Re: [PATCH 1/8] migrate_pages: organize stats with struct migrate_pages_stats

["Huang, Ying" <ying.huang@intel.com>]

Alistair Popple <apopple@nvidia.com> writes:

> "Huang, Ying" <ying.huang@intel.com> writes:
>
>> Alistair Popple <apopple@nvidia.com> writes:
>>
>>> Huang Ying <ying.huang@intel.com> writes:
>>>
>>>> Define struct migrate_pages_stats to organize the various statistics
>>>> in migrate_pages().  This makes it easier to collect and consume the
>>>> statistics in multiple functions.  This will be needed in the
>>>> following patches in the series.
>>>>
>>>> Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
>>>> Cc: Zi Yan <ziy@nvidia.com>
>>>> Cc: Yang Shi <shy828301@gmail.com>
>>>> Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
>>>> Cc: Oscar Salvador <osalvador@suse.de>
>>>> Cc: Matthew Wilcox <willy@infradead.org>
>>>> Cc: Bharata B Rao <bharata@amd.com>
>>>> Cc: Alistair Popple <apopple@nvidia.com>
>>>> Cc: haoxin <xhao@linux.alibaba.com>
>>>> ---
>>>>  mm/migrate.c | 58 +++++++++++++++++++++++++++++-----------------------
>>>>  1 file changed, 32 insertions(+), 26 deletions(-)
>>>>
>>>> diff --git a/mm/migrate.c b/mm/migrate.c
>>>> index a4d3fc65085f..ec9263a33d38 100644
>>>> --- a/mm/migrate.c
>>>> +++ b/mm/migrate.c
>>>> @@ -1396,6 +1396,14 @@ static inline int try_split_folio(struct folio *folio, struct list_head *split_f
>>>>  	return rc;
>>>>  }
>>>>  
>>>> +struct migrate_pages_stats {
>>>> +	int nr_succeeded;
>>>> +	int nr_failed_pages;
>>>> +	int nr_thp_succeeded;
>>>> +	int nr_thp_failed;
>>>> +	int nr_thp_split;
>>>
>>> I think some brief comments in the code for what each stat is tracking
>>> and their relationship to each other would be helpful (ie. does
>>> nr_succeeded include thp subpages, etc). Or at least a reference to
>>> where this is documented (ie. page_migration.rst) as I recall there has
>>> been some confusion in the past that has lead to bugs.
>>
>> OK, will do that in the next version.
>
> You should add that nr_failed_pages doesn't count failures of migrations
> that weren't attempted because eg. allocation failure as that was a
> surprising detail to me at least. Unless of course you decide to fix
> that :-)

nr_failed_pages are used for /proc/vmstat.  Syscall move_pages() cares
about how many pages requested but not tried.  But the system wide
statistics doesn't care about it.  I think that is the appropriate.

Best Regards,
Huang, Ying

>>> Otherwise the patch looks good so:
>>>
>>> Reviewed-by: Alistair Popple <apopple@nvidia.com>
>>
>> Thanks!
>>
>> Best Regards,
>> Huang, Ying
>>
>>>> +};
>>>> +
>>>>  /*
>>>>   * migrate_pages - migrate the folios specified in a list, to the free folios
>>>>   *		   supplied as the target for the page migration
>>>> @@ -1430,13 +1438,8 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
>>>>  	int large_retry = 1;
>>>>  	int thp_retry = 1;
>>>>  	int nr_failed = 0;
>>>> -	int nr_failed_pages = 0;
>>>>  	int nr_retry_pages = 0;
>>>> -	int nr_succeeded = 0;
>>>> -	int nr_thp_succeeded = 0;
>>>>  	int nr_large_failed = 0;
>>>> -	int nr_thp_failed = 0;
>>>> -	int nr_thp_split = 0;
>>>>  	int pass = 0;
>>>>  	bool is_large = false;
>>>>  	bool is_thp = false;
>>>> @@ -1446,9 +1449,11 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
>>>>  	LIST_HEAD(split_folios);
>>>>  	bool nosplit = (reason == MR_NUMA_MISPLACED);
>>>>  	bool no_split_folio_counting = false;
>>>> +	struct migrate_pages_stats stats;
>>>>  
>>>>  	trace_mm_migrate_pages_start(mode, reason);
>>>>  
>>>> +	memset(&stats, 0, sizeof(stats));
>>>>  split_folio_migration:
>>>>  	for (pass = 0; pass < 10 && (retry || large_retry); pass++) {
>>>>  		retry = 0;
>>>> @@ -1502,9 +1507,9 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
>>>>  				/* Large folio migration is unsupported */
>>>>  				if (is_large) {
>>>>  					nr_large_failed++;
>>>> -					nr_thp_failed += is_thp;
>>>> +					stats.nr_thp_failed += is_thp;
>>>>  					if (!try_split_folio(folio, &split_folios)) {
>>>> -						nr_thp_split += is_thp;
>>>> +						stats.nr_thp_split += is_thp;
>>>>  						break;
>>>>  					}
>>>>  				/* Hugetlb migration is unsupported */
>>>> @@ -1512,7 +1517,7 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
>>>>  					nr_failed++;
>>>>  				}
>>>>  
>>>> -				nr_failed_pages += nr_pages;
>>>> +				stats.nr_failed_pages += nr_pages;
>>>>  				list_move_tail(&folio->lru, &ret_folios);
>>>>  				break;
>>>>  			case -ENOMEM:
>>>> @@ -1522,13 +1527,13 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
>>>>  				 */
>>>>  				if (is_large) {
>>>>  					nr_large_failed++;
>>>> -					nr_thp_failed += is_thp;
>>>> +					stats.nr_thp_failed += is_thp;
>>>>  					/* Large folio NUMA faulting doesn't split to retry. */
>>>>  					if (!nosplit) {
>>>>  						int ret = try_split_folio(folio, &split_folios);
>>>>  
>>>>  						if (!ret) {
>>>> -							nr_thp_split += is_thp;
>>>> +							stats.nr_thp_split += is_thp;
>>>>  							break;
>>>>  						} else if (reason == MR_LONGTERM_PIN &&
>>>>  							   ret == -EAGAIN) {
>>>> @@ -1546,7 +1551,7 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
>>>>  					nr_failed++;
>>>>  				}
>>>>  
>>>> -				nr_failed_pages += nr_pages + nr_retry_pages;
>>>> +				stats.nr_failed_pages += nr_pages + nr_retry_pages;
>>>>  				/*
>>>>  				 * There might be some split folios of fail-to-migrate large
>>>>  				 * folios left in split_folios list. Move them back to migration
>>>> @@ -1556,7 +1561,7 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
>>>>  				list_splice_init(&split_folios, from);
>>>>  				/* nr_failed isn't updated for not used */
>>>>  				nr_large_failed += large_retry;
>>>> -				nr_thp_failed += thp_retry;
>>>> +				stats.nr_thp_failed += thp_retry;
>>>>  				goto out;
>>>>  			case -EAGAIN:
>>>>  				if (is_large) {
>>>> @@ -1568,8 +1573,8 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
>>>>  				nr_retry_pages += nr_pages;
>>>>  				break;
>>>>  			case MIGRATEPAGE_SUCCESS:
>>>> -				nr_succeeded += nr_pages;
>>>> -				nr_thp_succeeded += is_thp;
>>>> +				stats.nr_succeeded += nr_pages;
>>>> +				stats.nr_thp_succeeded += is_thp;
>>>>  				break;
>>>>  			default:
>>>>  				/*
>>>> @@ -1580,20 +1585,20 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
>>>>  				 */
>>>>  				if (is_large) {
>>>>  					nr_large_failed++;
>>>> -					nr_thp_failed += is_thp;
>>>> +					stats.nr_thp_failed += is_thp;
>>>>  				} else if (!no_split_folio_counting) {
>>>>  					nr_failed++;
>>>>  				}
>>>>  
>>>> -				nr_failed_pages += nr_pages;
>>>> +				stats.nr_failed_pages += nr_pages;
>>>>  				break;
>>>>  			}
>>>>  		}
>>>>  	}
>>>>  	nr_failed += retry;
>>>>  	nr_large_failed += large_retry;
>>>> -	nr_thp_failed += thp_retry;
>>>> -	nr_failed_pages += nr_retry_pages;
>>>> +	stats.nr_thp_failed += thp_retry;
>>>> +	stats.nr_failed_pages += nr_retry_pages;
>>>>  	/*
>>>>  	 * Try to migrate split folios of fail-to-migrate large folios, no
>>>>  	 * nr_failed counting in this round, since all split folios of a
>>>> @@ -1626,16 +1631,17 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
>>>>  	if (list_empty(from))
>>>>  		rc = 0;
>>>>  
>>>> -	count_vm_events(PGMIGRATE_SUCCESS, nr_succeeded);
>>>> -	count_vm_events(PGMIGRATE_FAIL, nr_failed_pages);
>>>> -	count_vm_events(THP_MIGRATION_SUCCESS, nr_thp_succeeded);
>>>> -	count_vm_events(THP_MIGRATION_FAIL, nr_thp_failed);
>>>> -	count_vm_events(THP_MIGRATION_SPLIT, nr_thp_split);
>>>> -	trace_mm_migrate_pages(nr_succeeded, nr_failed_pages, nr_thp_succeeded,
>>>> -			       nr_thp_failed, nr_thp_split, mode, reason);
>>>> +	count_vm_events(PGMIGRATE_SUCCESS, stats.nr_succeeded);
>>>> +	count_vm_events(PGMIGRATE_FAIL, stats.nr_failed_pages);
>>>> +	count_vm_events(THP_MIGRATION_SUCCESS, stats.nr_thp_succeeded);
>>>> +	count_vm_events(THP_MIGRATION_FAIL, stats.nr_thp_failed);
>>>> +	count_vm_events(THP_MIGRATION_SPLIT, stats.nr_thp_split);
>>>> +	trace_mm_migrate_pages(stats.nr_succeeded, stats.nr_failed_pages,
>>>> +			       stats.nr_thp_succeeded, stats.nr_thp_failed,
>>>> +			       stats.nr_thp_split, mode, reason);
>>>>  
>>>>  	if (ret_succeeded)
>>>> -		*ret_succeeded = nr_succeeded;
>>>> +		*ret_succeeded = stats.nr_succeeded;
>>>>  
>>>>  	return rc;
>>>>  }