netdev - RE: [HELP] BAD interrupts

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Thu, 24 Dec 2009 16:15:44 +0530
From:	"Kumar Gopalpet-B05799" <B05799@...escale.com>
To:	"gshan" <gshan@...atel-lucent.com>, <michael@...erman.id.au>,
	<avorontsov@...mvista.com>
Cc:	<netdev@...r.kernel.org>, <linuxppc-dev@...ts.ozlabs.org>
Subject: RE: [HELP] BAD interrupts

 

>-----Original Message-----
>From: gshan [mailto:gshan@...atel-lucent.com] 
>Sent: Thursday, December 24, 2009 5:16 PM
>To: michael@...erman.id.au
>Cc: Kumar Gopalpet-B05799; netdev@...r.kernel.org; 
>linuxppc-dev@...ts.ozlabs.org
>Subject: Re: [HELP] BAD interrupts
>
>Michael Ellerman wrote:
>> On Wed, 2009-12-23 at 19:41 +0530, Kumar Gopalpet-B05799 wrote:
>>   
>>> Hi all,
>>>  
>>> I am trying linux 2.6.32-rc3 in SMP mode. I am seeing a lot of BAD 
>>> interrupts when I do a "cat  /proc/interrupts".
>>>  
>>> I am running a forwarding application b/w two ethernet ports 
>>> (ethernet uses gianfar driver).
>>>  
>>> Has any one observed these BAD interrupts ? If so, can someone help 
>>> me in understanding why these interrupts come and how to 
>resolve it ?
>>>     
>>
>> You'll need to tell us what platform you're running on.
>>
>> The BAD interrupts come from ppc_spurious_interrupts. It's a 
>count of 
>> the number of times we entered do_IRQ() (ie. took an external 
>> interrupt), but when we asked the interrupt controller which irq it 
>> was, the interrupt controller said there was no irq.
>>
>> Depending on your interrupt controller that might happen 
>sometimes for 
>> valid reasons. Or it might indicate something is setup wrong.
>>
>> cheers
>>   
>I think it will help to show us your /proc/interrupts so that 
>how you suffered from bad interrupts.
>

I am running linux-2.6.29 in SMP mode on P2020RDB ( ruuning at
1200/600/667). The test scenario forwarding 
application and is a bidirectioanl flow between eth0 & eth2.

Attached is the complete log of the test scenario.

I also noted another observation that when all the interrupts are mapped
to a single core, the BAD interrupts stop coming.

--

Thanks
Sandeep 


View attachment "smp_log_bad_intrs.txt" of type "text/plain" (27221 bytes)