Received-SPF: pass (google.com: domain of linux-kernel+bounces-122405-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.199.223 as permitted sender) client-ip=147.75.199.223;
Message-ID: <e059df52-48fc-4e65-9eb0-c0d197625e6e@amd.com>
Date: Thu, 28 Mar 2024 10:09:50 +0530
User-Agent: Mozilla Thunderbird
Subject: Re: [RFC PATCH 1/2] sched/numa: Fault count based NUMA hint fault
 latency
To: "Huang, Ying" <ying.huang@intel.com>
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org,
 akpm@linux-foundation.org, mingo@redhat.com, peterz@infradead.org,
 mgorman@techsingularity.net, raghavendra.kt@amd.com,
 dave.hansen@linux.intel.com, hannes@cmpxchg.org
References: <20240327160237.2355-1-bharata@amd.com>
 <20240327160237.2355-2-bharata@amd.com>
 <87r0fvktkn.fsf@yhuang6-desk2.ccr.corp.intel.com>
Content-Language: en-US
From: Bharata B Rao <bharata@amd.com>
In-Reply-To: <87r0fvktkn.fsf@yhuang6-desk2.ccr.corp.intel.com>
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 7bit
Precedence: bulk
MIME-Version: 1.0
X-MS-Exchange-AntiSpam-MessageData-ChunkCount: 1
X-MS-Exchange-AntiSpam-MessageData-0:
	=?utf-8?B?eVFpRFowNGtBcmY5SHBQTjJxMWdzcVR1aUUzNmFxakxVVk5uN3YxNm0yM2la?=
 =?utf-8?B?cTR1aWRSbjBJdi9mL0xMeFQ1MGEwc2svbUdWam5GMm4yUmRqandaMENYNGdx?=
 =?utf-8?B?dlk5amtXVTR1b0FTN1lVaDNwbmlxUDlBVFhHY3Rqd0FVMjgrakFSUEhNYzFD?=
 =?utf-8?B?NUNOUU16VjNlRTBVcGtTYjRvYWd4RStCWGlyS1Jucmhqd0VaNno0TlhsNDB4?=
 =?utf-8?B?bU9MNFMveWhkb04zdGx5aTFsbUxISkVFOHNhU05HSUhabk54MUNsWHk0TDNN?=
 =?utf-8?B?VkdKay9LTzhPWnlXWmJZcmRKUFJoUEF2dXRQSGlyYUpEWHdCL3FMVEl2UHdO?=
 =?utf-8?B?ZW9FSm80YjUxeW1BOFphcjZ3RFllS3UwaVp2N2pjaDNwV3R1TFFUbVp1ZE1i?=
 =?utf-8?B?WUNqMWNDMWtzYThrTjZydmFmSlRKN0dBU3RYRFFRNmpLaGZrbFVKSU1pL250?=
 =?utf-8?B?SWtIUVhaa0NBSDlmcFlaRUpvVXdlTDE1cjhOZ2x2cVZxL2RWKzhqVFViNHdH?=
 =?utf-8?B?OGx0dG5sQVVFYktkellvaW5hbXFYN1g2T1lZMGZ5ZTNtNXlxbmhTaGo4VzJ6?=
 =?utf-8?B?UEFhd2VmTmREaHRFUWFRZmV6bVZTeVc1Skl2Z3FSY0tpaUZON0tPRFRXZ1Vi?=
 =?utf-8?B?d3I2RndITDhyNWVQUFRLMEo5OWNwL3RjeWl6RGdyNFJGZEFuMTUxODJnZ1V6?=
 =?utf-8?B?RnA1UExsZUwrd29saXB5aC8xSW9zTzN0aFdXM3B4YzlRUW9VRWduRDZGa3NB?=
 =?utf-8?B?M3JrbCtBczc4ckQxZE5uOGgwRnZ4VGV5alVMZTY0eE9ZK0VwZEk0MjVLRWJw?=
 =?utf-8?B?RWlQVEFzZUhNSWh0eU12UllJQkl1WUgveittRkdQUmMvSmJIcWhDdzRhSHhN?=
 =?utf-8?B?UVQ4bGdIRkJmbXJDK2s5a2lIS2toZzU4KzduVVIxck04VjB2OEZJZ3ZqL0hX?=
 =?utf-8?B?WjB1amVQRTE2S0F3OWNlOXZSaDVHZjRiR2IrUHRCZnVXK00rVTFRSjZvalEr?=
 =?utf-8?B?cHpqK2l2VE85YW9FYnZvL2hKVEltSHd1eWF1QUVubEp4eUJHZGVzMGhjV0tE?=
 =?utf-8?B?dlNpL1ZSR29vamlPRHc4MjFMbk1xdzhyN0RDQjgwRGtobEYrSGFNZ1BJd2Vt?=
 =?utf-8?B?VWgrWVdSRGpXRkFxS0Q3RHdIOHNSWWFNZTdnaFZzVWZib093Mjhpak9KQ3RX?=
 =?utf-8?B?SU5xSHZpZEVxRWJVOEluV1VwTGIweHhEeUdkMmdtMzk2STZuRkRnT09OREZj?=
 =?utf-8?B?S3NWK1MrL0lJVlFKcWZoVmF4U2RaMzkrbi9LdUJTb01FYTV5NE9TWUt6WnEz?=
 =?utf-8?B?L25qdjcreTY1UmNwVFc5TkxIYitGdjNJUWIxTTlKbnBJTVJrZmo1TFpjUTR5?=
 =?utf-8?B?THFZckNTOCsveHVtWVEvRXFpUmVodzBTWW5YSjZnYllJcnV2TTljcHZ1OGx2?=
 =?utf-8?B?TE9WcmFuNlhiM2o1TEc0U2kzaHZ6WGRwVHNnU2JYb1VtSExuZUVaNGtjWTZo?=
 =?utf-8?B?emVOZHhka3hVcS9QYjNKL1pZYmI5RGlvMmpvclozQXYxeG96RWluZVBDZm9Y?=
 =?utf-8?B?TUFSS0U0TVJmdXVGSTRucll4QU1IclIyZ0NlTEdvWHY0QzllcE1JL3lieWcr?=
 =?utf-8?B?bjdMNldSY1MyK1FacmpCOUxta2hhYjMzZklHSmZFUWMvK1pMTmp0WmIxcFRU?=
 =?utf-8?B?TkZEVDVzdE9qcDUzNzFBd2FIZDRXdy85ME13VVR0NmdzcUVaVHBEanljRjlY?=
 =?utf-8?B?S3g2NFJjSjNOV0xKb2RhbjNSQXlBek9UUUlxTENGbUt2NGtwNStKT1I4YWJm?=
 =?utf-8?B?M1F5cFZ3K29HRkNzVTcraTJHT3luMUhqaXNOM05zRTdyTmx1eWpnRHNBeHlO?=
 =?utf-8?B?V21hUmV5SkVGRGRkMFdFUU1RWHluZGJJUS9BQitCSkF6aWpDWndjT1p1VUY4?=
 =?utf-8?B?UUtlYVpLR2RMZUc1NmxoTjZublFTNmF3MExJakpCa25lL2VxN2VoeVdNalcx?=
 =?utf-8?B?ck5SblEwWVJ3Vm1ralBrYytpS3ltRWt0MUF1VDFkT2wyajJCQmZ3SXVPRm9O?=
 =?utf-8?B?YnJ3Mlh6QkYxd3N5dk9nS0xWNTZGOHJqOVVsallxU1hpbm1iejBacE0ybHU2?=
 =?utf-8?Q?Ui+ZHPggvlHCfpIRfDHBCpG1l?=
X-OriginatorOrg: amd.com
X-MS-Exchange-CrossTenant-Network-Message-Id: 45bc9b98-b52f-4bbd-1f9a-08dc4ee11f7d
X-MS-Exchange-CrossTenant-AuthSource: IA1PR12MB6434.namprd12.prod.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Internal
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 28 Mar 2024 04:39:58.5728
 (UTC)
X-MS-Exchange-CrossTenant-FromEntityHeader: Hosted
X-MS-Exchange-CrossTenant-Id: 3dd8961f-e488-4e60-8e11-a82d994e183d
X-MS-Exchange-CrossTenant-MailboxType: HOSTED
X-MS-Exchange-CrossTenant-UserPrincipalName: 5TD5+AAREJfJSKLxKiAmgmI5jh2NgVHioj8QpsDjlmev3b9vfleyCNK66jX+Z2Wj8cCGDO4B65hQc0/YRgEUag==
X-MS-Exchange-Transport-CrossTenantHeadersStamped: MW6PR12MB8913

On 28-Mar-24 7:26 AM, Huang, Ying wrote:
> Bharata B Rao <bharata@amd.com> writes:
> 
> [snip]
> 
>> @@ -1750,25 +1753,20 @@ static bool pgdat_free_space_enough(struct pglist_data *pgdat)
>>  }
>>  
>>  /*
>> - * For memory tiering mode, when page tables are scanned, the scan
>> - * time will be recorded in struct page in addition to make page
>> - * PROT_NONE for slow memory page.  So when the page is accessed, in
>> - * hint page fault handler, the hint page fault latency is calculated
>> - * via,
>> + * For memory tiering mode, when page tables are scanned, the current
>> + * hint fault count will be recorded in struct page in addition to
>> + * make page PROT_NONE for slow memory page.  So when the page is
>> + * accessed, in hint page fault handler, the hint page fault latency is
>> + * calculated via,
>>   *
>> - *	hint page fault latency = hint page fault time - scan time
>> + * hint page fault latency = current hint fault count - fault count at scan time
>>   *
>>   * The smaller the hint page fault latency, the higher the possibility
>>   * for the page to be hot.
>>   */
>> -static int numa_hint_fault_latency(struct folio *folio)
>> +static inline int numa_hint_fault_latency(struct folio *folio, int count)
>>  {
>> -	int last_time, time;
>> -
>> -	time = jiffies_to_msecs(jiffies);
>> -	last_time = folio_xchg_access_time(folio, time);
>> -
>> -	return (time - last_time) & PAGE_ACCESS_TIME_MASK;
>> +	return count - folio_xchg_fault_count(folio, count);
>>  }
> 
> I found count is task->mm->hint_faults.  That is a process wide
> counting.  How do you connect the hotness of a folio with the count of
> hint page fault in the process?  How do you compare the hotness of
> folios among different processes?

The global hint fault count that we already maintain could
be used instead of per-task fault. That should take care
of the concern you mention right?

Regards,
Bharata.