Re: Fw: DriveReady SeekComplete problems

Re: Fw: DriveReady SeekComplete problems

[Artur Jasowicz]

Andre,
I've been away from the office for a few days. I am getting back to you
with results after applying the patch.

The patch applied cleanly, but did not fix the problem. I am still getting
bad DMA status (dma_stat=1) and status=0x50 { DriveReady SeekComplete }
messages with DMA on.

I've done further tests and observed following:

-creating RAID1 array of 5 drives does not produce errors
-creating RAID5 array causes errors
-doing dd if=/dev/hdx of=/dev/null bs=512 with x=one of the drives in array
 works fine as long as the drives are on the same controller. I've tried
this
 with up to 10 dd commands, 5/drive 2 drives on same controller
-the above command causes errors when used with drives on diferent
 controllers. i.e. if I start dd on hde - works fine, then I execute dd on
hdi
 and see errors

Creating RAID1 is mostly writing to drives, while doing dd and creating
RAID5 involves intense reading from drives. This de me think that the
system can't keep up with reading flood of data comming from the drives.

I've tried limiting speed of resyncing array by doing
#echo 1000 > /proc/sys/dev/raid/speed_limit_max
This slowed down pace at which error messages appeared in logs, but
did not eliminate them. I've tried diferent values instead of 1000,
the higher, the worse things were.

What else can I try?

Artur

From: Andre Hedrick <andre@linux-ide.org>
>
> Please try the latest driver changes on www.linuxdiskcert.org
>
> If it still presists let me know, again!
>
> Cheers,
>
> On Mon, 13 May 2002, Artur Jasowicz wrote:
>
> > ----- Original Message -----
> > From: Artur Jasowicz <arturj@mousebusiness.com>
> > To: <linux-kernel@vger.kernel.org>
> > Sent: Wednesday, May 08, 2002 12:34 PM
> > Subject: DriveReady SeekComplete problems
> >
> >
> > > I am building a file server with 5 drive software RAID5 array. I am
using
> > three IWill SIDE-100 (Highpoint 370A) controllers as my IDE interfaces,
not
> > using their RAID functionality. One Maxtor 160GB drive per channel, two
> > channels per controller. I plan on adding hot spare as the sixth drive
in
> > the future. There's one 160GB partition on each drive. Linux version
> > 2.4.19-pre7smp-020502b (root@production) (gcc version 2.96 20000731 (Red
Hat
> > Linux 7.1 2.96-98)) #6 SMP Thu May 2 12:15:34 CDT 2002
> > > This is a dual Athlon 2000+ MP on Tyan Tiger S2466N-4 with 1GB RAM. OS
and
> > swap runs on separate drives and controllers. This array will be just
for
> > data once it is configured.
> > >
[snip lengthy description of error messages]

Re: Fw: DriveReady SeekComplete problems

[Artur Jasowicz]

Actually, I did something along these lines early on in testing. I had four
diferent drives plugged in. I had one 6GB, two 80GB and one 160GB. I've
tried doing dd if=/dev/hd... of=/dev/null. This was with DMA on. Everything
seemed to work fine with up to three drives, but after I've issused above
command for the fourth drive, I started getting errror messages. Now, to my
knowledge I'm not using a Highpoint driver. I'm just letting Kernel detect
whatever it sees and use it.

Today, I've tried mkraid on 4-drive config. With DMA disabled it seemed to
work without errors at miserable 500K/s reported by /proc/mdstat. Even my
old K6-2 333 with four 80GB on two IWills ran at 800+K/s. You would expect
more from a dual 2GHz. With DMA enabled I got 2000K/s with log full of the
same errors again.

Another odd thing is that both CPUs are running at 99% usage when trying to
sync array. Strange for 4GHz total clock speed. I was expecting that such
fast CPU's would barely break the sweat doing IDE I/O.

Any other IDE controllers I should be looking at?

Artur

From: Pieter Hollants <pieter@hollants.com>
> I'd say it's a driver problem (had nothing but trouble with Highpoint
> myself).
> To verify this: try creating an ordinary partition on one of the disks and
> do some mass copying & reading onto it, with and without DMA disabled.
> You'll most certainly still get these errors.
>
> Artur Jasowicz sagte:
> > I am building a file server with 5 drive software RAID5 array. I am
> > using three IWill SIDE-100 (Highpoint 370A) controllers as my IDE
> > interfaces, not using their RAID functionality. One Maxtor 160GB drive
> > per channel, two channels per controller. I plan on adding hot spare as
> > the sixth drive in the future. There's one 160GB partition on each
> > drive. Linux version 2.4.19-pre7smp-020502b (root@production) (gcc
> > version 2.96 20000731 (Red Hat Linux 7.1 2.96-98)) #6 SMP Thu May 2
> > 12:15:34 CDT 2002
>  This is a dual Athlon 2000+ MP on Tyan Tiger
> > S2466N-4 with 1GB RAM. OS and swap runs on separate drives and
> > controllers. This array will be just for data once it is configured.
> [...]
> > 17:34:39 production kernel: md: hdk1 [events: 00000001]<6>(write)
> > hdk1's sb offset: 160079552
>  May  7 17:34:39 production kernel: hde: 0
> > bytes in FIFO
> > May  7 17:34:39 production kernel: ide_dmaproc: chipset supported
> > ide_dma_timeout func only: 14
>  May  7 17:34:39 production kernel: hde:
> > dma_intr: bad DMA status (dma_stat=1)
>  May  7 17:34:39 production
> > kernel: hde: dma_intr: status=0x50 { DriveReady SeekComplete }
>  May  7
> > 17:34:39 production kernel: hdi: 4 bytes in FIFO
> [...]
> >
> > I've mdstopped the process and disbled DMA for all RAID members with
> > hdparm -d 0. Tried mdrun again and got following messages:
>
> > May  7 18:43:26 production kernel: hdi: status error: status=0x58 {
> > DriveReady SeekComplete DataRequest }
>  May  7 18:43:26 production
> > kernel: hdi: drive not ready for command
>  May  7 18:44:40 production
> > kernel: hdi: status error: status=0x58 { DriveReady SeekComplete
> > DataRequest }
>  May  7 18:44:40 production kernel: hdi: drive not ready
> > for command