running bonnie proves it - the performance is horrible.
>
> So, we set the standby mode to off (i.e., 'hdparm -S 0' and it never spins the
> drive down) and try to write to the disk - at some point in the future after
> turning DMA on, DMA gets turned off for no obvious reason.
>
> This is a big deal to us since we require the read/write speed to exceed
> 6MB/sec (and of course it would be nice if it was in the 14-15MB/s range).
>
> Any ideas?
>
> Here's the specifics of the 2 drives we're using. The WD disks are on an
> Intel Lancewood MB, the Maxtor's are on an ASUS P2BD:
>
>
> /dev/hdc:
>
> Model=Maxtor 91700U5, FwRev=MA540RR0, SerialNo=C5H00JXC
> Config={ Fixed }
> RawCHS=32972/16/63, TrkSize=0, SectSize=0, ECCbytes=57
> BuffType=3(DualPortCache), BuffSize=2048kB, MaxMultSect=16, MultSect=off
> DblWordIO=no, maxPIO=2(fast), DMA=yes, maxDMA=0(slow)
> CurCHS=32972/16/63, CurSects=33235776, LBA=yes, LBAsects=33235776
> tDMA={min:120,rec:120}, DMA modes: mword0 mword1 mword2
> IORDY=on/off, tPIO={min:120,w/IORDY:120}, PIO modes: mode3 mode4
>
>
>
> /dev/hdc:
>
> Model=WDC AC418000D, FwRev=J78OA30K, SerialNo=WD-WT669
> Config={ HardSect NotMFM HdSw>15uSec Fixed DTR>10Mbs }
> RawCHS=34960/16/63, TrkSize=0, SectSize=0, ECCbytes=34
> BuffType=3(DualPortCache), BuffSize=1966kB, MaxMultSect=16, MultSect=off
> DblWordIO=no, maxPIO=2(fast), DMA=yes, maxDMA=2(fast)
> CurCHS=34960/16/63, CurSects=35239680, LBA=yes, LBAsects=35239680
> tDMA={min:120,rec:120}, DMA modes: mword0 mword1 mword2
> IORDY=on/off, tPIO={min:240,w/IORDY:120}, PIO modes: mode3 mode4
>
>
> Thanks, in advance, for the help.
>
> Dan
>
> ___________________________________________________________________________
> Dan Yocum | Phone: (630) 840-8525
> Linux Research and Development | Fax: (630) 840-6345
> Computing Division, OSS Dept. | email: yocum@fnal.gov .~. L
> Fermi National Accelerator Lab | WWW: www-oss.fnal.gov/~yocum/ /V\ I
> P.O. Box 500 | // \\ N
> Batavia, IL 60510 | "TANSTAAFL" /( )\ U
> ________________________________|_________________________________ ^`~'^__X_
>
>
>
>
> -
> 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/
>
-
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/