Re: Native preemption is the culprit [was Re: today's CURRENT lockups]

From: Thorsten Greiner <thorsten_at_tgreiner.net>
Date: Thu, 8 Jul 2004 16:10:21 +0200
* Taku YAMAMOTO <taku_at_tackymt.homeip.net> [2004-07-08 15:31]:
> This patch is tested on P4_at_2.8GHz HTT-enabled machine.
> 
> It has been running for several hours without a hang, although I have to
> admit that this machine is too idle, far from being stressed.

On my box I get these warnings:

Jul  8 15:56:46 tybalt kernel: ad0: WARNING - WRITE_DMA interrupt
was seen but timeout fired LBA=4063551
Jul  8 15:57:03 tybalt kernel: ad0: WARNING - READ_DMA interrupt was
seen but timeout fired LBA=19449983
Jul  8 15:57:30 tybalt kernel: ad0: WARNING - READ_DMA interrupt was
seen but timeout fired LBA=19981629
Jul  8 15:57:50 tybalt kernel: ad0: WARNING - READ_DMA interrupt was
seen but timeout fired LBA=11457711
Jul  8 15:58:22 tybalt kernel: ad0: WARNING - READ_DMA interrupt was
seen but timeout fired LBA=24073775
Jul  8 15:58:25 tybalt kernel: ad0: WARNING - WRITE_DMA interrupt
was seen but timeout fired LBA=25168335

This is while performing a background fsck. In this state the system
seems to hang, probably waiting for some disk i/o to finish.

Regards
        -Thorsten

-- 
Unix is user friendly, it's just particular about the friends it chooses.
 
This message is digitally signed. To verify its integrity, download a copy
of GnuPG for your operating system from http://www.gnupg.org .

Received on Thu Jul 08 2004 - 12:10:27 UTC

This archive was generated by hypermail 2.4.0 : Wed May 19 2021 - 11:38:00 UTC