netdev - "rcu_sched self-detected stall on CPU" on highload dns servers

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>] [day] [month] [year] [list]

Date:	Tue, 16 Apr 2013 22:03:02 +0400
From:	ya dmesg <ya.dmesg@...dex.ru>
To:	linux-kernel@...r.kernel.org, netdev@...r.kernel.org
Subject: "rcu_sched self-detected stall on CPU" on highload dns servers

Hi everyone.

We areexperiencing  100% reproducable kernel lockups (4 servers crashes 2-3 times a day each) on a highload DNS servers (30-40kpps udp requests).
Hardware is pretty different, I can provide lspci if needed. We are using Intel ethernet adapters with Jumbo Frames enabled and we are using no swap at all. 

e1000e driver:
03:00.0 Ethernet controller: Intel Corporation 82574L Gigabit Network Connection
08:00.0 Ethernet controller: Intel Corporation 82572EI Gigabit Ethernet Controller (Copper) (rev 06)

igb driver:
01:00.1 Ethernet controller: Intel Corporation 82576 Gigabit Network Connection (rev 01)

All hardware affected. 

My system is Ubuntu-12.04 Server LTS. But this problem occures on many kernel versions:
linux-3.2 ubuntu lts
linux-3.5 quantal ubuntu lts
linux-3.4.* kernel.org LTS
linux-3.8.* kernel.org LTS

I've attached crash I've catched with ipmitool. If there is anything I can do to help to debug this problem, please, let me know!
Thanks.

View attachment "crash.txt" of type "text/plain" (50281 bytes)