* no DRQ after issuing MULTWRITE_EXT ?
@ 2007-02-01 9:18 Steven Scholz
2007-02-01 9:25 ` Eric D. Mudama
2007-02-01 13:06 ` Sergei Shtylyov
0 siblings, 2 replies; 8+ messages in thread
From: Steven Scholz @ 2007-02-01 9:18 UTC (permalink / raw)
To: linux-ide
Hi all,
I am seeing kernel messages like
[ 1284.480000] hda: status timeout: status=0xd0 { Busy }
[ 1284.480000] ide: failed opcode was: unknown
[ 1284.480000] hda: no DRQ after issuing MULTWRITE_EXT
[ 1284.490000] ide0: unexpected interrupt, status=0x80, count=1
[ 1284.830000] ide0: reset: success
with a 2.5" Seagate ST940813AM on my embedded ARM system (linux 2.6.14, no
IDE controller. HDD registers just memory mapped).
HDD is used in PIO4 with MultSect=16.
What exactly does that mean? Only that the HDD is to slow to answer this
request with 100ms (WAIT_DRQ=(HZ/10))?
And will the request issued again after the reset of the drive?
Some old posting mentions that disabling "multi sector write" would help.
But I did not find any references to why this would solve the problem.
Is it a bug of this special HDD? Or a kernel problem?
Thanks a million!
Steven
^ permalink raw reply [flat|nested] 8+ messages in thread* Re: no DRQ after issuing MULTWRITE_EXT ?
2007-02-01 9:18 no DRQ after issuing MULTWRITE_EXT ? Steven Scholz
@ 2007-02-01 9:25 ` Eric D. Mudama
2007-02-01 9:30 ` Steven Scholz
2007-02-01 13:06 ` Sergei Shtylyov
1 sibling, 1 reply; 8+ messages in thread
From: Eric D. Mudama @ 2007-02-01 9:25 UTC (permalink / raw)
To: Steven Scholz; +Cc: linux-ide
On 2/1/07, Steven Scholz <steven.scholz@imc-berlin.de> wrote:
> Hi all,
>
> I am seeing kernel messages like
>
> [ 1284.480000] hda: status timeout: status=0xd0 { Busy }
> [ 1284.480000] ide: failed opcode was: unknown
> [ 1284.480000] hda: no DRQ after issuing MULTWRITE_EXT
> [ 1284.490000] ide0: unexpected interrupt, status=0x80, count=1
> [ 1284.830000] ide0: reset: success
>
> with a 2.5" Seagate ST940813AM on my embedded ARM system (linux 2.6.14, no
> IDE controller. HDD registers just memory mapped).
>
> HDD is used in PIO4 with MultSect=16.
>
> What exactly does that mean? Only that the HDD is to slow to answer this
> request with 100ms (WAIT_DRQ=(HZ/10))?
>
> And will the request issued again after the reset of the drive?
>
> Some old posting mentions that disabling "multi sector write" would help.
> But I did not find any references to why this would solve the problem.
> Is it a bug of this special HDD? Or a kernel problem?
Do you see this on every multiblock PIO write? Or just occasionally?
^ permalink raw reply [flat|nested] 8+ messages in thread* Re: no DRQ after issuing MULTWRITE_EXT ?
2007-02-01 9:25 ` Eric D. Mudama
@ 2007-02-01 9:30 ` Steven Scholz
0 siblings, 0 replies; 8+ messages in thread
From: Steven Scholz @ 2007-02-01 9:30 UTC (permalink / raw)
To: Eric D. Mudama; +Cc: linux-ide
Eric,
>> I am seeing kernel messages like
>>
>> [ 1284.480000] hda: status timeout: status=0xd0 { Busy }
>> [ 1284.480000] ide: failed opcode was: unknown
>> [ 1284.480000] hda: no DRQ after issuing MULTWRITE_EXT
>> [ 1284.490000] ide0: unexpected interrupt, status=0x80, count=1
>> [ 1284.830000] ide0: reset: success
>> ...
>
> Do you see this on every multiblock PIO write? Or just occasionally?
Only occasionally.
--
Steven
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: no DRQ after issuing MULTWRITE_EXT ?
2007-02-01 9:18 no DRQ after issuing MULTWRITE_EXT ? Steven Scholz
2007-02-01 9:25 ` Eric D. Mudama
@ 2007-02-01 13:06 ` Sergei Shtylyov
2007-02-01 13:33 ` Steven Scholz
1 sibling, 1 reply; 8+ messages in thread
From: Sergei Shtylyov @ 2007-02-01 13:06 UTC (permalink / raw)
To: Steven Scholz; +Cc: linux-ide
Hello.
Steven Scholz wrote:
> I am seeing kernel messages like
> [ 1284.480000] hda: status timeout: status=0xd0 { Busy }
> [ 1284.480000] ide: failed opcode was: unknown
> [ 1284.480000] hda: no DRQ after issuing MULTWRITE_EXT
> [ 1284.490000] ide0: unexpected interrupt, status=0x80, count=1
> [ 1284.830000] ide0: reset: success
Looks like a spurious interrupt... Is your IDE IRQ shared with other devices?
> with a 2.5" Seagate ST940813AM on my embedded ARM system (linux 2.6.14, no
> IDE controller. HDD registers just memory mapped).
> HDD is used in PIO4 with MultSect=16.
> What exactly does that mean? Only that the HDD is to slow to answer this
> request with 100ms (WAIT_DRQ=(HZ/10))?
Doubt it. The old ATA standard specified the maximum DRQ assertion time of
20 ms.
> And will the request issued again after the reset of the drive?
It should be.
MBR, Sergei
^ permalink raw reply [flat|nested] 8+ messages in thread* Re: no DRQ after issuing MULTWRITE_EXT ?
2007-02-01 13:06 ` Sergei Shtylyov
@ 2007-02-01 13:33 ` Steven Scholz
2007-02-01 13:39 ` Sergei Shtylyov
0 siblings, 1 reply; 8+ messages in thread
From: Steven Scholz @ 2007-02-01 13:33 UTC (permalink / raw)
To: Sergei Shtylyov; +Cc: linux-ide
Hi,
>> I am seeing kernel messages like
>
>> [ 1284.480000] hda: status timeout: status=0xd0 { Busy }
>> [ 1284.480000] ide: failed opcode was: unknown
>> [ 1284.480000] hda: no DRQ after issuing MULTWRITE_EXT
>> [ 1284.490000] ide0: unexpected interrupt, status=0x80, count=1
>> [ 1284.830000] ide0: reset: success
>
> Looks like a spurious interrupt... Is your IDE IRQ shared with other
> devices?
No.
But IIUC then first the HDD times out, the ide driver handles this and then
an irq occurs which is probably the irq the driver was waiting for. And
since the driver already handled the timeout that (delayed) irq is of course
"unexpected" ... (Just a guess)
> Doubt it. The old ATA standard specified the maximum DRQ assertion
> time of 20 ms.
I know.
>> And will the request issued again after the reset of the drive?
>
> It should be.
Thanks.
Steven
^ permalink raw reply [flat|nested] 8+ messages in thread* Re: no DRQ after issuing MULTWRITE_EXT ?
2007-02-01 13:33 ` Steven Scholz
@ 2007-02-01 13:39 ` Sergei Shtylyov
2007-02-01 16:02 ` Steven Scholz
0 siblings, 1 reply; 8+ messages in thread
From: Sergei Shtylyov @ 2007-02-01 13:39 UTC (permalink / raw)
To: Steven Scholz; +Cc: linux-ide
Hello.
Steven Scholz wrote:
>>>I am seeing kernel messages like
>>>[ 1284.480000] hda: status timeout: status=0xd0 { Busy }
>>>[ 1284.480000] ide: failed opcode was: unknown
>>>[ 1284.480000] hda: no DRQ after issuing MULTWRITE_EXT
>>>[ 1284.490000] ide0: unexpected interrupt, status=0x80, count=1
>>>[ 1284.830000] ide0: reset: success
>>
>> Looks like a spurious interrupt... Is your IDE IRQ shared with other
>>devices?
> No.
> But IIUC then first the HDD times out, the ide driver handles this and then
> an irq occurs which is probably the irq the driver was waiting for. And
The driver is *not* waiting for any IRQ after issuing MULTWRITE_EXT, that's
why it's "unexpected".
> since the driver already handled the timeout that (delayed) irq is of course
> "unexpected" ... (Just a guess)
>> Doubt it. The old ATA standard specified the maximum DRQ assertion
>>time of 20 ms.
> I know.
>>>And will the request issued again after the reset of the drive?
>> It should be.
> Thanks.
> Steven
MBR, Sergei
^ permalink raw reply [flat|nested] 8+ messages in thread* Re: no DRQ after issuing MULTWRITE_EXT ?
2007-02-01 13:39 ` Sergei Shtylyov
@ 2007-02-01 16:02 ` Steven Scholz
2007-02-01 16:06 ` Sergei Shtylyov
0 siblings, 1 reply; 8+ messages in thread
From: Steven Scholz @ 2007-02-01 16:02 UTC (permalink / raw)
To: Sergei Shtylyov; +Cc: linux-ide
Hi Sergei,
>>> Looks like a spurious interrupt... Is your IDE IRQ shared with other
>>> devices?
>> ..
>> But IIUC then first the HDD times out, the ide driver handles this and
>> then an irq occurs which is probably the irq the driver was waiting for.
>
> The driver is *not* waiting for any IRQ after issuing MULTWRITE_EXT,
> that's why it's "unexpected".
Hmm. But how does he "know" when that MULTWRITE_EXT is finished!?
Steven
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: no DRQ after issuing MULTWRITE_EXT ?
2007-02-01 16:02 ` Steven Scholz
@ 2007-02-01 16:06 ` Sergei Shtylyov
0 siblings, 0 replies; 8+ messages in thread
From: Sergei Shtylyov @ 2007-02-01 16:06 UTC (permalink / raw)
To: Steven Scholz; +Cc: linux-ide
Hello.
Steven Scholz wrote:
>>>> Looks like a spurious interrupt... Is your IDE IRQ shared with other
>>>>devices?
>>>..
>>>But IIUC then first the HDD times out, the ide driver handles this and
>>>then an irq occurs which is probably the irq the driver was waiting for.
>> The driver is *not* waiting for any IRQ after issuing MULTWRITE_EXT,
>>that's why it's "unexpected".
> Hmm. But how does he "know" when that MULTWRITE_EXT is finished!?
It's considered finished in this case as there was no starting DRQ
"handshake". The first interrupt should happen only after the first block of
data is written.
> Steven
MBR, Sergei
^ permalink raw reply [flat|nested] 8+ messages in thread
end of thread, other threads:[~2007-02-01 16:06 UTC | newest]
Thread overview: 8+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2007-02-01 9:18 no DRQ after issuing MULTWRITE_EXT ? Steven Scholz
2007-02-01 9:25 ` Eric D. Mudama
2007-02-01 9:30 ` Steven Scholz
2007-02-01 13:06 ` Sergei Shtylyov
2007-02-01 13:33 ` Steven Scholz
2007-02-01 13:39 ` Sergei Shtylyov
2007-02-01 16:02 ` Steven Scholz
2007-02-01 16:06 ` Sergei Shtylyov
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).