netdev - Re: [E1000-devel] Performance degradration 2.6.25->2.6.26

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]

Message-ID: <48CA839D.308@uwaterloo.ca>
Date:	Fri, 12 Sep 2008 10:58:37 -0400
From:	Elad Lahav <elahav@...terloo.ca>
To:	"Brandeburg, Jesse" <jesse.brandeburg@...el.com>
CC:	Elad Lahav <elad_lahav@...rs.sourceforge.net>,
	e1000-devel@...ts.sourceforge.net, netdev@...r.kernel.org
Subject: Re: [E1000-devel] Performance degradration 2.6.25->2.6.26

>> HyperThreading, for a total of 4 logical processors, and 4 Intel Gigabit
>>   NICs on a PCI 64/66 bus (82546EB). In the experiments, I am pinning
>> four sending processes (one per NIC) to logical processors 0 and 2, and
>> the NIC interrupts to logical processors 1 and 3, such that interrupts
>> are serviced by the sibling logical processor of the one sending the
>> packets. I have used both the driver that comes with the Linux kernel
>> (7.3.20-k2-NAPI), as well as a more recent one (7.6.15.5).

I believe I have found the problem, and it has nothing to do with the driver.
Up to the latest kernel, logical processors on the same chip had sequential CPU IDs. So 
CPU 0 and CPU 1 were two logical processors on the first physical one, 2 and 3 on the 
second physical one, etc.
It seems that now this ordering has changed. I was running my experiments on logical 
processors 0 and 2, assuming they were on different physical processors, when, in fact, 
they were sharing the same one. When pinning the processes to logical processor 0 and 1, I 
get at least as good a performance as I do on previous kernels.

Thanks,
Elad

--
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