Re: 5.3-RELEASE: WARNING - WRITE_DMA interrupt timout - what does it mean?

From: Frode Nordahl <frode_at_nordahl.net>
Date: Mon, 15 Nov 2004 14:21:45 +0100
On Nov 10, 2004, at 11:34, Robert Watson wrote:

>
> On Wed, 10 Nov 2004, Søren Schmidt wrote:
>
>>> I'm still a bit skeptical that the task queue is at fault -- I run my
>>> notebook with continuous measurement of the latency to schedule 
>>> tasks,
>>> generating a warning for any latency > .5 seconds, and the only time 
>>> I
>>> ever see that sort of latency is during the boot process when ACPI 
>>> has
>>> scheduled a task to run, but the task queue thread has not yet been
>>> allowed to run:
>>
>> Right, the timeout is 5 secs. I havn't looked into how the taskqueues
>> are handled recently, but in case of ATA read/writes it is the
>> bio_taskqueue handled by geom thats in use not the catchall ones, does
>> your timing cover that as well?
>
> Nope -- I had assumed that the suggested task problems in question was 
> the
> use of taskqueue_enqueue() in ata-queue for the timeout, rather than 
> the
> bio_taskqueue() ata_completed() call.

Do you have a patch that covers these as well?

I have two systems not going production anytime soon, and I will be 
more than happy to put these to work to help find this problem in the 
mean time.

I can make them panic at will, but I think the panics are useless for 
finding the problem, since the panic probably occurs after errors made 
to the filesystem because of this bug.

Mvh,
Frode Nordahl


> Robert N M Watson             FreeBSD Core Team, TrustedBSD Projects
> robert_at_fledge.watson.org      Principal Research Scientist, McAfee 
> Research
>
> _______________________________________________
> freebsd-current_at_freebsd.org mailing list
> http://lists.freebsd.org/mailman/listinfo/freebsd-current
> To unsubscribe, send any mail to 
> "freebsd-current-unsubscribe_at_freebsd.org"
Received on Mon Nov 15 2004 - 12:21:46 UTC

This archive was generated by hypermail 2.4.0 : Wed May 19 2021 - 11:38:22 UTC