All of lore.kernel.org
 help / color / mirror / Atom feed
From: Anand Raj Manickam <anandrm@gmail.com>
To: Patrick McHardy <kaber@trash.net>
Cc: Eric Dumazet <eric.dumazet@gmail.com>,
	netdev@vger.kernel.org, netfilter-devel@vger.kernel.org
Subject: Re: Kernel Panic on OOM with 10 HTB rules
Date: Thu, 16 Sep 2010 17:50:39 +0530	[thread overview]
Message-ID: <AANLkTi=H5WnSWBNW3s8M9cWfAt32JFyvNwNTSoYiiF1W@mail.gmail.com> (raw)
In-Reply-To: <4C91E4E1.4030001@trash.net>

Things seem to be fine now after i reduced imq devs txqueuelen to 32
and MTU to 1600 and no of imqs to 2.
Thank you all for the Suggestions .
Anand

On Thu, Sep 16, 2010 at 3:05 PM, Patrick McHardy <kaber@trash.net> wrote:
> On 08.09.2010 14:42, Eric Dumazet wrote:
>> Le mercredi 08 septembre 2010 à 16:22 +0530, Anand Raj Manickam a
>> écrit :
>>> I m struck with
>>> Kernel Panic - Out of Memory Issue  when  traffic  is more than 100k
>>> pps  and have  around 10 tc rules.
>>>
>>> There is NO kernel panic with 1 tc rule .
>>>
>>> I using a 2.6.34.6 ( latest stable kernel) with SMP enabled
>>>
>>> The rules are simple -
>>> 10 iptable rules :
>>> iptables -t mangle -I FORWARD -s x.x.x.x  -j CLASSIFY --set-class 0xz:0xy
>>>
>>> 10 tc rules :
>>> tc  class add dev imq0 parent 1:z classid 1:y htb rate 2kbit ceil 32768kbps
>>>
>>> I m using  Intel Xeon Quad core x5570, 12GB RAM , with 8 e1000e , irq
>>> affined ( 1 pair per core)
>>>
>>> There is NO issue / CRASH with multiple iptable rules marking to the
>>> same tc rule/HTB class , i can sucessfully pass more than 200k pps /
>>> 800Mbps traffic .
>>>
>>> But when each iptable rule is marking to seprate tc rule/HTB class and
>>> when the traffic exceeds 100K pps / 20000 connections per second , we
>>> hit this Out of Memory - Kernel panic condition .
>>> Any help is appreciated . Do let me know if any more further
>>> information is need.
>>
>> Hi Anand
>>
>> Could you give :
>>
>> 1) A complete stack trace / panic report
>> 2) cat /proc/interrupts
>> 3) ifconfig -a
>> 4) cat /proc/sys/vm/min_free_kbytes
>> 5) cat /proc/meminfo
>>
>> for each eth*
>>  ethtool -g eth*
>
> Please try to reproduce without the imq patch.
>
--
To unsubscribe from this list: send the line "unsubscribe netfilter-devel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

      reply	other threads:[~2010-09-16 12:20 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-09-08 10:52 Kernel Panic on OOM with 10 HTB rules Anand Raj Manickam
2010-09-08 12:42 ` Eric Dumazet
2010-09-08 14:09   ` Anand Raj Manickam
2010-09-08 14:45     ` Eric Dumazet
2010-09-08 15:02       ` Krzysztof Olędzki
2010-09-08 17:25       ` Jarek Poplawski
2010-09-16  9:35   ` Patrick McHardy
2010-09-16 12:20     ` Anand Raj Manickam [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to='AANLkTi=H5WnSWBNW3s8M9cWfAt32JFyvNwNTSoYiiF1W@mail.gmail.com' \
    --to=anandrm@gmail.com \
    --cc=eric.dumazet@gmail.com \
    --cc=kaber@trash.net \
    --cc=netdev@vger.kernel.org \
    --cc=netfilter-devel@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.