linux-kernel - Re: [PATCH v3 2/2] Documentation: kdump: add description of bringing up SMP dump-capture kernel

Open Source and information security mailing list archives

Message-ID: <57A154B7.4090407@cn.fujitsu.com>
Date:	Wed, 3 Aug 2016 10:19:35 +0800
From:	"Zhou, Wenjian/周文剑" 
	<zhouwj-fnst@...fujitsu.com>
To:	Baoquan He <bhe@...hat.com>
CC:	<linux-kernel@...r.kernel.org>, <dyoung@...hat.com>,
	<d.hatayama@...fujitsu.com>, <kexec@...ts.infradead.org>
Subject: Re: [PATCH v3 2/2] Documentation: kdump: add description of bringing
 up SMP dump-capture kernel

On 08/03/2016 10:18 AM, Baoquan He wrote:
> On 08/03/16 at 10:05am, "Zhou, Wenjian/周文剑" wrote:
>> On 08/03/2016 09:58 AM, Baoquan He wrote:
>>> On 08/03/16 at 08:59am, Zhou Wenjian wrote:
>>>> SMP dump-capture kernel is useful to improve the performance of kdump in
>>>> some cases. So add the description of bringing up SMP dump-capture kernel.
>>>>
>>>> Signed-off-by: Zhou Wenjian <zhouwj-fnst@...fujitsu.com>
>>>> ---
>>>>   Documentation/kdump/kdump.txt | 7 +++++++
>>>>   1 file changed, 7 insertions(+)
>>>>
>>>> diff --git a/Documentation/kdump/kdump.txt b/Documentation/kdump/kdump.txt
>>>> index 4aa194e..948b42d 100644
>>>> --- a/Documentation/kdump/kdump.txt
>>>> +++ b/Documentation/kdump/kdump.txt
>>>> @@ -396,6 +396,13 @@ Notes on loading the dump-capture kernel:
>>>>     Note, though maxcpus always works, we should replace it by nr_cpus to
>>>>     save memory if supported by the current ARCH, such as x86.
>>>>
>>>> +* We should bring up a SMP dump-capture kernel if we intend to use
>>>
>>> Well, here about SMP dump-capture kernel do you mean kdump kernel with
>>> multi-cpu? If I understand it correctly, it's still SMP kdump kernel
>>> though nr_cpus=1 is specified.
>>>
>>
>> Actually, I haven't know the detail about it. I wrote the sentence almost
>> based on the original description:
>>
>> * We generally don' have to bring up a SMP kernel just to capture the
>>    dump. Hence generally it is useful either to build a UP dump-capture
>>    kernel or specify maxcpus=1 option while loading dump-capture kernel.
>
> This is right. Here it means either you build a UP kernel used for kdump
> kernel because kdump kernel doesn't have to be the same as the 1st
> kernel, or you use smp kernel with maxcpus=1 specified. So if you want
> to say kdump kernel with multi-cpu need be brought up to improve the
> performance of parallel dumping, you need point it out clearly.
>

I see. I will update the patch.

>>
>>>> +  multi-threads programs with it, such as parallel dump feature of
>>>> +  makedumpfile. Otherwise, the multi-threads program may have a great
>>>> +  performance degradation. To bring up a SMP dump-capture kernel, we
>>>> +  should specify maxcpus\nr_cpus and disable_cpu_apic=[X] options while
>>>> +  loading it.
>>>> +
>>>>   * For s390x there are two kdump modes: If a ELF header is specified with
>>>>     the elfcorehdr= kernel parameter, it is used by the kdump kernel as it
>>>>     is done on all other architectures. If no elfcorehdr= kernel parameter is
>>>> --
>>>> 1.8.3.1
>>>>
>>>>
>>>>
>>>>
>>>> _______________________________________________
>>>> kexec mailing list
>>>> kexec@...ts.infradead.org
>>>> http://lists.infradead.org/mailman/listinfo/kexec
>>>
>>>
>>
>>
>> --
>> Thanks
>> Zhou
>>
>>
>
>

-- 
Thanks
Zhou

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