Subject: Re: [RFC PATCH] sched/topology: Introduce NUMA identity node sched
 domain
To: Peter Zijlstra <peterz@infradead.org>
References: <1502378452-6632-1-git-send-email-suravee.suthikulpanit@amd.com>
 <20170810164149.2rkkp55km5cxcarg@hirez.programming.kicks-ass.net>
 <ab9866af-f88b-91d8-0e48-423dbcb00ae9@amd.com>
 <f1eed7cb-ea9f-08c4-153d-36006ffc033c@amd.com>
 <20170811091527.wyngvvq2dy3yzik2@hirez.programming.kicks-ass.net>
Cc: linux-kernel@vger.kernel.org, mingo@redhat.com, bp@suse.de
From: Suravee Suthikulpanit <Suravee.Suthikulpanit@amd.com>
Message-ID: <f85d6d5d-64b7-7e08-939f-b321e5f05949@amd.com>
Date: Mon, 14 Aug 2017 14:44:59 +0700
User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.12; rv:45.0)
 Gecko/20100101 Thunderbird/45.8.0
MIME-Version: 1.0
In-Reply-To: <20170811091527.wyngvvq2dy3yzik2@hirez.programming.kicks-ass.net>
Content-Type: text/plain; charset=windows-1252; format=flowed
Content-Transfer-Encoding: 7bit
SpamDiagnosticOutput: 1:99
SpamDiagnosticMetadata: NSPM
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 14 Aug 2017 07:45:05.6071 (UTC)
X-MS-Exchange-CrossTenant-FromEntityHeader: Hosted
X-MS-Exchange-Transport-CrossTenantHeadersStamped: DM5PR12MB1739
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org
Content-Length: 2129
Lines: 53


On 8/11/17 16:15, Peter Zijlstra wrote:
> On Fri, Aug 11, 2017 at 12:58:22PM +0700, Suravee Suthikulpanit wrote:
>>
>>
>> On 8/11/17 11:57, Suravee Suthikulpanit wrote:
>>>
>>>>> [...]
>>>>> @@ -1445,9 +1448,24 @@ void sched_init_numa(void)
>>>>>          tl[i] = sched_domain_topology[i];
>>>>>
>>>>>      /*
>>>>> +     * Ignore the NUMA identity level if it has the same cpumask
>>>>> +     * as previous level. This is the case for:
>>>>> +     *   - System with last-level-cache (MC) sched domain span a NUMA node.
>>>>> +     *   - System with DIE sched domain span a NUMA node.
>>>>> +     *
>>>>> +     * Assume all NUMA nodes are identical, so only check node 0.
>>>>> +     */
>>>>> +    if (!cpumask_equal(sched_domains_numa_masks[0][0], tl[i-1].mask(0)))
>>>>> +        tl[i++] = (struct sched_domain_topology_level){
>>>>> +            .mask = sd_numa_mask,
>>>>> +            .numa_level = 0,
>>>>> +            SD_INIT_NAME(NODE)
>>>>> +        };
>>>>
>>>> So what you've forgotten to mention is that for those systems where the
>>>> LLC == NODE this now superfluous level gets removed by the degenerate
>>>> code. Have you verified that does the right thing?
>>>
>>> Let me check with that one and get back.
>>
>> Actually, it is not removed by the degenerate code. That is what this logic
>> is for. It checks for LCC == NODE or DIE == NODE before setting up the NODE
>> sched level. I can update the comment. This has also been tested on system
>> w/ LLC == NODE.
>
> Why does the degenerate code fail to remove things?
>

Sorry for confusion. Actually, the degenerate code does remove the duplicate 
NODE sched-domain.

The logic above is taking a different approach. Instead of depending on the 
degenerate code during cpu_attach_domain() at a later time, it would exclude the 
NODE sched-domain during sched_init_numa().  The difference is, without 
!cpumask_equal(), now the MC sched-domain would have the SD_PREFER_SIBLING flag 
set by the degenerate code since the flag got transferred down from the NODE to 
MC sched-domain. Would this be the preferred behavior for MC sched-domain?

Regards,
Suravee