netdev - Re: [PATCH: 2.6.13-15-SMP 3/3] network: concurrentlyrunsoftirqnetwork code on SMP

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

Date:	Wed, 26 Sep 2007 09:26:37 -0400
From:	jamal <hadi@...erus.ca>
To:	John Ye <johny@...mco.com.cn>
Cc:	Stephen Hemminger <shemminger@...ux-foundation.org>,
	David Miller <davem@...emloft.net>, netdev@...r.kernel.org,
	kuznet@....inr.ac.ru, pekkas@...core.fi, jmorris@...ei.org,
	kaber@...eworks.de, iceburgue@...il.com
Subject: Re: [PATCH: 2.6.13-15-SMP 3/3] network:
	concurrentlyrunsoftirqnetwork code on SMP

On Wed, 2007-26-09 at 10:12 +0800, John Ye wrote:

> cpu hash (srcip + dstip) % nr_cpus, plus checking cpu balance periodically,
> shift cpu by an extra seed value?

That may work maybe even add ipproto as a 3rd tuple; experiments will
tell - you need to be able to generate a random enough traffic pattern.
For example if the traffic pattern is always for your local host the
dstip may not be useful to the hash. 
You could always try the hash tests outside first; look at some of the
jenkins hashes in the kernel

> __do_IRQ has a tendency to collect same IRQ on different CPUs into one CPU
> when NIC is busy(by IRQ_PENDING & IRQ_INPROGRESS control skill). so,
> dispatch the load to SMP here may be good thing(?).

possibly. Or you may wanna tie the NIC IRQ to a CPU. 

cheers,
jamal


-
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html