linux-kernel - Re: maxcpus confusion

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: <c89c1a15-7a71-fbbb-e72d-dbdbb4cc515e@infradead.org>
Date:   Mon, 4 Dec 2017 14:40:43 -0800
From:   Randy Dunlap <rdunlap@...radead.org>
To:     Heiko Carstens <heiko.carstens@...ibm.com>
Cc:     LKML <linux-kernel@...r.kernel.org>, X86 ML <x86@...nel.org>
Subject: Re: maxcpus confusion

On 12/04/2017 01:02 PM, Heiko Carstens wrote:
> On Fri, Dec 01, 2017 at 12:58:47PM -0800, Randy Dunlap wrote:
>> Hi,
>>
>> I used "maxcpus=1" on a recent x86 boot (4.15-rc1) and got 4 CPUs (all of
>> them AFAICT).  When I use "nr_cpus=1", I do get a hard limit of one CPU.
>>
>>
>> A few boot log excerpts:
>>
>> [    0.000000] smpboot: Allowing 8 CPUs, 4 hotplug CPUs
>> ...
>> [    0.030007] smp: Bringing up secondary CPUs ...
>> [    0.030109] smp: Brought up 1 node, 1 CPU
>> [    0.030181] smpboot: Max logical packages: 4
>> [    0.030255] smpboot: Total of 1 processors activated (4789.06 BogoMIPS)
>>
>>
>> Is systemd (or something else) later onlining the other CPUs?
>>
>> /sys/devices/system/cpu/online is 0-3
>> /sys/devices/system/cpu/offline is 4-7
> 
> Check /lib/udev/rules.d/ for a rule that auto-onlines CPUs.
> This behavior is distribution specific.

You got it in one try.  Thanks.  It would have taken me awhile to find that.

I owe you a beer if you get to Portland, Oregon. :)

-- 
~Randy